Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Shangzhi Gu; Lixue Wang; Rong Han; Xiaohong Liu; Yizhe Wang; Ting Chen; Zhuozhao Zheng

doi:10.3389/fphys.2023.1092352

Detection of sarcopenia using deep learning-based artificial intelligence body part measure system (AIBMS)

Front Physiol. 2023 Jan 26:14:1092352. doi: 10.3389/fphys.2023.1092352. eCollection 2023.

Authors

Shangzhi Gu^{1

2}, Lixue Wang³, Rong Han¹, Xiaohong Liu¹, Yizhe Wang³, Ting Chen^{1

4}, Zhuozhao Zheng³

Affiliations

¹ Department of Computer Science and Technology, Institute for Artificial Intelligence, and BNRist, Tsinghua University, Beijing, China.
² School of Medicine, Tsinghua University, Beijing, China.
³ Department of Radiology, Beijing Tsinghua Changgung Hospital, School of Clinical Medicine, Tsinghua University, Beijing, China.
⁴ Department of Bioinformatics, Fujian Key Laboratory of Medical Bioinformatics, School of Medical Technology and Engineering, Fujian Medical University, Fuzhou, China.

Abstract

Background: Sarcopenia is an aging syndrome that increases the risks of various adverse outcomes, including falls, fractures, physical disability, and death. Sarcopenia can be diagnosed through medical images-based body part analysis, which requires laborious and time-consuming outlining of irregular contours of abdominal body parts. Therefore, it is critical to develop an efficient computational method for automatically segmenting body parts and predicting diseases. Methods: In this study, we designed an Artificial Intelligence Body Part Measure System (AIBMS) based on deep learning to automate body parts segmentation from abdominal CT scans and quantification of body part areas and volumes. The system was developed using three network models, including SEG-NET, U-NET, and Attention U-NET, and trained on abdominal CT plain scan data. Results: This segmentation model was evaluated using multi-device developmental and independent test datasets and demonstrated a high level of accuracy with over 0.9 DSC score in segment body parts. Based on the characteristics of the three network models, we gave recommendations for the appropriate model selection in various clinical scenarios. We constructed a sarcopenia classification model based on cutoff values (Auto SMI model), which demonstrated high accuracy in predicting sarcopenia with an AUC of 0.874. We used Youden index to optimize the Auto SMI model and found a better threshold of 40.69. Conclusion: We developed an AI system to segment body parts in abdominal CT images and constructed a model based on cutoff value to achieve the prediction of sarcopenia with high accuracy.

Keywords: abdomen; artificial intelligence; deep learning; sarcopenia; segmentation.

Grants and funding

This work is supported by the National Key R&D Program of China (2021YFF1201303), National Natural Science Foundation of China (grants 61872218 and 61721003), Guoqiang Institute of Tsinghua University, Tsinghua University Initiative Scientific Research Program, and Beijing National Research Center for Information Science and Technology (BNRist). The funders had no roles in study design, data collection and analysis, the decision to publish, and preparation of the manuscript.