Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Enabling Collagen Quantification on HE-stained Slides Through Stain Deconvolution and Restained HE-HES

Guillaume Balezo, Christof A. Bertram, Cyprien Tilmant, Stéphanie Petit, Saima Ben Hadj, Rutger H. J. Fick

TL;DR

It is shown that it is possible to quantify the collagen content from the HE image alone and to digitally create an HES image, and it is hoped this approach can aid in improving the clinical workflow while reducing reagent costs for laboratories.

Abstract

In histology, the presence of collagen in the extra-cellular matrix has both diagnostic and prognostic value for cancer malignancy, and can be highlighted by adding Saffron (S) to a routine Hematoxylin and Eosin (HE) staining. However, Saffron is not usually added because of the additional cost and because pathologists are accustomed to HE, with the exception of France-based laboratories. In this paper, we show that it is possible to quantify the collagen content from the HE image alone and to digitally create an HES image. To do so, we trained a UNet to predict the Saffron densities from HE images. We created a dataset of registered, restained HE-HES slides and we extracted the Saffron concentrations as ground truth using stain deconvolution on the HES images. Our model reached a Mean Absolute Error of 0.0668 $\pm$ 0.0002 (Saffron values between 0 and 1) on a 3-fold testing set. We hope our approach can aid in improving the clinical workflow while reducing reagent costs for laboratories.

Enabling Collagen Quantification on HE-stained Slides Through Stain Deconvolution and Restained HE-HES

TL;DR

It is shown that it is possible to quantify the collagen content from the HE image alone and to digitally create an HES image, and it is hoped this approach can aid in improving the clinical workflow while reducing reagent costs for laboratories.

Abstract

In histology, the presence of collagen in the extra-cellular matrix has both diagnostic and prognostic value for cancer malignancy, and can be highlighted by adding Saffron (S) to a routine Hematoxylin and Eosin (HE) staining. However, Saffron is not usually added because of the additional cost and because pathologists are accustomed to HE, with the exception of France-based laboratories. In this paper, we show that it is possible to quantify the collagen content from the HE image alone and to digitally create an HES image. To do so, we trained a UNet to predict the Saffron densities from HE images. We created a dataset of registered, restained HE-HES slides and we extracted the Saffron concentrations as ground truth using stain deconvolution on the HES images. Our model reached a Mean Absolute Error of 0.0668 0.0002 (Saffron values between 0 and 1) on a 3-fold testing set. We hope our approach can aid in improving the clinical workflow while reducing reagent costs for laboratories.
Paper Structure (12 sections, 4 equations, 3 figures, 1 table)

This paper contains 12 sections, 4 equations, 3 figures, 1 table.

Table of Contents

  1. Introduction
  2. Materials and Methods
  3. Dataset Acquisition
  4. Slide Registration
  5. Ground Truth extraction via stain deconvolution
  6. Predicting Saffron concentration from HE
  7. HE to HES Reconstruction
  8. Results
  9. Quantitative analysis
  10. Qualitative analysis
  11. Discussion & Conclusion
  12. Compliance with Ethical Standards

Figures (3)

  • Figure 1: Slide Registration - Example of a registered pair of HE-HES slides in the test set (first fold). The defined regions $A\text{-}F$ (2024x2024 pixels patches) are used in Figures 2 and 3.
  • Figure 2: Quantitative Evaluation - Least squares linear regression between the mean Saffron concentrations from the predictions $mH_{\hat{S}}$ and the ground truths $m{H_{S}}$ on test images (fold 1). Regions with green dots are the regions of Figure 3.
  • Figure 3: Prediction Visualization - The columns represent in this order: four input HE patches $I_{HE}$ extracted from the figure 1, the estimated Saffron concentrations $H_{\hat{S}}$, the ground truths Saffron concentrations $H_{S}$, the reconstructed HES images $I_{HE+\hat{S}}$ and the registered HES patches $I_{HES}$. Regions A and B are in tumor areas while C and D are benign regions.