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

TL;DR

FocusSDF introduces a boundary-aware loss function using signed distance functions to improve medical image segmentation accuracy, especially near boundaries, across various datasets and models.

Contribution

It proposes a novel boundary-aware loss function based on signed distance functions, enhancing boundary preservation in medical image segmentation.

Findings

FocusSDF outperforms existing distance-based loss functions.

It improves segmentation accuracy across multiple datasets and models.

The method is effective in diverse medical imaging modalities.

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.