Medical Imaging Datasets

Annotating large radiology datasets is bottlenecked by the manual effort of delineating structures slice-by-slice in 3D volumes. Interactive methods reduce this effort but stay interaction-inefficient: slice-wise methods (including many foundation models) ignore inter-slice continuity, while 3D and video-based methods propagate a prompt with a \emph{fixed} propagator that never adapts to the target volume, so it drifts on low-contrast or pathological structures and must be re-prompted. We present IMVS, a human-in-the-loop annotation framework that composes three components into a closed loop rather than a new segmentation primitive: a lightweight 2D Slice Mask Adapter (SMA) fine-tuned online from user scribbles, a frozen Volume Mask Tracker (VMT) that propagates corrected masks across adjacent slices, and a soft teacher--student alignment that limits forgetting. The SMA is backbone-agnostic (UNet++, DeepLabV3, TransUNet). Across 8 public CT/MRI datasets, IMVS matches strong interactive baselines in quality while sharply cutting annotation effort: $14.4\times$ faster than a proficient copy-based manual workflow ($22.3\times$ over naive manual), $4.6\times$ over slice-wise and $1.9\times$ over 3D interactive methods. MedSAM2 and ScribblePrompt stay competitive or stronger on well-delineated organs; IMVS's advantage is largest on challenging targets and on interaction efficiency. Source code and Demo Video: https://github.com/AbhilakshSinghReen/imvs.

Model pruning is widely used to compress deep neural networks, reducing memory and computational requirements with minimal impact on aggregate performance. However, its effect on model behavior remains poorly understood, particularly for long-tailed medical datasets where rare but clinically important conditions are underrepresented. Furthermore, it remains unclear whether pruned models preserve reliable explanations of their predictions. To address this gap, we present a systematic study of long-tail forgetting and explanation reliability under model pruning. Across two long-tailed medical imaging datasets, two CNN architectures, four pruning methods, and sparsity levels up to 95%, we evaluate predictive performance, explanation stability, and explanation faithfulness. Our results show that predictive performance exhibits a strong frequency-dependent trend, with lower-frequency classes generally experiencing earlier and larger degradation than higher-frequency classes. In contrast, explanation stability and faithfulness are influenced primarily by the pruning strategy, with gradient-informed methods preserving explanation reliability more effectively under aggressive compression. Qualitative and mechanistic analyses further indicate that explanation degradation is primarily associated with the collapse of class-discriminative gradients rather than the disappearance of feature activations. These findings suggest that model compression should be evaluated beyond aggregate performance. Incorporating class-aware and explanation-aware evaluation reveals failure modes that would otherwise remain hidden, while moderate sparsity levels provide a practical balance between compression, predictive performance, and explanation reliability.

Segmenting a new biomedical dataset usually means a domain-specific model trained on substantial annotation, or a foundation model steered at inference time. We present Exemplar, a few-shot segmenter that fuses a frozen DINOv3 backbone with a fixed bank of classical native-resolution filter responses in one lightweight head, fitted from the support masks alone. In the few-mask, native-resolution regime, classical priors and frozen self-supervised features are complementary: fused in one head, a single fixed configuration spans eleven biomedical imaging datasets. Under the same head, the classical bank alone reaches 0.693 on the eleven-dataset panel, scored by foreground intersection-over-union or centreline Dice, and the frozen features alone 0.672; the bank leads on seven of the eleven and the features on the rest, and fused they reach 0.782. Against five forward-pass few-shot methods, Exemplar leads in 54 of 55 method-dataset comparisons, 52 of them significant after Holm correction. From a single annotated mask it reaches 0.703 on the same panel, against 0.682 for a from-scratch nnU-Net trained on that same mask. At eight masks nnU-Net overtakes it on the panel mean, chiefly on centreline agreement, but takes 16-77x longer to fit.

Visual Counterfactual Explanations (VCEs) aim to explain image classifiers by generating minimally edited and realistic versions of an input image that change the classifier's prediction. Existing VCE methods are inherently classifier-dependent and therefore susceptible to classifier biases and failure modes, such as sensitivity to shortcut features and calibration errors. In this paper, we propose a classifier-free approach for visual counterfactual generation based on Contrastive Analysis (CA). Given two datasets corresponding to different classes (e.g., healthy and patients), we disentangle the generative factors that are common across the two datasets from those that are salient to each dataset, and generate counterfactual images by swapping only the salient factors. By operating directly on data distributions rather than decision boundaries, our method provides model-agnostic VCEs that are less sensitive to classifier biases. Our approach leverages the high-quality synthesis and well-structured latent space of StyleGAN2. We use the feature space F, instead than the usual W-space, to improve detail preservation. Unlike conventional CA approaches, which typically assume salient factors in only one dataset, we introduce an adapted framework and loss functions for VCE that allow multiple salient factors in each dataset. We evaluate our method on three medical imaging datasets and demonstrate superior counterfactual generation quality compared to existing approaches.

Deploying unsupervised domain adaptation (UDA) in clinical practice requires choosing which algorithm to use and which of its trained models to ship. However, the deployment (target) domain is unlabeled, so models cannot be evaluated directly on it, leaving it unclear which to select. We address this by evaluating the complete UDA pipeline, considering both adaptation and label-free selection together. Our study covers eleven clinically relevant cross-domain scenarios from nine medical imaging datasets, with ten UDA algorithms and 13 label-free selection methods (validators), evaluating over 80,000 trained models in total. By this, we find that a capable adapted model usually exists, but identifying it without target labels is difficult: the validator-selected models leave a large and structural target performance gap to the best available one, with no evaluated validator consistently reliable. Towards closing it, we explore two strategies, ensembling and a small target-labeling budget; both narrow this gap but do not close it entirely. Overall, deployable UDA depends on the complete pipeline; addressing the less explored selection step could bring much of current UDA closer to clinical use.

Public chest X-ray repositories are widely used to train medical AI systems, yet their labels are typically extracted from radiology reports rather than verified directly on images. As a result, repository labels are often treated as image-level ground truth without validating whether they reflect what is actually visible in the radiograph. We introduce Repository Supervision Auditing (RSA), a framework that evaluates repository-derived labels against expert image-level annotations before model development. Using cardiomegaly in MIMIC-CXR as a case study, RSA compares repository labels with radiologist-reviewed image annotations, characterizes disagreement sources, and builds a curated cohort for deployment-oriented evaluation. Repository-derived cardiomegaly labels showed near-zero agreement with expert image-level assessment, identifying only 1% of expert-confirmed cases. Most discrepancies resulted from non-mention rather than explicit report negation, with expert-confirmed cardiomegaly identified in nearly half of studies assigned a repository-derived No Finding label. Using the resulting expert-curated cohort, a DenseNet121 model achieved a test ROC-AUC of 0.853. These findings show that repository labels may not reliably represent image-level truth and highlight supervision auditing as a critical step for developing trustworthy medical imaging AI.

