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 papers69 papers in the last four weeks, down 8% on the four weeks before. 0.5% of all new papers.

Nov 13, 2026

X-Strata: Separating Aneurysms and Overlapping Vessels into Layers from 2D X-ray Angiography

An X-ray angiogram sums every structure along a ray into one pixel. When vessels cross an aneurysm, they obscure part of it and mix their contrast into its filling curve. We present X-Strata, a network that separates a cine angiogram into three layers: the complete aneurysm sac, the vessels in front of it, and the vessels behind it. Contrast timing indicates how much each layer contributes to a pixel, and parallax between two views indicates their order, which a single view cannot determine. X-Strata first estimates the layers and their contrast curves, then uses the second view to assign vessels to the front or back layer, and lifts all layers into 3D. It learns from layer labels projected from same-session 3D rotational angiography, but needs only 2D cine runs and their acquisition geometry at inference. On 220 held-out patients from three centers (122 external), two-view X-Strata ranks first among 14 baselines, including VGGT and C2^2RV, in recovering the sac where vessels overlap it (Dice 0.693 internal, 0.641 external) and in ordering the layers (balanced accuracy 0.703, 0.659). Its order accuracy exceeds that of all 11 end-to-end baselines by at least 4.1 points internally and 3.3 externally (Holm-adjusted p<0.001p < 0.001) and grows with view separation. Recovered 3D sac surfaces have a median Chamfer distance of 0.34 mm on the internal cohort. X-Strata may therefore provide layered aneurysm and vessel information, including 3D sac shape, for patients who undergo only 2D angiography.
Nov 11, 2026

PCLSegNet: Anatomy-Aware Deep Learning Framework for MRI-based Pancreatic Cyst Segmentation and Size Assessment

Early detection and follow-up of pancreatic cystic lesions (PCLs) are crucial, as some of their subtypes, such as mucinous cystic neoplasms (MCNs) and intraductal papillary mucinous neoplasms, carry a significant risk of malignant transformation. Although most AI studies investigating PCLs rely on computed tomography (CT) scans, magnetic resonance imaging (MRI) offers superior soft tissue contrast, making it highly suitable for PCLs assessment. In this work, we propose an anatomy-aware two-stage deep learning framework for automated PCLs segmentation on abdominal MRI scans. First, a publicly available pancreas segmentation model is used to localize the pancreas. Then, we introduce the anatomyaware PCLSegNet, which incorporates anatomical priors as guidance for pancreas and PCLs segmentation. To address the class imbalance problem, we develop a Class-Specific ErrorWeighted (CSEW) loss function. Postprocessing is applied through anatomical constraints.Our proposed method outperforms multi-organ segmentation models such as TotalSegmentator, achieving substantially higher Dice scores for pancreas segmentation. Moreover, it also achieves a superior normalized surface Dice (NSD) and recall for PCLs segmentationcompared to other state-of-the-art models like nnU-Net, while also notably reducing the false negative rate, facilitating the automatic early detection and the noninvasive imaging-based assessment of PCLs.
Nov 11, 2026

GingivitisSeg: A Public Dataset and Comparative Benchmark for Gingivitis Segmentation in Intraoral Images

Gingivitis segmentation from intraoral photographs can support computer-assisted periodontal assessment, but pixel-level delineation remains challenging due to severe foreground-background class imbalance, low-contrast boundaries, and variations in illumination and anatomy. We introduce GingivitisSeg, a public benchmark comprising 961 intraoral images with pixel-level annotations of gingival inflammation and predefined training (672), validation (144), and test (145) partitions. Seven semantic segmentation model-backbone configurations were compared using standardized partitions, input resolution, and evaluation metrics. Controlled ablation experiments examined class-weighted cross-entropy loss, Dice loss, and auxiliary supervision. UPerNet with ResNet50 achieved the highest mean Intersection over Union (mIoU) of 76.49% and gingivitis IoU of 54.91%. However, differences from DeepLabV3+ with ResNet50 and SegFormer with MiT-B2 were not statistically significant after Holm correction. The evaluated optimization components improved performance when combined in the UPerNet-ResNet50 configuration. Further analyses showed that performance was associated with gingivitis region size and decreased under stronger image blur. The dataset, benchmark splits, and source code are available at https://github.com/zeynepozdemir/GingivitisSeg.
Nov 10, 2026

Medical Image Segmentation: Foundation Model Adaptation versus Task-Specific Training

Foundation models pretrained on large natural-image collections are increasingly adapted for medical image segmentation, in the expectation that they will replace models trained for each task. Most comparisons, however, use data from the training distribution and a single task-specific baseline whose configuration is rarely justified, and therefore provide limited evidence of performance at new clinical sites. It also remains unclear how much of a foundation model must be adapted, and what determines this. We adapted a foundation model, DINOv2, with strategies ranging from tuning only its bias terms to full fine-tuning, and compared it with U-Nets and ResU-Nets trained from scratch. Experiments covered colonoscopy, breast ultrasound and dermoscopy, with testing on held-out data from the training source and on independent datasets from other institutions. The adapted foundation model generalised better on every external dataset. Within the training distribution, the task-specific models remained competitive when training data were abundant, and delineated boundaries more precisely, while the foundation model more often missed small lesions. Only a small fraction of the foundation model required adaptation, and the capacity needed was determined by the imaging domain rather than by the adaptation method. A widely used polyp test set was also found to duplicate images from another benchmark. Foundation-model adaptation is therefore warranted where models must work across sites, with capacity selected on the target domain.
Nov 10, 2026

