A1 Refereed original research article in a scientific journal
External validation of a deep learning-based algorithm for detection of tall cells in papillary thyroid carcinoma: A multicenter study
Authors: Stenman Sebastian, Bétrisey Sylvain, Vainio Paula, Huvila Jutta, Lundin Mikael, Linder Nina, Schmitt Anja, Perren Aurel, Dettmer Matthias S., Haglund Caj, Arola Johanna, Lundin Johan
Publisher: Elsevier
Publication year: 2024
Journal: Journal of Pathology Informatics
Journal name in source: Journal of Pathology Informatics
Article number: 100366
Volume: 15
ISSN: 2153-3539
eISSN: 2153-3539
DOI: https://doi.org/10.1016/j.jpi.2024.100366
Web address : https://doi.org/10.1016/j.jpi.2024.100366
Self-archived copy’s web address: https://research.utu.fi/converis/portal/detail/Publication/381223889
The tall cell variant (TCV) is an aggressive subtype of papillary thyroid carcinoma (PTC). The TCV is defined as a PTC comprising at least 30% epithelial cells that are three times as tall as they are wide. In practice, this definition is difficult to adhere to, resulting in high inter-observer variability. In this multicenter study, we validated a previously trained deep learning (DL)-based algorithm for detection of tall cells on 160 externally collected hematoxylin and eosin (HE)-stained PTC whole-slide images. In a test set of 360 manual annotations of regions of interest from 18 separate tissue sections in the external dataset, the DL-based algorithm detected TCs with a sensitivity of 90.6% and a specificity of 88.5%. The DL algorithm detected non-TC areas with a sensitivity of 81.6% and a specificity of 92.9%. In the validation datasets, 20% and 30% TC thresholds correlated with a significantly shorter relapse-free survival. In conclusion, the DL algorithm detected TCs in unseen, external scanned HE tissue slides with high sensitivity and specificity without any retraining.
Downloadable publication This is an electronic reprint of the original article. |  |
