A deep learning framework for glomeruli segmentation with boundary attention

TL;DR

This paper introduces a boundary-aware deep learning model for precise glomeruli segmentation in kidney tissue, enhancing diagnostic accuracy by better distinguishing adjacent structures.

Contribution

It presents a novel U-Net-based architecture with a boundary attention decoder, leveraging pathology foundation models for improved instance segmentation.

Findings

Outperforms state-of-the-art methods in Dice score

Achieves higher Intersection over Union

Demonstrates superior delineation of adjacent glomeruli

Abstract

Accurate detection and segmentation of glomeruli in kidney tissue are essential for diagnostic applications. Traditional deep learning methods primarily rely on semantic segmentation, which often fails to precisely delineate adjacent glomeruli. To address this challenge, we propose a novel glomerulus detection and segmentation model that emphasises boundary separation. Leveraging pathology foundation models, the proposed U-Net-based architecture incorporates a specialised attention decoder designed to highlight critical regions and improve instancelevel segmentation. Experimental evaluations demonstrate that our approach surpasses state-of-the-art methods in both Dice score and Intersection over Union, indicating superior performance in glomerular delineation.