Counterfactual Analysis of Extent Leakage from Annotation-Derived Prompts in Vision-Language Medical Image Segmentation

Text-guided segmentation models receive an image and a short caption about the lesion, and on public benchmarks the caption improves accuracy considerably. On colonoscopy and breast ultrasound, however, the size, count and location words of each caption were computed from the mask that later scores the prediction, and the chest X-ray captions were written by benchmark annotators. We tested what two published models take from them. On colonoscopy and chest X-ray, it is mostly the lesion's extent. Keeping only the size word or the lung-zone phrase recovers 84 to 98 percent of the improvement over an empty caption, and removing it loses 52 to 77 percent. The rest matters little, and a polyp called a rock is segmented just as well. We call this extent leakage. On breast ultrasound, nearly half the captions also name the diagnosis, which carries part of the benefit. Retraining on three datasets shows that models pick up this habit from their training captions, though only partly on breast ultrasound, and that it weakens their segmentation from the image alone. The leak can be measured without training a model, since caption words alone predict lesion area (coefficient of determination 0.54 to 0.77 on six of seven test sets). Without the test mask, the best method we tested, which estimates extent from the image, reaches 74.59 Dice on colonoscopy against the published 77.23. We propose an evaluation protocol that keeps what a caption says about the image apart from what it copies from the label.
Nov 10, 2026

MicroBT: Centroid-Guided Synergistic Learning for Multi-Modal Micro Brain Tumor Segmentation and Counting

Multi-modal brain tumor segmentation is essential for clinical diagnosis, radiotherapy planning, and longitudinal monitoring. While recent studies have achieved remarkable overall segmentation performance, they rely on overlap-based objectives that inherently favor large regions, causing sub-3 mm micro-lesions to be systematically suppressed during training. Moreover, existing pixel-level segmentation frameworks lack explicit instance-level modeling, leading to unreliable lesion counting that directly impacts clinical staging and therapeutic decisions. To address these challenges, we propose MicroBT, a unified multi-modal framework for micro brain tumor segmentation and counting. Our core insight is that a fundamental geometric property is inherently scale-invariant: regardless of size, each lesion possesses a well-defined centroid. Leveraging this, we first devise a centroid-anchored synergistic paradigm that utilizes predicted centroids as shared anchors to simultaneously condition dense segmentation and instance-level localization. To counteract the tumor size imbalance, we further devise a Volume-Calibrated Loss (VC-Loss) that adaptively amplifies the gradient contribution of micro-lesions, alongside a Size-Aware Curriculum Optimization (SACO) that stabilizes multi-task training by establishing global representations before progressively unlocking fine-grained localization. Extensive experiments demonstrate that MicroBT outperforms state-of-the-art methods, particularly on metastases, where micro-lesion (≤3\leq 3 mm) localization precision improves by approximately 7% and counting estimation errors decrease by approximately 26%. The code is available at https://github.com/leonlou921/MicroBT.
Nov 10, 2026

Region-Wise Logit Fusion and Utility-Gated Refinement for Brain Metastasis Segmentation

BraTS-METS 2026 Task 1 evaluates segmentation of brain metastases and postoperative resection cavities on heterogeneous multiparametric MRI, requiring detection of small enhancing foci while preserving the geometry and hierarchy of enhancing tumor (ET), tumor core (TC), whole tumor (WT), and resection cavity (RC). We present COMPASS-METS (Component-Aware Multi-Trainer Probability Assembly with Structured Segmentation), which combines three five-fold nnU-Net configurations into aligned regional probability ensembles. A structured-probability anchor applies region-specific component decisions, TC boundary completion, RC filtering, and hierarchy-preserving conversion. Omitted ET candidates are recovered additively using learned component confidence and deterministic multi-trainer support for ET and its TC/WT parents; a final utility gate admits only disconnected candidates with sufficient lesion-existence and geometry-safety probabilities. On the reused 179-case challenge development cohort, COMPASS-METS (Team: MicroBT) achieved Small F1 0.354, lesion-wise DSC 0.712, NSD 0.714, All F1 0.779, and HD95 56.6 mm. Relative to ResEncXL, it improved DSC, NSD, and All F1 and reduced HD95, while Small F1 changed from 0.367 to 0.354. Stagewise analysis attributes the principal geometric gains to structured probability construction and shows that guarded ET refinement recovers most of the associated small-lesion detection loss. These 179-case results remain selection-aware development estimates. The source code is publicly available at https://github.com/leonlou921/COMPASS-METS.
Nov 10, 2026

