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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Shafique, Muzammal, Rahim, Nasir, Ahmad, Jamil, Siadat, Mohammad, Malik, Khalid, Malik, Ghaus
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917081090359296
author Shafique, Muzammal
Rahim, Nasir
Ahmad, Jamil
Siadat, Mohammad
Malik, Khalid
Malik, Ghaus
author_facet Shafique, Muzammal
Rahim, Nasir
Ahmad, Jamil
Siadat, Mohammad
Malik, Khalid
Malik, Ghaus
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2511_11864
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FocusSDF: Boundary-Aware Learning for Medical Image Segmentation via Signed Distance Supervision
Shafique, Muzammal
Rahim, Nasir
Ahmad, Jamil
Siadat, Mohammad
Malik, Khalid
Malik, Ghaus
Computer Vision and Pattern Recognition
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.
title FocusSDF: Boundary-Aware Learning for Medical Image Segmentation via Signed Distance Supervision
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2511.11864