Medical Image Segmentation

Overview

Medical image segmentation assigns labels to pixels or voxels to outline structures such as tumors, organs, vessels, and surgical instruments, enabling quantitative analysis and clinical workflows. Common approaches include U-Net-style convolutional networks, transformers and state-space models, and promptable foundation models; work also uses anatomical and topological priors, text guidance, and generative models. To reduce reliance on dense expert labels, researchers study self-supervised pretraining, semi- and weakly supervised learning, synthetic data, and interactive annotation, while domain adaptation addresses differences across scanners, hospitals, and modalities. A central challenge is making models reliable beyond their training data: high overlap scores can conceal boundary, connectivity, small-lesion, or subgroup failures, so external validation, uncertainty estimates, and clinically relevant metrics remain important.

Latest papers

839 papers62 papers in the last four weeks, down 11% on the four weeks before. 0.5% of all new papers.

Oct 30, 2026

Directional Dual-Head Supervision for Real-Time Source-Free Polyp Segmentation

Source-free domain adaptation (SFDA) is critical for medical image segmentation as it adapts a model to an unlabeled target domain without accessing source data, thereby preserving data privacy. However, its effectiveness is often limited by confirmation bias: self-training models tend to miss small polyps, hallucinate foreground, and produce imprecise contours. We propose MedRT-SFSeg, a real-time SFDA framework built on a dual-head one-to-one/one-to-many YOLO segmentation architecture. Mask-DHF fuses precision- and recall-oriented predictions into stable pseudo-instances, while DURR uses the sign of pixel-level dual-head disagreement as a directional cue to expand or shrink masks, and additionally recovers missed instances and suppresses hallucinations. Seg-MARD further regularizes feature representations through mask-guided, region-stratified sampling. Experiments on bidirectional adaptation between Kvasir-SEG and CVC-ClinicDB show that MedRT-SFSeg achieves 80.43%/80.77% Dice and 5.53/8.44 mm ASD, improving the non-adapted baseline by 7.7 and 9.8 Dice points while running at more than 62 FPS end-to-end. These results suggest that segmentation-aware dual-head supervision can improve pseudo-label quality without sacrificing real-time inference. Project page: https://danielnguyen-05.github.io/MedRT-SFSeg
Oct 30, 2026

Different Models, Shared Failures: Auditing Frozen-Encoder Pools for Medical Segmentation

Average segmentation accuracy and model count do not reveal whether models fail on the same cases. We present CoFailMed, an audit of correlated failures in pretrained-encoder pools for medical segmentation. Across five 2D tasks, we evaluate 11 public pretrained encoders (a controlled sample, not a census) using frozen features and separately trained 1×11\times 1 readouts with four seeds per encoder. Shared-checkpoint pairs have the highest mean per-case Dice correlation. An expanded 17-encoder analysis shows that distinct checkpoints within the same encoder family remain more correlated than cross-family pairs. At the pooled 33rd-percentile Dice threshold, four-member pools drawn from distinct encoders have mean effective sizes of 1.56-2.92, estimated from failure correlations in pools with enough failures and passes per member. In the primary pool, richer readouts and fine-tuning narrow the Dice-correlation gap between pairs sharing a checkpoint (or the DINOv2-B/S release) and all other pairs. Yet dependence between different encoders can increase, and fine-tuning does not consistently increase effective pool size at 33rd-percentile thresholds recomputed for each training recipe. A smaller between-group gap can coexist with greater dependence. Pool evaluation should therefore report absolute dependence and threshold-specific effective size alongside accuracy and nominal pool size. The CoFailMed release provides aligned per-case traces, analysis scripts and study code to reproduce the central audit results.
Oct 30, 2026

Enhancing Medical Lesion Segmentation via Several Simple Modules

This work introduces three lightweight enhancement modules for medical lesion segmentation to improve clinical applicability, particularly under data-scarce and computationally constrained environments. Current mainstream methods struggle with the lack of high-quality annotations for rare pathologies, which often leads to severe morphological distortions during inference, despite achieving seemingly ideal DSC scores. Furthermore, the isolated development of individual segmentation tasks restricts cross-domain methodological innovation, underscoring the need for leveraging shared knowledge across different lesions within the same anatomical region. However, constrained access to historical data and annotations hinders efficient knowledge extraction and triggers catastrophic forgetting when adapting to new classes. To address these challenges, we first propose DT-Morph Combined Loss with continuous spatial pooling to optimize differentiable topological structures and boundary continuity. Second, we introduce 3D Group Prompt, which extracts domain-universal knowledge via curated volumetric image-mask alignment prompts together with text prompts built on SAT baseline. Finally, we replace conventional output layers with Many-to-One Conditional Segmentation Head equipped with synonym-resolved routing, which brings negligible computational cost and enables fast incremental learning for new categories without sacrificing performance on old tasks. Ablation studies on abdominal and extra-abdominal datasets covering both organ and lesion segmentation verify the efficacy of our modules.
Oct 29, 2026

Single-Annotation, Multi-Hypothesis Segmentation with Semantic-Spatial Residual Banks