Seeing the Small: Deformable Duality Mamba for Retinal Lesion Segmentation

Diabetic retinopathy (DR) lesions vary widely in shape, and microaneurysms (MAs) span only a few pixels. We hypothesize that modeling the spatial organization of lesion regions, with global context and shape-adaptive scanning, improves the segmentation of such small and irregular lesions. To test this, we propose D2^2Mamba, which couples non-causal state space duality with deformable Mamba scanning. We evaluate it with five-fold cross-validation on the DDR dataset, comparing against representative segmentation baselines under an identical training protocol, and conduct ablations on each component. D2^2Mamba achieved the best overall performance, with 33.87% mIoU, 2.99 percentage points above the strongest baseline. The largest gain appeared on MAs, the smallest and most easily missed lesions, where Dice improved by 10.06 percentage points. These results confirm our hypothesis that spatially adaptive state space modeling benefits tiny-lesion segmentation. Code and pretrained weights are available at https://github.com/PUREPANEL1/D2Mamba.
Nov 9, 2026

Comparative Evaluation of Deep Learning Models for Geographic Atrophy Segmentation in En Face OCT Images

Background: Geographic atrophy (GA) is an advanced form of age-related macular degeneration (AMD). It causes irreversible vision loss due to progressive degeneration of the retinal pigment epithelium (RPE) and photoreceptors. Accurate segmentation of GA in en-face image is crucial for early diagnosis, monitoring disease progression, and developing personalized treatment strategies. However, existing deep learning approaches are typically evaluated using single architectures and single-device datasets, limiting insight into relative performance and cross-device robustness. Methods: We trained and systematically compared five deep learning architectures for GA segmentation: Nested U-Net, ResU-Net, nnUnet, Swin-Unet and MedSegDiff model, together with a thresholding based classical baseline. The models were trained on a dataset of en-face OCT images derived from 269 OCT volumes from two different devices, following a three-step preprocessing technique involving normalization and inpainting to enhance the quality of the en-face images. Results: On the fixed held-out validation set comprising OCT scans from both Cirrus (R) (Carl Zeiss Meditec, Inc., USA) and Spectralis (R) (Heidelberg Engineering, Germany) devices, nnUnet achieved the highest mean Dice similarity coefficient (DSC) of 0.8882 +/- 0.0033. The other models yielded the following Dice scores: Nested U-Net (0.7932 +/- 0.0423), ResU-Net (0.8453 +/- 0.0074), Swin-Unet (0.6886 +/- 0.0294), and Diffusion model (0.7959 +/- 0.0242). Conclusions: nnUnet framework, demonstrated most reliable performance for GA segmentation in en-face OCT under limited data conditions. It offers the best balance of accuracy, stability, and efficiency for GA quantification.
Nov 7, 2026

3D Segmentation in the Clinic: A Grand Challenge

This paper describes the set-up of a segmentation competition for automatic and semi-automatic extraction of the liver from computed tomography scans and the caudate nucleus from brain MRI data. This competition was held in the form of a workshop at the 2007 Medical Image Computing and Computer Assisted Intervention conference. The rationale for organizing the competition is discussed, the training and test data sets for both segmentation tasks are described and the scoring system used to evaluate the segmentation is presented.
Nov 6, 2026

ATLAS: A Multi-Procedure Benchmark and Context-Aware Model for Surgical Anatomy Segmentation

Recognizing anatomical structures during minimally invasive surgery (MIS) could support intraoperative navigation and improve patient safety, but progress is limited by small, single-procedure datasets and by segmentation methods developed for natural scenes. This work addresses both limitations through a new dataset and model. First, we introduce ATLAS-120k, a clip-level semantic segmentation dataset of 121,018 annotated frames from 100 surgical videos, covering 14 laparoscopic and robot-assisted procedures and 41 classes. Annotations were created with a pipeline that combines manual labeling, tracker-based propagation, and review by surgeons. Second, we propose ATLAS (Anatomy Recognition with Context Learning using Foundation Representations), a video semantic segmentation model for surgical anatomy recognition. ATLAS builds on in-domain foundation-model embeddings and adds context queries for the procedure and surgical phase, together with query propagation between frames for short-term memory. ATLAS outperforms state-of-the-art natural-image and in-domain foundation models in both segmentation accuracy and temporal consistency, achieving a Dice score of 0.70 with ViT-L while running in real time at 76.2 FPS. Ablations show that the context queries improve accuracy and that query propagation improves temporal consistency. ATLAS also generalizes well, matching a dedicated model zero-shot on CholecSeg8k and improving phase recognition on AutoLaparo over SurgeNet initialization. The model weights, dataset annotations, and annotation tool are publicly available at https://github.com/TimJaspers0801/ATLAS.
Nov 6, 2026

The Role Of Recurrent Refinement In Medical Image Segmentation

While feed-forward segmentation networks perform well on large cohorts, they degrade in constrained clinical settings with few training samples and imaging artifacts. Human vision, by contrast, remains robust under these conditions, a property partly attributed to the recurrent and feedback connectivity of the visual cortex, which refines visual information over time. Inspired by this, we append lightweight recurrent refinement blocks to segmentation backbones, namely Conditional Random Fields (CRFs), modern Hopfield networks and convolutional GRUs, and study their behaviour as the number of iterations increases at test time (including beyond the training horizon). Evaluated on two open-source datasets, Kvasir- SEG and ARCADE, our recurrent blocks add less than 1.5% parameters and yield gains on clean data (up to 1.4 pp) and under noise (up to 17 pp) while reducing HD95. Code is available at https://github.com/joaodsmarques/recurrencehelpsegmentation .
Nov 6, 2026

