Deep Learning-Based Fully Automated Segmentation of Regional Muscle Volume and Spatial Intermuscular Fat Using CT

Rui Zhang; Aiting He; Wei Xia; Yongbin Su; Junming Jian; Yandong Liu; Zhe Guo; Wei Shi; Zhenguang Zhang; Bo He; Xiaoguang Cheng; Xin Gao; Yajun Liu; Ling Wang

doi:10.1016/j.acra.2023.06.009

Deep Learning-Based Fully Automated Segmentation of Regional Muscle Volume and Spatial Intermuscular Fat Using CT

Acad Radiol. 2023 Oct;30(10):2280-2289. doi: 10.1016/j.acra.2023.06.009. Epub 2023 Jul 8.

Authors

Rui Zhang¹, Aiting He², Wei Xia³, Yongbin Su⁴, Junming Jian³, Yandong Liu⁴, Zhe Guo⁴, Wei Shi³, Zhenguang Zhang⁵, Bo He⁵, Xiaoguang Cheng⁴, Xin Gao³, Yajun Liu⁶, Ling Wang⁷

Affiliations

¹ School of Biomedical Engineering (Suzhou), Division of Life Sciences and Medicine, University of Science and Technology of China, Hefei, Anhui, China (R.Z.); Medical Imaging Department, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China (R.Z., W.X., J.J., W.S., X.G.).
² Department of Radiology, Yuxi Third Hospital, Yuxi, China (A.H.).
³ Medical Imaging Department, Suzhou Institute of Biomedical Engineering and Technology, Chinese Academy of Sciences, Suzhou, China (R.Z., W.X., J.J., W.S., X.G.).
⁴ Department of Radiology, Beijing Jishuitan Hospital, Beijing 100035, China (Y.S., Y.L., Z.G., X.C., L.W.).
⁵ Department of Radiology, The First Affiliated Hospital of Kunming Medical University, Kunming, Yunnan, China (Z.Z., B.H.).
⁶ Department of Spine Surgery, Beijing Jishuitan Hospital, Beijing, China (Y.L.).
⁷ Department of Radiology, Beijing Jishuitan Hospital, Beijing 100035, China (Y.S., Y.L., Z.G., X.C., L.W.). Electronic address: doctorwl@bjmu.edu.cn.

PMID: 37429780
DOI: 10.1016/j.acra.2023.06.009

Abstract

Rationale and objectives: We aim to develop a CT-based deep learning (DL) system for fully automatic segmentation of regional muscle volume and measurement of the spatial intermuscular fat distribution of the gluteus maximus muscle.

Materials and methods: A total of 472 subjects were enrolled and randomly assigned to one of three groups: a training set, test set 1, and test set 2. For each subject in the training set and test set 1, we selected six slices of the CT images as the region of interest for manual segmentation by a radiologist. For each subject in test set 2, we selected all slices of the gluteus maximus muscle on the CT images for manual segmentation. The DL system was constructed using Attention U-Net and the Otsu binary thresholding method to segment the muscle and measure the fat fraction of the gluteus maximus muscle. The segmentation results of the DL system were evaluated using the Dice similarity coefficient (DSC), Hausdorff distance (HD), and the average surface distance (ASD) as metrics. Intraclass correlation coefficients (ICCs) and Bland-Altman plots were used to assess agreement in the measurements of fat fraction between the radiologist and the DL system.

Results: The DL system showed good segmentation performance on the two test sets, with DSCs of 0.930 and 0.873, respectively. The fat fraction of the gluteus maximus muscle measured by the DL system was in agreement with the radiologist (ICC=0.748).

Conclusion: The proposed DL system showed accurate, fully automated segmentation performance and good agreement with the radiologist at fat fraction evaluation, and can be further used for muscle evaluation.

Keywords: Deep learning; Fat fraction; Gluteus maximus muscle; Sarcopenia; Segmentation.

Publication types

Randomized Controlled Trial
Research Support, Non-U.S. Gov't

MeSH terms

Deep Learning*
Humans
Image Processing, Computer-Assisted / methods
Muscle, Skeletal / diagnostic imaging
Tomography, X-Ray Computed