Improving Lesion Segmentation in Medical Images by Global and Regional Feature Compensation

TL;DR

This paper introduces a novel segmentation framework that enhances lesion detection in medical images by preserving global details and utilizing self-supervised residual maps for precise localization, outperforming existing methods.

Contribution

The paper proposes the GRCSF framework with GCU and RCU units, integrating self-supervised residual maps and patch-based attention to improve lesion segmentation accuracy.

Findings

Outperforms state-of-the-art methods on multiple datasets

Effectively captures fine-grained global and regional features

Demonstrates robustness across diverse lesion types

Abstract

Automated lesion segmentation of medical images has made tremendous improvements in recent years due to deep learning advancements. However, accurately capturing fine-grained global and regional feature representations remains a challenge. Many existing methods obtain suboptimal performance on complex lesion segmentation due to information loss during typical downsampling operations and the insufficient capture of either regional or global features. To address these issues, we propose the Global and Regional Compensation Segmentation Framework (GRCSF), which introduces two key innovations: the Global Compensation Unit (GCU) and the Region Compensation Unit (RCU). The proposed GCU addresses resolution loss in the U-shaped backbone by preserving global contextual features and fine-grained details during multiscale downsampling. Meanwhile, the RCU introduces a self-supervised learning (SSL) residual map generated by Masked Autoencoders (MAE), obtained as pixel-wise differences between reconstructed and original images, to highlight regions with potential lesions. These SSL residual maps guide precise lesion localization and segmentation through a patch-based cross-attention mechanism that integrates regional spatial and pixel-level features. Additionally, the RCU incorporates patch-level importance scoring to enhance feature fusion by leveraging global spatial information from the backbone. Experiments on two publicly available medical image segmentation datasets, including brain stroke lesion and coronary artery calcification datasets, demonstrate that our GRCSF outperforms state-of-the-art methods, confirming its effectiveness across diverse lesion types and its potential as a generalizable lesion segmentation solution.