Investigation of distributed learning for automated lesion detection in head MR images.
Aiki YamadaShouhei HanaokaTomomi TakenagaSoichiro MikiTakeharu YoshikawaYukihiro NomuraPublished in: Radiological physics and technology (2024)
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.
Keyphrases
- contrast enhanced
- magnetic resonance
- data analysis
- deep learning
- optical coherence tomography
- magnetic resonance imaging
- computed tomography
- diffusion weighted
- loop mediated isothermal amplification
- label free
- real time pcr
- convolutional neural network
- electronic health record
- white matter
- multiple sclerosis
- physical activity
- resistance training
- big data
- single cell
- high throughput
- weight gain
- cerebral ischemia
- abdominal aortic aneurysm
- blood brain barrier
- sensitive detection