Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning–based Prostate Cancer Detection Using Biparametric MRI
Radiology: Artificial Intelligence · 01.09.2023 · 5 (5)
DOI: 10.1148/ryai.230031 ↗Kurz gefasst
Fachartikel in der Zeitschrift Radiology: Artificial Intelligence, erschienen am 01.09.2023. Verfasst von Joeran S Bosma und 5 weiteren Autor:innen. Beteiligte Einrichtung: From the Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA Nijmeg…. Die Arbeit wurde bisher 59-mal zitiert (Crossref) und nennt 22 Literaturangaben. Der Volltext ist frei in PubMed Central verfügbar. Gefördert von: Health~Holland, Siemens Healthineers.
Abstract (Originalsprache)
Purpose
To evaluate a novel method of semisupervised learning (SSL) guided by automated sparse information from diagnostic reports to leverage additional data for deep learning-based malignancy detection in patients with clinically significant prostate cancer. Materials and Methods: This retrospective study included 7756 prostate MRI examinations (6380 patients) performed between January 2014 and December 2020 for model development. An SSL method, report-guided SSL (RG-SSL), was developed for detection of clinically significant prostate cancer using biparametric MRI. RG-SSL, supervised learning (SL), and state-of-the-art SSL methods were trained using 100, 300, 1000, or 3050 manually annotated examinations. Performance on detection of clinically significant prostate cancer by RG-SSL, SL, and SSL was compared on 300 unseen examinations from an external center with a histopathologically confirmed reference standard. Performance was evaluated using receiver operating characteristic (ROC) and free-response ROC analysis. P values for performance differences were generated with a permutation test.
Results
At 100 manually annotated examinations, mean examination-based diagnostic area under the ROC curve (AUC) values for RG-SSL, SL, and the best SSL were 0.86 ± 0.01 (SD), 0.78 ± 0.03, and 0.81 ± 0.02, respectively. Lesion-based detection partial AUCs were 0.62 ± 0.02, 0.44 ± 0.04, and 0.48 ± 0.09, respectively. Examination-based performance of SL with 3050 examinations was matched by RG-SSL with 169 manually annotated examinations, thus requiring 14 times fewer annotations. Lesion-based performance was matched with 431 manually annotated examinations, requiring six times fewer annotations.
Conclusion
RG-SSL outperformed SSL in clinically significant prostate cancer detection and achieved performance similar to SL even at very low annotation budgets.Keywords: Annotation Efficiency, Computer-aided Detection and Diagnosis, MRI, Prostate Cancer, Semisupervised Deep Learning Supplemental material is available for this article. Published under a CC BY 4.0 license.
Autor:innen und Institutionen
- From the Diagnostic Image Analysis Group, Department of Medical Imaging, Radboud University Medical Center, Geert Grooteplein Zuid 10, 6525 GA Nijmegen, the Netherlands.
ORCID-Profile: Joeran S Bosma, Anindo Saha, Ivan Slootweg, Maarten de Rooij, Henkjan Huisman
Förderung
- Health~Holland
- Siemens Healthineers
Zitieren
APA
Bosma, J. S., Saha, A., Hosseinzadeh, M., Slootweg, I., de Rooij, M., & Huisman, H. (2023). Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning–based Prostate Cancer Detection Using Biparametric MRI. Radiology: Artificial Intelligence, 5(5). https://doi.org/10.1148/ryai.230031
Vancouver
Bosma JS, Saha A, Hosseinzadeh M, Slootweg I, de Rooij M, Huisman H. Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning–based Prostate Cancer Detection Using Biparametric MRI. Radiology: Artificial Intelligence. 2023;5(5). doi:10.1148/ryai.230031
BibTeX
@article{Bosma2023,
author = {Bosma, Joeran S and Saha, Anindo and Hosseinzadeh, Matin and Slootweg, Ivan and de Rooij, Maarten and Huisman, Henkjan},
title = {Semisupervised Learning with Report-guided Pseudo Labels for Deep Learning–based Prostate Cancer Detection Using Biparametric MRI},
journal = {Radiology: Artificial Intelligence},
year = {2023},
volume = {5},
number = {5},
doi = {10.1148/ryai.230031}
}
EUVIMED