Region-aware error triage for medical image segmentation with groupwise conformal risk control

Segmentation masks are increasingly reviewed rather than redrawn, which requires knowing where a mask is likely wrong. Learned error maps rank pixels by risk, but the number of pixels to warn is chosen ad hoc, and calibrating one warning threshold over all error pixels may leave errors far from the predicted contour under-flagged. We propose RACE-Triage, a post-hoc error triage framework that leaves the segmentation mask unchanged. A risk network is trained on out-of-fold predictions from backbone-independent inputs. The predicted contour partitions each image into a boundary band and a non-boundary region, and conformal risk control is applied separately in each region to bound the expected fraction of missed errors among cases with errors there. On ISIC 2018 dermoscopy and BUSI breast ultrasound (where patient identifiers are unavailable, so independence across images is assumed), pooled control met its overall target but missed on average 31.8% and 36.4% of non-boundary errors. Regional control reduced these fractions to 19.3% and 20.9% and raised the recall of size-filtered false-negative components from 0.722 to 0.818 and from 0.611 to 0.763. The mean warned area grew by 1.6 and 4.9 percentage points, and its 95th percentile reached 23.5% and 38.5%. The effect held across three seeds and a second backbone, and area-matched heuristics did not reproduce it. On the external PH2^2 set, frozen thresholds exceeded both targets, whereas recalibration with 100 local images brought the mean over repeated splits below them. Regional calibration improves non-boundary error coverage at a measured increase in warned area.
Nov 5, 2026

An Anatomy-guided 3D Segmentation Pipeline for Prostate Surgical Phantoms from CT Scans

Full autonomy has been a long-term goal in robotic surgery and a near-to-medium-term goal for prostatectomy. Due to the relatively closed structure of the procedure, its standard-of-care robotic/laparoscopic solutions, and procedure economics, prostate procedures are an optimal early target for surgical automation. Prototyping and testing of possible solutions is done in constructed laboratory phantoms, either synthetic tissues or animal phantoms. To enable measurement of perceptual and robotic motion error, phantoms undergo volumetric imaging; these images are critical to both a potential deployed automatic system, used in planning motion and treatment (cutting, ablation, suturing, etc.), as well as post-hoc assessment of system performance. Rapid iteration on these phantom models yields small, inconsistent datasets, while the current workflow for human annotation is often anatomically unreliable and prohibitively time-consuming, rendering deep learning unsuitable at reasonable scales. To address these limitations, we present an automated 3D segmentation pipeline that uses classical medical image-processing techniques to encode the known anatomy of the phantoms as explicit geometric and intensity priors, which requires no training corpus and is transferred to each new phantom revision without re-annotation. Across 57 scans spanning multiple phantom revisions, our pipeline recovers the capsule interior at 0.83 median Dice on 11 contrast-suppressed scans and detects all 32 annotated focal lesions without false positives, completing a full scan in 2-8 minutes on commodity CPU hardware versus 1-2 hours by hand.
Nov 5, 2026

GMD-Mamba: Lightweight 3D Medical Image Segmentation Using a Grouped Multi-Directional Mamba

Mamba has the capability to capture global context in linear time for 3D medical image segmentation. However, existing methods employ Mamba with full-width directional scans at every resolution, keeping the model large (64-138M parameters and high FLOPs). We propose Grouped Multi-Directional (GMD) Mamba, a lightweight network based on the GMD scan that divides input channels CC into groups GG and flattens each group in different directions in one pass. This gives multi-directional context at O(C2/G)O(C^2/G) instead of O(K⋅C2)O(K \cdot C^2), where KK is the number of scan directions. Additionally, we employ Mamba only at the deepest encoder stages, resulting in 19.2M parameters. On BraTS2023, it achieves the best average Dice of 92.0% and the lowest HD95 of 2.7 at ∼\sim1/7 the parameters of SegMamba-V2. For model validation, we also ran experiments on the MSD Spleen dataset, achieving competitive performance. The implementation details and code are publicly available at https://github.com/2802990u/GMD-Mamba.
Nov 5, 2026

CMDiff: Left Atrial Scar Segmentation from 3D LGE MRI Using Conditional Mask Diffusion Model: A Feasibility Study