Image mixup is a widely adopted data augmentation strategy, yet it is ill-suited for ordinal classification tasks such as medical disease grading, where labels encode a progression of severity. By indiscriminately blending disease-severity cues (ordinal) with appearance-level variation (non-ordinal), standard mixup produces samples that distort the very ordinal structure that underpins clinical severity grading. We introduce DisMix, an order-aware mixup framework for ordinal classification. DisMix disentangles ordinal and non-ordinal features via a dual-codebook VQ-VAE, allowing each subspace to be mixed independently: ordinal codes are interpolated to produce meaningful intermediate ranks, while non-ordinal codes are varied to introduce appearance diversity without corrupting the ordinal signal. Across four medical imaging datasets, DisMix shows the best aggregate performance among six image mixup baselines paired with six ordinal classifiers and remains effective under data scarcity and clinical grading variability.

Label noise is common in medical imaging datasets due to factors such as inter-rater variability, annotation errors, and ambiguous cases. This can severely undermine the reliability and clinical effectiveness of machine learning models trained using those datasets. To address this challenge, we introduce Lightweight Noise Correction (LiNC), which adds a single trainable trust parameter per training sample and learns when to use the observed label and when to defer to the model during a standard training loop. The key idea is to train using a convex combination of the observed label and the model's own predictive distribution, controlled by a per-sample trust parameter. We show that the gradient of this objective drives trust values in opposite directions for clean versus noisy samples in the early training phase, yielding separable trust distributions. We use a 3-component Gaussian Mixture Model over the trust values to separate them into clean, ambiguous, and noisy cases and then execute a short soft-correction phase on the noisy cases and a final hard correction phase. Experiments on ten 2D datasets from MedMNISTv2 under label noise of up to 50% show consistent gains in accuracy and strong mislabel detection. LiNC adds negligible asymptotic overhead: the training-time complexity remains dominated by the base network, with additional memory growing linearly with the size of the training set.

Rigorous dataset partitioning is a foundational, yet frequently overlooked, prerequisite for reliable deep learning in longitudinal medical imaging. Naively shuffling small clinical cohorts routinely introduces covariate shifts and temporal sampling imbalances across training, validation, and test subsets, exposing downstream models to out-of-distribution evaluation. We address this vulnerability with an auditable Tripartite Dataset Analytics Framework that systematically characterizes spatial grid integrity, multi-parametric intensity fingerprints, and longitudinal temporal trajectories, quantifying the heavy-tailed feature dispersion and irregular, episodic sampling intervals typical of real-world clinical cohorts. Building on this characterization, we formalize an unsupervised spatio-temporal cohort-balancing standard operating procedure (SOP) that combines elbow-optimized K-means clustering over a standardized, six-dimensional joint intensity-temporal feature space with intra-cluster proportionate stratified sampling. On a longitudinal, contrast-enhanced $T1$-weighted brain MRI cohort (N=149), the protocol reduces the maximum cross-subset intensity bias from 34.1% under conventional random shuffling to under 2.1%, while aligning longitudinal follow-up intervals closely around the population mean. Monte Carlo stress testing across ten random seeds and three split configurations confirms that this alignment remains tightly bounded, in clear contrast to the substantial variability of random partitioning. The resulting protocol offers a reproducible, generalizable procedure for cohort engineering in variable-length longitudinal clinical imaging workflows.

The accurate diagnosis of spinal pathologies depends heavily on radiological interpretation, yet automated systems are hindered by the lack of diverse, high-quality benchmarks. In this study, we present PhenSPINE, a Magnetic Resonance Imaging dataset comprising 16,813 images from 250 patients, curated to facilitate advanced deep learning research. We propose a robust diagnostic benchmark that integrates state-of-theart convolutional backbones with a Positional Encoding mechanism to explicitly model the anatomical context of intervertebral discs. Evaluating across four standard MRI sequences, our experiments demonstrate that the Sagittal T2-weighted sequence offers the most robust diagnostic value, achieving a superior Macro F1-score of 50.31%. We find that multisequence fusion strategies yield inferior performance compared to this single-sequence baseline, as the images across sequences in our dataset are significantly compromised by noise interference from surrounding anatomical regions. This work establishes a robust baseline and offers critical insights into sequence selection for spine analysis.

Medical image classification models are ideally expected to identify diagnostically relevant regions while making predictions, yet standard classification losses rarely provide spatial supervision. Explicit supervision via anatomical shape information, such as segmentation masks of task-relevant anatomy, has been shown to guide the network toward regions relevant to the target prediction. However, obtaining such masks incurs substantial manual annotation effort and computational overhead. With the advent of segmentation foundation models that exhibit strong localization of anatomical structures across diverse imaging modalities, we leverage this capability to extract anatomical shape priors without the burden of training a dedicated segmentation model. In this paper, we propose a new framework, Locus, an anatomical attention regularization framework that leverages pretrained segmentation foundation models to guide a classifier's attention toward diagnostically meaningful anatomical structures across diverse imaging modalities. Instead of enforcing pixel-wise alignment with the foundation-model-derived mask, we introduce a regularization term that adaptively balances attention between anatomical (foreground) and background regions, penalizing the classifier when background attention dominates. We validate Locus on eight diverse medical imaging datasets spanning dermoscopy, X-ray, histopathology, and cardiac MRI, showing consistent gains in classification performance alongside improved anatomically grounded attention.

Extracting textual information from scanned medical documents, such as external laboratory reports and manually filled forms, has been a major challenge in modern electronic health records (EHRs). Recent advancements in vision language models (VLMs) have shown great promise over traditional OCR tools. However, at this point, most clinical OCR studies were conducted on private, institutional data. To our knowledge, there are few publicly available datasets for evaluating OCR models in the clinical domain. Furthermore, common scanning artifacts that undermine OCR performance are not reflected in those datasets, leaving a systematic evaluation unfeasible. Therefore, we release a publicly available, realistic-looking OCR benchmark dataset, ClinOCR-Bench, with 384 scanned images across 6 subsets: Normal, Handwriting, Poor Quality, Rotation, Tables, and Mix-artifacts. ClinOCR-Bench features: 1) diverse document types and layouts, 2) full coverage of common EHR scan artifacts, 3) protected health information-free, 4) template-aware train/test split, and 5) adequate sample size for OCR benchmarking. Baseline OCR performance was evaluated using state-of-the-art open-weight and proprietary VLMs. The dataset and documentation are available on GitHub (https://github.com/ClinOCR-Bench/ClinOCR-Bench).

