Evaluation of artificial-intelligence-based liver segmentation and its application for longitudinal liver volume measurement

Kimura, Rina; Hirata, Kenji; Tsuneta, Satonori; Takenaka, Junki; Watanabe, Shiro; Abo, Daisuke; Kudo, Kohsuke

Evaluation of artificial-intelligence-based liver segmentation and its application for longitudinal liver volume measurement

Kimura, Rina; Hirata, Kenji; Tsuneta, Satonori et al.

Abdominal Radiology, 2025, 50(12), 6192-6200

Permalink : https://hdl.handle.net/2115/97904

このアイテムのアクセス数:61件（2026-10-07 04:55 集計）

閲覧可能ファイル

ファイル	フォーマット	サイズ	閲覧回数	説明
manuscript_114392	pdf	1.08 MB	56
After_revision_20250527_abdominalradiology_supplement_liversegmentation	docx	2.22 MB	16	Supplementary Information

論文情報

ファイル出力 EndNote Basic出力 Mendeley出力

アクセス権	open access
URI	https://hdl.handle.net/2115/97904
タイトル	Evaluation of artificial-intelligence-based liver segmentation and its application for longitudinal liver volume measurement
著者	Kimura, Rina ; Hirata, Kenji ; Tsuneta, Satonori ; Takenaka, Junki ; Watanabe, Shiro ; Abo, Daisuke ; Kudo, Kohsuke
著者名 Kimura, Rina
e-Rad_Researcher 30431365 著者名 Hirata, Kenji
e-Rad_Researcher 80944868 著者名 Tsuneta, Satonori
e-Rad_Researcher 20998603 著者名 Takenaka, Junki
e-Rad_Researcher 10802415 著者名 Watanabe, Shiro
e-Rad_Researcher 30399844 著者名 Abo, Daisuke
e-Rad_Researcher 10374232 著者名 Kudo, Kohsuke
言語	英語
キーワード	Liver
	Volumetric
	Computed tomography (CT)
	Artificial intelligence
	Neural networks
発行日	2025-06-10
出版者	Springer
収録物名	Abdominal Radiology
巻(号)	50(12)
ページ	6192-6200
抄録	Background Accurate liver-volume measurements from CT scans are essential for treatment planning, particularly in liver resection cases, to avoid postoperative liver failure. However, manual segmentation is time-consuming and prone to variability. Advancements in artificial intelligence (AI), specifically convolutional neural networks, have enhanced liver segmentation accuracy. We aimed to identify optimal CT phases for AI-based liver volume estimation and apply the model to track liver volume changes over time. We also evaluated temporal changes in liver volume in participants without liver disease. Methods In this retrospective, single-center study, we assessed the performance of an open-source AI-based liver segmentation model previously reported, using non-contrast and dynamic CT phases. The accuracy of the model was compared with that of expert radiologists. The Dice similarity coefficient (DSC) was calculated across various CT phases, including arterial, portal venous, and non-contrast, to validate the model. The model was then applied to a longitudinal study involving 39 patients without liver disease (527 CT scans) to examine age-related liver volume changes over 5 to 20 years. Results The model demonstrated high accuracy across all phases compared to manual segmentation. Among the CT phases, the highest DSC of 0.988 +/- 0.010 was in the arterial phase. The intraclass correlation coefficients for liver volume were also high, exceeding 0.9 for contrast-enhanced phases and 0.8 for non-contrast CT. In the longitudinal study, the model indicated an annual decrease of 0.95%. Conclusion This model provides high accuracy in liver segmentation across various CT phases and offers insights into age-related liver volume reduction. Measuring changes in liver volume may help with the early detection of diseases and the understanding of pathophysiology.
資源タイプ	学術雑誌論文
出版タイプ	Accepted Manuscript
権利情報	This version of the article has been accepted for publication, after peer review (when applicable) and is subject to Springer Nature’s AM terms of use, but is not the Version of Record and does not reflect post-acceptance improvements, or any corrections. The Version of Record is available online at: https://doi.org/10.1007/s00261-025-05050-3
PISSN	2366-004X
関連情報 (isVersionOf)	出版社版DOI https://doi.org/10.1007/s00261-025-05050-3