Multi-rater segmentation datasets show that a single image can admit several valid masks, yet most training sets expose only one annotation per image. We study single-annotation multi-hypothesis segmentation: each training image exposes one fixed mask, while the model must return a finite bank that covers held-out human annotations at test time. Our experiments reveal a representation tradeoff. Banks learned directly from images recover variations in local boundaries and extent but lose structural hypotheses, whereas frozen semantic features preserve structural grouping but underrepresent spatial variation. We introduce the Semantic-Spatial Residual Bank (SSRB), which freezes a semantic bank trained with balanced assignments and learns a residual from the image for each hypothesis. Across five medical endpoints, SSRB improves coverage of held-out masks at K=8K=8 over a Probabilistic U-Net under the same one-mask constraint. On LIDC and LIDC-hard, it also produces substantially more distinct useful masks. On BSDS, it preserves the semantic bank's performance in grouping regions. Its advantage grows as more masks are returned, showing that residuals learned for corresponding heads improve coverage of local annotation variation while preserving how regions are grouped.
Oct 29, 2026

Segment Anything Pancreas: A Unified MRI Segmentation Model for Pancreatic Cancer Radiotherapy

Background: Limited tumor annotations and incomplete labels across MRI datasets hinder unified segmentation of pancreatic tumors and organs at risk (OARs) for MRI-guided radiotherapy. Purpose: We propose Pancreas-MedNeXt, a unified model that segments the whole pancreas, its subregions, tumors, and surrounding OARs from one MRI volume. Methods: The model uses a shared MedNeXt encoder-decoder with supervised whole-pancreas and subregion pretraining, followed by multitask fine-tuning. Three output heads predict the pancreatic subregions, tumor, and OARs (stomach, duodenum, kidneys). An annotation-aware loss allows training on partially labeled data without treating unannotated structures as background. Pancreas and tumor were evaluated by three-fold cross-validation on 142 PANTHER patients (92 diagnostic, 50 MR-Linac), subregions and OARs on Cyst-X and AMOS test sets, and pancreas and OARs on 33 external T1-weighted TotalSegmentator scans. Comparisons with nnU-Net, MedNeXt, VISTA3D, and Swin UNETR used the Dice similarity coefficient (DSC) with paired bootstrap 95% CIs. Results: Pancreas-MedNeXt achieved the highest mean pancreas and tumor DSC on diagnostic and MR-Linac MRI. Tumor DSC was 58.41% and 42.55%, exceeding task-specific MedNeXt by 4.94 (95% CI: 0.28-9.45) and 5.89 (95% CI: 2.37-9.72) percentage points, respectively. Whole-pancreas DSC was 85.73% and 70.66%. Pretraining improved head, body, and tail DSC by 2.01, 3.00, and 3.78 percentage points over training from scratch. It also achieved the highest DSC for the pancreas, duodenum, and right kidney on AMOS, and for all five organs on external MRI, exceeding the next-best method by 4.92-8.85 percentage points.Conclusion: A single Pancreas-MedNeXt model segments tumors, pancreatic subregions, and OARs on diagnostic and MR-Linac MRI, which could streamline contouring for pancreatic cancer radiotherapy.
Oct 29, 2026

Spatial Atlas-Informed Loss Ensembles for Whole-Body PSMA PET/CT Metastasis Segmentation

Existing whole-body PSMA PET/CT prostate metastasis segmentation methods generally rely on images alone, without explicitly incorporating where metastases tend to occur. We investigate whether a population metastasis atlas can improve lesion detection when integrated into model training. We constructed voxel-wise mean and standard deviation maps from 375 expert-annotated training scans and used them to weight the cross-entropy loss of an nnU-Net. The additional penalties for missed lesions and false positives depend on spatial atlas statistics and diminish as predictions become confidently correct. Seven configurations were compared on validation data; three were combined by majority voting into SAILS (Spatial Atlas-Informed Loss enSemble). We compared SAILS with a baseline nnU-Net and inference-time atlas fusion on AutoPETIII (110 disease-positive cases) and Deep-PSMA (100 external cases). No atlas or registration is needed at inference. Results: On AutoPETIII, SAILS improved whole-body Dice (0.531 vs. 0.520; p=0.006), reduced missed-lesion volume (9.5 vs. 12.1 cc/case; p<0.01), and increased pooled lesion sensitivity (0.857 vs. 0.843; p=0.004). On Deep-PSMA, SAILS detected 126 additional reference lesions (sensitivity 0.769 vs. 0.751; p<0.001), without a significant whole-body Dice change (-0.009; p=0.36). High-risk bone Dice improved in both cohorts (0.576 vs. 0.552 and 0.667 vs. 0.653; both p<0.01). False-positive volume increased by 2.3 and 18.2 cc/case, respectively (p<0.001). Atlas-weighted training improves lesion detection, especially in high-risk bone, without test-time atlas registration, but increases false positives.
Oct 29, 2026

Beyond Ground Truth: A Heuristic Unsupervised Quality Assurance Engine for Diagnosing Calibrational Blindness in Dental Segmentation

