Accelerating imaging: deep learning for enhanced 123I-ioflupane SPECT efficiency
A compact four-layer U-Net restores diagnostic fidelity to 5-min <sup>123</sup>I-ioflupane SPECT, enabling an 80% reduction in scan time without loss of quantitative metrics or interpretability. DL-accelerated protocols may enhance comfort, reduce motion artefacts and increase throughput, warranting prospective multicentre validation.
Authors
- Yuka Takeuchi (ORCID: https://orcid.org/0000-0002-2432-0370)
- Shingo Kato (ORCID: https://orcid.org/0000-0002-7545-0669)
- Keiichi Horie
- Ryo Aoki (ORCID: https://orcid.org/0000-0002-6021-935X)
- Daisuke Utsunomiya (ORCID: https://orcid.org/0000-0002-1723-1724)
- Tsuneo Yamashiro (ORCID: https://orcid.org/0000-0002-1904-2548)
- Yoshinobu Ishiwata (ORCID: https://orcid.org/0000-0002-9425-0582)
- Hitoshi Iizuka
- Shoko Takano (ORCID: https://orcid.org/0000-0002-4289-6250)
- Shinjiro Aso
- Akira Haga
- Yuka Misumi
- Kazuhiro Aritome
Institutions
- Yokohama City University Medical Center (JP)
- Yokohama City University Hospital (JP)
- Yokohama City University (JP)
Publication Details
- Journal
- Japanese Journal of Radiology
- Published
- 2025-12-18
- DOI
- https://doi.org/10.1007/s11604-025-01933-z
- Primary Topic
- Medical Imaging Techniques and Applications
- Type
- article
- Field-Weighted Citation Impact
- 0.00
Funders
- Japan Society for the Promotion of Science