AUTHOR=Lee Seungyeon , Shimbo Genya , Yokoyama Nozomu , Nakamura Kensuke , Togo Ren , Ogawa Takahiro , Haseyama Miki , Takiguchi Mitsuyoshi 

TITLE=Deep-learning-based automatic liver segmentation using computed tomography images in dogs

JOURNAL=Frontiers in Veterinary Science

VOLUME=Volume 12 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/veterinary-science/articles/10.3389/fvets.2025.1681820

DOI=10.3389/fvets.2025.1681820

ISSN=2297-1769

ABSTRACT=IntroductionDeep learning-based automated segmentation has significantly improved the efficiency and accuracy of human medicine applications. However, veterinary applications, particularly canine liver segmentation, remain limited. This study aimed to develop and validate a deep learning model based on a 3D U-Net architecture for automated liver segmentation in canine abdominal computed tomography (CT) scans.MethodsA total of 221 canine abdominal CT scans were analyzed, comprising 159 cases without hepatic masses and 62 cases with hepatic masses. The model was trained and evaluated using two separate datasets: one containing cases without hepatic masses (Experiment 1) and the other combining cases with and without hepatic masses (Experiment 2).ResultsBoth experiments demonstrated high segmentation performance, achieving mean Dice similarity coefficients of 0.926 (Experiment 1) and 0.929 (Experiment 2).DiscussionThe manual and predicted liver volumes showed excellent agreement, highlighting the potential clinical applicability of this approach.