anatomical prior integration

SAM faces critical challenges in medical image segmentation, including ill-defined boundaries, insufficient modeling of anatomical relationships, and lack of uncertainty quantification. To address these, we propose KG-SAM—a novel framework that first integrates an anatomical knowledge graph (KG) and an energy-driven conditional random field (CRF) into the SAM architecture. The KG encodes prior anatomical structural constraints, while the CRF jointly optimizes segmentation boundaries and models prediction uncertainty. An uncertainty-aware fusion module further enhances robustness. This design significantly improves segmentation consistency, interpretability, and clinical applicability. Extensive evaluation on multi-center datasets demonstrates state-of-the-art performance: Dice scores of 82.69% for prostate segmentation, and 78.05% and 79.68% for abdominal MRI and CT segmentation, respectively—each substantially surpassing existing methods.

This study addresses the challenge of accurately detecting small-scale anatomical structures—such as the inferior epigastric vessels—in laparoscopic inguinal hernia repair videos, where visual blur and intermittent visibility hinder reliable identification. To tackle this, the authors propose a Gaussian Spatial Prior (GSP) module that, for the first time, explicitly models spatial constraints among anatomical structures as learnable, compact Gaussian parameters. These priors are integrated into the self-attention mechanism of the DAB-DETR decoder and dynamically updated through iteratively refined reference points. Evaluated on a surgical video dataset of inguinal hernia repairs, the method significantly improves detection performance: compared to DAB-DETR and YOLOv26, it achieves relative gains of 33.5% and 53.9% in class-specific AP50, respectively, and enhances landmark detection accuracy by 6.0% (p=0.012), demonstrating the efficacy of anatomy-aware spatial priors for fine-grained object detection in surgical scenes.

This work proposes a covariate-conditioned probabilistic 3D shape model that integrates implicit neural representations with uncertainty-aware statistical shape analysis to address the dynamic modeling of anatomical shape heterogeneity during development and the quantification of its spatial uncertainty. The method introduces a closed-form Fisher information metric, enabling efficient analytical computation of local temporal uncertainties through automatic differentiation, thereby supporting spatially continuous and interpretable uncertainty modeling. Experiments on three synthetic datasets and one clinical dataset demonstrate that the proposed framework simultaneously achieves high-fidelity shape reconstruction and clinically interpretable uncertainty estimation.

Current medical image segmentation methods lack a unified geometric prior capable of generalizing across organs and imaging modalities, often failing to simultaneously preserve structural consistency and fine anatomical details. This work proposes HadBalance, the first plug-and-play framework that introduces a unified geometric prior grounded in the near-convex shape assumption. Leveraging the Hadwiger theorem, it formulates global geometric constraints based on area, perimeter, and Euler characteristic, and incorporates a conflict-aware objective balancing mechanism to adaptively fuse geometric priors with task-specific gradients. Evaluated across diverse organs and imaging modalities, HadBalance significantly improves segmentation accuracy while avoiding over-regularization, effectively enhancing both structural coherence and fidelity to anatomical detail.

Automatic pancreatic segmentation in abdominal CT suffers from low accuracy and high false-negative rates. Method: We propose a 3D full-resolution nnU-Net framework integrated with anatomical prior knowledge—specifically, multi-organ anatomical labels from TotalSegmentator, leveraging spatial constraints from neighboring organs as strong priors, and jointly trained end-to-end on the PANORAMA dataset. Contribution/Results: Our method significantly improves segmentation robustness: Dice score increases by 6.0% (p < 0.001), Hausdorff distance decreases by 36.5 mm (p < 0.001), and achieves 100% pancreatic detection with zero false negatives. This work empirically validates the critical value of anatomical priors for fine-grained single-organ segmentation, establishing a highly reliable foundation for radiomic biomarker extraction and pancreatic lesion identification.

This study addresses the challenges of intraluminal thrombus segmentation in abdominal aortic aneurysms, which include high thrombus heterogeneity, low contrast with surrounding tissues, and domain shift caused by variations in multicenter CTA protocols. The authors propose a patient-specific segmentation framework that integrates discriminative learning with anatomical priors. Specifically, they employ a local anatomical Gaussian mixture model for intensity normalization and introduce an uncertainty-gated anatomical attention module that adaptively modulates the influence of anatomical priors based on voxel-wise confidence. By explicitly decoupling anatomical priors from visual evidence and incorporating an uncertainty-aware mechanism, the method provides reliable guidance in ambiguous regions while suppressing unreliable priors, thereby enhancing both interpretability and generalization. Experiments demonstrate state-of-the-art performance on in-distribution test sets and significantly superior results on multicenter external CTA datasets compared to existing approaches.

This work addresses the inherent uncertainty in 3D scene reconstruction from limited observations—such as a single view, sparse pixels, or noisy images—by proposing a probabilistic framework that integrates Neural Radiance Fields (NeRF) with score-based diffusion models. The method represents the 3D scene as a stochastic latent variable, employs NeRF to model the likelihood of observations, and leverages a diffusion model to learn the prior distribution over the latent space. Crucially, it introduces, for the first time, a score-based diffusion mechanism to sample from the posterior distribution of the latent variables, enabling a unified treatment of uncertainty across diverse observation conditions. A two-stage training strategy jointly optimizes the reconstruction and prior networks, achieving high-fidelity 3D reconstructions under various settings—including single-view, multi-view, noisy images, sparse pixels, and depth inputs—while faithfully capturing task-specific uncertainties.

Standard CNNs for whole-heart multi-chamber CT segmentation often lack explicit anatomical constraints, compromising clinical reliability. This work proposes a lightweight approach that explicitly incorporates statistical shape priors through a shape-aware loss and a 3D U-Net variant guided by spatial label distribution heatmaps. The method is systematically evaluated on the MM-WHS CT and WHS++ datasets. Results reveal that, despite modern architectures implicitly learning substantial anatomical regularities from data, explicitly integrating handcrafted shape priors yields only marginal and inconsistent performance gains—and frequently leads to degradation. These findings underscore the limited added value of manually designed anatomical priors when deployed within highly data-driven deep learning models.

This work addresses the generalization bottleneck in cross-domain few-shot medical image segmentation, where entangled anatomical structures and domain-specific appearance hinder performance. To tackle this challenge, the authors propose GeoProto, a framework that integrates geometric-aware prototype enhancement (GAPE) and an ordinal shape branch (OSB) to encode the ordered geometric layout of organ topology as geometric offsets. These offsets are incorporated into local appearance prototypes to construct domain-invariant, structure-aware prototype representations. Requiring only a few annotated samples, GeoProto simultaneously generalizes to novel anatomical classes and unseen imaging domains. Extensive experiments across seven datasets under three evaluation settings demonstrate that GeoProto consistently outperforms existing methods, achieving state-of-the-art performance.

This work addresses the performance degradation in cross-modal few-shot medical image segmentation caused by texture discrepancies across imaging domains. To mitigate this issue, the authors propose a novel approach that explicitly decouples semantic structure from domain-specific appearance. By leveraging the consistent organ location and geometric shape across modalities—a structural prior modeled for the first time in this context—the method introduces three key components: Position Coordinate Embedding (PCE), Shape Prototype Modulation (SPM), and Hybrid Prototype Prediction (HPP). These modules collectively enhance generalization by effectively exploiting structural consistency. Experimental results on two public medical imaging datasets demonstrate that the proposed method significantly outperforms current state-of-the-art approaches, achieving substantial improvements in cross-domain segmentation performance.