In real-world clinical settings, dental X-ray segmentation using deep learning methods suffers from reliability issues. Even when the segmentation quality is bad, deep learning models show high confidence in their predictions (calibrational blindness). Moreover, in real use, doctors do not have ground-truth masks to check their accuracy. To address this problem, we introduce a simple quality-checking engine called HUS-QA with three stages. We train it on the PRAD (Periapical Dental X-ray) dataset to build our SimCLR self-supervised ResNet-18 U-Net model, which generates the segmentation mask and then evaluates its quality. Our HUS-QA checks the segmentation mask quality without a ground-truth mask. Prediction confidence, edge sharpness, shape connectivity, and area-size penalty are the simple indicators considered in this research. Results show that standard confidence methods fail (r = -0.1394, p = 1.7864e-3, ROC AUC = 0.4275). By contrast, our HUS-QA shows a positive correlation with actual Dice scores (r = 0.4647, p = 3.7510e-28) and achieves a strong ROC-AUC of 0.8405. Therefore, HUS-QA serves as a practical tool for clinical quality control.
Oct 29, 2026

RepConTUR: A Report-Conditioned Volumetric Multimodal Model for Abdominal Tumor Segmentation

Tumor delineation is required for radiotherapy planning, yet automatic segmentation is limited by errors, predominantly false positives, that distort dose and increase editing time. The radiology report accompanies the scan and localizes disease at the suborgan level, but existing text-promptable models condition on short referring phrases, and most operate in 2D. We present RepConTUR, a single native-3D early-fusion multimodal model that conditions volumetric abdominal tumor segmentation on the narrative report. We extend AbdomenAtlas 3.0 to a suborgan-level promptable segmentation dataset and generate report-based VQA pairs, yielding four report-derived tasks on the same annotations: referring segmentation (RES), report-grounded segmentation (GSEG), report generation (RRG), and visual question answering (VQA). We train RepConTUR, comprising a 3D CT encoder, an early-fusion language model, and a native-3D segmentation module, jointly on the four tasks. Across liver, kidney and pancreas, RepConTUR attains the highest Dice similarity coefficient (DSC), instance-wise precision, and detection F1 among the text-promptable baselines, and adding the report raises mean precision while leaving recall comparable. Against two vision-only specialists, nnU-Net and the report-supervised R-Super, RepConTUR attains the highest value on every in-domain metric for liver and pancreas and the highest mean DSC, recall, precision, and detection F1 over the four out-of-distribution public cohorts. Ablations indicate that conditioning on the narrative report raises detection F1 from 0.499 to 0.528 within the same model, that joint GSEG training raises RES F1 from 0.450 to 0.482, and that the native-3D segmentation module raises GSEG F1 from 0.139 to 0.528 over its 2D counterpart. Code is available at https://github.com/Oncosoft-Research/RepConTUR.
Oct 29, 2026

Morphology-Aware Channel-Decoupled Mamba Network for Medical Image Segmentation

Accurate multi-organ segmentation in computed tomography (CT) is essential for computer-aided diagnosis, treatment planning, and disease monitoring. However, substantial variations in organ shape and size, together with low tissue contrast and ambiguous boundaries, complicate the modeling of heterogeneous anatomical structures. To address these challenges, we propose a Morphology-Aware Channel-Decoupled Mamba Network (MCDNet), which integrates adaptive local structural enhancement with channel-decoupled long-range modeling. Specifically, we introduce a Morphology-Aware Channel-Decoupled State-Space (MCSS) block that divides feature channels into separate processing groups, allowing differentiated structural representations to be learned within an efficient state-space framework. Within each group, a Morphology-Aware Enhancement Module (MAEM) combines deformable convolutions with channel attention to adapt local feature extraction to anatomical shape variations. Group-wise state-space modeling then captures long-range spatial dependencies, and channel gating adaptively integrates the resulting features. Experiments on the Synapse abdominal CT dataset demonstrate the effectiveness of MCDNet, achieving an average Dice Similarity Coefficient of 81.61% for multi-organ segmentation.
Oct 29, 2026

Uncertainty-aware Coarse-to-Fine Main Pancreatic Duct Segmentation for Width Measurement in 3D MRCP

Assessment of the main pancreatic duct (MPD) from volumetric magnetic resonance cholangiopancreatography (MRCP) scans is an essential task for ductal dilatation diagnosis and pancreatic cancer analysis. However, manual assessment is affected by reader variability in which automated analysis may assist. Nevertheless, fully automated and uncertainty-aware MPD analysis from volumetric MRCP remains underexplored area of research. In this study, we propose an automatic and uncertainty-aware deep learning-based pipeline for MPD segmentation and maximum-width analysis from MRCP scans. A coarse localisation model first identifies the ductal region-of-interest, followed by a fine model that segments the MPD within the region. The dataset consists of 256 MPD-segmented MRCP scans from 69 patients. A randomly selected holdout test subset of 14 patients with 55 MRCP volumes was used for evaluation. We employed a five-model cross-validation ensemble for improved performance and uncertainty estimation. The best MPD segmentation performance was 0.634 DSC, 0.744 precision, and 0.593 recall. The mean absolute error for maximum MPD width prediction was 0.355~mm and dilated MPD (≥5\geq 5~mm) was detected with 75.0% sensitivity and 74.4% specificity. These novel results suggest that automated MPD segmentation can be used to aid MRCP-based duct measurements.
Oct 29, 2026

Segment Anything Model Based Context Guided Mamba Unet for Medical Image Segmentation

