Medical Vision-Language Models

Picking the frozen image encoder for a 3D~CT vision--language model (VLM), together with the token-compression scheme on top of it, is a search over many candidates. There are several encoders, several ways to compress their tokens, and several token budgets, and the combinations grow fast. Comparing them the usual way means fine-tuning a large language model (LLM) on each combination, and running the whole sweep this way needs far more compute than most groups can spend. We ask whether a cheap probe on the encoder's cached embeddings can stand in for that comparison. We build an image-grounded probing benchmark over (encoder $\times$ compression) cells, with clinical attribute families and two validation gates, scale-sanity and probe-separability, that keep each attribute well-scaled and decodable. These gates are the main methodological contribution. On this benchmark we compare a range of read-out heads, and in a preliminary study we pair each probe with its matched downstream task. The early signal is encouraging: the cheap probe orders the candidates in close agreement with expensive fine-tuning, at about $r\approx0.95$ on the cells measured so far. We read this as an ordinal claim, a ranking predictor rather than an exact estimate, and we are explicit about where it stays preliminary. If it holds up, encoder and compression choices can be screened in minutes with frozen-token probes, with full training spent only on the finalists.

Despite rapid progress, most existing vision-language models (VLMs) built from 2D visual inputs often struggle when handling various 3D tasks that require fine-grained spatial understanding and reasoning. To bridge this gap, we present VLM-IE3D, a unified framework that enhances the 3D spatial awareness of VLMs by equipping them with both implicit and explicit 3D geometries learned from RGB videos. Our VLM-IE3D introduces Implicit Geometry Tokens (IGTs) that capture high-level geometric priors from input videos, as well as complementary Explicit Geometry Tokens (EGTs) that encode detailed geometric structures from reconstructed 3D attributes. On top of that, VLM-IE3D comes with a 3D-aware adapter that effectively fuses the two types of geometric representations with 2D visual cues. This RGB-only design injects strong 3D inductive biases for fine-grained spatial understanding and reasoning without requiring any additional 3D inputs. Extensive experiments show that VLM-IE3D achieves superior performance consistently across various 3D tasks including 3D video detection, 3D visual grounding, 3D dense captioning, and spatial reasoning. Code and models are available at https://github.com/Vegetebird/VLM-IE3D.

Pathology vision-language models (VLMs) have recently progressed rapidly and are commonly evaluated by answer accuracy on pathology VQA benchmarks. However, we dig into current evaluations and identify three overlooked issues: 1) Visual evidence is not always necessary. For instance, Gemini-3-Pro achieves 53.5% average accuracy across 5 VQA benchmarks without any visual input. 2) Domain training can improve accuracy without proportional gains in visual binding. Compared with Qwen2.5-VL-7B, Patho-R1-7B exhibits a 5.8-point lower multimodal gain and a 3.7-point lower attention IoU. 3) Entity-level attention is diffuse and weakly query-specific. On PathVG, attention maps remain highly correlated across different entity queries. These issues can lead to substantial misjudgments of pathology VLMs' actual multimodal capabilities. To this end, we present PathBind, a benchmark comprising 2,600 samples: PathBind-VQA with 1,500 questions across six dimensions, PathBind-PTA with 600 questions from a private pathology teaching atlas, and PathBind-Grounding with 500 expert-curated region-level samples. Each component undergoes task-specific automated filtering and expert review to reduce textual shortcuts and improve entity-region correspondence. We evaluate 18 representative VLMs on VQA samples of PathBind and five existing pathology VQA benchmarks, and further evaluate 10 VLMs on PathBind-Grounding and PathVG. Results show that current pathology VLMs still exhibit a substantial gap between answer-side performance and visual-semantic binding.

Large vision-language models are becoming increasingly dominant in 3D medical image interpretation, but we rarely know <i>which</i> internal units encode clinical findings or <i>where</i> that information lives in the representation. We first study this on a 3D chest vision-language model (Pillar-0) by probing its frozen vision embeddings. We show that (i) each radiological finding is encoded by a <i>sparse</i> set of ~10 vision-encoder channels that match full-feature classification performance and far exceed a zero-shot text prompting; (ii) turning off the channels tied to one finding, that finding's score collapses while unrelated labels stay stable; and (iii) the same sparse probe <i>replicates</i> on an architecturally unrelated 3D abdominal VLM (Merlin) suggesting a general property of frozen medical encoders. Our training-free concept channel probe (CCP) method, paired with a corpus-derived report template, outperforms published CT-CHAT on clinical efficacy and NLG metrics (F1 0.549 vs. 0.184; BLEU 0.483 vs. 0.373) at 22x lower latency. Our results provide a clear, reproducible characterization of how frozen medical encoders represent findings, demonstrating direct applicability across models.

Medical imaging is a cornerstone of diagnostics, yet automated chest X-ray report generation struggles with structural adherence, anatomical completeness, and semantic faithfulness. We introduce DobicVLM, a vision-language model combining supervised fine-tuning on MedGemma-4B with Group Relative Policy Optimization (GRPO) and clinically-grounded programmatic rewards. Our approach uses interpretable, rule-based reward components; structural verification, anatomical checklist, semantic similarity, and length constraints to enforce clinical standards without neural reward models. Trained on 1,000 de-identified image-report pairs from a private clinical dataset (with ethics approval and compliance to local regulations), DobicVLM is evaluated via blinded expert review on 69 held-out cases. DobicVLM outperforms Gemini 2.5 Flash across the majority of criteria, achieving the highest impression accuracy (27.2%) and medical terminology (86.5%) compared to both Gemini 2.5 Flash and MedGemma 4B baselines, with minor trade-offs in completeness and referrals. This demonstrates GRPO's value for transparent alignment in resource-limited settings. Keywords: Vision-Language Models, Radiology Report Generation, Reinforcement Learning, Medical AI, GRPO

Attention and saliency heatmaps are widely used to explain medical Vision-Language Model (VLM) outputs on chest X-rays, yet whether they truly highlight the image evidence driving predictions has not been causally tested. We audit faithfulness via overlap with radiologist bounding boxes on PadChest (n=637), attribution mass within radiologist masks on CheXlocalize (n=643), and 16x16 patch-occlusion maps that record which regions, when hidden, change the answer. We study three MedGemma-4B variants, cross-family probes on LLaVA-RAD and Qwen3-VL-8B-Instruct, and the specialist CheXagent-2-3b, with two CXR-trained classifiers (DenseNet121, ResNet50) as positive controls. A heatmap is faithful only if the model uses the image and attention concentrates on regions whose occlusion alters the prediction. No evaluated VLM meets both criteria. MedGemma and Qwen3-VL use the image, but attention anti-correlates with patch-occlusion importance (rho < 0 with 95% bootstrap CIs below zero). LLaVA-RAD's attention correlates positively, but the model is almost text-only (99.1% text-only agreement, near-zero causal mass), so correlation ties two near-zero signals. Attention also misses annotated anatomy: overlap with true regions never beats shifted or random controls, and no method places more than 22% of its mass inside radiologist masks. The two CXR classifiers pass all metrics, indicating the failure is specific to VLM heatmaps, not the evaluation. These heatmaps are visually reassuring but not faithful; clinical explanations require controlled localization metrics and causal perturbation, not visual inspection alone.

Medical vision-language models (MVLMs) promise broad zero-shot generalization, yet their reliability collapses when confronted with unseen modalities and domains, precisely where clinical robustness matters most. To address this gap, we revisit test-time modality generalization from the perspective of Mixture-of-Experts (MoE) and ask: can experts route-and-adapt without any optimization during inference? We identify a fundamental specialization-generalization dilemma at test time, where blindly aggregating modality experts dilutes modality-specific knowledge, while selecting one highly confident expert risks mismatch under shift. To address this, we propose MoBE: a fully optimization-free framework that performs dynamic expert selection and adaptation at test time. MoBE combines entropy-guided dynamic routing in MoE settings with expert-wise Bayesian adaptation, enabling experts to update their confidence and adapt online without gradient updates. Without parametric updates, MoBE augments a static MVLM with test-time routing and online statistics, achieving average accuracy gains of +4.72, +7.17, and +4.3 over state-of-the-art TTA methods across seen, unseen, and heterogeneous medical benchmarks, highlighting the effectiveness of training-free expert adaptation for robust modality generalization.

Large vision-language models (LVLMs) can be adapted to specialized medical imaging tasks via parameter-efficient fine-tuning approaches such as low-rank adaptation (LoRA), leading to a growing ecosystem of expert models tailored to specific imaging modalities and clinical scenarios. However, deploying multiple expert LVLMs in practice incurs substantial computational and operational overhead. Model merging provides a promising solution by consolidating multiple experts into a single model without retraining, yet it remains largely unexplored in the medical domain. In this work, we present the first systematic study of model merging for medical LVLMs. We introduce MergeMedBench, a comprehensive benchmark spanning eight imaging modalities and diverse clinical task types, comprising 16 LoRA fine-tuned models built upon two mainstream architectures. We conduct an extensive evaluation of existing merging methods and further propose winner-take-all, a simple and hyperparameter-free approach that retains only the most dominant parameters across expert models. By preserving the critical parameters that govern model behavior and discarding weaker ones, our method avoids the information dilution inherent in averaging- or alignment-based strategies. Despite its simplicity, winner-take-all consistently outperforms existing approaches, offering both a new perspective on LoRA merging and a strong practical baseline for future research.

