Open AccessAdaptive adversarial neural networks for the analysis of lossy and domain-shifted datasets of medical images
Author(s) -
Manoj Kumar Kanakasabapathy,
Prudhvi Thirumalaraju,
Hemanth Kandula,
Fenil Doshi,
Anjali Devi Sivakumar,
Deeksha Kartik,
Raghav Gupta,
Rohan Pooniwala,
John A. Branda,
Athe Tsibris,
Daniel R. Kuritzkes,
John C. Petrozza,
Charles L. Bormann,
Hadi Shafiee
Publication year - 2021
Publication title -
nature biomedical engineering
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 5.961
H-Index - 56
ISSN - 2157-846X
DOI - 10.1038/s41551-021-00733-w
Subject(s) - computer science , artificial intelligence , convolutional neural network , machine learning , domain (mathematical analysis) , deep learning , artificial neural network , adversarial system , domain knowledge , pattern recognition (psychology) , medical imaging , supervised learning , mathematical analysis , mathematics
In machine learning for image-based medical diagnostics, supervised convolutional neural networks are typically trained with large and expertly annotated datasets obtained using high-resolution imaging systems. Moreover, the network's performance can degrade substantially when applied to a dataset with a different distribution. Here, we show that adversarial learning can be used to develop high-performing networks trained on unannotated medical images of varying image quality. Specifically, we used low-quality images acquired using inexpensive portable optical systems to train networks for the evaluation of human embryos, the quantification of human sperm morphology and the diagnosis of malarial infections in the blood, and show that the networks performed well across different data distributions. We also show that adversarial learning can be used with unlabelled data from unseen domain-shifted datasets to adapt pretrained supervised networks to new distributions, even when data from the original distribution are not available. Adaptive adversarial networks may expand the use of validated neural-network models for the evaluation of data collected from multiple imaging systems of varying quality without compromising the knowledge stored in the network.