Kagoshima University · Graduate School of Medical and Dental Sciences · 教授

Research keywordsFDG-PET機械学習・腫瘍PET AI・dual-energy CT・頭頸部MRI・CESTイメージング・Spectral Imaging・胃静脈瘤塞栓術・細胞外容積分画CT・術後予後画像評価

Research fieldsRadiation science・Psychiatric science・Biomedical engineering・内科・General internal medicine (including Psychosomatic medicine)・Clinical internal medicine・Medicine・Medical Physics and Radiological Technology

This is a public-data preview. Personalized fit, contact angles, and saved workflows require sign-in.

• 山岸 良司, 鮎川 卓朗, 恵島 史貴, 中野 翼, 長谷川 知仁, 長野 広明, 内匠 浩二, 上村 清央, 吉浦 敬2025 · 記述言語： 日本語 出版者・発行元： (公社)日本医学放射線学会
• Nakajo M., Hirahara D., Hirahara M., Eizuru Y., Tani A., Kanzaki F., Takumi K., Kamimura K., Yoshiura T. . Artificial intelligence in oncological positron emission tomography: advancing image2025 · 記述言語： 日本語 出版者・発行元： Clinical Radiology Functional and metabolic information provided by positron emission tomography (PET) imaging, such as patient diagnosis, tumour staging, and treatment evaluation, plays an important role in the clinical management of patients with cancer. Nonetheless, its clinical efficacy may be inhibited by differences in image quality and limitations in quantitative robustness. Artificial intelligence (AI) has transformed oncological PET imaging by improving image quality and facilitating a more consistent extraction of quantitative metrics. Recent research emphasises the value of AI in improving diagnostic accuracy and prognostic modelling. However, to ensure that AI-based PET analysis is successfully implemented in clinical practice, challenges such as imaging data standardisation, the development of reliable explainability methods, and the establishment of regulatory frameworks must be addressed. To optimise individualised care, future progress will likely be based on multimodal integration, federated learning, and probabilistic deep learning. Overall, this review highlights both the current progress and the remaining challenges of AI in oncological PET, aiming to provide a balanced perspective for future clinical translation. DOI： 10.1016/j.crad.2025.107187 Scopus PubMed
• Takumi K., Hakamada H., Nagano H., Nakanosono R., Kanzaki F., Nakajo M., Kamimura K., Nakajo M., Nagano D., Ueda K., Yoshiura T. . Postoperative prognostic assessment using ECV fraction derive2025 · 記述言語： 日本語 出版者・発行元： European Journal of Radiology Purpose: To assess the postoperative prognostic utility of extracellular volume (ECV) fraction measurement using equilibrium contrast-enhanced CT (CECT) in patients with thymomas. Methods: Enrolled in the study were patients with thymomas who were assessed by pretreatment CECT. ECV fraction was determined from measurements within the lesion and aorta on unenhanced and equilibrium phase CECT. Masaoka–Koga stage, WHO histological classification, and morphological features on CT including tumor size and boundary clarity were also evaluated. Univariate and bivariate analyses using Cox proportional hazards regression model were performed to evaluate the factors affecting recurrence-free survival (RFS). RFS rates were analyzed using the Kaplan–Meier method. Results: A total of 100 consecutive patients (52 low-risk and 48 high-risk thymomas) were enrolled in this study. Bivariate analyses identified boundary, Masaoka–Koga stage, and ECV fraction as independent significant variables for predicting RFS across all parameters. Mean RFS was significantly shorter in the group with ill-defined boundary (ill-defined, 102.5 months; well-defined, 167.4 months; p < 0.001), high Masaoka–Koga stage (stage 3 or 4, 54.9 months; stage 1 or 2, 164.2 months; p < 0.001), and high ECV fraction (ECV fraction ≥ 27.5 %, 110.3 months; ECV fraction < 27.5 %, 170.1 months; p < 0.001). Conclusions: ECV fraction derived from equilibrium CECT was an independent risk factor for RFS in patients with thymoma. DOI： 10.1016/j.ejrad.2025.111978 Scopus PubMed
• 平原 充穂, 谷 淳至, 神宮司 メグミ, 中條 正豊, 吉浦 敬, 豊川 建二2025 · 記述言語： 日本語 出版者・発行元： (公社)日本医学放射線学会

• Official profile
• KAKEN
• CiNii