Deep generative abnormal lesion emphasization validated by nine radiologists and 1000 chest X-rays with lung nodules.

Autor: Hanaoka S; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Nomura Y; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan.; Center for Frontier Medical Engineering, Chiba University, Chiba, Japan., Hayashi N; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Sato I; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan.; Department of Computer Science, Graduate School of Information Science and Technology, The University of Tokyo, Bunkyo-ku, Japan., Miki S; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Yoshikawa T; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Shibata H; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Nakao T; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Takenaga T; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Koyama H; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Cho S; Toranomon Hospital, Minato-ku, Tokyo, Japan., Kanemaru N; Kanto Rosai Hospital, Kawasaki City, Kanagawa Prefecture, Japan., Fujimoto K; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan.; Teikyo University Hospital, Itabashi-ku, Tokyo, Japan., Sakamoto N; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Nishiyama T; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan., Matsuzaki H; Center for Epidemiology and Preventive Medicine, Graduate School of Medicine, Tokyo, Bunkyo-ku, Tokyo, Japan.; Department of Respiratory Medicine, Graduate School of Medicine, Tokyo, Bunkyo-ku, Tokyo, Japan., Yamamichi N; Center for Epidemiology and Preventive Medicine, Graduate School of Medicine, Tokyo, Bunkyo-ku, Tokyo, Japan., Abe O; Department of Radiology and Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, Bunkyo-ku, Tokyo, Japan.
Jazyk: angličtina
Zdroj: PloS one [PLoS One] 2024 Dec 12; Vol. 19 (12), pp. e0315646. Date of Electronic Publication: 2024 Dec 12 (Print Publication: 2024).
DOI: 10.1371/journal.pone.0315646
Abstrakt: A general-purpose method of emphasizing abnormal lesions in chest radiographs, named EGGPALE (Extrapolative, Generative and General-Purpose Abnormal Lesion Emphasizer), is presented. The proposed EGGPALE method is composed of a flow-based generative model and L-infinity-distance-based extrapolation in a latent space. The flow-based model is trained using only normal chest radiographs, and an invertible mapping function from the image space to the latent space is determined. In the latent space, a given unseen image is extrapolated so that the image point moves away from the normal chest X-ray hyperplane. Finally, the moved point is mapped back to the image space and the corresponding emphasized image is created. The proposed method was evaluated by an image interpretation experiment with nine radiologists and 1,000 chest radiographs, of which positive suspected lung cancer cases and negative cases were validated by computed tomography examinations. The sensitivity of EGGPALE-processed images showed +0.0559 average improvement compared with that of the original images, with -0.0192 deterioration of average specificity. The area under the receiver operating characteristic curve of the ensemble of nine radiologists showed a statistically significant improvement. From these results, the feasibility of EGGPALE for enhancing abnormal lesions was validated. Our code is available at https://github.com/utrad-ical/Eggpale.
Competing Interests: The authors have declared that no competing interests exist.
(Copyright: © 2024 Hanaoka et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)
Databáze: MEDLINE
Externí odkaz:
Nepřihlášeným uživatelům se plný text nezobrazuje