Improving lesion segmentation in medical images by global and regional feature compensation

• Dual-feature compensation framework to improve medical image segmentation of challenging lesions. • Addresses the loss of detailed global features caused by downsampling. • Uses SSL residual maps to provide additional pixel-level feature representations. • Applies patch-based cross-attention to integrate SSL residual maps, targeting likely lesion regions. 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 achieve suboptimal performance in complex lesion segmentation due to information loss during typical downsampling operations and 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 three publicly available medical image segmentation datasets, including brain stroke lesion, lung tumor 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.