High resolution medical images contain fine grained, spatially sparse cues that are critical for diagnosis, yet preserving full resolution incurs substantial computational and memory costs. Most deep models process images uniformly, leading to redundant computation or loss of diagnostic detail under downsampling. We propose Chained Perceptual Refinement, CPR, a coarse to fine framework that formulates medical image analysis as a sequential global to local decision process. Starting from a low resolution global view, CPR dynamically predicts the location and spatial extent of refinement regions, extracts high resolution evidence from the original image, and incrementally integrates it with global context. By keeping the backbone input size fixed while contracting the perceptual field, CPR preserves diagnostic fidelity with constant peak GPU memory. Extensive experiments on five medical imaging datasets and multiple backbone architectures demonstrate that CPR consistently outperforms both fixed resolution and multi scale state of the art baselines, achieving improvements of up to 2.27 percentage points over the second best method. It also achieves up to a 19.6 fold reduction in GFLOPs at matched accuracy, establishing a superior accuracy and efficiency trade off for high resolution medical image analysis. The code is available on GitHub.

Few-Shot Medical Image Segmentation (FSMIS) offers a powerful solution to data scarcity but struggles to generalize across different imaging modalities. This performance collapse stems primarily from the drastic texture discrepancies between domains, which mislead models trained on source-specific intensity distributions. While existing methods attempt to align frequency or local texture features, they often fail to decouple semantic structure from domain-specific appearance. To address this, we identify a critical invariance: despite distinct imaging physics, the position and geometric shape of organs remain robustly consistent across modalities. Therefore, we propose a novel framework that harnesses Position and Shape Priors (PSP) for cross-domain FSMIS. Specifically, PSP first introduces a Position Coordinate Embedding (PCE) module to inject relative spatial coordinates for rapid organ localization. Subsequently, a Shape Prototype Modulation (SPM) module constructs domain-invariant structural prototypes via explicit shape priors, effectively filtering out texture noise. Furthermore, the Hybrid-Prototype Prediction (HPP) module adaptively calibrates the support prototype to the query feature distribution, mitigating feature misalignment. Extensive experiments on two public medical imaging datasets demonstrate that PSP significantly outperforms state-of-the-art methods.

Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a statistically grounded patient augmentation approach that generates realistic patients directly in embedding space. Using Gaussian Mixture Models as a probabilistic clustering approach on pooled instance embeddings from all patients, our method learns disease-specific "recipes"-statistical distributions of instances across unsupervised clusters. New patients are then generated by sampling embeddings from clusters based on learned recipes. Unlike existing methods that require examples from all categories, our method can generate patients offline by re-mixing pooled embeddings. Generated patients are further selected based on uncertainty quantification to improve MIL performance. We evaluate our method across three clinically relevant scarcity scenarios: (i) cross-dataset transfer, where an entirely missing "healthy" class is generated using statistics from an external cohort; (ii) low-data regimes, where class sizes are extremely limited; and (iii) small-cohort non-image tasks, including single-cell RNA-seq and flow cytometry. Across all experiments, our method improves performance over baseline, often outperforming other bag-mixing strategies. Notably, in the missing-class scenario, a performance comparable to full-dataset training is achieved, demonstrating its potential for rare disease diagnostic and privacy-preserving patient augmentation. The code is available at https://github.com/marrlab/RECIPE

Artificial intelligence (AI) has achieved remarkable success in medical imaging, but it is widely recognized that these models often perform inconsistently across real-world clinical settings. Such inconsistencies occur when patient demographics and imaging protocols vary, for example, in detecting small tumors, analyzing scans from different contrast phases, or evaluating patients of different ages or sexes. To quantify these inconsistencies, we develop a large-scale, open benchmark of 85,355 CT scans that systematically evaluates 12 tumor-detection AI models across tumor size, location, patient subgroup, and imaging protocol. We leverage large language models (LLMs) to extract and organize subgroup information from clinical data, which makes the analysis both scalable and reproducible. Our benchmark reveals that current state-of-the-art AI models, optimized for average accuracy, perform poorly in rare or underrepresented subgroups, such as young, female African Americans. However, collecting sufficient annotated data for these rare cases is often impractical. The benchmark provides a foundation for building more reliable and robust AI models for tumor detection and highlighting the need for rigorous, subgroup-level evaluation in medical imaging and computer vision. Datasets, code

Deep learning-based medical image segmentation models are trained using annotations that exhibit systematic bias and variability across raters. While probabilistic multi-rater approaches can emulate annotator-specific delineations, annotator characteristics are typically encoded implicitly in deep latent feature space, making direct analysis of their influence on predictive distributions less straightforward. We propose a logit-space probabilistic segmentation framework based on stochastic variational Gaussian Process that explicitly decomposes predictions into an image-dependent reference logit distribution and annotator specific perturbations parameterised by bias and variance. This formulation enables more explicit analysis on how intra- and inter-rater variability propagate to predictive distributions. We evaluate the method on a multi-annotator medical image dataset, which shows that explicitly modelling annotator specific perturbations improves uncertainty calibration while maintaining comparable segmentation accuracy, compared with state-of-the-art multi-rater probabilistic segmentation method. The learned bias and variance parameters quantitatively reflect annotator-specific behaviour. Furthermore, controlled perturbation experiments over bias and variance demonstrate how changes in annotator parameters systematically influence predictive performance. The code used in this paper is made publicly available at https://github.com/QiLi111/GPS-Var.

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.

Gastrointestinal cancers represent a growing health burden in the South Asian region, driven largely by rapid changes in socio-economic conditions & lifestyle habits. However, early diagnosis of such malignancies remains a significant challenge, largely due to a lack of modern equipment, lack of financial support, and a scarcity of GI experts. AI-assisted diagnosis & report generation, show great promise in alleviating this problem by providing low-skill manpower the technical expertise to perform diagnosis. However, almost all open-source, publicly available datasets are predominantly collected from the European region, with no representation from the South Asian region. The lack of open-source GI datasets from diverse geographic regions has made it difficult to assess whether population bias is present in existing models, and to develop geographically inclusive AI tools for automated GI diagnosis. To address this gap, we introduce SAGE: An Expert-Annotated South Asian GI Endoscopy dataset for image captioning, multi-label classification, and visual question answering (VQA) tasks. It consists of 1,300 images, their captions along with hallucination tag, 18 labels and 14,726 question-answer pairs making it well-suited for diverse range of tasks including classification, benchmarking, and fine-tuning large multimodal models (LMMs). We further conducted benchmarking of multi-class classifiers on the effect of population shift in GI imaging AI tasks, and contemporary LMMs on their performance. Our study reveals that task-specific models, such as multi-class classification models, suffer the most, with an average performance drop of 58% when evaluated on the South Asian dataset. For contemporary LMMs, benchmarking reveals a substantial drop in the average GREEN score for anatomical landmark detection (0.308) and abnormality detection (0.410).