Late gadolinium enhancement (LGE) cardiac MRI enables non-invasive assessment of left atrial (LA) scar, an imaging marker associated with atrial fibrillation ablation outcome. However, automatic scar segmentation is hindered by low contrast, the thin atrial wall, scarce labels, and extreme class imbalance. Conditional diffusion offers iterative mask generation, but its suitability for sparse 3D LA scar segmentation remains unclear. To address this gap, we propose Conditional Mask Diffusion (CMDiff), which predicts clean masks using a dynamic-encoder-conditioned 3D sinusoidal UNet. We compared CMDiff with a deterministic baseline on identical cases in five-fold cross-validation of 60 scar-labelled public LASCARQS subjects, with 48 training and 12 held-out cases per fold. CMDiff achieved a scar DSC of 0.47 ±\pm 0.08, HD95 of 12.89 ±\pm 6.39 mm, and ASD of 1.91 ±\pm 0.96 mm, compared with deterministic baseline values of 0.51 ±\pm 0.08, 10.86 ±\pm 5.39 mm, and 1.58 ±\pm 1.03 mm, respectively. Under the same implementation, clean-mask prediction performed substantially better than the noise-prediction configuration evaluated in this study. Thus, CMDiff was technically feasible but did not improve segmentation performance: DSC was lower, and both HD95 and ASD were higher. Direct mask diffusion therefore provides an analytical alternative, but not a competitive performance advance for this task. The source code is publicly available at https://github.com/jizhang02/CMDiff.
Nov 5, 2026

TRiST: Topology-Reinforced Swin Transformer for Medical Image Analysis

Medical images contain topological patterns, such as connected components and loops, at scales ranging from small lesions to organ boundaries. Although hierarchical Vision Transformers have advanced medical image analysis, they do not explicitly incorporate topology throughout their multiscale representations. We propose Topology-Reinforced Swin Transformer (TRiST), a framework that integrates topological information into feature construction, refinement, and attention. First, a Hierarchical Multi-Scale Topology Representation algorithm computes 2D persistent homology (H0 and H1) independently at four native Swin stages, producing descriptors aligned with each stage's token grid rather than downsampling fine-scale topology. Second, a Band-Aware H0/H1 Residual Refinement module uses gated residual networks to process short-, medium-, and long-persistence information separately. Third, a Persistence-Band Progressive Attention Bias converts stage-specific descriptors into learned key-saliency scores that directly modify shifted-window attention logits. We instantiate TRiST as Topo-SwinV2-B for classification and Topo-Swin-UNet for segmentation, preserving the underlying Swin-based backbones. Experiments on five medical image datasets show consistent improvements over Swin-based baselines and competitive performance relative to existing topology-augmented methods.
Nov 4, 2026

LungMend: A Healthy-Only Latent Diffusion Shape Prior for Lung Mask Correction in Severe Tuberculosis CT

Lung segmentation models such as R231 are widely used, but they fail on severe tuberculosis (TB) CT: cavities and consolidations look like non-lung tissue and are left out of the mask. We present LungMend, a post-processing model that corrects such masks using only healthy anatomy. A latent diffusion model, trained on healthy lungs with synthetically corrupted masks, learns to recover the complete lung from the faulty mask and the bone anatomy, without any pathological data or CT intensities. LungMend recovers cavities and consolidations that R231 misses and improves accuracy on expert-annotated slices. Code: https://github.com/noureddinekhiati/LungMend
Nov 3, 2026

Anchored Slice Propagation with Boundary Transport for 3D CT Segmentation from Three Orthogonal Annotated Slices

Sli2Vol propagates a binary mask through affinities between adjacent slices, but an error can persist because each prediction becomes the input to the next step. Three orthogonal annotations reduce dependence on any one chain, yet they offer more than three starting masks: where a chain crosses another annotated plane, the correct label is already known. Those labels could correct drift during propagation and indicate how much to trust each chain at fusion. Between annotated planes, the information carried by the chain may matter as well. A binary mask records foreground membership but discards distance to the boundary, a cue that could help follow gradual shape changes between slices.We address these two sources of error with a fixed pretrained affinity backbone. We anchor each chain by correcting its prediction where it crosses another annotated plane, then use its agreement with those labels to weight fusion. We compare this anchored mask with two ways of transporting boundary geometry: a truncated signed-distance field (SDF) propagated by dense affinity averaging, and a contour whose vertices follow motion cues from the same affinity. The contour tracker starts from a hand-crafted rule and learns a motion correction from supervoxel pseudo-objects in 506 CT volumes, without manual organ labels. On 2,091 held-out structure instances from approximately 403 CT scans spanning 17 abdominal structures, anchoring raises mean Dice from 0.737 with orthogonal mask propagation to 0.769 and improves every structure. Beyond the anchored mask, learned contour tracking improves Dice by 5.7% for the esophagus and 5.9% for the postcava, while SDF transport improves right-adrenal Dice by 2.8%. The anchored methods have similar mean Dice (0.769--0.772); contour tracking performs worse on the kidneys, stomach, and hepatic vessel tree.
Nov 3, 2026

Lesion Overlap Ranks PET Segmentation Models but Does Not Certify Patient-Level Tumor Burden

Metabolic tumor volume (MTV) summarizes whole-body PET disease burden for prognostic stratification and treatment assessment. Automated MTV is useful only if its estimate is reliable for the individual patient, yet segmentation models are usually evaluated with overlap metrics such as Dice rather than burden error. We examined whether overlap metrics identify unreliable MTV estimates using 1,014 autoPET FDG PET/CT studies. We evaluated LesionTracer predictions held out from fine-tuning, compared five selected released models on 489 tumor-positive patients, and examined the findings in 597 PSMA studies. Across the five FDG models, ranking by higher mean Dice gave the same order as ranking by lower mean relative MTV error (ρ=−1.00ρ=-1.00, exact p=0.017p=0.017). At the patient level, however, out-of-fold Dice tracked relative MTV error strongly (ρ=−0.75ρ=-0.75), yet 82 of 489 patients (16.8%) fell on opposite sides of the Dice 0.80 and MTV-error 25% thresholds. Within the training-exposed released models, correlations ranged from −0.47-0.47 to −0.74-0.74 over narrower, high-Dice ranges. Out of fold, opposing false-positive and false-negative volumes cancelled about one third of spatial error in net MTV. In 236 of 489 patients, each of the five models missed at least one lesion, though not necessarily the same lesion. Thus, agreement in average model rankings did not establish the reliability of individual MTV estimates or reveal shared lesion misses. PET segmentation benchmarks should report patient-level MTV error and missed-lesion counts alongside Dice and other overlap metrics.
Nov 3, 2026

OpenBrain: An Auditable Generated-Label Release for Whole-Brain MRI Parcellation

Automatic tools can now generate whole-brain MRI parcellations at cohort scale, but generated-label releases often provide little evidence about which cases are reliable enough to reuse. We introduce OpenBrain, a confidence-aware release of 35,838 provenance-verified OpenNeuro T1w cases from 607 source datasets. OpenBrain is organized as an auditable case-record release rather than a directory of standalone segmentation files: each record links a primary parcellation, two committee parcellations, source/license provenance, raw QC-7 measurements, percentile risks, a combined risk score R, and a confidence tier. QC-7 is a reference-free reliability panel over label geometry, image-label consistency, and committee disagreement, so users can filter, weight, audit, or re-threshold generated labels without rerunning inference. We evaluate this released evidence under a frozen protocol. Across external cohorts, lower QC-7 risk corresponds to higher generated-label quality; in fixed-budget training, lower-risk selections improve paired macro Dice over random selection by +3.2 to +3.7 percentage points. OpenBrain also exposes raw axes, committee outputs, provenance, and datasheet documentation, so confidence claims remain inspectable after download. It does not turn generated labels into manual annotations or clinical-grade segmentations. Its contribution is a large open generated-parcellation substrate, a reusable case-level risk-evidence layer, and an external validation protocol for release-time QC. Dataset: https://huggingface.co/datasets/lanqz7766/OpenBrain. Code: https://github.com/lanqz7766/openbrain.
Nov 3, 2026

Quality-Governed Deep Learning Network for Brain Tumor MRI Segmentation

The segmentation of brain tumors from magnetic resonance imaging (MRI) is an essential step for computer-aided neuro-oncology, treatment planning and follow-up. While effective encoder-decoder representations are achieved by U-Net and Attention U-Net, the skip sections of the network can generate weak-contrast or noisy responses in the case of heterogeneous boundaries of the tumor. In this paper, we introduce a Quality-Governed Deep Learning Network (QGDL-Net) that can be used for binary tumor segmentation from FLAIR MRI slices. The proposed model is able to predict the slice quality based on contrast and SNR statistics and to fine-tune the encoder features prior to decoding by learnable quality gates. We used the 80:20 train-validation split for experiments with BraTS 2021. QGDL-Net achieved a Dice of 0.9747, IoU of 0.9506, precision of 0.9755, recall of 0.9739, F1 of 0.9747 and accuracy of 0.9982, outperforming U-Net and Attention U-Net. The EigenCAM maps and segmentation overlays provide better tumor localization and interpretable activation around the lesion regions.
Nov 3, 2026

Label-Preserving Fourier Domain Adaptation with Generative-AI and Real Style Donors for 3D Mitral Valve Segmentation

Accurate segmentation of the mitral valve from three-dimensional transesophageal echocardiography (3D TEE) is severely restricted by the scarcity of publicly available expert- annotated volumetric datasets. To address this critical limitation, we investigated Fourier Domain Adaptation (FDA), utilizing general-purpose generative-AI images (from platforms like Chat- GPT, Google Gemini, and Microsoft MAI) as annotation-free style donors for 3D mitral valve segmentation. We employed a DeepMitral residual U-Net model on the public MVSeg2023 dataset, comparing six conditions over three runs: real-only training, traditional augmentation, FDA with each generative source, and a non-AI FDA control using real-image style donors, plus an optimization-matched real-only control and a \b{eta} sensitivity analysis. Case-level paired testing showed that FDA with these generative sources led to significant reductions in boundary- and surface-related errors across all three donor conditions relative to the primary real-only baseline. However, the impact on the core segmentation metric, Generalized Dice Score (GDS), proved generator-dependent. ChatGPT-FDA showed a significant GDS advantage over the optimization-matched control but not over the primary baseline, and Gemini-FDA showed no significant GDS difference. Notably, only MAI-FDA provided a statistically robust and significant increase in GDS compared to the primary baseline. The \b{eta} sensitivity was not robust across training runs. These findings confirm that FDA remains an important augmentation mechanism. While generative-AI images offer a practical means of acquiring style diversity without new annotations, the non-AI control performed comparably to ChatGPT-FDA, so we do not conclude that this approach is superior to training with real-image donors.
Nov 3, 2026

