FocusSDF: Boundary-Aware Learning for Medical Image Segmentation via Signed Distance Supervision

• URL: http://arxiv.org/abs/2511.11864v1
• Date: Fri, 14 Nov 2025 20:49:44 GMT
• Title: FocusSDF: Boundary-Aware Learning for Medical Image Segmentation via Signed Distance Supervision
• Authors: Muzammal Shafique, Nasir Rahim, Jamil Ahmad, Mohammad Siadat, Khalid Malik, Ghaus Malik,
• Abstract summary: We introduce FocusSDF, a novel loss function based on the signed distance functions (SDFs)<n>We perform evaluations against five state-of-the-art medical image segmentation models, including the foundation model MedSAM.<n>The experimental results consistently demonstrate the superior performance of FocusSDF over existing distance transform based loss functions.
• Score: 1.5290834004335336
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Segmentation of medical images constitutes an essential component of medical image analysis, providing the foundation for precise diagnosis and efficient therapeutic interventions in clinical practices. Despite substantial progress, most segmentation models do not explicitly encode boundary information; as a result, making boundary preservation a persistent challenge in medical image segmentation. To address this challenge, we introduce FocusSDF, a novel loss function based on the signed distance functions (SDFs), which redirects the network to concentrate on boundary regions by adaptively assigning higher weights to pixels closer to the lesion or organ boundary, effectively making it boundary aware. To rigorously validate FocusSDF, we perform extensive evaluations against five state-of-the-art medical image segmentation models, including the foundation model MedSAM, using four distance-based loss functions across diverse datasets covering cerebral aneurysm, stroke, liver, and breast tumor segmentation tasks spanning multiple imaging modalities. The experimental results consistently demonstrate the superior performance of FocusSDF over existing distance transform based loss functions.

Related papers

• Sim4Seg: Boosting Multimodal Multi-disease Medical Diagnosis Segmentation with Region-Aware Vision-Language Similarity Masks [54.00822479127598]
  We introduce a medical vision-language task named Medical Diagnosis (MDS)<n>MDS aims to understand clinical queries for medical images and generate the corresponding segmentation masks as well as diagnostic results.<n>We propose Sim4Seg, a novel framework that improves the performance of diagnosis segmentation.
  arXiv  Detail & Related papers  (2025-11-10T03:22:42Z)
• Multimodal Causal-Driven Representation Learning for Generalizable Medical Image Segmentation [56.52520416420957]
  We propose Multimodal Causal-Driven Representation Learning (MCDRL) to tackle domain generalization in medical image segmentation.<n>MCDRL consistently outperforms competing methods, yielding superior segmentation accuracy and exhibiting robust generalizability.
  arXiv  Detail & Related papers  (2025-08-07T03:41:41Z)
• MedSAM-CA: A CNN-Augmented ViT with Attention-Enhanced Multi-Scale Fusion for Medical Image Segmentation [10.36607107686106]
  We propose MedSAM-CA, an architecture-level fine-tuning approach that mitigates reliance on extensive manual annotations.<n>On dermoscopy dataset, MedSAM-CA achieves 94.43% Dice with only 2% of full training data, reaching 97.25% of full-data training performance.
  arXiv  Detail & Related papers  (2025-06-30T10:24:29Z)
• MAMBO-NET: Multi-Causal Aware Modeling Backdoor-Intervention Optimization for Medical Image Segmentation Network [51.68708264694361]
  Confusion factors can affect medical images, such as complex anatomical variations and imaging modality limitations.<n>We propose a multi-causal aware modeling backdoor-intervention optimization network for medical image segmentation.<n>Our method significantly reduces the influence of confusion factors, leading to enhanced segmentation accuracy.
  arXiv  Detail & Related papers  (2025-05-28T01:40:10Z)
• Enhancing Medical Image Segmentation with Deep Learning and Diffusion Models [7.53596352508181]
  Medical image segmentation is crucial for accurate clinical diagnoses.<n>It faces challenges such as low contrast between lesions and normal tissues, unclear boundaries, and high variability across patients.<n>Deep learning has improved segmentation accuracy and efficiency, but it still relies heavily on expert annotations.<n>This article discusses the importance of medical image segmentation, the limitations of current deep learning approaches, and the potential of diffusion models to address these challenges.
  arXiv  Detail & Related papers  (2024-11-21T17:49:15Z)
• FESS Loss: Feature-Enhanced Spatial Segmentation Loss for Optimizing Medical Image Analysis [0.0]
  We propose Feature-Enhanced Spatial Loss (FESS Loss) to overcome the challenge of balancing spatial precision and comprehensive feature representation. FESS Loss integrates the benefits of contrastive learning with the spatial accuracy inherent in the Dice loss. The objective is to augment both spatial precision and feature-based representation in the segmentation of medical images.
  arXiv  Detail & Related papers  (2024-02-13T16:36:21Z)
• Reliable Joint Segmentation of Retinal Edema Lesions in OCT Images [55.83984261827332]
  In this paper, we propose a novel reliable multi-scale wavelet-enhanced transformer network. We develop a novel segmentation backbone that integrates a wavelet-enhanced feature extractor network and a multi-scale transformer module. Our proposed method achieves better segmentation accuracy with a high degree of reliability as compared to other state-of-the-art segmentation approaches.
  arXiv  Detail & Related papers  (2022-12-01T07:32:56Z)
• JOINED : Prior Guided Multi-task Learning for Joint Optic Disc/Cup Segmentation and Fovea Detection [1.2250035750661867]
  We present a novel method, named JOINED, for prior guided multi-task learning for joint OD/OC segmentation and fovea detection. Our proposed JOINED pipeline consists of a coarse stage and a fine stage. Experimental results reveal that our proposed JOINED outperforms existing state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-03-01T13:47:48Z)
• Global Guidance Network for Breast Lesion Segmentation in Ultrasound Images [84.03487786163781]
  We develop a deep convolutional neural network equipped with a global guidance block (GGB) and breast lesion boundary detection modules. Our network outperforms other medical image segmentation methods and the recent semantic segmentation methods on breast ultrasound lesion segmentation.
  arXiv  Detail & Related papers  (2021-04-05T13:15:22Z)
• Few-shot Medical Image Segmentation using a Global Correlation Network with Discriminative Embedding [60.89561661441736]
  We propose a novel method for few-shot medical image segmentation. We construct our few-shot image segmentor using a deep convolutional network trained episodically. We enhance discriminability of deep embedding to encourage clustering of the feature domains of the same class.
  arXiv  Detail & Related papers  (2020-12-10T04:01:07Z)
• Enhancing Foreground Boundaries for Medical Image Segmentation [13.954358685870886]
  We propose a boundary enhancement loss to enforce additional constraints on optimizing machine learning models. Our experimental results validate that our loss function are better than, or at least comparable to, other state-of-the-art loss functions in terms of segmentation accuracy.
  arXiv  Detail & Related papers  (2020-05-29T00:50:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.