Investigation of distributed learning for automated lesion detection in head MR images.

Autor: Yamada A; Department of Medical Engineering, Graduate School of Science and Engineering, Chiba University, 1-33 Yayoi-Cho, Inage-Ku, Chiba, 263-8522, Japan. aiki-yamada@chiba-u.jp.; Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-8655, Japan. aiki-yamada@chiba-u.jp., Hanaoka S; Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-8655, Japan., Takenaga T; Department of Radiology, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-8655, Japan., Miki S; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-8655, Japan., Yoshikawa T; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-8655, Japan., Nomura Y; Department of Computational Diagnostic Radiology and Preventive Medicine, The University of Tokyo Hospital, 7-3-1 Hongo, Bunkyo-Ku, Tokyo, 113-8655, Japan.; Center for Frontier Medical Engineering, Chiba University, 1-33 Yayoi-Cho, Inage-Ku, Chiba, 263-8522, Japan.
Jazyk: angličtina
Zdroj: Radiological physics and technology [Radiol Phys Technol] 2024 Sep; Vol. 17 (3), pp. 725-738. Date of Electronic Publication: 2024 Jul 24.
DOI: 10.1007/s12194-024-00827-5
Abstrakt: In this study, we investigated the application of distributed learning, including federated learning and cyclical weight transfer, in the development of computer-aided detection (CADe) software for (1) cerebral aneurysm detection in magnetic resonance (MR) angiography images and (2) brain metastasis detection in brain contrast-enhanced MR images. We used datasets collected from various institutions, scanner vendors, and magnetic field strengths for each target CADe software. We compared the performance of multiple strategies, including a centralized strategy, in which software development is conducted at a development institution after collecting de-identified data from multiple institutions. Our results showed that the performance of CADe software trained through distributed learning was equal to or better than that trained through the centralized strategy. However, the distributed learning strategies that achieved the highest performance depend on the target CADe software. Hence, distributed learning can become one of the strategies for CADe software development using data collected from multiple institutions.
(© 2024. The Author(s).)
Databáze: MEDLINE
Externí odkaz: