Multi-scale Multi-site Renal Microvascular Structures Segmentation for Whole Slide Imaging in Renal Pathology

TL;DR

This paper introduces Omni-Seg, a deep learning network capable of multi-site, multi-scale segmentation of renal microvascular structures from whole slide images, even with partially labeled data, improving accuracy over existing methods.

Contribution

Omni-Seg is a novel single dynamic network that effectively utilizes multi-site, multi-scale training data with partial labels for renal microvascular segmentation.

Findings

Outperforms existing methods in DSC and IoU metrics.

Successfully segments microvascular structures across different magnifications.

Handles partially labeled training data effectively.

Abstract

Segmentation of microvascular structures, such as arterioles, venules, and capillaries, from human kidney whole slide images (WSI) has become a focal point in renal pathology. Current manual segmentation techniques are time-consuming and not feasible for large-scale digital pathology images. While deep learning-based methods offer a solution for automatic segmentation, most suffer from a limitation: they are designed for and restricted to training on single-site, single-scale data. In this paper, we present Omni-Seg, a novel single dynamic network method that capitalizes on multi-site, multi-scale training data. Unique to our approach, we utilize partially labeled images, where only one tissue type is labeled per training image, to segment microvascular structures. We train a singular deep network using images from two datasets, HuBMAP and NEPTUNE, across different magnifications (40x, 20x, 10x, and 5x). Experimental results indicate that Omni-Seg outperforms in terms of both the Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). Our proposed method provides renal pathologists with a powerful computational tool for the quantitative analysis of renal microvascular structures.