Skip to main content

A Fully Automated Deep Learning Pipeline for Multi-Vertebral Level Quantification and Characterization of Muscle and Adipose Tissue on Chest CT Scans.

Publication ,  Journal Article
Bridge, CP; Best, TD; Wrobel, MM; Marquardt, JP; Magudia, K; Javidan, C; Chung, JH; Kalpathy-Cramer, J; Andriole, KP; Fintelmann, FJ
Published in: Radiology. Artificial intelligence
January 2022

Body composition on chest CT scans encompasses a set of important imaging biomarkers. This study developed and validated a fully automated analysis pipeline for multi-vertebral level assessment of muscle and adipose tissue on routine chest CT scans. This study retrospectively trained two convolutional neural networks on 629 chest CT scans from 629 patients (55% women; mean age, 67 years ± 10 [standard deviation]) obtained between 2014 and 2017 prior to lobectomy for primary lung cancer at three institutions. A slice-selection network was developed to identify an axial image at the level of the fifth, eighth, and 10th thoracic vertebral bodies. A segmentation network (U-Net) was trained to segment muscle and adipose tissue on an axial image. Radiologist-guided manual-level selection and segmentation generated ground truth. The authors then assessed the predictive performance of their approach for cross-sectional area (CSA) (in centimeters squared) and attenuation (in Hounsfield units) on an independent test set. For the pipeline, median absolute error and intraclass correlation coefficients for both tissues were 3.6% (interquartile range, 1.3%-7.0%) and 0.959-0.998 for the CSA and 1.0 HU (interquartile range, 0.0-2.0 HU) and 0.95-0.99 for median attenuation. This study demonstrates accurate and reliable fully automated multi-vertebral level quantification and characterization of muscle and adipose tissue on routine chest CT scans. Keywords: Skeletal Muscle, Adipose Tissue, CT, Chest, Body Composition Analysis, Convolutional Neural Network (CNN), Supervised Learning Supplemental material is available for this article. © RSNA, 2022.

Duke Scholars

Altmetric Attention Stats
Dimensions Citation Stats

Published In

Radiology. Artificial intelligence

DOI

EISSN

2638-6100

ISSN

2638-6100

Publication Date

January 2022

Volume

4

Issue

1

Start / End Page

e210080
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Bridge, C. P., Best, T. D., Wrobel, M. M., Marquardt, J. P., Magudia, K., Javidan, C., … Fintelmann, F. J. (2022). A Fully Automated Deep Learning Pipeline for Multi-Vertebral Level Quantification and Characterization of Muscle and Adipose Tissue on Chest CT Scans. Radiology. Artificial Intelligence, 4(1), e210080. https://doi.org/10.1148/ryai.210080
Bridge, Christopher P., Till D. Best, Maria M. Wrobel, J Peter Marquardt, Kirti Magudia, Cylen Javidan, Jonathan H. Chung, Jayashree Kalpathy-Cramer, Katherine P. Andriole, and Florian J. Fintelmann. “A Fully Automated Deep Learning Pipeline for Multi-Vertebral Level Quantification and Characterization of Muscle and Adipose Tissue on Chest CT Scans.Radiology. Artificial Intelligence 4, no. 1 (January 2022): e210080. https://doi.org/10.1148/ryai.210080.
Bridge CP, Best TD, Wrobel MM, Marquardt JP, Magudia K, Javidan C, et al. A Fully Automated Deep Learning Pipeline for Multi-Vertebral Level Quantification and Characterization of Muscle and Adipose Tissue on Chest CT Scans. Radiology Artificial intelligence. 2022 Jan;4(1):e210080.
Bridge, Christopher P., et al. “A Fully Automated Deep Learning Pipeline for Multi-Vertebral Level Quantification and Characterization of Muscle and Adipose Tissue on Chest CT Scans.Radiology. Artificial Intelligence, vol. 4, no. 1, Jan. 2022, p. e210080. Epmc, doi:10.1148/ryai.210080.
Bridge CP, Best TD, Wrobel MM, Marquardt JP, Magudia K, Javidan C, Chung JH, Kalpathy-Cramer J, Andriole KP, Fintelmann FJ. A Fully Automated Deep Learning Pipeline for Multi-Vertebral Level Quantification and Characterization of Muscle and Adipose Tissue on Chest CT Scans. Radiology Artificial intelligence. 2022 Jan;4(1):e210080.

Published In

Radiology. Artificial intelligence

DOI

EISSN

2638-6100

ISSN

2638-6100

Publication Date

January 2022

Volume

4

Issue

1

Start / End Page

e210080