Vision-language models trained with contrastive objectives have shown promise in medical image analysis. However, conventional global image-text alignment is ill-suited for mammography, where diagnostically relevant lesions are spatially localized and occupy only a small fraction of the image. Subtle morphological cues critical for malignancy assessment can be diluted when representations are learned at the whole-image level. In this work, we propose a novel region-grounded vision-language learning method for detection-guided mammographic lesion classification. The method mirrors radiologists' diagnostic paradigm. First, a region-text contrastive pretraining stage aligns lesion-specific features with structured clinical descriptors derived from radiology metadata. To mitigate semantic collapse and background bias in low-vocabulary settings, we introduce a multi-component objective incorporating positive alignment, fine-grained semantic hard negatives, and background suppression. Second, an auxiliary lesion detection head is jointly optimized with contrastive classification to preserve spatial sensitivity and enable localization-aware malignancy classification. Extensive experiments on two independent datasets, CBIS-DDSM and VinDr-Mammo, show superior performance of our method compared to related methods under in-domain, cross-dataset, and transfer learning settings.

3D CT vision-language models (VLMs) classify abnormalities from text prompts in a zero-shot manner, enabling cross-institution deployment where labels are scarce and clinical tasks shift faster than supervised models can be retrained. A real CT scan, however, typically contains several co-occurring abnormalities, and the reliability of zero-shot multi-label prediction under distribution shift remains poorly understood. Test-time adaptation (TTA) updates a model on unlabeled target scans without source data or target annotations, yet existing TTA methods target multi-class softmax prediction on natural images or 2D medical segmentation, and none addresses unsupervised multi-label adaptation for zero-shot 3D CT VLMs. We study when TTA helps zero-shot 3D CT VLMs. A controlled diagnostic analysis shows that TTA is conditional: the volumetric input must preserve the encoder's depth structure, and the base representation must transfer to the target cohort, with depth reduction alone lowering internal AUROC by more than 0.12. We then focus on the regime where the base model already separates present from absent abnormalities. We introduce CARVE (Cardinality-Aware Retained-View Entropy), the first TTA method for this setting. CARVE estimates a sample-specific positive-label cardinality $\hat{k}$, optimizes a top-$\hat{k}$ objective to preserve co-occurring abnormalities, and performs memory-efficient multi-view adaptation by scoring weak 3D views without gradients before updating on a retained subset. Across contrastive CT-CLIP and anatomy-aware fVLM, CARVE provides the most consistent improvements across multi-label, three-class, and binary CT tasks when the base model is already discriminative. These results establish multi-label TTA for zero-shot 3D CT VLMs as a distinct problem and CARVE as a cardinality-aware solution.

Recent advances in large language models (LLMs) and their extension to vision-language models (VLMs) have made it easier to combine text and images for tasks such as report generation. Existing VLMs in medicine typically focus on 2D images (chest X-rays), and their extension to 3D imaging has been difficult because of the lack of paired 3D imaging-text data. Thus, we introduce a new method for creating a 3D image-text dataset for brain oncology using 3D MRI scans of glioma and meningioma cases. We use a cooperative system in which several LLMs work together to generate and check reports, ensuring that they are accurate and clear. By leveraging the new 3D MRI-text dataset, we further build a VLM that converts MRI scans into tokens and aligns them with text instructions. Our VLM performed better in report generation and visual question answering tasks than other 2D and 3D methods. Our method not only improves the quality of reports but also helps with better diagnosis and treatment in brain oncology.

Computed tomography (CT) vision-language pretraining from paired volumes and radiology reports is a scalable yet challenging task. Existing methods commonly adopt global scan-report contrast, which is scalable but obscures heterogeneous organ evidence. Meanwhile, direct organ-level alignment remains coarse, since the same anatomy can exhibit multiple distinct radiological appearances. Therefore, pretraining requires a finer alignment unit: the organ-conditioned radiological pattern. In this work, we propose OCP-CT, an organ-conditioned pattern-token alignment framework for CT vision-language pretraining. Specifically, OCP-CT preserves a stable global CT-report contrastive branch and introduces an organ pattern interface: sparse Mixture-of-Experts (MoE) routes image and text tokens according to latent radiological patterns, learnable slots query the routed tokens into continuous pattern tokens, and paired token contrast aligns image-text pattern tokens with structured soft targets built from report-derived clinical similarity. On the publicly available CT-RATE and RAD-ChestCT benchmarks, OCP-CT achieves average AUROCs of 84.5% and 69.9% for zero-shot abnormality diagnosis, respectively. Compared with the strongest prior reported results, these results yield absolute AUROC gains of 6.7 and 0.8 percentage points.

While Multimodal Large Language Models (MLLMs) have demonstrated remarkable success in 2D medical image understanding, their extension to 3D volumetric imaging remains hindered by prohibitive annotation costs and dataset opacity. Current data formats, predominantly consisting of rigid Visual Question Answering (VQA) pairs or unstructured final clinical reports, typically fail to capture explicit clinical reasoning. To address this limitation, we introduce a large-scale structured reasoning dataset constructed via a novel slice-wise data synthesis paradigm. Inspired by the genuine diagnostic workflow of radiologists, this paradigm models visual cognition by decomposing the complex 3D reading process, translating global clinical priors into fine-grained, per-slice observations that are subsequently synthesized into an interpretable Chain-of-Thought (CoT). Crucially, this synthesized reasoning framework enforces essential clinical principles: sequential spatial tracking, multi-slice spatial awareness for artifact mitigation, and differential exclusion. To validate this approach, we instruction-tune a standard 2D-pretrained MLLM baseline using the synthesized data to enhance its volumetric comprehension. Comprehensive evaluations across multiple 3D medical benchmarks demonstrate that our method yields significant performance improvements over the 2D baseline. Furthermore, the resulting model exhibits robust spatial reasoning capabilities and rivals resource-intensive native 3D architectures, effectively bridging the performance gap. Ultimately, this data-centric strategy unlocks deep volumetric understanding and highly interpretable clinical logic without requiring computationally expensive 3D-specific pre-training. The complete repository, including datasets and training workflows, is publicly available at https://github.com/2020420145009/hounsfield.

Automatic voxel-level grounding of free-text findings in 3D chest Computed Tomography (CT) is critical for clinical interpretability. However, this task remains highly challenging due to the intricate spatial complexity of large 3D volumes and the heterogeneity of free-text findings. Existing end-to-end approaches often struggle to simultaneously learn the localized feature representations required for accurate 3D segmentation and the complex semantic understanding needed for text alignment, leading to suboptimal grounding performance. To overcome this fundamental limitation, we propose a novel decoupled framework that disentangles the problem into two specialized stages: (1) class-agnostic lesion segmentation and (2) text-volume reasoning. This structural separation allows the model to first extract candidate sub-volumes by localizing potential abnormalities. Subsequently, intensive cross-modal reasoning is performed to align these localized sub-volumes with free-text medical findings. To resolve the spatial ambiguities inherent in local regions, the reasoning module is augmented with explicit anatomical guidance, utilizing relative spatial coordinates and lung lobe priors. Evaluated on the ReXGroundingCT benchmark, our method achieves state-of-the-art performance in overall grounding quality on the official leaderboard. These results demonstrate that decoupling detection from reasoning is a highly effective paradigm for handling the complexity of 3D medical visual grounding. Our code is publicly available at https://github.com/khuhm/DAGG.

Deploying medical visual question answering (MedVQA) systems in real-world clinical settings requires models that adapt to new clinical tasks without forgetting previously acquired knowledge. Continual learning (CL) provides a practical framework for this setting. Despite rapid progress in medical vision-language models, the behavior of CL methods when training these models across heterogeneous MedVQA tasks remains underexplored. This work presents a systematic evaluation of CL for MedVQA across diverse clinical objectives, including classification, multi-label classification, detection, cell counting, and report generation. Specifically, we explore (1) the ability of existing CL methods to mitigate catastrophic forgetting; (2) their sensitivity to task ordering, analyzing how different task sequences influence performance retention and forgetting; and (3) the evolution of low-rank adaptation parameters as new tasks are learned, revealing patterns of weight drift under different CL methods. Our findings suggest that existing CL methods struggle to maintain stability-plasticity balance when tasks with different objectives and supervision formats are interleaved. Code and full experimental setup will be publicly available.

