Jul 2026· IEEE Transactions on Image Processing· Vol 35, pp. 7277-7292· 0 citations· 58 references
MedicineComputer Science
Abstract
Accurate boundary segmentation is critical for high-stakes applications such as disease diagnosis, yet remains challenging due to complex topology, boundary ambiguity, and annotation uncertainty. Diffusion Probabilistic Models (DPMs) generate multiple masks with inherent uncertainty, enhancing boundary delineation compared to deterministic models. However, most existing DPM based segmentation approaches learn discrete binary masks, conflicting with the continuous diffusion process and leading to hard-to-learn degradation during noise addition. Moreover, the prevailing approach of averaging stochastic predictions and applying a fixed threshold disregards structural consistency, often leading to imprecise boundaries, isolated artifacts, and holes. To address these challenges, we propose the <inline-formula> <tex-math notation="LaTeX">$L$ </tex-math></inline-formula>evel <inline-formula> <tex-math notation="LaTeX">$S$ </tex-math></inline-formula>et <inline-formula> <tex-math notation="LaTeX">$R$ </tex-math></inline-formula>epresentation <inline-formula> <tex-math notation="LaTeX">$D$ </tex-math></inline-formula>iffusion model (LSR-Diff), which incorporates a diffusion model with a hybrid mask representation to better capture boundary information, and a novel strategy <inline-formula> <tex-math notation="LaTeX">$E$ </tex-math></inline-formula>nsemble <inline-formula> <tex-math notation="LaTeX">$A$ </tex-math></inline-formula>ggregation via Level <inline-formula> <tex-math notation="LaTeX">$S$ </tex-math></inline-formula>et <inline-formula> <tex-math notation="LaTeX">$E$ </tex-math></inline-formula>volution (EASE) to merge prediction candidates while respecting structural information. The hybrid representation takes advantage of both discrete binary masks and continuous implicit masks, with an intermediate representation to ensure a smooth transition. The EASE module guided by ambiguity estimation and anatomical structure then refines boundary topology, preventing arbitrary mask assembly during the aggregation of stochastic predictions. We conduct extensive experiments across various clinical applications including multiple modalities and tissues, showing that LSR-Diff achieves competitive overall performance and improved edge quality and topology accuracy on the tested tasks.
Automatic medical image segmentation, as a prerequisite for clinical quantitative analysis, forms the basis of computer-aided diagnosis. However, blurry object boundaries caused by factors such as imaging quality and inherent physiological properties of tissues or lesions are the main causes of imprecise segmentation. This aligns with the common understanding that high uncertainty and misclassification tend to occur at boundaries in segmentation. To address the challenge, we investigate this phenomenon and explore the connection between uncertainty and tissue boundaries by analysing various tissues. Then an Evidential Uncertainty-Guided Boundary (EUGB) loss is further proposed to demonstrate that uncertainty information can indeed facilitate combating boundary segmentation errors. The proposed EUGB loss not only emphasizes challenging pixels along blurry boundaries using evidential uncertainty, but also introduces a regularization term that constrains uncertainty learning by penalizing incorrect predictions and reinforcing correct ones. The effectiveness of the proposed EUGB loss is verified in the public LIDC-IDRI, ISIC 2018, and OCTA-500 datasets with two classic medical image segmentation networks (U-Net and TransU-Net). Experimental results demonstrate that the proposed loss outperforms seven other segmentation loss functions in terms of boundary segmentation, while maintaining competitive region-level segmentation accuracy. Beyond introducing a new loss function, this paper provides empirical insights for selecting appropriate loss functions across different application scenarios. We systematically analyze the strengths and limitations of existing losses from multiple perspectives, including reliability and dataset characteristics. This analysis offers practical insights that enable researchers and practitioners to optimize segmentation performance based on specific data attributes.
Na Zeng, Qiao Lin, Xingyue Wang et al.· IEEE Transactions on Medical...· 0 citations
Acquiring pixel-level annotations for medical image segmentation is a severe bottleneck. Traditional U-Net architectures, while effective, learn local texture patterns and lack awareness of global anatomical structures, leading to boundary delineation failures in low-data regimes. This research paper proposes utilizing unsupervised Denoising Diffusion Probabilistic Models (DDPMs) to extract anatomical features. We train a DDPM on 21 unlabeled abdominal CT scans to learn structural representations, transferring the encoder weights to a downstream segmentation task evaluated on the BTCV multi-organ dataset. Diffusion pretraining significantly improved liver segmentation: Dice increased from $0.75\pm0.36$ to $0.93\pm0.16$ ($p<5.33\times10^{-26}$, 0.529 Cohen's d), Average Surface Distance (ASD) decreased by 66%, and 95th-percentile Hausdorff Distance (HD95) reduced by 45%. For kidney segmentation, Dice improved from $0.90\pm0.19$ to $0.95\pm0.10$ ($p<4.01\times10^{-11}$). Multi-organ pooled performance showed a 68% variance reduction and a 74% improvement in boundary precision (Dice $0.95\pm0.07$). Crucially, frozen encoder models retained>80% of fine-tuned performance without exposure to segmentation labels, proving the existence of learned anatomical priors. In low-data scenarios, diffusion-pretrained models maintained robust performance with only 50% (Dice: 0.92 liver, 0.94 kidney), 25%, and even 10% (Dice: 0.89 liver, 0.71 kidney) of labeled data. Using unlabeled images for diffusion-based pretraining successfully embeds robust anatomical features prior to human supervision, transforming U-Nets into anatomy-aware systems.
