Deep Learning Based Segmentation of Blood Vessels from H&E Stained Oesophageal Adenocarcinoma Whole-Slide Images

2025-01-21

AI Summary

To address the challenges of strong morphological heterogeneity of blood vessels in esophageal adenocarcinoma (EAC) H&E whole-slide images, labor-intensive pixel-level annotation, and model overfitting under limited training samples, this work proposes a guidance-map-enhanced vascular segmentation framework. We introduce a novel self-generated vascular response guidance map construction strategy, integrated with multi-scale feature distillation and embedded within mainstream segmentation architectures (e.g., U-Net). The method operates under weak supervision—requiring no pixel-level annotations—thereby significantly improving segmentation robustness and accuracy. Quantitatively, it achieves an absolute Dice coefficient improvement of over 8% compared to baseline methods. Comprehensive generalization evaluation across multiple tissue types further validates its cross-domain applicability. This work establishes a new paradigm for automated analysis of the vascular microenvironment in computational pathology, offering high segmentation accuracy with minimal annotation dependency.

Technology Category

• Computer Vision: Segmentation
• Machine Learning: Calibration & Uncertainty Quantification
• Search and Optimization: Mixed Discrete/Continuous Search

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Blood vessels (BVs) play a critical role in the Tumor Micro-Environment (TME), potentially influencing cancer progression and treatment response. However, manually quantifying BVs in Hematoxylin and Eosin (H&E) stained images is challenging and labor-intensive due to their heterogeneous appearances. We propose a novel approach of constructing guiding maps to improve the performance of state-of-the-art segmentation models for BV segmentation, the guiding maps encourage the models to learn representative features of BVs. This is particularly beneficial for computational pathology, where labeled training data is often limited and large models are prone to overfitting. We have quantitative and qualitative results to demonstrate the efficacy of our approach in improving segmentation accuracy. In future, we plan to validate this method to segment BVs across various tissue types and investigate the role of cellular structures in relation to BVs in the TME.

Problem

• Vessel Segmentation
• Esophageal Cancer
• Image Analysis

Innovation

• Computer-assisted method
• Vessel identification
• Esophageal cancer imaging