Glioma subtype classification from histopathological images using in-domain and out-of-domain transfer learning: An experimental study

TL;DR

This study compares transfer learning strategies and deep learning architectures for glioma classification in histopathological images, demonstrating improved semi-supervised methods and visualization tools that aid pathologists.

Contribution

It introduces a semi-supervised learning approach for glioma classification that enhances accuracy and reduces annotation effort, along with a visualization tool for tumor localization.

Findings

Achieved 96.91% balanced accuracy and 97.07% F1-score.

Out-of-domain ImageNet representations have limited generalizability.

Semi-supervised training improves model performance and annotation efficiency.

Abstract

We provide in this paper a comprehensive comparison of various transfer learning strategies and deep learning architectures for computer-aided classification of adult-type diffuse gliomas. We evaluate the generalizability of out-of-domain ImageNet representations for a target domain of histopathological images, and study the impact of in-domain adaptation using self-supervised and multi-task learning approaches for pretraining the models using the medium-to-large scale datasets of histopathological images. A semi-supervised learning approach is furthermore proposed, where the fine-tuned models are utilized to predict the labels of unannotated regions of the whole slide images (WSI). The models are subsequently retrained using the ground-truth labels and weak labels determined in the previous step, providing superior performance in comparison to standard in-domain transfer learning with balanced accuracy of 96.91% and F1-score 97.07%, and minimizing the pathologist's efforts for annotation. Finally, we provide a visualization tool working at WSI level which generates heatmaps that highlight tumor areas; thus, providing insights to pathologists concerning the most informative parts of the WSI.