Multi-view imaging, such as mammography and chest radiography, is a standard component of clinical practice. However, medical images are often unregistered and contain view-specific artifacts or irrelevant background cues that can obscure diagnostically relevant findings. Many existing methods directly fuse per-view representations, allowing such irrelevant content to contaminate the fused embedding and reducing robustness under varying view configurations. We propose OTCHA, a confidence-aware latent hub token alignment module based on optimal transport (OT) that refines patch tokens before fusion for multi-view classification. OTCHA introduces a set of learnable latent hub tokens shared across views. For each view, we compute an OT plan between patch tokens and hub tokens that jointly considers feature similarity and geometry, and augment the OT formulation with token-conditional dustbins to enable partial matching and discard irrelevant tokens. The resulting transport plan provides token-wise matching confidence, which gates hub-mediated message passing and weights a novel optimal-transport-based representation alignment loss to stabilize refinement. Experiments on three multi-view medical image datasets demonstrate consistent improvements over competing baselines across diverse anatomies and view configurations. Our code is available at https://github.com/labhai/OTCHA.

Few-shot medical image segmentation methods typically assume a single ground-truth annotation, overlooking systematic variability across expert raters commonly observed in clinical datasets. We propose an attention-based prototype calibration framework for few-shot multi-rater segmentation that models rater-specific deviations from a consensus representation in prototype space. A lightweight yet principled attention operator directly refines rater prototypes without modifying the backbone feature extractor, making the approach fully compatible with existing prototype-based few-shot segmentation methods. This design preserves semantic consistency while enabling personalized segmentation outputs with minimal computational overhead. Experiments on multi-rater medical imaging datasets demonstrate consistent improvements over baseline prototype approaches, highlighting the effectiveness of structured prototype calibration for modeling annotation variability.

Anatomical landmark detection is a fundamental task in medical image analysis supporting a wide range of diagnostic and interventional workflows. Although recent methods have achieved sub-millimetric localisation, accuracy alone is not sufficient for clinical deployment, requiring reliability and robustness in prediction. Despite its clinical relevance, the impact of representation learning in this context is still underexplored. In this work, we introduce CDPM-align, a multi-scale guidance-aligned conditional diffusion pre-training for anatomical landmark detection. Our experimental setup focuses on a few images and a few annotation regimes. Specifically, we employ three popular heterogeneous small-scale benchmark datasets for representation learning via conditional generative pre-training. Furthermore, we consider low-annotation scenarios for the downstream task of landmark detection, with 10 and 25 annotated images, reflecting realistic trade-offs between clinical effort and resource constraints for annotations. Our results confirm that generative pre-training enables the model to learn a robust representation. This improves both accuracy and uncertainty on the downstream tasks, advancing towards safe and efficient clinical deployment.

Vision-Language Models (VLMs) struggle when applied to medical image-text data, yet the tools available to diagnose this failure remain limited. Existing representation alignment metrics are symmetric, collapsing both modalities into a single score and hiding which modality drives cross-modal degradation. We introduce the Spectral Alignment Score (SAS), an asymmetric metric that projects both modalities onto the principal eigenbasis of an anchor modality and computes eigenvalue-weighted per-eigenmode correlations, resulting in directional scores whose difference quantifies modality information imbalance. We embed SAS within a benchmarking framework evaluating 15 VLMs across natural and medical image-text datasets alongside 6 alignment metrics and bidirectional retrieval. Our experiments show that medical images retain richer structural information than their paired clinical reports, a directional asymmetry invisible to all competing metrics, and that SAS achieves the strongest zero-label correlation with retrieval performance in the medical domain, positioning it as a practical diagnostic tool for clinical deployment. Code is available at this URL: https://github.com/iamalegambetti/medical-vlms-assessment.

Large-scale biomedical image-text datasets extracted from scientific literature provide valuable resources for medical multimodal model training. These datasets are commonly organized as image-caption pairs; however, figure captions are often short, context-dependent, and only partially informative without the surrounding article text. At the same time, large-scale automatic extraction introduces structural noise such as missing captions, residual markup, duplicated context, and incoherent multi-paragraph figure descriptions. We revisit data construction for medical multimodal continued pretraining (CPT) and present PMC-InterCPT, a context-grounded biomedical interleaved corpus that incorporates figure-referencing body text in addition to captions. Our pipeline recovers missing captions, cleans caption and context text, reconstructs coherent interleaved image-text samples, and applies LLM-supervised medical relevance and quality classifiers to filter noisy records. We further reveal strong modality imbalance in the resulting corpus and introduce a four-bucket evidence taxonomy for modality-aware resampling. Through CPT followed by supervised fine-tuning (SFT) on Qwen3.5-4B-Base, PMC-InterCPT effectively improves medical and general multimodal performance while using fewer CPT tokens than the raw source pool. The experimental results also illustrate the complementarity between the data quality and modality for medical multimodal CPT.

Compact Vision Transformers are attractive for medical imaging in low-data and resource-constrained settings, but most existing variants assume that Euclidean latent geometry is sufficient for organizing image representations. We introduce hZACH-ViT, a family of curved-geometry extensions of ZACH-ViT, a compact zero-token Vision Transformer that removes positional embeddings and the class token and relies on global average pooling over patch representations. To isolate the role of geometry, we preserve the verified ZACH-ViT backbone and modify only the final representation space and prototype-based classifier head, enabling a controlled comparison between Euclidean, hyperbolic, and spherical latent geometries. We evaluate Poincaré, Klein, and spherical hZACH-ViT heads on seven MedMNIST datasets under an identical few-shot protocol with 50 samples per class and five random seeds. The completed benchmark contains 770 training runs spanning seven datasets, three non-Euclidean geometries, seven curvature magnitudes, and a Euclidean baseline. Across all seven datasets, the best non-Euclidean hZACH-ViT configuration improves over Euclidean ZACH-ViT, with an average gain of +0.021 in the dataset-specific primary metric and the largest improvement on OCTMNIST (+0.055 MacroF1). Fixed low-curvature configurations retain positive gains on the majority of datasets, and low curvature values (c = 0.1 or 0.2) account for six of the seven dataset-level winners. Rather than identifying a universally optimal manifold, our results establish geometry and curvature as dataset-dependent model-selection variables, with fixed low-curvature analyses confirming that gains persist beyond exhaustive per-dataset tuning.