Medical image segmentation is crucial for clinical diagnosis and treatment planning, requiring both global contextual understanding and fine-grained structural precision. While the Segment Anything Model (SAM) demonstrates strong generalization capabilities, its direct application to medical images often lacks domain-specific adaptability. Meanwhile, State Space Models (SSMs)-based methods, such as Mamba, efficiently capture long-range dependencies but may struggle with preserving fine anatomical details. To address these challenges, we propose a segment anything model based context guided mamba unet, SAMBA-UNet, a novel framework that integrates SAM's context knowledge with Mamba's hierarchical feature learning to enhance both global representation and local detail refinement. Specifically, we introduce the Hierarchical Context Enhancement Module (HCEM), an attention-based fusion module that deeply incorporates the multi-level features of SAM and Mamba to improve detail perception and segmentation precision. Additionally, we employ LoRA and Adapter-based fine-tuning to adapt SAM to medical imaging tasks, further enhancing its domain-specific segmentation capability and robustness. We conducted a comprehensive study on several medical segmentation datasets, including Synapse, ISIC17, and ISIC18, evaluating our method across multiple metrics. Experimental results demonstrate that SAMBA-UNet achieves state-of-the-art performance, effectively balancing generalization, segmentation accuracy, and computational efficiency. Our code will be released upon acceptance.
Oct 29, 2026

DINOv2 for PET: A Pre-Training Domain Benchmark Across Classification, Segmentation, and Prognosis

DINO (self-DIstillation with NO labels) has become a stan- dard for self-supervised pre-training, producing features that generalise across datasets and downstream tasks. In medical imaging it has been adopted mainly for radiology (X-ray, CT and MRI), where even natural- image DINO features transfer well. In the literature, these features have been reported to transfer worse to functional imaging such as PET. Yet PET-specific DINO models have barely been introduced, and even less validated across multiple tasks and datasets. We present PET-DINOv2-2D, the first DINOv2 model pre-trained on 2D PET, and benchmark it against open-source encoders: the origi- nal DINOv2 (pre-trained on the LVD-142M natural-image dataset) and OmniRad (pre-trained on CT, MRI and ultrasound). Using the same lightweight heads for every backbone, and despite far less pre-training data, PET-DINOv2-2D matches or outperforms both on three down- stream PET tasks: normal/abnormal classification, lesion segmentation and recurrence-free survival prognosis. Its advantage is largest when few labels are available, suggesting that PET pre-training gives more transferable, label-efficient features. Code is made available at https://github.com/nuclivision/pet-dinov2-2d/.
Oct 29, 2026

Anatomical Prior-Guided Routing for 3D Lung Tumor Segmentation

Accurate lung tumor segmentation in computed tomography (CT) is essential for treatment planning, response assessment, and quantitative imaging analysis. However, 3D lung tumor segmentation remains challenging because tumors occupy only a small portion of the whole volume and exhibit heterogeneous appearances across anatomical locations. In patch-based training and sliding-window inference for 3D medical image segmentation, location-dependent heterogeneity is further amplified because cropped image patches provide limited global anatomical context, making it difficult for a model to adapt its feature processing according to the anatomical region from which each patch is extracted. To address this limitation, we propose an Anatomical Prior-guided Routing Module (APRM) for lung tumor segmentation. For each image patch, we obtain anatomical prior information of regional occupancy and deterministically select an anatomical routing gate. The selected gate then performs sparse feature routing over a shared expert adapter pool, enabling anatomy-specific feature adaptation while sharing expert capacity across regions. We evaluate APRM on two datasets with various backbone networks and demonstrate consistent improvements over baseline models. Furthermore, feature visualizations show that APRM produces different feature responses depending on patch location, indicating that the proposed routing mechanism effectively adapts feature processing according to anatomical context.
Oct 27, 2026

Effects of Deep Learning Architecture and Pretraining on Automated Vocal Fold Segmentation in Ex Vivo High-Speed Phonation Images

Two-dimensional (2D) intraglottal particle image velocimetry (PIV) of ex vivo phonation experiments quantifies vocal fold medial surface dynamics and the intraglottal flow field. However, it relies on manual segmentation because residual glare, low tissue-to-flow contrast, and tracer-particle speckle obscure the vocal fold boundaries. This study assessed how deep learning architecture and ImageNet pretraining affect automated vocal fold segmentation in these high-speed images. Four established architectures from three categories were benchmarked: the convolutional neural network (CNN)-based UNet and UNet++, the hybrid CNN-transformer-based TransUNet, and the pure transformer-based Swin-UNet, the latter two trained from scratch and from ImageNet-pretrained weights. Using 16,344 expert-annotated images from 227 phonation trials of excised canine larynges, the six pipelines were trained with five seeds under a standardized protocol and compared on 50 held-out test trials using trial-level Wilcoxon signed-rank tests with Holm correction. Mean Dice similarity coefficient (DSC) spanned only 0.9734 to 0.9764, so the pipelines differed mainly in boundary fidelity. Pretraining significantly improved the boundary F1 score (BF1) and 95th percentile Hausdorff distance (HD95) of the TransUNet and Swin-UNet, about four times more for the Swin-UNet. Once pretrained, the two performed similarly, although the Swin-UNet has only about a quarter of the trainable parameters. Without pretraining, the TransUNet had a significantly higher BF1 and a lower HD95 than both CNN-based pipelines and about half their share of images with HD95 > 50 pixels. To our knowledge, this is the first study to apply deep learning to vocal fold segmentation in 2D intraglottal PIV, and it offers a reference framework for segmenting experimental flow-visualization images with noisy optical conditions or highly deformable objects.
Oct 27, 2026

