Automated Histopathologic Assessment of Hirschsprung Disease Using a Multi-Stage Vision Transformer Framework

2025-11-25

AI Summary

This study addresses the subjectivity and inefficiency of manual interpretation of muscularis propria, myenteric plexus, and aganglionic regions in Hirschsprung disease (HSCR) histopathological diagnosis. We propose a multi-stage vision transformer (ViT-B/16)-based segmentation framework featuring an anatomy-guided three-level cascaded strategy: first localizing the muscularis propria, then focusing on the myenteric plexus region, and finally identifying ganglion cells. The method integrates resolution-adaptive patching, global-local feature fusion, and anatomy-constrained post-processing. Under five-fold cross-validation, the framework achieves a Dice score of 89.9% for muscularis propria segmentation and 100% myenteric plexus detection rate; at high confidence thresholds, ganglion cell recall and precision reach 89.1% and 67.0%, respectively. To our knowledge, this is the first end-to-end, anatomy-consistent automated quantitative analysis framework for key HSCR histopathological structures, significantly improving diagnostic reproducibility and enabling robust deployment in digital pathology.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Multi-instance/Multi-view Learning
• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Search and Retrieval-Augmented AI: Web query analysis, representation and understanding
• Security and Privacy: Data transparency and provenance

Abstract

Hirschsprung Disease is characterized by the absence of ganglion cells in the myenteric plexus. Therefore, their correct identification is crucial for diagnosing Hirschsprung disease. We introduce a three-stage segmentation framework based on a Vision Transformer (ViT-B/16) that mimics the pathologist's diagnostic approach. The framework sequentially segments the muscularis propria, delineates the myenteric plexus, and identifies ganglion cells within anatomically valid regions. 30 whole-slide images of colon tissue were used, each containing expert manual annotations of muscularis, plexus, and ganglion cells at varying levels of certainty. A 5-fold cross-validation scheme was applied to each stage, along with resolution-specific tiling strategies and tailored postprocessing to ensure anatomical consistency. The proposed method achieved a Dice coefficient of 89.9% and a Plexus Inclusion Rate of 100% for muscularis segmentation. Plexus segmentation reached a recall of 94.8%, a precision of 84.2% and a Ganglia Inclusion Rate of 99.7%. For high-certainty ganglion cells, the model achieved 62.1% precision and 89.1% recall, while joint certainty scores yielded 67.0% precision. These results indicate that ViT-based models are effective at leveraging global tissue context and capturing cellular morphology at small scales, even within complex histological tissue structures. This multi-stage methodology has great potential to support digital pathology workflows by reducing inter-observer variability and assisting in the evaluation of Hirschsprung disease. The clinical impact will be evaluated in future work with larger multi-center datasets and additional expert annotations.

Problem

• Automating identification of ganglion cells absence for Hirschsprung disease diagnosis
• Segmenting muscularis propria and myenteric plexus in colon tissue histology
• Reducing inter-observer variability in digital pathology workflows

Innovation

• Multi-stage Vision Transformer framework for histopathology
• Sequential segmentation of muscularis, plexus, ganglion cells
• Anatomical consistency through resolution-specific tiling strategies