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

• Published in: arXiv.org
• Main Authors: Despotovic, Vladimir, Sang-Yoon, Kim, Hau, Ann-Christin, Kakoichankava, Aliaksandra, Gilbert, Georg Klamminger, Felix Bruno Kleine Borgmann, Frauenknecht, Katrin B M, Mittelbronn, Michel, Nazarov, Petr V
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 29.09.2023
• Subjects: Annotations; Computer Science - Computer Vision and Pattern Recognition; Deep learning; Image classification; Labels; Semi-supervised learning
• ISSN: 2331-8422
• DOI: 10.48550/arxiv.2309.17223

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.