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

Autor: Valliani AA; Department of Neurosurgery, Mount Sinai Health System, New York, NY, United States of America., Gulamali FF; Department of Neurosurgery, Mount Sinai Health System, New York, NY, United States of America., Kwon YJ; Department of Neurosurgery, Mount Sinai Health System, New York, NY, United States of America., Martini ML; Department of Neurosurgery, Mount Sinai Health System, New York, NY, United States of America., Wang C; Data Science Degree Program, National Taiwan University, Taipei, Taiwan., Kondziolka D; Department of Neurosurgery, New York University Langone Medical Center, New York, NY, United States of America.; Department of Radiation Oncology, New York University Langone Medical Center, New York, NY, United States of America., Chen VJ; Oncology Early Development, Merck Co., Inc, Kenilworth, NJ, United States of America., Wang W; Data Science Degree Program, National Taiwan University, Taipei, Taiwan.; Institute of Applied Mathematical Sciences, National Taiwan University, Taipei, Taiwan., Costa AB; NVIDIA, Santa Clara, CA, United States of America., Oermann EK; Department of Neurosurgery, New York University Langone Medical Center, New York, NY, United States of America.; Department of Radiology, New York University Langone Medical Center, New York, NY, United States of America.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2022 Oct 14; Vol. 17 (10), pp. e0273262. Date of Electronic Publication: 2022 Oct 14 (Print Publication: 2022).
DOI: 10.1371/journal.pone.0273262
Abstrakt: 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.
Competing Interests: The authors have declared that no competing interests exist.
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje