A General Pipeline for Glomerulus Whole-Slide Image Segmentation
This work addresses kidney disease diagnosis by enhancing glomerulus segmentation in medical images, representing an incremental improvement with practical applications in pathology.
The authors tackled the problem of glomerulus segmentation in whole-slide kidney images by proposing a general pipeline that improves both patch-level and WSI-level segmentation through stitching overlapping patches, achieving superior results over previous state-of-the-art methods across two large datasets with over 30K annotations.
Whole-slide images (WSI) glomerulus segmentation is essential for accurately diagnosing kidney diseases. In this work, we propose a general and practical pipeline for glomerulus segmentation that effectively enhances both patch-level and WSI-level segmentation tasks. Our approach leverages stitching on overlapping patches, increasing the detection coverage, especially when glomeruli are located near patch image borders. In addition, we conduct comprehensive evaluations from different segmentation models across two large and diverse datasets with over 30K glomerulus annotations. Experimental results demonstrate that models using our pipeline outperform the previous state-of-the-art method, achieving superior results across both datasets and setting a new benchmark for glomerulus segmentation in WSIs. The code and pre-trained models are available at https://github.com/huuquan1994/wsi_glomerulus_seg.