Literature DB >> 33694046

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

Pablo Borrelli1, Reza Kaboteh2, Olof Enqvist3,4, Johannes Ulén3, Elin Trägårdh5, Henrik Kjölhede6,7, Lars Edenbrandt2,8.   

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 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.

Entities:  

Keywords:  Body composition; Muscles; Neural networks (computer); Subcutaneous fat; Tomography (x-ray; computed)

Mesh:

Year:  2021        PMID: 33694046      PMCID: PMC7947128          DOI: 10.1186/s41747-021-00210-8

Source DB:  PubMed          Journal:  Eur Radiol Exp        ISSN: 2509-9280


  26 in total

1.  Muscle segmentation in axial computed tomography (CT) images at the lumbar (L3) and thoracic (T4) levels for body composition analysis.

Authors:  Setareh Dabiri; Karteek Popuri; Elizabeth M Cespedes Feliciano; Bette J Caan; Vickie E Baracos; Mirza Faisal Beg
Journal:  Comput Med Imaging Graph       Date:  2019-05-09       Impact factor: 4.790

2.  Anthropometer3D: Automatic Multi-Slice Segmentation Software for the Measurement of Anthropometric Parameters from CT of PET/CT.

Authors:  Pierre Decazes; David Tonnelet; Pierre Vera; Isabelle Gardin
Journal:  J Digit Imaging       Date:  2019-04       Impact factor: 4.056

3.  Automated body composition analysis of clinically acquired computed tomography scans using neural networks.

Authors:  Michael T Paris; Puneeta Tandon; Daren K Heyland; Helena Furberg; Tahira Premji; Gavin Low; Marina Mourtzakis
Journal:  Clin Nutr       Date:  2020-01-22       Impact factor: 7.324

Review 4.  Imaging of sarcopenia: old evidence and new insights.

Authors:  Domenico Albano; Carmelo Messina; Jacopo Vitale; Luca Maria Sconfienza
Journal:  Eur Radiol       Date:  2019-12-13       Impact factor: 5.315

5.  Regional intra-subject variability in abdominal adiposity limits usefulness of computed tomography.

Authors:  Jerry R Greenfield; Katherine Samaras; Donald J Chisholm; Lesley V Campbell
Journal:  Obes Res       Date:  2002-04

6.  Body composition in patients with non-small cell lung cancer: a contemporary view of cancer cachexia with the use of computed tomography image analysis.

Authors:  Vickie E Baracos; Tony Reiman; Marina Mourtzakis; Ioannis Gioulbasanis; Sami Antoun
Journal:  Am J Clin Nutr       Date:  2010-02-17       Impact factor: 7.045

7.  Visceral adipose tissue: relations between single-slice areas and total volume.

Authors:  Wei Shen; Mark Punyanitya; ZiMian Wang; Dympna Gallagher; Marie-Pierre St-Onge; Jeanine Albu; Steven B Heymsfield; Stanley Heshka
Journal:  Am J Clin Nutr       Date:  2004-08       Impact factor: 7.045

8.  Sarcopenia is highly prevalent in patients undergoing surgery for gastric cancer but not associated with worse outcomes.

Authors:  Juul J W Tegels; Jeroen L A van Vugt; Kostan W Reisinger; Karel W E Hulsewé; Anton G M Hoofwijk; Joep P M Derikx; Jan H M B Stoot
Journal:  J Surg Oncol       Date:  2015-08-31       Impact factor: 3.454

9.  Preoperative sarcopenia is associated with poor overall survival in pancreatic cancer patients following pancreaticoduodenectomy.

Authors:  Yan-Chih Peng; Chien-Hui Wu; Yu-Wen Tien; Tzu-Pin Lu; Yu-Hsin Wang; Bang-Bin Chen
Journal:  Eur Radiol       Date:  2020-09-24       Impact factor: 5.315

10.  Body composition is associated with clinical outcomes in patients with non-dialysis-dependent chronic kidney disease.

Authors:  Ting-Yun Lin; Ching-Hsiu Peng; Szu-Chun Hung; Der-Cherng Tarng
Journal:  Kidney Int       Date:  2018-03       Impact factor: 10.612

View more
  4 in total

1.  Evaluation of AI-Based Segmentation Tools for COVID-19 Lung Lesions on Conventional and Ultra-low Dose CT Scans.

Authors:  Marco Aiello; Dario Baldi; Giuseppina Esposito; Marika Valentino; Marco Randon; Marco Salvatore; Carlo Cavaliere
Journal:  Dose Response       Date:  2022-04-06       Impact factor: 2.658

2.  Automated artificial intelligence-based analysis of skeletal muscle volume predicts overall survival after cystectomy for urinary bladder cancer.

Authors:  Thomas Ying; Pablo Borrelli; Lars Edenbrandt; Olof Enqvist; Reza Kaboteh; Elin Trägårdh; Johannes Ulén; Henrik Kjölhede
Journal:  Eur Radiol Exp       Date:  2021-11-19

Review 3.  The Value of Artificial Intelligence-Assisted Imaging in Identifying Diagnostic Markers of Sarcopenia in Patients with Cancer.

Authors:  Ying-Tzu Huang; Yi-Shan Tsai; Peng-Chan Lin; Yu-Min Yeh; Ya-Ting Hsu; Pei-Ying Wu; Meng-Ru Shen
Journal:  Dis Markers       Date:  2022-03-29       Impact factor: 3.434

4.  Concordance of Computed Tomography Regional Body Composition Analysis Using a Fully Automated Open-Source Neural Network versus a Reference Semi-Automated Program with Manual Correction.

Authors:  Sandra L Gomez-Perez; Yanyu Zhang; Cecily Byrne; Connor Wakefield; Thomas Geesey; Joy Sclamberg; Sarah Peterson
Journal:  Sensors (Basel)       Date:  2022-04-27       Impact factor: 3.576

  4 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.