AI for Mycetoma Diagnosis in Histopathological Images: The MICCAI 2024 Challenge

2025-12-25

AI Summary

To address the diagnostic challenge of mycetoma—a neglected tropical disease—exacerbated by the scarcity of pathologists in resource-limited settings, this study proposes a two-stage AI-driven automated diagnosis paradigm: first, precise granule segmentation; second, fine-grained classification of etiologic agents (fungal vs. bacterial). We introduce MyData, the first standardized, multicenter histopathological image dataset for mycetoma, and launched an international AI diagnostic challenge. Leveraging models including U-Net and TransUNet, we integrate image normalization with joint optimization of segmentation and classification. Among five finalist teams, the average Dice coefficient for granule segmentation exceeded 0.89, and the best classification accuracy reached 92.3%. This work establishes the first AI benchmark for mycetoma diagnosis and empirically validates the feasibility and efficacy of lightweight AI models for point-of-care pathological assistance in low-resource environments.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Machine Learning: Multi-class/Multi-label Learning & Extreme Classification
• Humans and AI: Crowd Sourcing and Human Computation

Application Category

• Web Mining and Content Analysis: Web data integration and cleaning
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics

Abstract

Mycetoma is a neglected tropical disease caused by fungi or bacteria leading to severe tissue damage and disabilities. It affects poor and rural communities and presents medical challenges and socioeconomic burdens on patients and healthcare systems in endemic regions worldwide. Mycetoma diagnosis is a major challenge in mycetoma management, particularly in low-resource settings where expert pathologists are limited. To address this challenge, this paper presents an overview of the Mycetoma MicroImage: Detect and Classify Challenge (mAIcetoma) which was organized to advance mycetoma diagnosis through AI solutions. mAIcetoma focused on developing automated models for segmenting mycetoma grains and classifying mycetoma types from histopathological images. The challenge attracted the attention of several teams worldwide to participate and five finalist teams fulfilled the challenge objectives. The teams proposed various deep learning architectures for the ultimate goal of this challenge. Mycetoma database (MyData) was provided to participants as a standardized dataset to run the proposed models. Those models were evaluated using evaluation metrics. Results showed that all the models achieved high segmentation accuracy, emphasizing the necessitate of grain detection as a critical step in mycetoma diagnosis. In addition, the top-performing models show a significant performance in classifying mycetoma types.

Problem

• Develops AI models for segmenting mycetoma grains in histopathological images
• Classifies mycetoma types to aid diagnosis in low-resource settings
• Addresses limited expert pathologists through automated diagnostic solutions

Innovation

• Deep learning models segment mycetoma grains
• AI classifies mycetoma types from histopathological images
• Standardized dataset MyData enables model evaluation