KPIs 2024 Challenge: Advancing Glomerular Segmentation from Patch- to Slide-Level

2025-02-11

AI Summary

Chronic kidney disease (CKD) lacks a standardized, whole-slide-level glomeruli segmentation benchmark for quantitative renal pathology analysis. Method: We introduce the first large-scale, expert-annotated dataset for glomeruli segmentation in PAS-stained whole-slide images (WSIs), comprising >60 WSIs and >10,000 precisely annotated glomeruli. We formalize two complementary tasks—patch-level segmentation and slide-level detection—and establish the first multi-model, multi-scale benchmark for CKD-oriented whole-slide analysis, enabling unified evaluation of both local recognition and global quantification performance. We propose a cross-granularity evaluation framework integrating Dice and F1-score, compatible with conventional segmentation, weakly supervised, and foundation model–based approaches. Results: The benchmark has attracted >20 participating teams; the top-performing method achieves a slide-level F1-score of 0.89. This work establishes a new standard for automated glomerular quantification, advancing CKD progression modeling and clinical diagnostic accuracy.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Evaluation and Analysis
• Constraint Satisfaction and Optimization: Other Foundations of Constraint Satisfaction

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Chronic kidney disease (CKD) is a major global health issue, affecting over 10% of the population and causing significant mortality. While kidney biopsy remains the gold standard for CKD diagnosis and treatment, the lack of comprehensive benchmarks for kidney pathology segmentation hinders progress in the field. To address this, we organized the Kidney Pathology Image Segmentation (KPIs) Challenge, introducing a dataset that incorporates preclinical rodent models of CKD with over 10,000 annotated glomeruli from 60+ Periodic Acid Schiff (PAS)-stained whole slide images. The challenge includes two tasks, patch-level segmentation and whole slide image segmentation and detection, evaluated using the Dice Similarity Coefficient (DSC) and F1-score. By encouraging innovative segmentation methods that adapt to diverse CKD models and tissue conditions, the KPIs Challenge aims to advance kidney pathology analysis, establish new benchmarks, and enable precise, large-scale quantification for disease research and diagnosis.

Problem

• Advance glomerular segmentation techniques
• Establish benchmarks for kidney pathology
• Enable precise CKD diagnosis and research

Innovation

• Glomerular segmentation challenge
• PAS-stained whole slide images
• Dice Similarity Coefficient evaluation