Deploying deep learning models on unseen medical imaging using adversarial domain adaptation

Autor: Aly A. Valliani, Faris F. Gulamali, Young Joon Kwon, Michael L. Martini, Chiatse Wang, Douglas Kondziolka, Viola J. Chen, Weichung Wang, Anthony B. Costa, Eric K. Oermann
Jazyk: angličtina
Rok vydání: 2022
Předmět:
Zdroj: PLoS ONE, Vol 17, Iss 10 (2022)
Druh dokumentu: article
ISSN: 1932-6203
Popis: The fundamental challenge in machine learning is ensuring that trained models generalize well to unseen data. We developed a general technique for ameliorating the effect of dataset shift using generative adversarial networks (GANs) on a dataset of 149,298 handwritten digits and dataset of 868,549 chest radiographs obtained from four academic medical centers. Efficacy was assessed by comparing area under the curve (AUC) pre- and post-adaptation. On the digit recognition task, the baseline CNN achieved an average internal test AUC of 99.87% (95% CI, 99.87-99.87%), which decreased to an average external test AUC of 91.85% (95% CI, 91.82-91.88%), with an average salvage of 35% from baseline upon adaptation. On the lung pathology classification task, the baseline CNN achieved an average internal test AUC of 78.07% (95% CI, 77.97-78.17%) and an average external test AUC of 71.43% (95% CI, 71.32-71.60%), with a salvage of 25% from baseline upon adaptation. Adversarial domain adaptation leads to improved model performance on radiographic data derived from multiple out-of-sample healthcare populations. This work can be applied to other medical imaging domains to help shape the deployment toolkit of machine learning in medicine.
Databáze: Directory of Open Access Journals
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje