Glioma subtype classification from histopathological images using in-domain and out-of-domain transfer learning: an experimental study
- 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.
Verfasserangaben: | Vladimir DespotovicORCiD, Sang-Yoon Kim, Ann-Christin HauORCiD, Aliaksandra KakoichankavaORCiD, Gilbert Georg KlammingerORCiDGND, Felix Bruno Kleine BorgmannORCiD, Katrin Barbara Magda FrauenknechtORCiDGND, Michel Guy André MittelbronnORCiDGND, Petr V. NazarovORCiD |
---|---|
URN: | urn:nbn:de:hebis:30:3-834349 |
DOI: | https://doi.org/10.1016/j.heliyon.2024.e27515 |
ISSN: | 2405-8440 |
Titel des übergeordneten Werkes (Englisch): | Heliyon |
Verlag: | Elsevier |
Verlagsort: | Amsterdam |
Dokumentart: | Wissenschaftlicher Artikel |
Sprache: | Englisch |
Datum der Veröffentlichung (online): | 06.03.2024 |
Datum der Erstveröffentlichung: | 06.03.2024 |
Veröffentlichende Institution: | Universitätsbibliothek Johann Christian Senckenberg |
Datum der Freischaltung: | 15.04.2024 |
Freies Schlagwort / Tag: | Deep learning; Digital pathology; Glioma; Transfer learning; Whole slide images |
Jahrgang: | 10 |
Ausgabe / Heft: | 5, e27515 |
Aufsatznummer: | e27515 |
Seitenzahl: | 14 |
Institute: | Medizin |
DDC-Klassifikation: | 6 Technik, Medizin, angewandte Wissenschaften / 61 Medizin und Gesundheit / 610 Medizin und Gesundheit |
Sammlungen: | Universitätspublikationen |
Lizenz (Deutsch): | Creative Commons - CC BY - Namensnennung 4.0 International |