Denoising of ultra-low-dose 15O positron emission tomography images using deep image prior with anatomical information extracted through magnetic resonance segmentation.

Saved in:
Bibliographic Details
Title: Denoising of ultra-low-dose 15O positron emission tomography images using deep image prior with anatomical information extracted through magnetic resonance segmentation.
Authors: Matsubara K; Department of Management Science and Engineering, Faculty of System Science and Technology, Akita Prefectural University, Japan; Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Japan. Electronic address: matsubara@akita-pu.ac.jp., Ibaraki M; Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Japan., Hashimoto F; J. Crayton Pruitt Family Department of Biomedical Engineering, University of Florida, United States; Central Research Laboratory, Hamamatsu Photonics K. K., Japan., Onishi Y; Central Research Laboratory, Hamamatsu Photonics K. K., Japan., Shinohara Y; Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Japan., Sato K; Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Japan., Yamamoto H; Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Japan., Kinoshita T; Department of Radiology and Nuclear Medicine, Research Institute for Brain and Blood Vessels, Akita Cerebrospinal and Cardiovascular Center, Japan.
Source: Physica medica : PM : an international journal devoted to the applications of physics to medicine and biology : official journal of the Italian Association of Biomedical Physics (AIFB) [Phys Med] 2026 Jun 20; Vol. 148, pp. 105841. Date of Electronic Publication: 2026 Jun 20.
Publication Type: Journal Article
Journal Info: Publisher: Istituti Editoriali e Poligrafici Internazionali Country of Publication: Italy NLM ID: 9302888 Publication Model: Print-Electronic Cited Medium: Internet ISSN: 1724-191X (Electronic) Linking ISSN: 11201797 NLM ISO Abbreviation: Phys Med Subsets: MEDLINE
Database: MEDLINE Ultimate
Description
ISSN:1724-191X
DOI:10.1016/j.ejmp.2026.105841