LocBAM: Advancing 3D Patch-Based Image Segmentation by Integrating Location Contex

TL;DR

This paper introduces LocBAM, an attention mechanism that incorporates spatial location context into patch-based 3D medical image segmentation, leading to improved accuracy and training stability especially with limited global context.

Contribution

The paper proposes LocBAM, a novel attention mechanism that explicitly integrates spatial location information into patch-based 3D segmentation models, enhancing performance over existing coordinate encoding methods.

Findings

LocBAM improves segmentation accuracy across multiple datasets.

Incorporating location context stabilizes training in patch-based segmentation.

LocBAM outperforms classical coordinate encoding methods.

Abstract

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