Segmentation Confidence for Arbitrary CNNs

Convolutional neural networks (CNN) are widely used for medical image segmentation. However, they lack an inherent measure of confidence. Existing methods for estimating prediction uncertainty often require a custom network architecture and/or dedicated training setups and need to be trained from scratch. In addition, the deduction of a single confidence score per input from the uncertainty maps is not always straightforward. In this study, we explore voxel-based uncertainty estimation methods that can be added to existing segmentation pipelines without training from scratch. We also propose a novel method to estimate a single confidence score from the uncertainty maps. Our evaluations on different ROIs and modalities suggest that our confidence score can predict segmentation performance in unseen data.
Oct 26, 2026

O2D-MedNet: An Optimization-Aware Dual-Domain Framework for Robust Medical Image Segmentation

Medical image segmentation (MIS) remains challenging due to composite degradations and multi-scale geometric variations, which jointly impair lesion-background separability, structural consistency, and optimization stability. Existing single-stream frameworks entangle heterogeneous cues within a single representation pathway, while hybrid-stream approaches often rely on generic or static fusion, limiting effective coordination across domains and failing to explicitly address optimization instability. To overcome these limitations, we propose a new optimization-aware dual-domain framework for MIS (O2D-MedNet). First, a degradation-aware dualdomain interaction (DDI) module integrates Fourier - and Wavelet-domain features to suppress degradation-sensitive responses while preserving structural and fine-detail information. Second, a cross-backbone contour-guided fusion (CGF) module enables selective interaction between CNN-based local detail modeling and visual state-space-based global structure modeling, improving boundary accuracy and representation consistency. Third, a gradient-context optimization (GCO) strategy stabilizes training by adaptively adjusting learning dynamics based on loss trends and gradient statistics, mitigating instability caused by class imbalance and heterogeneous sample difficulty. Extensive experiments on six benchmarks demonstrate consistent improvements over state-of-the-art MIS methods across multiple imaging modalities. Further analyses confirm enhanced sensitivity, structural consistency, and optimization stability, validating the effectiveness of the proposed O2D-MedNet for robust MIS under heterogeneous conditions.
Oct 26, 2026

Rethinking Data Imbalance in Class Incremental Surgical Instrument Segmentation

In surgical instrument segmentation, the increasing variety of instruments over time poses a significant challenge for existing neural networks, as they are unable to effectively learn such incremental tasks and suffer from catastrophic forgetting. When learning new data, the model experiences a sharp performance drop on previously learned data. Although several continual learning methods have been proposed for incremental understanding tasks in surgical scenarios, the issue of data imbalance often leads to a strong bias in the segmentation head, resulting in poor performance. Data imbalance can occur in two forms: (i) class imbalance between new and old data, and (ii) class imbalance within the same time point of data. Such imbalances often cause the dominant classes to take over the training process of continual semantic segmentation (CSS). To address this issue, we propose SurgCSS, a novel plug-and-play CSS framework for surgical instrument segmentation under data imbalance. Specifically, we generate realistic surgical backgrounds through inpainting and blend instrument foregrounds with the generated backgrounds in a class-aware manner to balance the data distribution in various scenarios. We further propose the Class Desensitization Loss by employing contrastive learning to correct edge biases caused by data imbalance. Moreover, we dynamically fuse the weight parameters of the old and new models to achieve a better trade-off between the biased and unbiased model weights. To investigate the data imbalance problem in surgical scenarios, we construct a new benchmark for surgical instrument CSS by integrating datasets. Extensive experiments demonstrate the effectiveness of the proposed framework, achieving significant performance improvement against existing baselines.
Oct 26, 2026

MedAdaptAgent: An Automatic Harness for Adapting Medical Imaging Models to New Sites

Reusing pretrained medical-imaging models offers an alternative to training from scratch. A model trained for the same task may perform poorly at a new hospital because imaging protocols and preprocessing differ. Effective adaptation depends on the model architecture, domain shift, and available labels and compute. Adaptation can improve scores on a small labeled set yet reduce performance on unseen data. We present MedAdaptAgent, an automatic harness that turns a supplied model, target data, and a free-text request into a new-site adaptation workflow. Its LLM-driven Adaptation Planner uses model-site evidence to choose compatible experiments and revise subsequent adjustments. The harness requires evidence of improvement over the pretrained model, then delivers the selected model as a complete, runnable package. Evaluation spans 26 segmentation and classification transfers across architectures and compute settings, with segmentation annotation budgets ranging from zero-shot transfer to few-shot adaptation. With 20 local annotations, mean segmentation Dice rises from 0.483 to 0.774 across 10 transfers, a 60.1% relative gain, with no harmful replacements. Mean classification AUROC rises from 0.810 to 0.837 across 13 transfers, a 3.4% relative gain. Comparing adapted models with the pretrained model reduces harmful classification replacements by 30.8% versus selecting the highest-scoring model on the available labels, using identical candidates. Seven public-model deployments demonstrate adaptation and reproducible package delivery across contrast and modality shifts. A CT-to-MRI study extends the evaluation to four LLM planners, including two open-weight models. We release the code on GitHub.
Oct 25, 2026

