TY  - JOUR
A1  - Despotovic, Vladimir
A1  - Kim, Sang-Yoon
A1  - Hau, Ann-Christin
A1  - Kakoichankava, Aliaksandra
A1  - Klamminger, Gilbert Georg
A1  - Kleine Borgmann, Felix Bruno
A1  - Frauenknecht, Katrin Barbara Magda
A1  - Mittelbronn, Michel Guy André
A1  - Nazarov, Petr V.
T1  - Glioma subtype classification from histopathological images using in-domain and out-of-domain transfer learning: an experimental study
T2  - Heliyon
N2  - 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.
KW  - Digital pathology
KW  - Whole slide images
KW  - Glioma
KW  - Deep learning
KW  - Transfer learning
Y1  - 2024
UR  - http://publikationen.ub.uni-frankfurt.de/frontdoor/index/index/docId/83434
UR  - https://nbn-resolving.org/urn:nbn:de:hebis:30:3-834349
SN  - 2405-8440
VL  - 10
IS  - 5, e27515
PB  - Elsevier
CY  - Amsterdam
ER  -