Pathology Foundation Models (PFMs) offer powerful Whole Slide Image (WSI) representations but suffer from massive computational costs. While Knowledge Distillation (KD) can create efficient student models, existing multi-teacher methods often use suboptimal uniform weighting that ignores tissue heterogeneity. We propose LaGuadia (Language-Guided Adaptive DistillAtion), a framework that develops a compact pathology image encoder by dynamically integrating expertise from multiple PFMs under clinical linguistic guidance. Our approach utilizes a multi-stage pipeline: first, extracting visually observable clinical keywords from pathology reports; second, aligning visual features with these keywords via a Vision-Language meta-teacher (MedSigLIP) to provide dense semantic guidance; and finally, performing adaptive KD where teacher contributions are weighted based on their semantic alignment with the clinical narrative. Experiments on WSI captioning, visual question answering, and slide-level classification tasks demonstrate that an 87M parameter LaGuadia student model matches or exceeds foundation-scale models such as GigaPath and UNI, achieving strong factual consistency and robust generalization. These results highlight clinical language as an effective semantic anchor for building efficient and reliable digital pathology systems. Code is available at https://github.com/hvcl/LaGuadia.

Medical vision-language pretraining (VLP) from paired CT images and radiology reports enables scalable representation learning, but most existing methods align either whole scans with entire reports or local image regions with text fragments. These formulations underuse a key property of radiology reports: findings are organized around anatomical structures, with abnormalities described by organs, disease concepts, locations, and severity-related attributes. We propose OKA-CT, an organ-hierarchical knowledge-augmented framework for CT-report VLP. OKA-CT first converts free-text reports into organ-conditioned knowledge using radiology report parsing and LLM-assisted semantic structuring. The extracted hierarchy is used across two learning stages. Stage1 injects anatomy-grounded evidence into the CT visual representation through fine-grained organ-conditioned supervision, while Stage2 uses organ-specific report evidence to guide structured report-CT contrastive learning, where hierarchy-derived semantic soft targets treat non-paired cases with shared organ-level findings as weak semantic positives rather than uniform negatives. A lightweight query-based global branch further aggregates disease-relevant volumetric evidence for whole-scan representation. On CT-RATE and RAD-ChestCT datasets, OKA-CT achieves zero-shot abnormality diagnosis AUROCs of 84.9 and 72.2, outperforming prior CT VLP baselines. Retrieval and patch-occlusion analyses further show improved report-image alignment and stronger sensitivity to disease-associated anatomical regions.

Foundation models are increasingly used as image feature extractors for mammography, but their robustness under external domain shift remains unclear. We benchmark 15 foundation-model backbones across breast density, BI-RADS severity, and cancer status using a unified frozen-backbone linear-probe protocol, training on 3 source datasets and evaluating on 12 task-compatible out-of-distribution (OOD) datasets after label harmonization. Mammography-specific vision-language models (Mammo-FM and MaMA) provide the strongest mean OOD performance, but robustness is not explained by mammography exposure alone. DINOv3 remains a competitive vision-only baseline, and mammography-adapted pretraining does not consistently improve generalization. Dataset-level analysis further shows that even leading models show heterogeneous performance across datasets. Feature-space inspection reveals that useful representations can preserve clinical signal while retaining dataset and acquisition structure. These findings highlight dataset-level OOD evaluation as a central criterion for assessing mammography representations. Our code is publicly available: https://github.com/biomedia-mira/mammo-ood.

Automated chest X-ray report generation has recently benefited from reinforcement learning (RL) and large language models. However, RL training often suffers from instability or limited exploration due to fixed Kullback-Leibler (KL) regularization and a static reference policy that accumulates KL pressure over time. We propose Response-Weighted and Validation-Anchored Policy Optimization (REVA-PO), a RL framework that stabilizes long-term training via Response-Weighted Regularization (RER) and Validation-Anchored Policy Reset (VAPR). RER dynamically adjusts per-response KL weights based on advantage and reference-policy entropy, relaxing constraints for high-quality responses while tightening them for low-quality ones. Complementarily, VAPR periodically synchronizes the reference and current policies to the best validation checkpoint, resetting accumulated regularization pressure to expand the viable exploration space. To ensure a robust starting point, we employ a three-stage pipeline consisting of warm-up training, classifier-guided supervised fine-tuning, and RL. Extensive evaluations on MIMIC-CXR and IU-Xray demonstrate that REVA-PO sets new state-of-the-art benchmarks in both linguistic quality and clinical accuracy. Notably, BLEU-4 improves by 5.1% on MIMIC-CXR and 3.6% on IU-Xray, while CheXpert F1 and RadGraph F1 scores increase by 4.5% and 12.8%, respectively, over prior leading methods. The code is publicly available at https://github.com/LiGuo12/REVA_PO/.

Medical Vision-Language Models (VLMs) exhibit strong zero-shot performance, yet their effectiveness still declines on out-of-distribution (OOD) data due to domain shifts and class bias inherited from large-scale pretraining. Existing few-shot adaptation methods typically introduce additional trainable components, which can be unstable in extremely low-data regimes (e.g., 1-shot), and lack robustness on different medical data. We present TCLA, a purely training-free few-shot adaptation method for Medical VLMs, which is fast and model-agnostic. TCLA corrects inference logits based on a small set of support samples, boosting pretrained VLMs performance by improving inter-class deconfusion and reducing domain shift. Extensive experiments on nine datasets across multiple medical imaging modalities including X-ray, Ultrasound, MRI, CT, Histopathology, demonstrate that TCLA consistently improves OOD performance of Medical VLMs and, in most of cases, outperforms existing training-based adaptation methods.

Medical images require comprehensive and accurate interpretation to support the diagnosis of diverse clincial conditions. Recent vision-language generalist models offer broad task coverage and promising zero-shot capabilities, yet often lack fine-grained anatomical and lesion awareness for reliable diagnosis and spatial interpretability. In contrast, supervised specialist models achieve strong performance on specific tasks but typically lack generalization across diseases and anatomies. In this work, we present SuG, a Super-Generalist framework that unifies generalist vision-language learning with specialist objectives, enabling both broad generalization and specialist-level diagnostic capability. We perform specialist-enhanced vision-language alignment in SuG by incorporating spatial priors from multiple segmentation experts, including anatomy, class-specific lesion and class-agnostic lesion segmentors that captures lesions beyond anatomies annotated during training. To improve lesion grounding capability, we leverage lesion masks as spatial priors to calibrate text-conditioned visual attention, encouraging disease-related semantics to focus on clinically relevant regions. We evaluate SuG on extensive chest and abdominal CT benchmarks, including CT-RATE, Merlin, MedVL-CT69K, and several in-house tumor datasets. SuG achieves state-of-the-art performance across a wide range of disease diagnosis tasks and surpasses specialist models on several critical tumor diagnosis benchmarks. Furthermore, SuG demonstrates strong lesion grounding capability, including robust generalization to lesion types lacking class-specific supervision.

Model editing promises a fast, targeted way to correct post-deployment mistakes in medical vision-language models (VLMs) without costly retraining. However, existing multimodal model editing benchmarks focus on general-purpose tasks and do not reflect realistic clinical domain requirements and variability. To address this, we introduce M3Bench, a clinically grounded benchmark for multimodal model editing that evaluates whether an edit remains reliable, precise, and generalizable under the challenges of image and text variation, modality and protocol shifts, clinical knowledge composition, and temporal progression. M3Bench contains 16,276 questions spanning diverse anatomy, modalities, and specialties, and supports both single and sequential edits. By evaluating 4 representative editors across 6 medical and general VLMs, we find that no method excels across all criteria. Gradient-based editors achieve strong transfer but suffer from catastrophic locality violations, whereas memory-based methods preserve locality but lack compositional generality and exhibit high backbone-dependent hyperparameter sensitivity. We further attribute these failures to the latent space geometry of VLMs and how different editing methods shift its landscape. Overall, M3Bench establishes a rigorous clinical stress test for multimodal model editing and offers actionable guidance for safer post-deployment adaptation. The benchmark is publicly available at https://github.com/BioMed-AI-Lab-U-Michgan/M3Bench .

Large vision language models (VLMs) report strong accuracy on medical question-answering, yet it remains unclear whether they reason from visual evidence or exploit textual shortcuts. We introduce a counterfactual evaluation framework that decouples visual and textual contributions by substituting input images with controlled surrogates blank, pixel-shuffled, image-absent, and CLIP-retrieved hard negatives and derive a suite of grounding metrics including the Visual Reliance Score (VRS) and Visual Hallucination Rate (VHR). We further introduce CORAL (COntrastive Retrieval-Augmented Learning), a 7B-parameter LoRA fine-tune of Qwen2.5-VL-7B trained with a Contrastive Grounding Objective (CGO) that penalises answer invariance under hard-negative image swaps. On a paired controlled evaluation across four closed-form medical VQA benchmarks (PathVQA, PMC-VQA, SLAKE, VQA-RAD; n=400 total), CORAL improves macro accuracy by +6.7 pp (P(Delta>0)=0.988) and reduces VHR by 8.0 pp (P<0.001) over the matched Qwen2.5-VL-7B base; neither MedVLThinker RL variant achieves a significant gain on either metric. Cross-domain diagnostics further reveal that image substitution costs only <=6.5 pp on medical benchmarks versus 48-61 pp on general-domain tasks, situating the grounding gap that CGO targets. We discuss evaluation limitations openly including train/eval benchmark overlap and underpowered secondary metrics and release our framework, training code, and model weights to support reproducible grounding audits of medical VLMs.

Large vision-language models (LVLMs) have achieved strong performance across many medical imaging tasks, yet their application to ultrasound remains limited due to its inherent complexity and variability. In this work, we revisit what is truly needed to enable real-world ultrasound understanding. Instead of introducing complex architectures or elaborate training strategies, we show that data scale and clinically faithful data alignment are the key factors. We construct a large-scale dataset of 1.5M real-world ultrasound examinations, containing 17.7M images, multi-organ coverage, and paired uncurated clinical reports. Crucially, we organize the data at the examination level, aligning multiple images with their corresponding reports to reflect real clinical workflows. We then fine-tune a standard LVLM using low-rank adaptation (LoRA) on this dataset without task-specific modifications. Surprisingly, this simple recipe already leads to strong performance across diverse ultrasound understanding tasks, outperforming prior methods designed with more complex pipelines. Beyond these results, we present model and data scaling analyses that provide insights into the role of scale in ultrasound LVLMs.

The Segment Anything Model with Concepts (SAM3) heralds a new paradigm for open-vocabulary segmentation through natural language interaction, offering significant potential for medical image analysis. However, effectively adapting such a powerful vision-language model to the diverse and nuanced domain of medical imaging remains a key challenge. Naive fine-tuning is parameter-inefficient, while standard Mixture-of-Experts (MoE) methods introduce prohibitive computational overhead, limiting their clinical applicability. To address this, we propose Dual-Adaptive SAM3 (DA-SAM3), a novel framework that achieves both high segmentation accuracy and extreme parameter efficiency via a dual-adaptive specialization mechanism. Our first adaptation is task-aware: a Dynamic Expert Router (DER) that sparsely activates the most relevant experts by jointly reasoning about the visual input and the textual concept prompt, mimicking a clinical consultation process. Our second adaptation is parameter-aware: a Decomposed Parameterized Experts (DPE) design that represents each expert as a shared frozen base (inherited from the pretrained SAM3) and a lightweight trainable low-rank delta, reducing MoE parameter overhead by over 80%. Extensive experiments on multiple public medical segmentation benchmarks demonstrate that Dual-Adaptive SAM3 not only matches or exceeds the accuracy of fully fine-tuned SAM3 and standard MoE baselines, but also achieves a notable 5% gain over current state-of-the-art methods, with interpretable results validating its effectiveness. The code is available at: https://github.com/Reconsider80/DA-SAM3.

Surgical vision-language foundation models typically adopt educational materials, such as surgical lecture videos, to transfer surgical knowledge encoded in language into visual representations. These knowledge are multi-dimensional and hierarchical: fine-grained action cues appear in narration, mid-level key steps are summarized in subsection headings, and global procedural context, such as patient history and surgical strategy, is described in abstract texts. Prior work largely collapses these heterogeneous signals into a single flat embedding space, implicitly assuming independence across hierarchy levels. However, this is suboptimal because it ignores cross-level semantic containment, e.g., actions belong to steps, steps compose phases, weakens long-range dependency modeling. To this end, we propose a hyperbolic surgical video-language pre-training framework that explicitly preserves the hierarchical structure by mitigating structural false negatives induced by procedural context and enforcing semantic consistency between parent phases and their constituent child steps. Extensive experiments on multiple surgical benchmarks show consistent gains in zero- and few-shot phase recognition across procedures and institutions.

Current evaluation protocols for Vision-Language Models (VLMs) in Radiology Report Generation (RRG) rely on report-level metrics that measure lexical overlap or aggregate clinical correctness. However, such metrics do not test whether individual diagnostic statements stem from the actual pathological evidence visible in the image. This allows models to achieve competitive scores by exploiting learned priors or spurious correlations, a failure mode we refer to as vision shortcut. We introduce SHOVIR, a benchmark for evaluating vision shortcut behavior in RRG. SHOVIR extends two spatially annotated chest X-ray datasets, MIMIC-CXR and PadChest-GR, with per-box CheXpert labels, and defines image-level and disease-level occlusion experiments that contrast baseline performance on clean images against localized, region-specific perturbations. Comparing predictions across these conditions isolates two failure modes at the disease-class level: direct shortcuts, where a finding persists after its visual evidence is removed, and contextual shortcuts, where detection degrades once co-occurring pathologies are occluded despite the target region remaining intact. Benchmarking eight state-of-the-art VLMs, we find that shortcut behavior varies substantially across architectures and datasets. Models achieving the highest baseline report quality do not necessarily rank highest in spatial grounding, revealing that clinically fluent generation can coexist with shallow reliance on visual evidence. These findings expose a blind spot in current RRG evaluation and motivate region-aware assessment protocols.

A synthetic measurement of model competence is useful only if it survives the move to real data, yet the real labels that would verify it are exactly what medical imaging lacks. We ask whether transfer can be predicted in advance, label-free, and answer with a mechanism: on synthetic digital twins, competence that is donor-driven (a property of the transplanted nodule) survives the synthetic to real change of host, while host-driven competence (a property of the surrounding anatomy) need not. We test this on three lung CT vision-language tasks chosen to span that axis, across five public VLMs, four guidance conditions, and seven real datasets. The prediction holds in every case: presence and size orderings transfer (R2 >= 0.96), lobe does not; the split survives leave-source-out calibration, and the diagnostic names that boundary before any real label. TrialCouncil, a training-free council calibrated only on synthetic CT, confirms it by matching the best fixed model exactly where transfer is predicted. The contribution is not the router but the finding that transfer itself is predictable, label-free, from synthetic data alone.

Large vision-language models (LVLMs) are increasingly used for clinical image understanding, yet they remain vulnerable to \emph{hallucinations}--producing textual findings or attributes not supported by the image. We present a vision-traceable hallucination detection framework that audits arbitrary LVLM responses via visual evidence grounding, requiring neither modification nor internal access to the hidden states of LVLMs. Given an LVLM response, we extract visually verifiable entities and use a medical-domain-adapted Qwen-VL grounding verifier to localize each entity on the input image. To enhance the robustness of our detection method, we introduce a counterfactual entity perturbation method and estimate visual evidence uncertainty by contrasting factual and counterfactual grounding results. Specifically, we compute an entity-level uncertainty score from the positive confidence, counterfactual confidence, and their grounding overlap for binary hallucination decision-making. Experiments on multiple medical imaging modalities and LVLM backbones demonstrate that our method consistently improves hallucination detection performance over recent baselines, while providing interpretable localization evidence and strong cross-model transferability. Code and dataset are available at https://github.com/Agentic-CliniAI/CounterVHD.

Large Vision-Language Models (LVLMs) specialized in healthcare are emerging as a promising research direction due to their potential impact in clinical and biomedical applications. However, progress is constrained by the scarcity of high-quality medical multimodal data, concerns about robustness in safety-critical settings, and the narrow and potentially contaminated evaluation benchmarks that limit reliable assessment. To address these issues, the field requires state-of-the-art solutions to be fully open and reproducible systems in which all components can be inspected, evaluated, and improved. This work introduces Aloe-Vision-Data, a large-scale, quality-filtered mixture which integrates both medical and general domains across multimodal and text-only sources, designed for direct use in model fine-tuning. Building on this dataset, we train the Aloe-Vision family of medical LVLMs, openly released with full weights, training recipes and data, in two scales (7B and 72B). Through comprehensive benchmarking, we demonstrate that high quality training mixtures produce balanced LVLMs which yield significant gains over the baseline models without compromising general capabilities, achieving competitive performance with respect to state-of-the-art alternatives. To support reliable evaluation, we introduce CareQA-Vision, a carefully curated vision benchmark derived from MIR and EIR exams, the residency entrance exams for medical and nursing specialists in Spain, offering novel vision questions with low likelihood of contamination. Finally, we show that current LVLMs remain vulnerable to adversarial and misleading inputs, underscoring reliability challenges in clinical contexts.

Reasoning in multimodal large language models (MLLMs) has shown strong promise in medical imaging. However, this reasoning is usually free-form text judged only by its final answer, making it hard to interpret and verify, especially in 3D radiology, where a diagnosis should be traceable to evidence in the scan. Existing chest CT question-answering datasets compound this by reducing expert radiology reports to answer-only pairs, dropping the reasoning that links findings to conclusions and omitting the patient history clinicians rely on. As a result, reasoning-capable 3D chest CT MLLMs remain out of reach, as neither the structured supervision needed to train them nor the protocol needed to verify their reasoning yet exists. We introduce CORTEX (Clinically Organized Reasoning and sTructured EXplanation), a structured reasoning benchmark for 3D chest CT. For each question, CORTEX restores the missing reasoning as a four-stage diagnostic trace mirroring a radiologist's workflow: task understanding, visual observation, diagnostic reasoning, and answer synthesis. We generate these traces using frontier large language models with broad medical and general-domain knowledge, then filter and verify them with a stage-level evaluation protocol combining automated rubric scoring with expert radiologist review. Crucially, both the reasoning structure and evaluation rubrics are designed in close collaboration with clinicians. Built on CT-RATE, a large, publicly available chest CT dataset without reasoning annotations, CORTEX comprises 76,177 validated reasoning traces across open-ended VQA, closed-ended VQA, and report generation, providing both the structured supervision and the stage-level evaluation protocol needed to build and evaluate trustworthy reasoning models for 3D chest CT. Our dataset and evaluation code is available at https://huggingface.co/datasets/aneesurhashmi/cortex

Transcatheter Aortic Valve Replacement (TAVR) planning requires meticulous multimodal reasoning. However, adapting Multimodal Large Language Models (MLLMs) to this high-stakes domain is severely impeded by diagnostic hallucinations, where generated text lacks anatomical grounding. To address this, TAVR-VLM is introduced: a novel framework featuring Risk-Conditioned Causal Grounding Attention (R-CGA) that instantiates a model-internal ``Risk $\rightarrow$ Region $\rightarrow$ Word'' structural grounding pathway. R-CGA compresses multimodal inputs into a causal risk bottleneck, purifying dense visual features into a global risk mask. During autoregressive generation, a support-projected causal consistency objective constrains token-level grounding within the risk-defined support mask. Evaluated on $\text{M}^3\text{TAVR}$, a comprehensive 1,482-patient cohort, TAVR-VLM establishes a new state-of-the-art. It achieves an AUROC of 0.896, boosts CIDEr to 0.936, and drastically reduces the hallucination rate to 8.1%, thereby improving interpretability for evidence-based surgical AI.