Ultrasound is the most widely used real-time imaging modality in clinical practice, yet per-frame video annotation remains a major bottleneck: expert labels are scarce and costly, and image appearance varies with speckle, shadowing, attenuation, and operator-dependent probe pose. This is especially limiting because clinically relevant information is often dynamic, from left-ventricular motion in echocardiography to muscle and bone kinematics in musculoskeletal imaging. Population atlases can amortize annotation cost by registering observations to a shared canonical coordinate system, but existing neural atlas methods mainly target single videos, small test-time image sets, or object-centric image collections. We introduce a cohort-scale neural atlas for ultrasound video: a single canonical chart with per-video Generative Latent Optimization embeddings, trained jointly over thousands of frames in DINOv3 feature space. Across five cardiac and musculoskeletal datasets with point landmarks and segmentation masks, our method learns coherent canonical templates and enables accurate atlas-space annotation transfer. On EchoNet-Dynamic and MSK-Bone, it supports single- and few-shot transfer with accuracy competitive with strong dense-correspondence baselines, while training in minutes on a single consumer GPU. The learned embeddings are interpretable: linear projections reveal structured cohort variation, image-decoder interpolation produces anatomically plausible intermediate frames, and test-time latent inversion reconstructs held-out frames through the atlas. These results suggest that cohort-scale neural atlases offer a practical, interpretable representation for reducing expert annotation burden in ultrasound video analysis.

Mislabeled samples in training datasets severely degrade the performance of deep networks, as overparameterized models tend to memorize erroneous labels. We address this challenge by proposing a novel approach for mislabeled data detection that leverages training dynamics. Our method is grounded in the key observation that correctly labeled samples exhibit consistent entropy decrease during training, while mislabeled samples maintain relatively high entropy throughout the training process. Building on this insight, we introduce a signed entropy integral (SEI) statistic that captures both the magnitude and temporal trend of prediction entropy across training epochs. SEI is broadly applicable to classification networks and demonstrates particular effectiveness when integrated with contrastive language-image pretraining (CLIP) architectures. Through extensive experiments on four medical imaging datasets -- a domain particularly susceptible to labeling errors due to diagnostic complexity -- spanning diverse modalities and pathologies, we demonstrate that SEI achieves state-of-the-art performance in mislabeled data identification, outperforming existing methods while maintaining computational efficiency and implementation simplicity. Our code is available at https://github.com/MedAITech/SEI.

Multilevel Image thresholding is an important preprocessing algorithm in computer vision applications nowadays. Since most common thresholding methods take the desired count of thresholds as input by the user, thresholding methods that automatically determines a suitable count of thresholds from the input image itself are advantageous. In this article, a novel thresholding method based on a dynamic programming algorithm and a modification of Minimum Error Thresholding (MET) criterion is thoroughly presented. An empirical statistical study is performed to pinpoint why this proposed method is superior. Moreover, an extended comparison between this proposed method and other state-of-the-art methods is performed on a comprehensive set of natural, satellite and medical test images. The numerical results show that the proposed MET-DP method takes much less time than traditional dynamic programming thresholding methods when the number of thresholds is high. The proposed method can detect a suitable count of thresholds for most of tested images of different types. However, traditional methods that take the count of thresholds as input produce thresholded images of higher structural similarity index measure (SSIM) and peak signal-to-noise ratio (PSNR) values than MET-DP. Source code can be found on https://w3id.org/met-dp/article1-code

Parameter-efficient adaptation of vision-language foundation models is crucial for precise multimodal understanding of biomedical images, yet existing methods remain deterministic and often struggle under domain shift or ambiguous image-text alignment. This limitation is particularly critical in the clinic, where models should remain robust in low-data regimes and domain shifts. We present Evi-Steer, an evidential cross-modal low-dimensional steering framework for BiomedCLIP that enables uncertainty-aware parameter-efficient fine-tuning while updating only 0.11% of total model parameters. Our approach performs lightweight low-dimensional token updates in both vision and text encoders while simultaneously estimating epistemic uncertainty. These uncertainty estimates update gate residuals, allowing the model to adapt conservatively when evidence is weak. Furthermore, we introduce cross-modal confidence fusion based on Dempster-Shafer theory, enabling visual adaptation to be conditioned on textual confidence and suppressing conflicting or uncertain cross-modal updates. We conduct a comprehensive evaluation on 15 biomedical imaging datasets spanning 8 organs and 8 imaging modalities under few-shot learning and domain generalization settings. Evi-Steer consistently outperforms state-of-the-art methods under few-shot learning and domain shift settings, demonstrating a practical and robust pathway for deploying vision-language models in real-world clinical settings. Code is available at https://github.com/HealthX-Lab/Evi-Steer.

This study presents a methodology for constructing a clinically verified dataset of dermatoscopic images for medical informatics research. The relevance of the work is driven by the fact that the performance of automated diagnostic support systems depends not only on the volume of images, but also on the reproducibility of the image acquisition procedure, the completeness of structured metadata, and the reliability of diagnostic labels. International collections were primarily created under conditions that differ substantially from routine Russian outpatient practice and mobile dermatoscopy. The proposed methodology integrates three interconnected components: (1) a standard operating procedure (SOP) for acquiring images via mobile dermatoscopy, (2) an information model comprising 16 structured metadata fields organized into six clinically oriented blocks in ISIC-compatible notation, and (3) a multi-stage expert verification of diagnostic labels (initial clinical annotation, consensus review by three specialists, and histological confirmation of all malignant neoplasms). Using this methodology, a dataset of 1,026 unique dermatoscopic images from 443 patients was collected between June 2025 and May 2026. From 1,044 initial records, 18 duplicates were excluded. The dataset includes nine nosological categories; all 39 malignant lesions (18 melanomas, 15 basal cell carcinomas, and 6 squamous cell carcinomas) were histologically verified. Patient age ranged from 2 to 90 years (median 38), with 279 females (63%) and 164 males (37%). Each image is accompanied by expert-annotated dermatoscopic structures and an explicit verification_stage field indicating the level of diagnostic confirmation. The resulting dataset serves as a pilot clinically verified resource suitable for independent model evaluation, domain shift analysis, interpretability studies, and further expansion.

Deep learning has brought significant progress to medical image classification, yet most existing methods still rely on isolated visual evidence and cannot effectively leverage similar cases or external knowledge. In clinical practice, diagnosis is typically supported by similar historical cases and their associated symptoms. To explicitly model this evidence-based diagnostic process, we propose a case-aware reasoning framework driven by multimodal knowledge graphs for medical image classification. Specifically, we construct a case-aware multimodal knowledge graph as a structured diagnostic memory, where diseases, images, and symptoms are hierarchically organized. Given an input image, our method adaptively retrieves similar cases from this memory and extracts their corresponding case-centered subgraphs. We further introduce a knowledge propagation and injection mechanism, in which an image-centric Graph Attention Network aggregates heterogeneous semantics into case-based features, followed by a bidirectional cross-modal attention mechanism that injects these features into visual representations for cross-modal alignment. To mitigate noisy retrieval, we design a confidence-calibrated decision refinement scheme that estimates the reliability of each retrieved case by jointly considering prediction confidence and sample similarity, and reweights its contribution to the final prediction, providing interpretable case-level evidence. Extensive experiments on multiple medical imaging datasets demonstrate that our approach consistently outperforms strong baselines, while ablation and qualitative analyses validate its effectiveness and interpretability. The code is available at https://anonymous.4open.science/r/MKG-CARE-8B7B.

