CovHuSeg: An Enhanced Approach for Kidney Pathology Segmentation

TL;DR

The paper tackles the challenge of kidney glomeruli segmentation by introducing CovHuSeg, a convex hull-based post-processing method that enforces convex, hole-free masks on baseline segmentation outputs. By transforming arbitrary predicted contours into convex hulls and filling the resulting shapes, CovHuSeg injects a geometric prior that better matches the ball-shaped morphology of glomeruli. Through experiments on the KPI Kidney Pathology dataset across multiple architectures (UNet, UNet++, UNet3+, TransUNet) and under data-scarce and noisy conditions, CovHuSeg yields consistent gains in Dice scores, with the largest improvements observed for weaker models and in low-data or noisy scenarios. The work suggests CovHuSeg as a practical, data-efficient enhancement for biomedical segmentation and points to future directions, such as integrating convexity constraints into training and combining thresholding with convex-hull post-processing to further improve convex masks.

Abstract

Segmentation has long been essential in computer vision due to its numerous real-world applications. However, most traditional deep learning and machine learning models need help to capture geometric features such as size and convexity of the segmentation targets, resulting in suboptimal outcomes. To resolve this problem, we propose using a CovHuSeg algorithm to solve the problem of kidney glomeruli segmentation. This simple post-processing method is specified to adapt to the segmentation of ball-shaped anomalies, including the glomerulus. Unlike other post-processing methods, the CovHuSeg algorithm assures that the outcome mask does not have holes in it or comes in unusual shapes that are impossible to be the shape of a glomerulus. We illustrate the effectiveness of our method by experimenting with multiple deep-learning models in the context of segmentation on kidney pathology images. The results show that all models have increased accuracy when using the CovHuSeg algorithm.

Figures (4)

• Figure 1: The proposed CovHuSeg algorithm for the kidney glomeruli segmentation.
• Figure 2: Segmentation Task
• Figure 3: An example of using the CovHuSeg algorithm for the problem of kidney glomeruli segmentation.
• Figure 4: Examples of Dataset