Domain-specific transfer learning in the automated scoring of tumor-stroma ratio from histopathological images of colorectal cancer

TL;DR

This study develops a CNN-based method for automated tumor-stroma ratio estimation in colorectal cancer histopathology, comparing transfer learning approaches and validating against pathologist assessments.

Contribution

It introduces a transfer learning approach using domain-specific data for TSR estimation from histopathological images, with detailed model evaluation.

Findings

Classification accuracy reached 96.1% for tissue classes.

Best model achieved 99.3% accuracy for tumor class.

Correlation between predicted and pathologist-estimated TSR was 0.57.

Abstract

Tumor-stroma ratio (TSR) is a prognostic factor for many types of solid tumors. In this study, we propose a method for automated estimation of TSR from histopathological images of colorectal cancer. The method is based on convolutional neural networks which were trained to classify colorectal cancer tissue in hematoxylin-eosin stained samples into three classes: stroma, tumor and other. The models were trained using a data set that consists of 1343 whole slide images. Three different training setups were applied with a transfer learning approach using domain-specific data i.e. an external colorectal cancer histopathological data set. The three most accurate models were chosen as a classifier, TSR values were predicted and the results were compared to a visual TSR estimation made by a pathologist. The results suggest that classification accuracy does not improve when domain-specific data are used in the pre-training of the convolutional neural network models in the task at hand. Classification accuracy for stroma, tumor and other reached 96.1$\%$ on an independent test set. Among the three classes the best model gained the highest accuracy (99.3$\%$) for class tumor. When TSR was predicted with the best model, the correlation between the predicted values and values estimated by an experienced pathologist was 0.57. Further research is needed to study associations between computationally predicted TSR values and other clinicopathological factors of colorectal cancer and the overall survival of the patients.