Medical vision-language models typically generate diagnoses through single-pass inference without indicating which image regions support their conclusions. This lack of spatial grounding limits clinical utility: outputs cannot be audited, and models may hallucinate findings on normal scans. We present BrReMark (Brain Rethink via ROI Marking), a framework that introduces explicit region marking into brain MRI diagnosis. The model first generates hypotheses about potential abnormalities and grounds them through explicit bounding box marking, then verifies conclusions by re-examining the marked evidence. Training combines supervised fine-tuning on structured reasoning trajectories with reinforcement learning using a composite reward over localization accuracy and diagnostic reasoning. Furthermore, we integrate a domain randomization-based pathology synthesis augmentation strategy to improve the model's generalizability to out-of-distribution (OOD) data. On internal benchmark, BrReMark improves mAP50 from 0.74% to 37.54% compared to the base model, while achieving 21.57% Clinical F1 and 45.26% diagnostic accuracy. On NOVA OOD benchmark, it also achieves competitive overall performance with a 45.7% reduction in false positives compared to the state-of-the-art, indicating reduced hallucination on rare pathologies. These findings suggest that explicit hypothesis-verification grounding is a practical path toward trustworthy open-ended brain MRI diagnosis across both in-distribution and OOD settings.

Vision-language pre-training (VLP) holds great promise for general-purpose medical AI by leveraging radiology reports as rich textual supervision, yet existing methods struggle with 3D CT imaging due to inefficient visual backbones and coarse semantic alignment. To address these issues, we propose a tailored VLP framework featuring three key components: (1) a CNN-ViT hybrid encoder that replaces ViT's patch embedding with a 3D CNN backbone to efficiently capture local anatomical details while preserving global attention and compatibility with pre-trained cross-modal priors; (2) a disease-level contrastive learning mechanism using learnable query tokens to dynamically extract disease-specific semantics from full reports and align them with corresponding visual features, thereby disentangling distinct diseases within the same anatomical region; and (3) a diagnosis-aware prompt strategy that employs real clinical phrases and aggregated disease prototypes to bridge the pre-training-inference gap and enhance zero-shot diagnostic reliability. Our model achieves state-of-the-art performance on CT-RATE (84.4% AUC, +5.1%) and Rad-ChestCT (75.4% AUC, +5.4%), with even larger gains (+9.8% AUC) on a challenging 60-disease benchmark, and demonstrates strong transferability to radiology report generation, underscoring the generality and clinical utility of our approach.

In longitudinal clinical practice, every chest X-ray is read in the context of the patients prior exam, and much of what the radiologist communicates is the change from one visit to the next. To the best of our knowledge, we present the first training-free best-of-N sampling scheme for pre-trained chest X-ray report generators that is explicitly aware of this longitudinal prior to current transition. We call it transition-aware best-of-N sampling, each report is split into sentences and embedded into an unordered set in Rd; each (prior, current) pair is reduced to a fixed-dim directional vector via a set-to-set distance designed to encode the change between the two sets; and candidates are scored by cosine distance from their candidate transition vector to a cached bank of ground-truth training transition vectors, aggregated as min or kNN. We instantiate the framework with four directional set distances (mean-shift, novelty residual, directed-Hausdorff anchor, and cost-weighted optimal transport) and evaluate on a multi-visit AP-PA cohort, running inference under three prompts on three vision-language generators. Transition-aware best-of-N outperforms random selection across the board, with the largest relative gains on the Impression section.

Recent advances in vision-language models (VLMs) such as CLIP have demonstrated strong generalization across natural-image domains. However, adapting these models to biomedical imaging is non-trivial: full-model fine-tuning is computationally expensive, while medical data are often scarce and exhibit subtle, fine-grained inter-class differences, making parameter-efficient adaptation particularly critical. Visual Reprogramming (VR) offers a parameter-efficient alternative by injecting learnable perturbations into the input space, but existing VR approaches for VLMs mainly focus on positive class prompts and overlook confusing negatives, leading to miscalibrated predictions in fine-grained medical scenarios. We present BioMedVR, the first VR-based framework for biomedical imaging, enabling few-shot adaptation of pretrained VLMs through compact learnable VR modules. To mitigate class confusion, we introduce a Confusion Minimization Mechanism that leverages LLM-generated confusion-aware attributes together with a Confusion-Suppression Loss to explicitly reduce false-positive alignment. Moreover, the designed Mixture-of-Prompt Experts combines a positive expert for main-class discrimination and a negative expert for confusion suppression, balanced via adaptive gating. Extensive experiments on 18 datasets, including 11 biomedical datasets and 7 natural image benchmarks, demonstrate that BioMedVR achieves superior accuracy and generalization, effectively bridging VR and VLMs in biomedical domains.

Vision-language contrastive pretraining has become the dominant recipe for 3D medical foundation models, leveraging the large volumes of paired scans and reports produced in clinical practice. However, medical images usually span dozens of organs, and radiological reports are much longer than typical natural image captions and are composed of multiple structured sections. CLIP-style pretraining compresses this structure by encoding each modality into a single global token, at the risk of losing important details. We introduce ConQuer (Concept Queries), an image-text pretraining method that augments CLIP's global alignment with a set of localized alignments, one per concept. ConQuer splits the report into concept-specific sections and learns cross-attention queries that pool the matching image features without using any segmentation mask or spatial supervision. Contrastive learning is then applied independently for each concept. Concepts can be any unit of semantic localization; here, they are anatomical regions, one query per organ or gross body region. As a byproduct, each query learns attention maps focused on its concept, providing built-in spatial interpretability. We use ConQuer to train Jolia, a 3D CT foundation model on chest and abdominal CT. Jolia consistently outperforms a CLIP baseline on findings classification, report generation, and cross-center transfer, and sets a new state of the art across multiple public benchmarks. Jolia's weights are available at https://huggingface.co/raidium/Jolia

Vision-language models (VLMs) are prone to hallucination, which remains a major barrier to their safe deployment in clinical practice. To date, most hallucination detection methods have been evaluated on radiology benchmarks such as MIMIC-CXR and VQA-RAD, while gastrointestinal (GI) endoscopy remains largely underexplored. In this paper, we benchmark nine hallucination detection methods on the Gut-VLM dataset, a GI diagnostic Visual Question Answering (VQA) dataset with 4,392 test VQA pairs, across five VLMs (MedGemma-4B, MedGemma-27B, LLaVA-Med-7B, LLaVA-v1.6-7B, and Lingshu-32B). The methods span three categories: black-box methods (RadFlag, SelfCheckGPT-NLI), gray-box methods (AvgProb, AvgEnt, MaxProb, MaxEnt, Semantic Entropy, and VASE), and a white-box method (ReXTrust). Our results show that ReXTrust, a white-box method, achieves the highest AUC across all five models, outperforming the strongest alternative method on each VLM by a statistically significant margin (paired permutation test, p < 0.001 in all cases), reaching a peak AUC of 93.0 on MedGemma-4B. White-box hidden-state access provides a consistent advantage of 19.5 AUC points on average (range: 9.5--33.5), with ReXTrust maintaining strong performance even on LLaVA-v1.6-7B (AUC 79.9), where black-box methods and clustering-based gray-box methods collapse to near-chance performance. Among non-white-box methods, token-level gray-box statistics (MaxEnt, MaxProb) are the strongest alternatives, outperforming both clustering-based gray-box methods (Semantic Entropy, VASE) and black-box approaches on average. We further identify confident confabulation, a failure mode in which models hallucinate with high inter-sample consistency or high token-level probability, as a systemic failure for both consistency and uncertainty-based methods.