An Agentic AI Workflow for Liver Lesion Segmentation and Structured Radiology Reporting

Despite advances in automated liver lesion segmentation, a gap remains between image-derived predictions and clinically interpretable radiology reports. Bridging this gap requires quantitative measurements that are both reproducible and traceable. We present an evidence-grounded agentic AI framework that connects liver and lesion segmentation with deterministic quantification and structured reporting. TotalSegmentator-based nnU-Net models delineate the liver, Couinaud segments, and lesions, while computational tools extract volumes, dimensions, counts, and anatomical locations. A large language model (LLM) organizes these measurements into a predefined reporting schema, with numerical consistency checks against source measurements. On 51 LiTS cases, the segmentation stage achieved a liver Dice score of 0.947, lesion sensitivity of 75.6%, and positive predictive value of 68.9%. Exploratory screening of 25,494 MERLIN reports identified 10,208 (40.0%) with liver-related abnormalities. By connecting quantitative imaging evidence with agentic report generation, this work takes a step toward human-centered medical AI that prioritizes traceability and clinical relevance.
Oct 24, 2026

End-to-end prostate lesion segmentation and detection from undersampled diffusion-weighted MRI

Automated prostate lesion detection from diffusion-weighted MR imaging (DWI) conventionally relies on reconstructed images and does not fully use all acquisition information. We present an end-to-end network that uses complex multicoil DWI data and coil sensitivity information for prostate lesion segmentation. We included 269 fastMRI prostate examinations with additional voxel-level lesion annotations. Of these, 64 examinations contained PIRADS 4 or 5 lesions. The proposed network, VarNet-Seg, consists of a k-space variational network (VarNet) with six variational cascades and an image-space 3D segmentation U-Net. Comparator models used the same segmentation architecture with fully coil-combined images (CC-Seg), fixed root-sum-of-squares reconstruction (RSS-Seg), or fixed SENSE reconstruction (SENSE-Seg). We performed ablations with end-to-end training and data consistency (DC) enabled or disabled. We evaluated lesion segmentation using Dice and patient-level detection using AUROC in five-fold cross-validation with full sampling, simulated undersampling, added noise, or both. VarNet-Seg achieved the highest Dice at every undersampling level. At eight-fold acceleration, Dice was 0.22 for VarNet-Seg, 0.14 for SENSE-Seg and 0.16 for VarNet-Seg (no DC). The paired difference from SENSE-Seg was 0.08 (95% CI, 0.04-0.11). With full sampling, VarNet-Seg and RSS-Seg performed similarly (0.40 vs 0.39). Patient-level AUROC decreased from 0.75 with full sampling to 0.63 at eight-fold acceleration; corresponding RSS-Seg AUROCs were 0.76 and 0.64. The proposed multicoil network improved prostate lesion segmentation under simulated undersampling compared to conventional models. Matched ablations supported contributions from both end-to-end training and data consistency. Prospective evaluation is needed to establish whether this approach can be used clinically in accelerated prostate DWI.
Oct 24, 2026

Energy Efficient Lung Tumor Segmentation with a modified CBAM ENet Skip Model

Lung tumor segmentation plays a vital role in early detection and treatment planning of lung cancer. Although state-of-the-art deep learning models achieve high dice score coefficients (DSC), each forward pass requires computing large amounts of floating point operations, making them computationally expensive, requiring GPU acceleration, and having slow inference speed, limiting real-world clinical deployment. We propose a lightweight, energy-efficient model that leverages the ENet architecture for its real-time inference capability and low computational cost, enhanced with UNet-style skip connections between encoder and decoder stages for feature reuse and the lightweight Convolutional Block Attention Module (CBAM) for improved feature representation. The model is trained on publicly available data from The Cancer Imaging Archive (TCIA) via the Medical Segmentation Decathlon Challenge (MSD) and evaluated on the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) dataset. Our model achieves a DSC of 0.90812 (threshold of 0.5) with its compact architecture of 430,052 parameters and 0.549 Giga Multiply-Accumulate operations (GMAC), making it up to 10 times faster, requires 79 times less GMAC than UNet, and has 22 times fewer parameters than SegNet. These characteristics make it well-suited for deployment in clinical settings where computational resources are limited and decrease the cost of utilizing such a system. Additionally, the explainable AI technique of Grad-CAM is used to provide visual interpretability of the model's predictions and to identify regions where segmentation performance requires improvement.
Oct 23, 2026

Sam-Correction: Fully Adaptive Label Noise Reduction for Medical Image Segmentation

