Weakly Supervised Segmentation and Classification of Alpha-Synuclein Aggregates in Brightfield Midbrain Images

2025-11-20

AI Summary

This study addresses the challenge of automatically identifying α-synuclein (α-syn) aggregates—specifically Lewy bodies and neurites—in immunohistochemically stained whole-slide images (WSIs) of Parkinson’s disease tissue. We propose a weakly supervised joint framework wherein sparse point annotations drive semantic segmentation, followed by morphological classification of segmented regions using ResNet50. This approach effectively mitigates both staining heterogeneity and high annotation costs, achieving balanced accuracy of 80% in distinguishing the two key pathological structures. To our knowledge, this is the first method enabling large-scale spatial distribution modeling and quantitative assessment of α-syn aggregate heterogeneity across WSIs. Furthermore, it provides a scalable, reproducible computational platform for investigating spatial interactions between α-syn aggregates and glial cells—including microglia and astrocytes—thereby facilitating mechanistic studies of neuroinflammation in Parkinson’s disease.

Technology Category

• Machine Learning: Neuro-Symbolic Learning
• Computer Vision: Segmentation
• Multiagent Systems: Distributed Problem Solving

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Graph Algorithms and Modeling for the Web: Algorithms and analysis for heterogeneous, signed, attributed, multi-relational, temporal, higher-order, and annotated Web-related graphs
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Parkinson's disease (PD) is a neurodegenerative disorder associated with the accumulation of misfolded alpha-synuclein aggregates, forming Lewy bodies and neuritic shape used for pathology diagnostics. Automatic analysis of immunohistochemistry histopathological images with Deep Learning provides a promising tool for better understanding the spatial organization of these aggregates. In this study, we develop an automated image processing pipeline to segment and classify these aggregates in whole-slide images (WSIs) of midbrain tissue from PD and incidental Lewy Body Disease (iLBD) cases based on weakly supervised segmentation, robust to immunohistochemical labelling variability, with a ResNet50 classifier. Our approach allows to differentiate between major aggregate morphologies, including Lewy bodies and neurites with a balanced accuracy of $80%$. This framework paves the way for large-scale characterization of the spatial distribution and heterogeneity of alpha-synuclein aggregates in brightfield immunohistochemical tissue, and for investigating their poorly understood relationships with surrounding cells such as microglia and astrocytes.

Problem

• Segmenting and classifying alpha-synuclein aggregates in brightfield midbrain images
• Developing automated analysis for Parkinson's disease pathology using weakly supervised learning
• Characterizing spatial distribution of protein aggregates and their cellular relationships

Innovation

• Weakly supervised segmentation of alpha-synuclein aggregates
• ResNet50 classifier for morphology differentiation
• Automated pipeline robust to labeling variability