While Vision-Language Models (VLMs) show great promise in volumetric medical report generation, they frequently suffer from visual hallucinations and a lack of grounding in 3D CT data. Current Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) strategies typically optimize text fidelity alone, essentially rewarding correct diagnoses derived from language priors rather than genuine visual perception. To address this, we propose cross-view aligned Evidence-driven Multimodal Reinforcement Learning (Evidence-MRL, noted as E-MRL), a reliable RL reasoning framework that formulates the generation process as a Markov Decision Process of "diagnosis-localization-verification". Unlike standard approaches, our model is explicitly trained to identify a "key evidence slice" alongside the global diagnostic report, grounding its findings in verifiable visual evidence. Crucially, we introduce a novel cross-view consistency reward, which validates the semantic alignment between the golden-standard report and a local visual re-query of the selected key slice, providing additional rewards for correctly-localized reasoning. Experiments on large-scale 3D CT tumor datasets demonstrate that E-MRL significantly reduces hallucinations and improves diagnostic accuracy compared to SFT and RL baselines, offering a clinically interpretable solution for visually-grounded and tumor analysis.

Automated diagnosis of 3D brain CT scans is essential for critical care, yet it remains challenging due to the heavy reliance on manual annotations and the limited semantic understanding of conventional models. While 2D foundation vision-language models (VLMs) have shown remarkable generalization, effectively transferring their representational power to 3D volumes remains an open problem. In this paper, we propose Brain-Adapter, a novel dual-stream multiple instance learning (MIL) framework that leverages pre-trained 2D biomedical VLMs and raw diagnostic reports for robust scan-level multi-label classification. Specifically, we introduce a Text-Conditioned Attention (TCA) mechanism, utilizing raw diagnostic sentences as semantic queries to dynamically align visual cues with specific disease concepts. Concurrently, a parallel visual MIL stream captures global scan characteristics, supervised by structured labels extracted via a Large Language Model (LLM). To ensure representation coherence, a consistency constraint enforces synergy between the two streams. During inference, an Uncertainty-Aware Refinement (UAR) module dynamically calibrates and fuses these dual-stream predictions to resolve ambiguous cases. Extensive experiments demonstrate that our method significantly outperforms state-of-the-art 3D models and standard MIL approaches. By eliminating the reliance on dense annotations, Brain-Adapter provides a highly scalable and clinically viable solution for 3D acute intracranial pathology analysis.

Medical vision-language models (VLMs) such as BiomedCLIP generalize broadly, but adapting them to a clinical service is as much a safety problem as an accuracy one. Updating a deployed model for a new imaging modality can fail silently in two ways that harm patients: it can forget modalities it already handled (catastrophic forgetting), and it can drift from its trustworthy pretrained prior toward modality-specific shortcuts. We study parameter-efficient continual adaptation through these two properties rather than leaderboard accuracy, presenting CADRE: a frozen-backbone framework combining low-rank adaptation (LoRA) with an online, self-scaling, similarity-aware elastic weight consolidation term that bounds retained-competence loss, and an anchor-to-prior penalty bounding embedding drift from the frozen prior. Two short guarantees, a bound on total consolidation mass and a scale-invariance property, remove the scale-related sources of vanilla EWC's order fragility. Using breast cancer across three maximally dissimilar modalities (histopathology, ultrasound, chest radiography) as a controlled cross-modality stress test, under a multi-seed, multi-order protocol with paired significance testing and training approximately 0.23% of parameters, CADRE attains the highest accuracy, SPQ, and backward transfer and the lowest forgetting among adapting methods, reducing forgetting roughly sevenfold versus the strongest regularized baseline (0.075 to 0.011; paired p=0.023) and achieving positive backward transfer where every baseline is negative. We frame these as stability properties aligned with clinical-safety desiderata, not a deployment guarantee; robustness to distribution shift and adversarial inputs is out of scope.

Purpose: To evaluate whether large language model (LLM)-assisted label cleaning can identify label-report discordance in CT-RATE, a large-scale public chest CT dataset. Materials and Methods: After report-level deduplication, 24,446 unique radiology reports were identified. Twelve reports were excluded from the primary GPT-5.4 analysis because of Microsoft Azure AI Foundry content-safety filtering, leaving 24,434 reports and 439,812 label instances across 18 abnormality categories. GPT-5.4-derived binary labels were generated from report text using structured JSON output and compared with existing CT-RATE labels. Discordant instances were adjudicated by radiologists. In addition, 100 randomly sampled reports were manually annotated to compare CT-RATE labels, individual LLM-derived labels, and multi-LLM majority-vote labels against radiologist-annotated reference labels. Results: Overall agreement between GPT-5.4-derived and CT-RATE labels was 96.4%, with Cohen's kappa of 0.884. Lymphadenopathy showed the lowest agreement and kappa. In discordance review, radiologist adjudication supported GPT-5.4-derived labels in 72 of 97 (74.2%) general discordant instances and 91 of 99 (91.9%) targeted lymphadenopathy discordant instances. Against radiologist-annotated reference labels, multi-LLM majority-vote labels achieved the highest label-macro-averaged F1 score and Cohen's kappa. Conclusion: LLM-assisted label cleaning identified clinically meaningful label-report discordance in CT-RATE and may support scalable quality improvement of public imaging datasets. The cleaned dataset will be made publicly available to support future research.

Precision medicine in ophthalmology requires accurate longitudinal predictions, but the fragmented nature of multimodal clinical data remains a barrier to forecasting. We introduce OphthaDT, an LLM-based digital twin for ophthalmology that serializes longitudinal patient histories from 3,220 patients across four Phase III clinical trials into structured narratives to forecast best corrected visual acuity (BCVA). In benchmarks spanning up to 100 weeks, OphthaDT demonstrated the lowest prediction error in neovascular age-related macular degeneration (nAMD), achieving an average mean absolute error (MAE) reduction of 6.0% compared to all baselines. In diabetic macular edema (DME), OphthaDT demonstrated competitive performance against all baselines while outperforming Random Forest and XGBoost by an average MAE reduction of 2.6% and 6.9%, respectively. Results reveal that OphthaDT's predictive advantage scales with trajectory complexity: whereas linear models remain effective for the more stable treatment responses of DME, OphthaDT's capacity is better suited for capturing the high longitudinal variability of nAMD. Finally, OphthaDT handles irregular sampling without imputation, positioning LLM-based clinical trajectory modeling as a methodology that could reduce patient burden and accelerate drug development.

Automated radiology report generation (RRG) has gained increasing attention because it can reduce the heavy workload of clinical report writing. However, most existing methods mainly optimize for natural language generation (NLG) metrics that focus on language fluency, while providing little control over clinically important factors such as precision and recall. As consequence, generated reports may be fluent but not well aligned with different clinical needs. To address this challenge, we propose a reinforcement learning framework for precision recall controllable RRG, where a control parameter explicitly adjusts the trade-off between clinical precision and recall during inference. This design allows the model to flexibly generate reports according to different clinical requirements. To ensure clinical correctness, we introduce a clinical reward into the training objective, which helps improve clinical efficacy (CE) beyond standard language-based optimization. In addition, we apply a group-relative training strategy that normalizes rewards within each training group, reducing reward variance and improving training stability. Extensive experiments on the MIMIC-CXR dataset show that our method consistently outperforms state-of-the-art approaches in both NLG and CE evaluation metrics, while providing reliable control over the CE precision recall trade-off.

Medical Vision-Language Models (Med-VLMs) achieve strong expert-level performance, yet their ability to generate patient-accessible descriptions remains underexplored. With the 21st Century Cures Act now mandating immediate patient access to diagnostic imaging results, evaluating whether Med-VLMs can bridge this Expert-Lay Gap is both urgent and clinically consequential for patient education and shared decision-making. To this end, we introduce MedLayXPlain, the first large-scale multimodal benchmark and evaluation framework for Medical Lay Language Generation (MLLG). MedLayXPlain-122K provides 122,789 region-grounded samples across 8 imaging modalities from 12 publicly available source datasets, each comprising a medical image with paired expert and lay captions anchored in a three-level Unified Medical Language System (UMLS) ontology hierarchy spanning 7 semantic groups, 43 semantic types, and 2,411 medical concepts. Lay captions are constructed via Hierarchical Ontology-Verified Refinement (HOVER), a three-step pipeline combining patient-centric vocabulary mapping, LLM-based constrained rewriting, and cross-model visual verification to enforce semantic equivalence while preventing hallucination. We further introduce MedLayEval, a lightweight 3B evaluator distilled from a 27B verifier that scores expert-lay alignment across five clinically grounded attributes, addressing the poor correlation between standard NLG metrics and clinical judgment. Benchmarking 33 VLMs on MedLayXPlain-122K reveals a systematic Expert-Lay Gap: medical VLMs achieve strong expert captioning but suffer significant lay-register degradation, while general-purpose VLMs produce more accessible language yet lack clinical precision, confirming that neither current paradigm adequately serves patient-facing communication.

The evaluation of vision-language models (VLMs) for chest X-ray (CXR) analysis has largely been limited to disease-presence classification without visual grounding. Such evaluations fail to verify the expert-level lesion perception necessary to ensure the clinical reliability of VLMs. To address these limitations, we introduce CheXpercept, a sequential, multi-level perception benchmark that mirrors a radiologist's cognitive workflow across coarse-level detection, fine-level contour evaluation and revision, and semantic-level attribute extraction. To ensure high clinical fidelity at scale, we construct the dataset using a semi-automated generation pipeline paired with a review by six medical experts. CheXpercept contains 10,400 QA items derived from 2,100 CXRs, covering seven clinically critical pulmonary and cardiac lesions. To demonstrate the current landscape of VLM perception, we benchmark 14 general and medical VLMs on CheXpercept. The models achieve adequate performance only at the coarse level, with accuracy degrading precipitously on deeper visual tasks. Notably, medical VLMs show almost no perceptual advantage over their general-domain counterparts, highlighting a systemic flaw in current domain adaptation. The code and dataset will be publicly available.

Medical vision-language models (VLMs) enable zero-shot clinical image classification, yet reliably detecting out-of-distribution (OOD) inputs at deployment remains an open problem. No static scoring method works across all shift types: Maximum Concept Matching (MCM) on FLAIR achieves 76.4% AUROC for far-OOD but only 42.4% for covariate shifts such as ultra-wide-field fundus images, effectively random. We trace this to a structural mismatch: covariate-shifted inputs are indistinguishable from in-distribution samples in softmax space, yet occupy distinct regions in the VLM embedding space. To exploit this untapped signal, we propose PROTON (PROtotype-based Test-time ONline OOD detection), a lightweight post-hoc module that maintains an online prototype bank from high-confidence test predictions and adaptively fuses prototype distance with MCM scoring via stream-level variance statistics, requiring no model modification, training data, or prompt engineering. On the ophthalmology benchmark FLAIR + FIVES, PROTON improves MCM by +23.9 AUROC on covariate shift, +8.8 on semantic shift, and +8.1 on far-OOD, making it the only zero-shot method to improve all three without hierarchical prompts or labeled data. Code is available at https://github.com/GenMI-Lab/PROTON, and the project page is available at https://genmi-lab.github.io/PROTON.

Inference-time engineering can alter model behavior without fine-tuning. However, its utility for improving diagnostic performance in medical vision-language models (VLMs) remains unclear. We aim to evaluate whether Contrastive Activation Addition (CAA) can improve pneumonia classification in chest radiograph VLMs without updating model weights. Three frozen chest radiograph VLMs (MedGemma-4B-IT, NV-Reason-CXR-3B, and CheXOne-3B) were evaluated on the public Kermany pneumonia test set. Classification was based on the logits of the tokens Yes and No under a binary prompt. Steering vectors included a 30-pair answer-bias control, a 30-pair pneumonia text contrast, and an image-conditioned contrast derived from 30 pneumonia and 30 normal development images. A deterministic 200-image development set was used for layer and scale selection (100 images) and threshold calibration (100 images). Performance was assessed using ROC-AUC, PR-AUC, F1 score, threshold analyses, reverse-vector controls, random-vector controls, and conditional bootstrap confidence intervals. Fixed-threshold F1 improvements were frequently observed but did not consistently indicate improved diagnostic performance. For MedGemma-4B-IT. NV-Reason-CXR-3B showed the strongest benefit: calibrated F1 improved from 0.7692 in the zero-shot setting to 0.8619 with pneumonia-text steering and to 0.8727 with image-conditioned steering. For CheXOne-3B, pneumonia-text steering increased calibrated F1 from 0.8528 to 0.8666, although the confidence interval crossed zero. On this public pneumonia benchmark, CAA substantially altered prediction score distributions and operating characteristics without fine-tuning. Meaningful performance gains were observed in one of three evaluated VLMs, suggesting that activation steering may serve as a lightweight approach for adapting medical VLM behavior.

We study how to train visually grounded vision-language models (VLMs) for radiology without manual spatial annotations. We introduce RefRad2D, a large-scale bilingual (German/English) dataset of 1.2M CT and MR image-text pairs derived from clinical practice, with task-specific VQA and spatial grounding subsets generated automatically via LLM-based curation and automated segmentation. Trained on this data, our model RadGrounder jointly performs report generation, visual question answering, and spatial grounding via bounding-box detection or segmentation. On external VQA benchmarks (Slake, VQA-RAD), RadGrounder achieves competitive results with specialized medical VLMs. Adding our clinical data to the training mixture improves open-ended VQA over fine-tuning on the downstream datasets alone, showing the transferability of our dataset. Crucially, adding grounding supervision does not degrade language quality, enabling spatially verifiable outputs at no cost to VQA performance.

Recently, vision-language models (VLMs) have made significant progress in 3D scene understanding, driving advances in applications such as embodied intelligence and robotic vision. However, existing approaches typically either rely directly on explicit 3D inputs (e.g., point clouds or RGB-D sequences), or introduce an additional 3D geometry encoder to derive 3D-aware visual tokens from 2D images. Such designs structurally decouple 3D geometric perception from the rich 2D semantics learned via vision-language pre-training, hindering the development of a unified 3D vision-language representation. In this work, we propose Occ-VLM, a novel framework for 3D scene understanding that operates purely on posed RGB images and employs a single 2D vision encoder. Specifically, Occ-VLM reconstructs 3D scene occupancy as an auxiliary geometric prior, which is utilized to spatially associate foreground 2D tokens with 3D space. These tokens are then decoded by a Large Language Model (LLM) for unified scene understanding. Extensive experiments demonstrate that Occ-VLM achieves both accurate geometric perception and robust vision-language reasoning: it attains state-of-the-art performance on multi-view occupancy prediction, while performing on par with 3D-input VLMs on 3D Visual Question Answering (VQA) and 3D dense captioning benchmarks.

Vision-Language models (VLMs) reliability in medical diagnosis is challenged by trust-undermining hallucinations. Existing hallucination detection approaches mainly focus on identifying factual inconsistencies between generated text and reference data. While some studies analyze where models attend in images, they seldom verify whether such attention truly reflects the visual evidence supporting the generated text. To address this gap, we propose Co}unter-Evidence Verification (CoEV), a training-free plug-and-play framework that detects and corrects hallucinations through evidence-based factual consistency verification. CoEV performs bidirectional verification between textual assertions and visual evidence, testing whether each statement is supported by its corresponding evidence region, and assigns each statement into a four-quadrant diagnostic map capturing combinations of text factuality and visual grounding. CoEV detects hallucinated content and serves as a post hoc refinement tool, correcting hallucinations without retraining. Extensive experiments on four medical datasets show that CoEV combats hallucinations in VLMs.For hallucination detection, CoEV consistently outperforms existing methods, improving average PR-AUC and ROC-AUC by 3.0% and 3.9% absolute points respectively, with notable gains of up to 18.5% in specific VQA scenarios. For hallucination correction, it improves Micro-F1 by up to 12.5%, reduces hallucination rates by over 11.9% on medical report generation, and also boosts medical VQA accuracy. These results show that CoEV enables reliable detection and correction of hallucinations, providing clinicians with dependable, evidence-based cues for diagnosis. Code will be released upon acceptance.

Chronic wound assessment remains a clinically challenging task that requires accurate interpretation of wound morphology, tissue composition, vascular characteristics, and infection risk. Recent advances in Vision-Language Models (VLMs) have introduced the possibility of automated multimodal wound analysis through image understanding combined with clinical reasoning. This study evaluates the performance of several general-purpose and medically specialized open-source and proprietary VLMs for clinical wound assessment using an expanded, curated dataset of 20 clinically diverse wounds spanning vascular, surgical, ischemic, venous, lymphedema, and amputation-related etiologies. Six VLMs were evaluated using a structured twelve-question clinical framework covering wound classification, infection risk, vascular intervention recommendations, debridement urgency, wound therapy selection, and advanced management planning. Across 20 wound cases and 240 clinician-graded wound-analysis decisions, ChatGPT achieved the highest overall performance with 174/240 correct responses (72.50%), followed by Claude with 149/240 (62.08%). Among the open-source and medically specialized models, HuluMed achieved the strongest performance with 96/240 correct responses (40.00%), followed by Gemma 3 (81/240, 33.75%), MedGemma 4B (62/240, 25.83%), and MedGemma 27B (42/240, 17.50%). The findings suggest that frontier general-purpose multimodal systems currently demonstrate substantially stronger wound-analysis performance than medically specialized alternatives, highlighting the continued importance of broad multimodal reasoning capabilities alongside domain-specific medical knowledge. Although current VLMs demonstrate promising potential for clinical decision support, substantial limitations remain in advanced wound-management reasoning, procedural planning, and autonomous clinical reliability.

Domain adaptation remains a central challenge in 3D vision, especially for multimodal foundation models that align 3D point clouds with visual and textual data. While these models demonstrate strong general capabilities, adapting them to downstream domains with limited data often leads to overfitting and catastrophic forgetting. To address this, we introduce ReFine3D, a regularized fine-tuning framework designed for domain-generalizable tuning of 3D large multimodal models (LMMs). ReFine3D combines selective layer tuning with two targeted regularization strategies: multi-view consistency across augmented point clouds and text diversity through synonym-based prompts generated by large language models. Additionally, we incorporate point-rendered vision supervision and a test-time augmentation mechanism with confidence-based aggregation to further enhance robustness. Extensive experiments across different 3D domain generalization benchmarks show that ReFine3D improves base-to-novel class generalization by 1.36%, cross-dataset transfer by 2.43%, robustness to corruption by 1.80%, and few-shot accuracy by up to 3.11%, outperforming prior state-of-the-art methods with minimal added computational overhead.

Medical vision-language models report strong chest radiograph accuracy, and this is increasingly read as evidence that they use the image. That inference is unsafe: a model exploiting finding-name priors scores like one that reads the scan, and no standard benchmark separates them. We introduce a causal audit that intervenes on the image, occluding the relevant region, occluding an irrelevant one, and swapping in another patient's same-label scan, and combines three behavioral metrics to test whether a correct answer depends on the image. Across nine systems, a text-only model with no image access reaches within 5.7 accuracy points of the best multimodal one, and a 119-billion-parameter multimodal model is statistically indistinguishable from a 7-billion text-only baseline. The audit splits the cohort into three models that ignore the image, one that is unstable, and five that use it selectively, for a subset of findings; the categories hold across a second dataset, resolution, and prompt phrasing. Against board-certified radiologists, a text-only model is statistically indistinguishable from a radiologist's accuracy while grounding at zero, whereas the image-using models ground at radiologist-comparable rates. Reported confidence flags ungrounded answers only when a model uses the image. Grounding audits, not accuracy, should gate clinical deployment.

Recent advances in multimodal learning, including large language models (LLMs) and vision-language models (VLMs), have demonstrated strong adaptability to natural images. However, extending their use to the medical domain, particularly for volumetric (3D) images, is challenging due to high computational complexity, volumetric dependencies and the semantic gap between visual features and clinical terminology. Naively fine-tuning LLMs on limited medical data often leads to overfitting and clinical hallucination, where linguistic fluency is prioritized over clinical factuality. In this study, we investigate parameter-efficient adaptation strategies for volumetric CT report generation and introduce RAD3D-Prefix, a lightweight diagnostic-prior conditioning framework that minimizes the need for extensive parameter training. This module integrates image embeddings with multi-label diagnostic classification logits, preserving critical clinical details while bridging the semantic gap. By keeping the LLM frozen, our method requires minimal trainable parameters and mitigates the risk of overfitting on small, domain-specific datasets. Through a systematic study spanning LLMs from 96.1M to 1.6B parameters, we find that fine-tuning is most beneficial for smaller LLMs, whereas freezing larger (~1B+ LLMs and training only lightweight projection layers provides a superior trade-off between performance, generalization, and computational efficiency. Across multiple automatic metrics and a clinical reader study, RAD3D-Prefix outperforms comparable parameter-efficient baselines and demonstrates strong out-of-domain generalization while using substantially fewer trainable parameters than fully fine-tuned alternatives.

This study proposes a domain-specific LLM-based Visual Explanation Evaluation Framework for assessing Grad-CAM explanations in facial skin disease diagnosis models. While previous studies have primarily focused on improving classification performance through data augmentation techniques, relatively few studies have systematically examined whether model explanations are grounded in clinically relevant lesion regions. In this study, geometric augmentation, color-based augmentation, and mixed augmentation strategies were applied to facial skin disease classification models based on EfficientNet-B0, MobileNetV3, and ResNet18. Grad-CAM was employed to generate visual explanations representing the models' decision-making processes. Furthermore, an LLM-as-a-Judge evaluation framework was designed using GPT-5.5, Gemini 3.5 Flash, and Claude Sonnet 4.6 to assess Grad-CAM explanations from the perspectives of lesion localization and explanation trustworthiness. To improve evaluation consistency and clinical grounding, a progressive prompt engineering strategy was introduced, incorporating evaluation rubrics, clinical knowledge, penalty rules, and structured output formats.

Foreground segmentation is the critical first step of every computational pathology pipeline, yet existing methods rely on hand-tuned heuristics or supervised models that overfit to narrow stain and scanner distributions, failing silently on specialised stains such as Jones silver or Elastica van Gieson. We propose a coarse-to-fine approach that recasts foreground segmentation as a visual perception task and leverages general-purpose vision-language models (VLMs) as zero-annotation oracles. Our key insight is that tissue-versus-background discrimination is a natural-image recognition problem, not a histopathological one, so VLMs trained on internet-scale corpora generalise where domain-specific models cannot. We introduce Leica-75, a benchmark of 75 renal transplant whole-slide images spanning three stain families. On Leica-75, our method achieves the highest segmentation quality on out-of-distribution stains (Dice 0.858 +/- 0.027 on Jones, 0.853 +/- 0.041 on EVG) with 7x lower cross-stain variance than the best supervised baseline, while remaining competitive on in-distribution H&E. Few-shot prompting with automatically curated exemplars (Auto-context) rescues hard cases on Stress-32 (n=32), a curated stress-test subset (Dice 0.470 to 0.819 for the 2B model). VLM-based annotation review matches human expert consensus (kappa=0.989 for blur detection; mean precision/recall grading accuracy 0.708 vs. human 0.646 for segmentation mask review). The resulting pseudo-labels are used to distil lightweight student models that are as performant as the teacher model while running for a fraction of the cost. Our framework provides a principled, scalable solution to a persistent infrastructure bottleneck in digital pathology.

Lung cancer is the leading cause of cancer-related mortality, with approximately 2.5 million new cases and 1.8 million deaths annually, making reliable diagnosis a clinical priority. Although deep learning models have achieved strong performance in lung cancer classification, evaluation has largely focused on predictive accuracy, leaving their decision-making processes insufficiently examined. This study compares three architecturally distinct models: a Convolutional Neural Network (CNN), a pretrained ResNet50, and a Vision Transformer (ViT), trained on the IQ-OTH/NCCD lung cancer CT dataset. Local Interpretable Model-Agnostic Explanations (LIME) were applied to investigate model reasoning. In addition to standard performance metrics, a dual-correlation framework was introduced to measure both prediction agreement and explanation agreement across model pairs. All three models achieved strong classification performance, with ResNet50 attaining 98.61% accuracy, CNN 97.91%, and ViT 93.75%, while all achieved ROC-AUC scores of 0.99. Prediction correlations exceeded 0.99 across all model pairs, indicating highly consistent outputs. However, LIME explanation correlations remained below 0.26, revealing substantial differences in the image regions used to reach those predictions. Analysis of misclassified samples further identified a consistent spatial pattern: incorrect predictions were associated with attention outside the lung parenchyma, whereas correct predictions focused primarily within lung regions. These findings demonstrate that prediction agreement is a poor proxy for reasoning consistency, and that interpretability evaluation must be treated as an independent validation criterion alongside predictive performance in clinical AI systems.

Chest X-ray (CXR) interpretation often requires longitudinal comparison to assess disease progression. Existing approaches typically rely on temporal feature fusion or inter-study discrepancy modeling, yet remain limited in capturing subtle progression semantics and overlook the inherently directional nature of disease trajectories. In this paper, we propose ProTrans, a novel vision-language pretraining framework that formulates disease progression as a directional semantic transition between paired CXR studies. ProTrans leverages radiology reports to anchor individual CXR representations within interpretable disease states, and introduces a learnable progression feature map to explicitly encode semantic shifts between states, aligned with report-derived progression descriptions. To enforce direction-aware perception, ProTrans incorporates a reversed temporal modeling process and imposes bidirectional reconstruction consistency across states and transitions, thereby disentangling directional semantics and promoting coherent trajectory modeling. Extensive experiments on longitudinal downstream tasks, including disease progression classification and progression captioning, demonstrate that ProTrans consistently outperforms existing methods, establishing a unified pretraining framework for longitudinal CXR understanding. https://github.com/RPIDIAL/ProTrans

A vision-language model can answer a question about a medical image fluently and confidently while barely using the image, leaning instead on language priors. In medicine this is the failure that matters most, because the answer looks trustworthy and is not, and the only protection is a confidence score reliable enough to tell the system when to abstain. We ask a deployment question rather than an accuracy one: how much imaging work a model can safely handle alone, and which confidence signal makes that possible. We evaluate seven confidence estimators across five open-weight LVLMs and three medical visual-question-answering datasets spanning broad clinical imaging, radiology, and pathology, with every probe trained only on natural images and applied without adaptation. Recast as bounded selective prediction (automate a case only when confidence clears a threshold, defer the rest), the comparison is cautionary. The standard metrics are poor guides: discrimination barely separates the methods, and the weak calibration of a cheap self-report is cheaply removed by off-domain temperature scaling without changing deployable yield. What distinguishes a usable estimator is the high-confidence region a clinician acts on: the weakest baselines are confidently wrong on 41 to 45 percent of their errors against 1 to 4 percent for the best probe, and no estimator is reliably best across domains or models. Safe handoff is governed at two levels: base-model competence sets a ceiling, so a well-calibrated score recovers roughly a third of radiology cases at a 20 percent error tolerance but almost none of pathology; the confidence layer then decides how much of that ceiling is reachable. The usable role today is calibrated triage, not autonomy: automate the cases a calibrated score marks safe, route the rest to a clinician. We release all outputs, correctness judgments, and confidence scores, with code.