The quality of the teacher label has a dramatic impact on the outcome of the machine learning process. Medical image segmentation often suffers from a noisy ground truth (GT) mask due to difficulties in consistent annotation. Although a recent study has proposed a promising method to curate the noisy GT mask, this requires additional well-curated GT masks that are not always accessible without the aid of multiple medical experts. As an alternative, we propose SAM-Correction, which utilizes a foundation model to correct the noisy GT mask in a fully adaptive manner instead of manually preparing well-curated masks. In our approach, we progressively mitigate label noise via the segment anything model (SAM), where prompts are given from another segmentation network that we train concurrently. Experiments with various types of label noise derived from actual human annotations demonstrate that SAM-C achieves precise noise reduction and high-performing segmentation models trained thereby. Our method paves the way for robust model training even when clean labels are entirely unavailable.
Oct 23, 2026

Polyp-VSSD: A Pre-trained Transformer with Local-Global Joint VSSD Decoding for Polyp Segmentation

Early detection of colorectal polyps is essential for preventing colorectal cancer, making accurate polyp segmentation a key component in computer-aided diagnosis systems. However, existing endoscopic segmentation methods often exhibit limited representational capacity and insufficient integration of global and local contextual information. To address these limitations, we propose Polyp-VSSD, a novel local-global joint decoding framework built upon a pre-trained Transformer backbone for high-precision polyp segmentation. Polyp-VSSD leverages the strong feature expressiveness of large-scale visual pre-training and unifies global semantic modeling with local fine-grained reconstruction to enhance segmentation fidelity. Extensive experiments on multiple public endoscopic datasets demonstrate that our approach significantly outperforms state-of-the-art methods in both Dice and IoU. On the EndoScene dataset, Polyp-VSSD achieves mIoU and mDice scores of 0.903 and 0.946, respectively, highlighting its robustness and strong generalization capability. This work presents an effective and scalable solution for intelligent endoscopic image analysis.
Oct 23, 2026

Hyperparameter-Free Boundary-Interior t-vMF Dice Loss for Medical Image Segmentation

Class imbalance and errors near anatomical boundaries remain challenges in medical image segmentation, motivating loss functions that account for these difficulties. Adaptive t-vMF Dice Loss adjusts the similarity function during training but requires hyperparameter tuning. We propose Self-Tuned Boundary-Aware t-vMF Dice Loss (STB-tvMF Dice), which adapts the function separately for boundary and interior regions without tuning shape-adaptation parameters. Each region's shape parameter of t-vMF function is determined from its mean prediction-target cosine similarity in the preceding epoch and remains fixed throughout the current epoch. This rule maximizes the slope of the similarity function at the observed mean similarity, providing a principled basis for adaptation without validation-based parameter selection. Experiments on three datasets and architectures demonstrated its effectiveness. On Synapse with U-Net, STB-tvMF Dice achieved a mean DSC of 70.75%, compared with 63.03% for Adaptive t-vMF Dice Loss. Our code will be available soon.
Oct 22, 2026

Evaluation of Uncertainty-Aware Multi-Software Ensembles for Hippocampal Segmentation

Accurate hippocampal segmentation can be a useful tool for diagnosing and monitoring neurological conditions such as Alzheimer's disease and epilepsy. While numerous automated segmentation methods exist, their clinical adoption remains limited. Reliable uncertainty assessment can enhance trust and facilitate clinical translation. This study evaluates ensembles of five heterogeneous hippocampal segmentation methods - InnerEye, ASHS, FastSurfer, HippoSeg, and FreeSurfer - across two dementia datasets and one epilepsy dataset. The sub-ensemble containing InnerEye, FastSurfer, and HippoSeg emerged as both accurate and efficient, highlighting the feasibility of balancing computational cost and performance. Additionally, ensemble-derived uncertainty quantification with sample variance, mutual information, and predictive entropy is shown to reduce inaccurate segmentations by flagging low-confidence cases, potentially providing a mechanism for automatically escalating ambiguous cases for expert assessment. Lastly, this study explores the downstream clinical utility of ensemble-derived uncertainty, finding a significant correlation with motion artefact severity and a modest contribution to Alzheimer's disease classification.
Oct 22, 2026

A General-Purpose Dual-Path Interaction Framework for Multi-View Medical Image Segmentation: Alleviating Data Volume Dependency in Small-Sample Regimes

The performance of medical image segmentation depends on a large amount of annotated data, and most segmentation models experience a significant drop in performance in low-sample-size scenarios. Existing semi-supervised and weakly supervised methods rely on specific network architectures, while traditional multi-view-assisted segmentation methods require strictly paired samples, which limits their clinical applications. To address these issues, we propose DPIF, a general-purpose plug-and-play dual-path interaction framework compatible with arbitrary encoder-decoder segmentation networks, which leverages cross-view anatomical complementarity to reduce annotation reliance. DPIF first performs Sinkhorn optimal transport-based cross-view distribution alignment to establish global semantic correspondence without sample-level pairing. It then adopts conditional mutual information-guided feature decoupling to enable bidirectional knowledge transfer only within the shared semantic space, suppressing view-specific noise. Finally, persistent homology-based topological regularization encodes anatomical invariants as unsupervised priors to mitigate overfitting. Experiments were conducted using 24 baseline models on a private multicenter echocardiography dataset and two public datasets. The results show that DPIF-enhanced models outperform single-view baseline models when trained on comparable amounts of data. Notably, most dual-path variants trained on 40% - 60% of the data achieve performance comparable to that of single-view models trained on the full dataset. This demonstrates that DPIF provides a general-purpose and scalable solution for data-scarce multi-view medical image segmentation problems.
Oct 21, 2026