Accurate detection and counting of virus patches in focus-forming unit (FFU) images, also known as foci images, are important for quantifying viral infection and analyzing cellular structures. This task is challenging because biomedical targets often vary substantially in size, density, contrast, and shape. In this paper, we propose an enhanced YOLOv2-based detector that integrates a Feature Pyramid Network (FPN) to improve multi-scale feature representation. We also incorporate a switchable atrous convolution mechanism to adapt the receptive field for fine-grained targets in dense microscopy images. The proposed method is evaluated on biomedical foci image datasets for virus patch and small cell patch detection. For small cell patch detection, the model achieves a mean average precision (mAP) of 40.5% at a 25% Intersection over Union (IoU) threshold. For FFU virus patch detection, the model achieves an mAP of 68%. These results indicate that combining FPN-based feature fusion with switchable convolution improves the suitability of YOLOv2 for specialized biomedical object detection tasks

Accurate and robust medical image classification is paramount for early disease diagnosis and treatment planning. However, challenges such as limited annotated data, high intra-class variability, and subtle inter-class differences often hinder the performance of deep learning models. This paper introduces a synergistic deep learning framework that leverages the strengths of self-supervised learning and transfer learning for enhanced medical image classification. Our approach employs two distinct ConvNeXt-Tiny models: one pre-trained on a large-scale natural image dataset (ImageNet) and another pre-trained using an entropy-guided Masked Autoencoder (MAE) on the target medical dataset. Both models are then fine-tuned on specific medical image classification tasks. A final ensemble strategy, based on averaging predicted probabilities, is utilized to combine the complementary insights from these two models. Rigorous experimental validation across four diverse medical imaging datasets (Breast Ultrasound Images (BUSI), International Skin Imaging Collaboration (ISIC) 2018, Kvasir, and COVID) demonstrates the superior performance and robustness of our ensemble approach. The MAE pre-training significantly improves feature learning on domain-specific data, while the ImageNet pre-training provides strong generalizable features. The ensemble consistently achieves state-of-the-art results, outperforming individual models and existing methods, highlighting the efficacy of combining diverse pre-training strategies for challenging medical image analysis.

In biomedical Subgroup Discovery, practitioners are interested in discovering interpretable and homogeneous subgroups within a group of patients. In this paper, assuming that healthy subjects (i.e., controls) share common but irrelevant factors of variation with the patients, we motivate and develop a Contrastive Subgroup Discovery method, entitled Deep UCSL. By contrasting patients with controls, Deep UCSL identifies subgroups driven solely by pathological factors, ignoring common variability shared with healthy subjects. Our framework employs a deep feature extractor to learn a discriminative representation space. Mathematically, we derive a novel loss based on the conditional joint likelihood of latent clusters and patient/control labels, optimized via an Expectation-Maximization strategy alternating between subgroup inference and feature encoder updates. A regularization term further encourages representations to capture disease-specific variability while ignoring variability shared with controls. Compared to previous related works, our approach quantitatively improves the quality of the estimated subgroups, as demonstrated on a MNIST example and four distinct real medical imaging datasets. Code and datasets are available at: https://github.com/rlouiset/deep_ucsl.

The microscopic examination of white blood cells (WBCs) plays a fundamental role in pathology and is essential for diagnosing blood disorders such as leukemia and anemia. To support further research on WBC images, multiple datasets have been proposed. However, they mainly annotate cell categories, and lack detailed morphological characteristics that pathologists use to explain their interpretations of cells. To address this gap, we introduce WBCAtt+, a novel dataset of WBC images densely annotated with 11 morphological attributes and five pixel-level cell components. With 113k image-level labels and 10k segmentation maps, WBCAtt+ is the first to provide comprehensive annotations for WBC images. Leveraging this dataset, we provide baseline models for attribute recognition and semantic segmentation. We also design an attribute recognition model to incorporate compositional structure of cells, further improving the recognition performance. Lastly, we showcase various applications enabled by our dataset, such as explainable AI models, including counterfactual example generation. \revision{The dataset and code are publicly available\footnote{https://doi.org/10.57967/hf/8143}}.

Noisy labels are common in large-scale medical imaging datasets due to inter-observer variability and ambiguous cases. We propose a statistically grounded and task-agnostic framework, Standardized Loss Aggregation (SLA), for detecting noisy labels at the sample level. SLA quantifies label reliability by aggregating standardized fold-level validation losses across repeated cross-validation runs. This formulation generalizes discrete hard-counting schemes into a continuous estimator that captures both the frequency and magnitude of performance deviations, yielding interpretable and statistically stable noisiness scores. Experiments on a public fundus dataset demonstrate that SLA consistently outperforms the hard-counting baseline across all noise levels and converges substantially faster, especially under low noise ratios where subtle loss variations are informative. Samples with high SLA scores indicate potentially ambiguous or mislabeled cases, guiding efficient re-annotation and improving dataset reliability for any classification task.

We propose a unified cross-domain transfer learning framework that leverages knowledge from multiple heterogeneous medical imaging datasets to improve performance across segmentation, classification, and object detection tasks. Our approach employs a teacher-student paradigm in which a joint teacher model aggregates domain-invariant representations learned from diverse source datasets, while a task-specific student model is trained via multi-level knowledge distillation. Originally developed for medical image segmentation, the framework is extended to support image-level classification and object-level detection, enabling a general multi-task formulation for medical image analysis. We evaluate our method on a broad suite of datasets, including six segmentation benchmarks, BrainMetShare, ISLES, BraTS (MRI) and Lung MSD, LiTS, KiTS (CT), as well as multiple classification datasets for pulmonary disease and dementia, and detection datasets with native bounding-box annotations. Across all tasks and modalities, the proposed approach yields consistent improvements over strong dataset-specific and multi-head baselines, demonstrating enhanced robustness to distributional shifts and superior generalization. These findings highlight the potential of multi-dataset knowledge distillation as a scalable and task-agnostic approach for enhancing segmentation, classification, and object detection performance across heterogeneous medical imaging domains.

Medical imaging datasets are often characterized by extreme class imbalances, where rare pathologies are significantly underrepresented compared to common conditions. This imbalance poses a dual challenge for Open-Set Recognition (OSR): models must maintain high classification accuracy on known classes while reliably rejecting unknown samples unseen during training in the clinical settings. While recently proposed Deep Simplex Classifier (DSC)\cite{cevikalp2024reaching} and UnCertainty-aware Deep Simplex Classifier (UCDSC)\cite{Aditya_2026_WACV} successfully leverage Neural Collapse to ensure maximal inter-class separation, they rely on a uniform margin that does not account for the varying densities of medical classes. In this paper, we propose DMDSC an enhanced framework featuring a dynamic margin approach. Our approach automatically adapts class-specific margins based on label frequency, enforcing a higher penalty and tighter feature clustering for rare pathologies to counteract the effects of data imbalance. Extensive experiments conducted on diverse medical benchmarks on BloodMNIST\cite{medmnistv2}, OCTMNIST\cite{medmnistv2}, DermaMNIST\cite{medmnistv2}, and BreaKHis~\cite{spanhol2015dataset} datasets, demonstrate that our framework outperforms state-of-the-art methods.

Machine learning models for medical image analysis often exhibit subgroup-dependent performance, which impacts how decisions should be allocated between automated systems and human experts under limited resources. Prior work on AI fairness and human-AI cooperation, including learning to defer (L2D) and learning to complement (L2C), typically addresses these problems in isolation. We propose People-Centred Medical Image Analysis (PecMan), a framework for fairness-aware human-AI co-operative classification that jointly models subgroup-dependent reliability, decision allocation, and collaborative prediction. PecMan combines subgroup-specialised predictors with a gating and consolidation mechanism that dynamically assigns cases to automated models, human experts, or their combination, without requiring sensitive attributes at test time. We also introduce the FairHAI benchmark for evaluating trade-offs between predictive accuracy, subgroup equity, and human involvement. In addition, we provide a theoretical analysis of multi-agent gating via selection regret and characterise fairness-coverage trade-offs under input-dependent allocation. Experiments across multiple medical imaging datasets demonstrate that PecMan achieves consistently improved trade-offs compared to methods that address fairness or human-AI cooperation separately.

Federated learning (FL) is a distributed machine learning method where multiple devices collaboratively train a model under the management of a central server without sharing underlying data. One of the key challenges of FL is the communication bottleneck caused by variations in connection speed and bandwidth across devices. Therefore, it is essential to reduce the size of transmitted data during training. Additionally, there is a potential risk of exposing sensitive information through the model or gradient analysis during training. To address both privacy and communication efficiency, we combine differential privacy (DP) and adaptive quantization methods. We use Laplacian-based DP to preserve privacy, which is relatively underexplored in FL and offers tighter privacy guarantees than Gaussian-based DP. We propose a simple and efficient global bit-length scheduler using round-based cosine annealing, along with a client-based scheduler that dynamically adapts based on client contribution estimated through dataset entropy analysis. We evaluate our approach through extensive experiments on CIFAR10, MNIST, and medical imaging datasets, using non-IID data distributions across varying client counts, bit-length schedulers, and privacy budgets. The results show that our adaptive quantization methods reduce total communicated data by up to 52.64% for MNIST, 45.06% for CIFAR10, and 31% to 37% for medical imaging datasets compared to 32-bit float training while maintaining competitive model accuracy and ensuring robust privacy through differential privacy.

This paper introduces EgoMAGIC (Medical Assistance, Guidance, Instruction, and Correction), an egocentric medical activity dataset collected as part of DARPA's Perceptually-enabled Task Guidance (PTG) program. This dataset comprises 3,355 videos of 50 medical tasks, with at least 50 labeled videos per task. The primary objective of the PTG program was to develop virtual assistants integrated into augmented reality headsets to assist users in performing complex tasks. To encourage exploration and research using this dataset, the medical training data has been released along with an action detection challenge focused on eight medical tasks. The majority of the videos were recorded using a head-mounted stereo camera with integrated audio. From this dataset, 40 YOLO models were trained using 1.95 million labels to detect 124 medical objects, providing a robust starting point for developers working on medical AI applications. In addition to introducing the dataset, this paper presents baseline results on action detection for the eight selected medical tasks across three models, with the best-performing method achieving average mAP 0.526. Although this paper primarily addresses action detection as the benchmark, the EgoMAGIC dataset is equally suitable for action recognition, object identification and detection, error detection, and other challenging computer vision tasks. The dataset is accessible via zenodo.org (DOI: 10.5281/zenodo.19239154).

Biomedical imaging data presents enormous potential for deep learning models to predict invaluable properties, such as diseases and drug effects. However, unavoidable alterations of the technical conditions cause batch effects: variations between groups of samples that are not due to any biological signal of interest. Batch effects greatly hinder the generalization abilities of deep learning models, preventing their practical use in the real world. Unsupervised Domain Adaptation (UDA) methods have been proposed to mitigate batch effects, but they usually assume that the data is comprised of only one source domain and one target domain, whereas biological datasets are comprised of multiple domains, both at training and at inference time. While Batch Normalization-based test-time and meta-learning adaptation methods offer a promising mechanism for domain alignment, we show that existing approaches exhibit degraded performance under the usual inference scenarios of small target batch sizes and label shift. We address these limitations by leveraging negative control samples, which are consistently present in every experimental batch in biological datasets, as stable context for adaptation. We propose CS-ARM-BN, a meta-learning BN adaptation method that uses controls both during training and inference to stabilize domain statistics. We perform a suite of experiments of Mechanism-Of-Action (MoA) classification, a crucial task for drug discovery, on the large JUMP-CP imaging dataset. Our experiments show that CS-ARM-BN substantially improves robustness to batch size and class distribution shifts, enabling practical use of deep learning models for biomedical images.

Accurate disease classification from radiology reports is essential for many applications. While supervised fine-tuning (SFT) of lightweight LLMs improves accuracy, it can degrade reasoning. We propose a two-stage approach: SFT on disease labels followed by Group Relative Policy Optimization (GRPO) to refine predictions by optimizing accuracy and format without reasoning supervision. Across three radiologist-annotated datasets, SFT outperformed baselines and GRPO further improved classification and enhanced reasoning recall and comprehensiveness.

Medical imaging AI development is fundamentally dependent on annotated datasets, yet no existing standard provides machine-enforceable validation across dataset structure, annotation provenance, quality documentation, and ML readiness within a single framework. DICOM standardizes image acquisition, storage, and communication at the individual study level. BIDS organizes neuroimaging research datasets with consistent naming conventions. Neither addresses the curation layer, viz., who annotated what, when, with what tool, and to what quality standard. This paper presents VIDS (Verified Imaging Dataset Standard), an open specification that defines folder layout, file naming, annotation provenance schemas, quality documentation, and 21 machine-enforceable validation rules across two compliance profiles. VIDS uses NIfTI as a canonical working format while preserving full DICOM metadata in sidecars for traceability, and supports export to any downstream ML framework (nnU-Net, MONAI, COCO, flat NIfTI) without loss of provenance. Twenty-two compliance dimensions are defined and four major public datasets -- LIDC-IDRI, BraTS, CheXpert, and the Medical Segmentation Decathlon -- are benchmarked against these dimensions. Even widely used datasets satisfy only 20--39% of these dimensions, with provenance and quality documentation as the largest systematic gaps. LIDC-Hybrid-100 is released as a 100-subject VIDS-compliant reference CT dataset with consensus segmentation masks from four radiologist annotations (mean pairwise Dice 0.7765), validating 21/21 on the Full compliance profile. VIDS is fully open source: the specification is CC BY 4.0, all tools are Apache 2.0, the reference validator is available on PyPI (pip install vids-validator), and LIDC-Hybrid-100 is published on Zenodo (https://doi.org/10.5281/zenodo.19582717).

