LocBAM: Advancing 3D Patch-Based Image Segmentation by Integrating Location Contex
This addresses segmentation accuracy issues in medical imaging for researchers and practitioners, but it is incremental as it builds on existing patch-based methods by adding location context.
The paper tackled the problem of patch-based 3D medical image segmentation neglecting location context, which limits performance, and proposed LocBAM, an attention mechanism that improves segmentation by explicitly processing spatial information, achieving consistent gains over methods like CoordConv on datasets such as BTCV, AMOS22, and KiTS23.
Patch-based methods are widely used in 3D medical image segmentation to address memory constraints in processing high-resolution volumetric data. However, these approaches often neglect the patch's location within the global volume, which can limit segmentation performance when anatomical context is important. In this paper, we investigate the role of location context in patch-based 3D segmentation and propose a novel attention mechanism, LocBAM, that explicitly processes spatial information. Experiments on BTCV, AMOS22, and KiTS23 demonstrate that incorporating location context stabilizes training and improves segmentation performance, particularly under low patch-to-volume coverage where global context is missing. Furthermore, LocBAM consistently outperforms classical coordinate encoding via CoordConv. Code is publicly available at https://github.com/compai-lab/2026-ISBI-hooft