TernScope: Model-Hardware Co-Design for Efficient Ternary Endoscopic Segmentation

Edge medical segmentation must reconcile small model size, high accuracy, and fast inference. TernScope addresses this tradeoff through model--hardware co-design, learning a compact segmentation network whose low-bit operators also simplify hardware execution. Split-channel large-kernel blocks preserve spatial context with limited computation, while branch fusion removes redundant inference paths. Ternary Progressive Quantization-aware Training (TPQ) then adapts the fused network from deep to shallow layers, through the decoder, and finally to the input and prediction layers. All 25 convolutions use ternary weights and 8-bit activations, enabling packed storage and multiplier-free computation. The resulting model uses 0.2483 M parameters and 0.0949 GMACs while retaining competitive segmentation accuracy on in-domain and external datasets. Under the same 45 nm technology, TernScope reduces compute-array area by 88.46% compared with the original Gemmini, a systolic-array accelerator with 8-bit ×\times 8-bit multipliers. These results demonstrate a path from accurate lightweight medical segmentation to compact low-bit hardware.
Oct 21, 2026

OpenMAP-HIE: Pathology Informed Score-based Diffusion Model for Unsupervised Neonatal Hypoxic-Ischemic Encephalopathy Lesion Segmentation

Accurate localization of neonatal hypoxic--ischemic encephalopathy (HIE) lesions on apparent diffusion coefficient (ADC) images is clinically important but is limited by scarce expert annotations and substantial variation in lesion appearance. We propose OpenMAP-HIE, a pathology-informed score-based diffusion model for unsupervised HIE lesion localization without voxel-wise lesion supervision. A denoising diffusion model learns the healthy neonatal ADC distribution, while a ControlNet-based conditional branch preserves patient-specific anatomy. At inference, anomaly evidence is derived directly from differences between conditional and unconditioned noise predictions at independently evaluated diffusion noise levels, avoiding dependence on a final pseudo-healthy reconstruction or sequential reverse-diffusion chain. Based on the characteristic ADC reduction associated with acute HIE, only discrepancies consistent with the expected pathological direction are retained and aggregated across noise levels using a geometric mean. Spatial mean filtering further suppresses isolated responses. The framework was evaluated on the BONBID-HIE dataset. The ADC-only method achieved a Dice score of 0.283±0.2440.283\pm0.244, average precision of 0.5050.505, Hausdorff distance of 25.45±15.6325.45\pm15.63 mm, mean average surface distance of 9.40±8.499.40\pm8.49 mm, and normalized surface distance of 0.355±0.2360.355\pm0.236, providing the best overlap and surface-distance performance among the evaluated unsupervised methods and Dice performance comparable to supervised ADC-only models. Optional population-derived ADC ZZ-map refinement further increased Dice to 0.602±0.2690.602\pm0.269. These findings support pathology-informed score discrepancies as a useful signal for neonatal HIE lesion localization, while highlighting remaining challenges in detecting small and low-contrast lesions.
Oct 20, 2026

Reliability-Guided Vision-Language Decoding with Text-Aware Skip Refinement for Medical Image Segmentation

Medical image segmentation remains challenging when targets exhibit limited visual distinction, irregular structure, or substantial variation across imaging modalities. Medical text can reduce this ambiguity, but indiscriminate fusion may introduce unreliable guidance. We present RELiF, a vision--language framework that integrates text through reliability-guided decoding. Its Reliability-guided Fusion Gate (RFG) adaptively controls cross-modal updates, while the Text-guided Skip Refinement Adapter (TSRA) refines high-resolution features using text guidance. RELiF is evaluated on radiographic, CT, and endoscopic segmentation tasks, where it shows competitive performance across diverse imaging characteristics and target appearances. Additional analyses examine efficiency and stability. The complementary uncertainty representation derived from the reliability response also shows an association with prediction difficulty, with higher uncertainty values occurring more frequently in pixels associated with segmentation errors. Code: https://github.com/SeivanTalaie/RELiF.
Oct 20, 2026

LatticeRank: Spacing-Ranked Consistency for Native-Grid 3D Medical Image Segmentation

Variable voxel spacing changes more than image resolution: it alters the discrete sampling lattice, tensor geometry, and anatomical evidence available to a 3D segmentation network. While conventional pipelines restore images to a canonical grid, direct-grid deployment requires the model itself to tolerate these changes. We observe that candidate grids are not exchangeable views -- a coarse grid removes more structural information than a mildly resampled one -- yet standard consistency objectives assign them equal influence. We therefore propose LatticeRank, a training-only framework that aligns candidate posteriors in physical space and allocates consistency supervision by voxel-spacing order: among endpoint-matched candidates, the auxiliary loss concentrates on the coarsest requested grid, while inference retains a single network forward with no candidate branch or ensemble. On MSD Task04, LatticeRank improves coarse-grid Extra Dice over mean consistency by 0.03436 across five seeds while meeting the prespecified reference-grid noninferiority criterion. A controlled ladder shows that grid exposure provides the largest recovery, posterior consistency adds a second gain, and spacing-ranked allocation yields the strongest direct-grid result; requested spacing thus provides a simple, model-independent ordering signal for direct-grid consistency learning.