Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Artificial intelligence-aided CT segmentation for body composition analysis : a validation study

Borrelli, Pablo ; Kaboteh, Reza ; Enqvist, Olof ; Ulén, Johannes LU ; Trägårdh, Elin LU ; Kjölhede, Henrik LU and Edenbrandt, Lars LU (2021) In European Radiology Experimental 5(1).
Abstract

Background: Body composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images. Methods: Ethical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a... (More)

Background: Body composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images. Methods: Ethical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a median interval between the studies of 3 days. Manual segmentations in a single CT slice were used for comparison. The accuracy was measured as overlap between the automated and manual segmentations. Results: The accuracy of the AI method was 0.96 for SAT and 0.94 for muscle. The average differences in volumes were significantly lower than the corresponding differences in areas in a single CT slice: 1.8% versus 5.0% (p < 0.001) for SAT and 1.9% versus 3.9% (p < 0.001) for muscle. The 95% confidence intervals for predicted volumes in an individual subject from the corresponding single CT slice areas were in the order of ± 20%. Conclusions: The AI-based tool for quantification of SAT and muscle volumes showed high accuracy and reproducibility and provided a body composition analysis that is more relevant than manual analysis of a single CT slice.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; ; and
organization
publishing date
type
Contribution to journal
publication status
published
subject
keywords
Body composition, computed), Muscles, Neural networks (computer), Subcutaneous fat, Tomography (x-ray
in
European Radiology Experimental
volume
5
issue
1
article number
11
publisher
Springer
external identifiers
  • pmid:33694046
  • scopus:85102358697
ISSN
2509-9280
DOI
10.1186/s41747-021-00210-8
language
English
LU publication?
yes
id
d92f3b81-03cc-40a7-9f32-872248f3d924
date added to LUP
2021-03-23 07:53:30
date last changed
2024-06-13 09:15:03
@article{d92f3b81-03cc-40a7-9f32-872248f3d924,
  abstract     = {{<p>Background: Body composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images. Methods: Ethical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a median interval between the studies of 3 days. Manual segmentations in a single CT slice were used for comparison. The accuracy was measured as overlap between the automated and manual segmentations. Results: The accuracy of the AI method was 0.96 for SAT and 0.94 for muscle. The average differences in volumes were significantly lower than the corresponding differences in areas in a single CT slice: 1.8% versus 5.0% (p &lt; 0.001) for SAT and 1.9% versus 3.9% (p &lt; 0.001) for muscle. The 95% confidence intervals for predicted volumes in an individual subject from the corresponding single CT slice areas were in the order of ± 20%. Conclusions: The AI-based tool for quantification of SAT and muscle volumes showed high accuracy and reproducibility and provided a body composition analysis that is more relevant than manual analysis of a single CT slice.</p>}},
  author       = {{Borrelli, Pablo and Kaboteh, Reza and Enqvist, Olof and Ulén, Johannes and Trägårdh, Elin and Kjölhede, Henrik and Edenbrandt, Lars}},
  issn         = {{2509-9280}},
  keywords     = {{Body composition; computed); Muscles; Neural networks (computer); Subcutaneous fat; Tomography (x-ray}},
  language     = {{eng}},
  number       = {{1}},
  publisher    = {{Springer}},
  series       = {{European Radiology Experimental}},
  title        = {{Artificial intelligence-aided CT segmentation for body composition analysis : a validation study}},
  url          = {{http://dx.doi.org/10.1186/s41747-021-00210-8}},
  doi          = {{10.1186/s41747-021-00210-8}},
  volume       = {{5}},
  year         = {{2021}},
}