Evaluating diagnostic content of AI-generated chest radiography: A multi-center visual Turing test
PLOS ONE · 12.04.2023 · 18 (4) · e0279349
DOI: 10.1371/journal.pone.0279349 ↗Kurz gefasst
Multizentrische Studie in der Zeitschrift PLOS ONE, online erschienen am 12.04.2023. Verfasst von Youho Myong und 8 weiteren Autor:innen. Beteiligte Einrichtung: Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Republic of Korea. Hauptthemen laut MEDLINE: Artificial Intelligence, Neural Networks, Computer. Die Arbeit wurde bisher 20-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: MD-PhD/Medical Scientist Training Program, Korea Health Industry Development Institute, Ministry of Health and Welfare, National Research Foundation of Korea, Ministry of ICT, Science, and Technology.
Abstract (Originalsprache)
Background
Accurate interpretation of chest radiographs requires years of medical training, and many countries face a shortage of medical professionals to meet such requirements. Recent advancements in artificial intelligence (AI) have aided diagnoses; however, their performance is often limited due to data imbalance. The aim of this study was to augment imbalanced medical data using generative adversarial networks (GANs) and evaluate the clinical quality of the generated images via a multi-center visual Turing test.
Methods
Using six chest radiograph datasets, (MIMIC, CheXPert, CXR8, JSRT, VBD, and OpenI), starGAN v2 generated chest radiographs with specific pathologies. Five board-certified radiologists from three university hospitals, each with at least five years of clinical experience, evaluated the image quality through a visual Turing test. Further evaluations were performed to investigate whether GAN augmentation enhanced the convolutional neural network (CNN) classifier performances.
Results
In terms of identifying GAN images as artificial, there was no significant difference in the sensitivity between radiologists and random guessing (result of radiologists: 147/275 (53.5%) vs result of random guessing: 137.5/275, (50%); p = .284). GAN augmentation enhanced CNN classifier performance by 11.7%.
Conclusion
Radiologists effectively classified chest pathologies with synthesized radiographs, suggesting that the images contained adequate clinical information. Furthermore, GAN augmentation enhanced CNN performance, providing a bypass to overcome data imbalance in medical AI training. CNN based methods rely on the amount and quality of training data; the present study showed that GAN augmentation could effectively augment training data for medical AI.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- Department of Biomedical Engineering, Seoul National University College of Medicine, Seoul, Republic of Korea.
- Department of Rehabilitation Medicine, Seoul National University Hospital, Seoul, Republic of Korea.
- Interdisciplinary Program in Bioengineering, Seoul National University Graduate School, Seoul, Republic of Korea.
- Department of Radiology, Severance Hospital, Yonsei University College of Medicine, Seoul, Republic of Korea.
- Department of Radiology and Research Institute of Radiological Science, Yonsei University College of Medicine, Seoul, Republic of Korea.
- Transdisciplinary Department of Medicine and Advanced Technology, Seoul National University Hospital, Seoul, Republic of Korea.
ORCID-Profile: Young Gyun Kim, Yongsik Sim, Sungwan Kim
Förderung
- MD-PhD/Medical Scientist Training Program, Korea Health Industry Development Institute, Ministry of Health and Welfare
- National Research Foundation of Korea, Ministry of ICT, Science, and Technology
Zitieren
APA
Myong, Y., Yoon, D., Kim, B. S., Kim, Y. G., Sim, Y., Lee, S., Yoon, J., Cho, M., & Kim, S. (2023). Evaluating diagnostic content of AI-generated chest radiography: A multi-center visual Turing test. PLOS ONE, 18(4), e0279349. https://doi.org/10.1371/journal.pone.0279349
Vancouver
Myong Y, Yoon D, Kim BS, Kim YG, Sim Y, Lee S, et al. Evaluating diagnostic content of AI-generated chest radiography: A multi-center visual Turing test. PLOS ONE. 2023;18(4):e0279349. doi:10.1371/journal.pone.0279349
BibTeX
@article{Myong2023,
author = {Myong, Youho and Yoon, Dan and Kim, Byeong Soo and Kim, Young Gyun and Sim, Yongsik and Lee, Suji and Yoon, Jiyoung and Cho, Minwoo and Kim, Sungwan},
title = {Evaluating diagnostic content of AI-generated chest radiography: A multi-center visual Turing test},
journal = {PLOS ONE},
year = {2023},
volume = {18},
number = {4},
pages = {e0279349},
doi = {10.1371/journal.pone.0279349}
}
EUVIMED