ProGeo-RC: Prototype-guided Semantic Reliability and Geometric Error Calibration for Semi-supervised Cardiac Image Segmentation

Semi-supervised medical image segmentation aims to train reliable segmentation models using limited labeled data and abundant unlabeled data. However, existing methods typically rely on prediction confidence or model consistency to estimate pseudo-label reliability, but these criteria are insufficient to characterize both semantic reliability and geometric plausibility. To address this issue, we propose ProGeo-RC, a prototype-guided semantic reliability and geometric error calibration framework for semi-supervised medical image segmentation. ProGeo-RC consists of two key modules: Prototype-guided Semantic Reliability Estimation (PSRE) and Structured Semantic-Geometric Error Calibration (S-SGEC). PSRE uses probabilistic class prototypes to estimate the semantic reliability of unlabeled predictions and calibrate pixel-wise teacher pseudo labels, while S-SGEC introduces signed-distance-field-based geometric constraints to refine ambiguous boundaries and suppress spurious foreground responses outside target structures. Experiments on the ACDC and MVAA-CT datasets show that ProGeo-RC achieves better performance compared with representative semi-supervised segmentation methods. Under the 10% labeled setting on ACDC, ProGeo-RC improves DSC and Jaccard by 0.37% and 0.49% over the corresponding second-best results, while reducing 95HD and ASD by 0.61 and 0.21, respectively. These results indicate that joint semantic reliability estimation and geometric error calibration can provide more reliable pseudo supervision for semi-supervised medical image segmentation.
Nov 3, 2026

LINDA: Low Resource Foot Ulcer Segmentation using Local Similarity and Iterative Neural Dynamics

Foot ulcers are a leading cause of lower limb amputation, and the highest burden often falls on low and middle income regions where specialists and computing hardware are both scarce. Wound monitoring tools are most useful there when they are accurate yet small enough to run on ordinary devices, but accuracy usually comes from heavy networks. We present LINDA, a compact model that grounds segmentation in an explicit structural prior instead of raw intensity. A Local Self-Similarity (LSS) map, computed directly from the image and stable under local lighting changes, is fused into a ResNet-34 encoder, and a small Liquid Time-Constant module refines the boundary over four iterative steps. With every model trained under one protocol on the FUSeg 2021 dataset, LINDA obtains the best Dice (86.68%), IoU (79.67%), and boundary accuracy (HD95 6.37 pixels) in our comparison while using only 25.70M parameters, fewer than the U-Net and transformer baselines. As the LSS map is a fixed function of the input, it exposes the structural cues the model follows in a readable form. Together this makes LINDA an accurate, inspectable, and lightweight option for wound assessment in resource-constrained care.
Nov 3, 2026

Reliability-Role Collaborative Learning for Semi-Supervised Cardiac Image Segmentation

Semi-supervised cardiac image segmentation aims to exploit abundant unlabeled images together with limited annotations, but the reliability of pseudo-label supervision is highly uneven across spatial regions. In a dual-network setting, interior regions are usually more stable, whereas boundary regions, low-confidence areas, and disagreements between networks can introduce noisy supervision. However, existing methods typically impose uniform supervision on all unlabeled pixels, overlooking reliability differences and limiting discriminative learning in challenging areas. To address this issue, we propose R2CL (Reliability-Role Collaborative Learning), a framework for semi-supervised cardiac image segmentation. R2CL models confidence relationships between two networks to assign roles to unlabeled regions: mutually uncertain regions are used for entropy regularization, confidence-discrepant regions for directional knowledge transfer, and mutually confident regions as reliable supervision anchors. Reliability-Role Mixed Cross Learning (RR-MCL) implements these roles through region-mixed training, directional cross-network supervision, and entropy regularization over mutually uncertain regions. Reliability-Transition Prototype Contrastive Learning (RT-PCL) constructs query features from foreground-adjacent reliability-transition regions and learns network-specific class prototypes from mutually confident regions, improving feature discrimination around ambiguous boundaries. High-confidence Context Refinement (HCR) exploits reliable interior pixels and trusted dense blocks within mutually confident regions to complement stable contextual supervision. R2CL achieves stable improvements in region-overlap and boundary-related metrics across multiple datasets, with more evident advantages on the foreground-sparse MVAA-CT dataset.
Nov 2, 2026

BGD-SF PolySegNet: boundary-guided dynamic selective fusion network for robust polyp segmentation in colonoscopy images

