Training an automated circulating tumor cell classifier when the true classification is uncertain
PNAS Nexus · 01.02.2024 · 3 (2)
DOI: 10.1093/pnasnexus/pgae048 ↗Kurz gefasst
Fachartikel in der Zeitschrift PNAS Nexus, online erschienen am 09.02.2024. Verfasst von Afroditi Nanou und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Medical Cell BioPhysics, Faculty of Science and Technology, University of Twente, Enschede 7522 NH, The Netherlands. Die Arbeit wurde bisher 13-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0). Gefördert von: Menarini Silicon Biosystems, German Network for Bioinformatics Infrastructure, Ministry of Culture and Science of the State of Northrhine Westphalia.
Abstract (Originalsprache)
Circulating tumor cell (CTC) and tumor-derived extracellular vesicle (tdEV) loads are prognostic factors of survival in patients with carcinoma. The current method of CTC enumeration relies on operator review and, unfortunately, has moderate interoperator agreement (Fleiss’ kappa 0.60) due to difficulties in classifying CTC-like events. We compared operator review, ACCEPT automated image processing, and refined the output of a deep-learning algorithm to identify CTC and tdEV for the prediction of survival in patients with metastatic and nonmetastatic cancers. Operator review is only defined for CTC. Refinement was performed using automatic contrast maximization CM-CTC of events detected in cancer and in benign samples (CM-CTC). We used 418 samples from benign diseases, 6,293 from nonmetastatic breast, 2,408 from metastatic breast, and 698 from metastatic prostate cancer to train, test, optimize, and evaluate CTC and tdEV enumeration. For CTC identification, the CM-CTC performed best on metastatic/nonmetastatic breast cancer, respectively, with a hazard ratio (HR) for overall survival of 2.6/2.1 vs. 2.4/1.4 for operator CTC and 1.2/0.8 for ACCEPT-CTC. For tdEV identification, CM-tdEV performed best with an HR of 1.6/2.9 vs. 1.5/1.0 with ACCEPT-tdEV. In conclusion, contrast maximization is effective even though it does not utilize domain knowledge.
Schlagwörter
Stichwörter der Autor:innen
Autor:innen und Institutionen
- Department of Medical Cell BioPhysics, Faculty of Science and Technology, University of Twente, Enschede 7522 NH, The Netherlands.
- Department of General, Visceral and Pediatric Surgery, Heinrich-Heine University, University Hospital Düsseldorf, Düsseldorf 40225, Germany.
- Institute for Medical Biometry and Bioinformatics, Heinrich Heine University, Düsseldorf, Germany.
- Decisive Science, Amsterdam 1019 BB, The Netherlands.
ORCID-Profile: Afroditi Nanou, Nikolas H Stoecklein, Leon W M M Terstappen, Frank A W Coumans
Förderung
- Menarini Silicon Biosystems
- German Network for Bioinformatics Infrastructure
- Ministry of Culture and Science of the State of Northrhine Westphalia
Zitieren
APA
Nanou, A., Stoecklein, N. H., Doerr, D., Driemel, C., Terstappen, L. W. M. M., & Coumans, F. A. W. (2024). Training an automated circulating tumor cell classifier when the true classification is uncertain. PNAS Nexus, 3(2). https://doi.org/10.1093/pnasnexus/pgae048
Vancouver
Nanou A, Stoecklein NH, Doerr D, Driemel C, Terstappen LWMM, Coumans FAW. Training an automated circulating tumor cell classifier when the true classification is uncertain. PNAS Nexus. 2024;3(2). doi:10.1093/pnasnexus/pgae048
BibTeX
@article{Nanou2024,
author = {Nanou, Afroditi and Stoecklein, Nikolas H and Doerr, Daniel and Driemel, Christiane and Terstappen, Leon W M M and Coumans, Frank A W},
title = {Training an automated circulating tumor cell classifier when the true classification is uncertain},
journal = {PNAS Nexus},
year = {2024},
volume = {3},
number = {2},
doi = {10.1093/pnasnexus/pgae048}
}
EUVIMED