While deep learning systems are becoming increasingly prevalent in medical image analysis, their vulnerabilities to adversarial perturbations raise serious concerns for clinical deployment. These vulnerability evaluations largely rely on Attack Success Rate (ASR), a binary metric that indicates solely whether an attack is successful. However, the ASR metric does not account for other factors, such as perturbation strength, perceptual image quality, and cross-architecture attack transferability, and therefore, the interpretation is incomplete. This gap requires consideration, as complex, large-scale deep learning systems, including Vision Transformers (ViTs), are increasingly challenging the dominance of Convolutional Neural Networks (CNNs). These architectures learn differently, and it is unclear whether a single metric, e.g., ASR, can effectively capture adversarial behavior. To address this, we perform a systematic empirical study on four medical image datasets: PathMNIST, DermaMNIST, RetinaMNIST, and CheXpert. We evaluate seven models (VGG-16, ResNet-50, DenseNet-121, Inception-v3, DeiT, Swin Transformer, and ViT-B/16) against seven attack methods at five perturbation budgets, measuring ASR, Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), and $L_2$ perturbation magnitude. Our findings show a consistent pattern: perceptual and distortion metrics are strongly associated with one another and exhibit minimal correlation with ASR. This applies to both CNNs and ViTs. The results demonstrate that ASR alone is an inadequate indicator of adversarial robustness and transferability. Consequently, we argue that a thorough assessment of adversarial risk in medical AI necessitates multi-metric frameworks that encompass not only the attack efficacy but also its methodology and associated overheads.

DINO models provide rich patch-level representations that have recently enabled strong performance in unsupervised anomaly detection (UAD). Most existing methods extract patch embeddings from normal images and model them independently, ignoring spatial and neighborhood relationships between patches. This implicitly assumes that self-attention and positional encodings sufficiently encode contextual information within each patch embedding. In addition, the normative distribution is often modeled as memory banks or prototype-based representations, which require storing large numbers of features and performing costly comparisons at inference time, leading to substantial memory and computational overhead. In this work, we explicitly model spatial and contextual dependencies between patch embeddings using a 2D autoregressive (AR) model, allowing us to use a simple and efficient model for normative modeling. Instead of storing embeddings or clustering prototypes, our approach learns a compact parametric model of the normative distribution via an AR convolutional neural network (CNN). At test time, anomaly detection reduces to a single forward pass through the network and enables fast and memory-efficient inference. We evaluate our method on the BMAD benchmark, comprising three medical imaging datasets, and the VisA dataset, comprising 12 industrial object categories, and compare it against existing methods, including recent DINO-based approaches. Experimental results demonstrate that explicitly modeling spatial dependencies achieves competitive anomaly detection performance while substantially reducing inference time and memory requirements. Code is available at the project page: https://eerdil.github.io/spatial-ar-dinov3-uad/

The classification performance of deep neural networks relies strongly on access to large, accurately annotated datasets. In medical imaging, however, obtaining such datasets is particularly challenging since annotations must be provided by specialized physicians, which severely limits the pool of annotators. Furthermore, class boundaries can often be ambiguous or difficult to define which further complicates machine learning-based classification. In this paper, we want to address this problem and introduce a framework for mislabel detection in medical datasets. This is validated on the two largest, publicly available datasets for Video Capsule Endoscopy, an important imaging procedure for examining the gastrointestinal tract based on a video stream of lowresolution images. In addition, potentially mislabeled samples identified by our pipeline were reviewed and re-annotated by three experienced gastroenterologists. Our results show that the proposed framework successfully detects incorrectly labeled data and results in an improved anomaly detection performance after cleaning the datasets compared to current baselines.

In high-stakes scenarios, such as medical imaging applications, it is critical to equip the predictions of a regression model with reliable confidence intervals. Recently, Conformal Prediction (CP) has emerged as a powerful statistical framework that, based on a labeled calibration set, generates intervals that include the true labels with a pre-specified probability. In this paper, we address the problem of applying CP for regression models when the calibration set contains noisy labels. We begin by establishing a mathematically grounded procedure for estimating the noise-free CP threshold. Then, we turn it into a practical algorithm that overcomes the challenges arising from the continuous nature of the regression problem. We evaluate the proposed method on two medical imaging regression datasets with Gaussian label noise. Our method significantly outperforms the existing alternative, achieving performance close to the clean-label setting.

Medical report understanding from real-world document images is essential for generating patient-facing explanations and enabling structured information exchange in clinical systems. Existing VLMs and LLMs have shown strong performance on document understanding, but structured understanding of medical reports remains insufficiently benchmarked. Therefore, we introduce MedRepBench, a benchmark with 1,925 de-identified Chinese medical report images spanning diverse departments, patient demographics, and acquisition formats. In MedRepBench, we mainly focus on report-grounded interpretation rather than evaluating diagnostic reasoning, treatment recommendation, or the integration of patient history. The interpretation is defined as structured extraction of report fields (e.g., item, value, unit, reference range, abnormal flag) plus a patient-facing explanation grounded strictly in the report content. The benchmark primarily evaluates end-to-end VLMs, and also includes a controlled text-only setting (high-quality OCR + LLM) to approximate an upper bound when character recognition errors are minimized. Our evaluation framework provides two complementary protocols: (1) an objective protocol measuring field-level recall of structured items, and (2) an automated subjective protocol that uses an LLM-based judge to score factuality, interpretability, and reasoning quality under a fixed prompt. Using the objective metric as a reward signal, we also provide a lightweight GRPO-based alignment baseline for a mid-sized VLM, which improves field-level recall by up to 6%. Finally, we analyze practical limitations of OCR+LLM pipelines, including layout-related errors and additional system latency, showing the need for robust end-to-end vision-based medical report understanding. The dataset and evaluation resources are publicly available on https://huggingface.co/datasets/MedRepBench/MedRepBench.

Manually refining radiological segmentation masks is highly resource-intensive. To determine when this expert commitment is truly justified for the training of segmentation models, we investigate the relationship between label quality and model performance. Expanding beyond models trained directly for inference, we conduct the first study isolating the impact of label quality in pre-training datasets. While high-quality labels remain essential for models proceeding directly to deployment, we find no evidence that strict label quality is crucial for pre-training efficacy. These results question the necessity of exhaustive human-in-the-loop refinement for massive corpora intended for pretraining and suggest that expert effort is more effectively invested in well-curated downstream target datasets.