Effective polyp segmentation in colonoscopy images is crucial for early detection of colorectal cancer, a leading cause of cancer-related death worldwide. While current deep learning models perform well on traditional Dice benchmarks, border segmentation remains difficult. Most methods use boundary information only as an additional loss signal during training, which prevents the network from explicitly learning border-guided feature selection or mask refinement. This paper introduces BGD-SF PolySegNet, a boundary-guided encoder-decoder architecture that controls three phases of the segmentation pipeline: dynamic multi-scale context aggregation, selective skip-feature fusion, and final mask refinement. The architecture comprises a pretrained EfficientNet-B4 backbone and three proposed modules: Boundary-Guided Dynamic Cascaded Multi-Scale Context Aggregation (BGD-CMSCA), Boundary-Guided Selective Attention Fusion (BG-SAGF), and a Multi-Level Boundary Guidance Head (MBGH). The model is trained on 3,535 annotated images from Kvasir-SEG, BKAI-IGH NeoPolyp-Small, and PolypGen, and evaluated on four held-out benchmark datasets. On the internal test set, BGD-SF achieves a Dice of 0.887, IoU of 0.839, mask-derived Boundary F1 of 0.531, HD95 of 30.32, and ASSD of 18.10, improving Boundary F1, HD95, and ASSD by 15.7%, 27.5%, and 34.6% over the strongest CNN baselines. External validation on CVC-ClinicDB, CVC-ColonDB, ETIS-Larib, and CVC-300 yielded Dice scores of 0.891, 0.776, 0.863, and 0.885, respectively. The model runs at 35 FPS with 22.51M parameters. Wilcoxon signed-rank tests confirm statistically significant mask-derived Boundary F1 improvements over six of seven ablation variants (p < 0.001; small-to-moderate effect sizes, r = 0.215-0.434), demonstrating that integrating boundary guidance as an active architectural component measurably advances polyp boundary delineation.
Nov 1, 2026

Peripheral prototypical contrastive loss for supervised medical image segmentation

Robust segmentation of biomedical images remains challenging primarily due to ill-defined object boundaries. Although several loss functions have recently been proposed to enhance object boundary recognition, concerns remain about the susceptibility to unstable annotations resulting from boundary ambiguities. Here, we introduce the Peripheral Prototypical Contrastive (PPC) loss, which leverages prototypical contrastive learning to improve boundary recognition and enable stable training even under noisy annotation conditions. The PPC loss utilizes prototype features obtained from local regions near object boundaries, focusing specifically on ambiguous areas that have been challenging for existing approaches. Extensive experiments across multiple datasets demonstrated that the PPC loss consistently improve segmentation performance even under conditions with noisy labels. A newly proposed strategy, which adaptively determines the local region for prototype calculation, enhanced robustness and outperformed existing methods. Our findings indicate the potential of the PPC loss in facilitating scalable and reliable medical image segmentation, including the development of foundation models with imperfect annotations.
Oct 31, 2026

Modeling Fat-shift for Improved Head Segmentation from MRI Scans using a Probabilistic Model

Personalized computational head models for biophysical simulations rely on accurate whole-head segmentations from T1-weighted (T1w) magnetic resonance imaging (MRI) scans. While T1w scans provide excellent contrast for intracranial anatomy, extracerebral tissues have partly almost no signal (compact bone) and also suffer from the so-called chemical shift artifact, which affects the fatty tissues in MRI and causes them to spatially shift in the frequency encoding direction of the scan. This artifact occurs primarily in two structures of the head: the spongy bone, a fatty compartment inside the compact bone, and the subcutaneous fat, located directly underneath the skin. The frequency-encoding direction is often set in the superior-inferior direction, causing the fatty tissues to shift down and, as a result, making the skull appear thinner than it actually is. Existing segmentation methods do not model this artifact, consequently leading to inaccurate labeling of the skull and scalp, which introduces a bias in biophysical simulations. The direction and magnitude of the fat-shift can be determined from the scan parameters, thus making it possible to explicitly model the shift and to recover the correct anatomy. This study introduces a probabilistic model that uses variational inference to segment head and brain structures from a T1w scan while accounting for the fat-shift artifact. The proposed Fat-shift-informed Label Optimization of the Whole head (FLOW) method reconstructs extracerebral anatomy more accurately than a fat-shift-agnostic segmentation approach while maintaining high segmentation accuracy in all other structures. FLOW-based fat-shift corrected segmentations significantly reduce bias in electric field simulations compared to a segmentation method that does not model the shift.
Oct 30, 2026

Taurus: LLM-in-the-Loop CT Annotation Matches Coding Agents at Half the Cost

Dense labels of the aorta in CT are slow to draw, and the public aortic CT datasets that could stand in for them each label different structures under their own conventions. Large language model (LLM) agents can now write code and read images. We asked whether such a model labels these scans better as a free-form agent that writes its own segmentation code, or inside a harness, where an automated pass labels the scan and the model reviews the result. We built a harness, Taurus, and compared it with free-form agents by blind label recovery: we withheld the human labels of six public datasets (939 volumes) and scored every approach against each dataset's own classes. In the first version of Taurus, the model's review raised the primary metric on only two of six datasets, by less than the noise between two reviews of the same case. A free-form agent running Claude Opus 5.5 scored higher on most datasets. Moving what the free-form agents did well into the automated pass then carried most of the gain on 38 held-out cases. The final version smooths the label surfaces with a fixed rule and checks for the large errors the automated pass tends to make, such as an aneurysm drawn to half its size. Each check that fires puts a multiple-choice question to the model, with candidate corrections drawn on the scan. It matched the surface smoothness of the human references, and in the primary metric we found no difference from the free-form Opus agent, at under half its cost, 1.22against1.22 against 2.71 per case. Most of what made Taurus competitive came from the harness and its automation rather than from the language model itself. Taurus shows that this kind of annotation can be automated, so that expert time can move from drawing labels to checking them.