G. Akshat, D. Gupta, Shaleen Bhatnagar et al.· 0 citations
Medical image segmentation plays a critical role in computer-aided diagnosis by enabling precise delineation of abnormalities in medical images. Accurate segmentation of these images is essential for early diagnosis and treatment planning. However, conventional models such as U-Net face challenges including boundary uncertainty, variations in image quality and limited generalization across datasets.
This study presents MRD-UNet, a U-Net based segmentation framework built on a channel-disjoint multi-path dilated fusion (MDF) block deployed uniformly across all encoder and decoder stages, a residual formulation within each MDF block that stabilizes gradient flow without introducing pooling branches, and a task-driven distribution of three functionally distinct attention modules. We evaluate the proposed model through extensive experiments on the CVC-ClinicDB dataset comprising 612 endoscopic images and the ISIC-2018 dataset containing 2,594 dermoscopic images. During data augmentation, we apply geometric transformations, elastic deformations, and brightness adjustments; training is performed using a composite loss that combines Dice loss and binary cross-entropy.
The proposed method achieves a DSC of 0.9140 on CVC-ClinicDB and 0.9106 on ISIC-2018, yielding an improvement of approximately 2–3% over the baseline U-Net architecture. Ablation studies confirm that the channel-disjoint MDF design reduces the number of parameters relative to the baseline while improving sensitivity to small and low-contrast lesions, and that the targeted attention layout enhances boundary delineation.
MRD-UNet provides a practical balance between segmentation accuracy and computational efficiency. It outperforms baseline CNNs and performs comparably to heavier transformer-based models while using significantly fewer parameters. Cross-dataset evaluations demonstrate its ability to generalize within the same imaging modality. Notably, the lightweight MRD-UNet-S variant maintains competitive accuracy, showing the architecture’s suitability for resource-constrained medical image segmentation tasks.
Not applicable.
Musa Doğan, I. Ozkan· BMC Medical Imaging· 0 citations
This paper proposes a novel framework that effectively leverages unlabeled data to improve segmentation performance in cardiac structures and applies a novel consistency constraint by a dual fine-grained boundary loss that provide global characteristics-based guidance from the transition of the boundary region and an edge-aware uncertainty loss.
Waqas Anwaar, Van Manh, Wufeng Xue et al.· Interdisciplinary Sciences C...· 0 citations
A comprehensive survey of UQ techniques in medical image segmentation is presented, categorizing existing approaches into Bayesian methods, deep ensembles, deterministic methods, test-time data augmentation, and hybrid models, while treating foundation-model-based UQ as a separate cross-cutting category.
Seyed Sina Ziaee, K. Ovens· Journal of Imaging· 0 citations
Accurate medical image segmentation remains challenging due to complex anatomical structures and ambiguous boundaries. To address the loss of structural cues in existing methods, we propose ContourFD-Net, a gradient-guided attention network. Unlike existing contour-aware networks that rely on auxiliary supervision, ContourFD-Net introduces an explicit structural prior via fixed finite-difference operators and couples gradient modeling with attention-based feature refinement. This approach preserves fine details through a dual-path architecture and decoupled spatial–channel attention. Extensive experiments on four benchmark datasets demonstrate the effectiveness and robustness of the proposed method. On the DSB 2018 dataset, ContourFD-Net achieves a Dice coefficient of 91.67%, demonstrating superior performance compared with representative state-of-the-art methods. Moreover, the framework requires only 6.40 M parameters and 3.39 GFLOPs, demonstrating a favorable accuracy–efficiency tradeoff. On the NVIDIA Jetson Orin NX platform, ContourFD-Net achieves an average inference latency of 16.97 ms and a throughput of 59.05 queries per second (QPS) with only 49-MiB memory consumption, validating its efficiency for real-time deployment on resource-constrained edge devices. The source code and model weights are available at https://github.com/ZBKim/ContourFD-Net
Zhengbei Jin, Jinghui Lu, Jindong Li et al.· IEEE Internet of Things Jour...· 0 citations