pISSN 3022-6783
eISSN 3022-7712

View

Article View

Korean J Transplant 2022; 36(Suppl 1): S92-S92

Published online November 17, 2022

https://doi.org/10.4285/ATW2022.F-2116

© The Korean Society for Transplantation

AI model for the segmentation of skeletal muscle, visceral and subcutaneous fat at L3 level using donor CT

Yunyoung Jang1, Eun-Ah Jo2, Jaehee Chun3, Seonggong Moon3, Jin Sung Kim3, Ahram Han2, Jongwon Ha2, Hajeong Lee1, Yong Chul Kim1, Sangil Min2

1Department of Nephrology, Seoul National University Hospital, Seoul, Korea
2Department of Transplantation Surgery, Seoul National University Hospital, Seoul, Korea
3Department of Radiation Oncology, Severance Hospital, Yonsei University College of Medicine, Seoul, Korea

Correspondence to: Sangil Min
E-mail:surgeonmsi@gmail.com

Abstract

Background: Although the L3 skeletal muscle index is accepted as a surrogate marker of sarcopenia and associated vulnerability, the effects of sarcopenia in kidney donors is not well defined. The purpose of this study was to develop and validate an automated method to quantify the skeletal muscle, visceral and subcutaneous fat from an L3 slice on contrast-enhanced abdominal CT images of kidney donors.
Methods: The predonation arterial phase CT DICOM images of living kidney donors were downloaded and uploaded to 'OncoStudio' (OncoSoft Inc., Seoul, South Korea), which was used as the AI-based auto-segmentation tool. The AI model within the OncoStudio has a U-Net structure based on a 3D Dense block and automatically proceeds to CT site detection and segmentation without clicking by humans. For this study, a total of 41 datasets were used, 33 for training, one for validation, and seven for independent testing.
Results: The consistency between manually segmented volumes and automatically segmented volumes based on AI was evaluated. The average of dice similarity coefficient (DSC) representing the degree of agreement between 3D volumes was 0.92; skeletal muscle: 0.92, subcutaneous fat: 0.97, visceral fat: 0.86. The average The Hausdorff distances 95% (HD95) representing the lower 95% distance between 3D surface points were 8.42, 3.81, and 1.72 mm, respectively.
Conclusions: An automated method for measuring volume of muscle and fats at L3 level was successfully developed. This auto-segmentation program can be easily used for prognostic evaluation including donor's sarcopenia and adult diseases.