Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

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

Jiaqi Lv, Stefan S Antonowicz, Shan E Ahmed Raza

TL;DR

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.

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.

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

TL;DR

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.

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.
Paper Structure (12 sections, 4 figures, 3 tables)

This paper contains 12 sections, 4 figures, 3 tables.

Table of Contents

  1. Introduction
  2. Method
  3. The overall framework
  4. Guiding map algorithm
  5. Experiments
  6. Dataset and metrics
  7. Implementation details
  8. Comparative experiments
  9. Results and Discussion
  10. Conclusion and future work
  11. Compliance with ethical standards
  12. Acknowledgments

Figures (4)

  • Figure 1: An overview of our proposed segmentation pipeline demonstrating how a guiding map is integrated into the input data to improve segmentation performance.
  • Figure 2: Algorithm to generate a guiding map from an RGB image.
  • Figure 3: Examples of guiding maps. Left: Input RGB images; Middle: Ground truth binary masks of BVs; Right: Guiding maps.
  • Figure 4: A comparison of segmentation quality using EfficientUnet-/B2 model with RGB input VS with RGB+Guiding Map input. (a)(b): Tumor BVs, (c): normal BV