CoChat

A systematic review of automated segmentation of 3D computed-tomography scans for volumetric body composition analysis

Mai, Dinh Van Chi, Drami, Ioanna, Pring, Edward T., Gould, Laura E., Lung, Phillip, Popuri, Karteek, Chow, Vincent, Beg, Mirza F., Athanasiou, Thanos, Jenkins, John T., the BiCyCLE Research Group · 2023 · Journal of Cachexia, Sarcopenia and Muscle
Cited by 78

The DOI matches its Crossref record; 15 of the 15 references it cites were found in a registry or an index.

Abstract

Automated computed tomography (CT) scan segmentation (labelling of pixels according to tissue type) is now possible. This technique is being adapted to achieve three‐dimensional (3D) segmentation of CT scans, opposed to single L3‐slice alone. This systematic review evaluates feasibility and accuracy of automated segmentation of 3D CT scans for volumetric body composition (BC) analysis, as well as current limitations and pitfalls clinicians and researchers should be aware of. OVID Medline, Embase and grey literature databases up to October 2021 were searched. Original studies investigating automated skeletal muscle, visceral and subcutaneous AT segmentation from CT were included. Seven of the 92 studies met inclusion criteria. Variation existed in expertise and numbers of humans performing ground‐truth segmentations used to train algorithms. There was heterogeneity in patient characteristics, pathology and CT phases that segmentation algorithms were developed upon. Reporting of anatomical CT coverage varied, with confusing terminology. Six studies covered volumetric regional slabs rather than the whole body. One study stated the use of whole‐body CT, but it was not clear whether this truly meant head‐to‐fingertip‐to‐toe. Two studies used conventional computer algorithms. The latter five used deep learning (DL), an artificial intelligence technique where algorithms are similarly organized to brain neuronal pathways. Six of seven reported excellent segmentation performance (Dice similarity coefficients > 0.9 per tissue). Internal testing on unseen scans was performed for only four of seven algorithms, whilst only three were tested externally. Trained DL algorithms achieved full CT segmentation in 12 to 75 s versus 25 min for non‐DL techniques. DL enables opportunistic, rapid and automated volumetric BC analysis of CT performed for clinical indications. However, most CT scans do not cover head‐to‐fingertip‐to‐toe; further research must validate using common CT regions to estimate true whole‐body BC, with direct comparison to single lumbar slice. Due to successes of DL, we expect progressive numbers of algorithms to materialize in addition to the seven discussed in this paper. Researchers and clinicians in the field of BC must therefore be aware of pitfalls. High Dice similarity coefficients do not inform the degree to which BC tissues may be under‐ or overestimated and nor does it inform on algorithm precision. Consensus is needed to define accuracy and precision standards for ground‐truth labelling. Creation of a large international, multicentre common CT dataset with BC ground‐truth labels from multiple experts could be a robust solution.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1002/jcsm.13310

Cites

15 of 15 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

2 more claims about this paper

Create a free account to see every claim other papers make about this one.

See all claims — free account

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 15 references

Research works printed but not linked: 60

  1. 10.1016/j.afos.2021.03.002 · DOI
  2. 10.1097/SLA.0000000000002679 · DOI · Paper page
  3. 10.1016/j.chest.2019.04.115 · DOI · Paper page
  4. 10.3389/fonc.2019.01561 · DOI
  5. 10.1186/s12885-019-6169-0 · DOI · Paper page
  6. 10.1002/jcsm.13126 · DOI
  7. Guo Y, 2023, Association between sarcopenia and clinical outcomes in patients with hepatocellular carcinoma: an updated meta‐analysis, Scientific Reports, 13, 1
  8. 10.1136/ijgc-2020-001678 · DOI
  9. 10.1007/s00384-021-03839-4 · DOI · Paper page
  10. 10.1001/jamaoncol.2018.0137 · DOI · Paper page
  11. 10.1200/JCO.2012.45.2722 · DOI · Paper page
  12. 10.1016/0720-048X(93)90023-G · doi:10.1016/0720-048x(93)90023-g
  13. 10.1002/jcsm.12573 · DOI
  14. Kvist H, 1986, Adipose tissue volume determinations in women by computed tomography: technical considerations, Int J Obes (Lond), 10, 53
  15. 10.1093/ajcn/54.1.18 · DOI
  16. 10.1038/oby.2012.168 · DOI · Paper page
  17. MalietzisG CurrieAC AthanasiouT JohnsN AnyameneN Glynne‐JonesR et al.Influence of body composition profile on outcomes following colorectal cancer surgery.2016;103:572–580. · DOI · Paper page
  18. 10.1158/1078-0432.CCR-08-2242 · DOI · Paper page
  19. 10.1245/s10434-016-5188-1 · DOI
  20. 10.1002/jmri.24726 · DOI · Paper page
  21. 10.1371/journal.pone.0163332 · DOI · Paper page
  22. 10.1038/s41598-022-07556-y · DOI
  23. Covidence systematic review software Veritas Health Innovation Melbourne Australia. Available atwww.covidence.org
  24. 10.1117/1.JRS.15.041501 · doi:10.1117/1.jrs.15.041501
  25. 10.1016/j.ejso.2018.04.008 · doi:10.1016/j.ejso.2018.04.008
  26. 10.1186/s12880-015-0068-x · DOI · Paper page
  27. 10.1117/1.JMI.5.1.015006 · DOI · Paper page
  28. HuP HuoY KongD CarrJJ AbramsonRG HartleyKGet al.Automated characterization of body composition and frailty with clinically acquired CT. Computational Methods and Clinical Applications in Musculoskeletal Imaging: 5th International Workshop MSKI 2017 Held in Conjunction with MICCAI 2017 Quebec City QC Canada September 10 2017 Revised Selected Papers/Ben Glocker Jianhua Yao Toma 2018;10734:25‐35. · DOI
  29. 10.1007/s10278-019-00178-3 · DOI
  30. 10.1002/mp.14465 · DOI
  31. 10.1002/mp.14141 · DOI
  32. DaMa VincentChow KarteekPopuri Mirza FaisalBeg.Comprehensive validation of automated whole body skeletal muscle adipose tissue and bone segmentation from 3D CT images for body composition analysis: towards extended body composition. ArXiv. 2021;Preprint.
  33. KoitkaS KrollL MalamutmannE OezcelikA NensaF.Fully‐automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks. ArXiv 2021. · DOI · Paper page
  34. 10.1016/j.clnu.2021.06.025 · DOI
  35. Wang M, 2019, Label fusion method combining pixel greyscale probability for brain MR segmentation, Scientific Reports, 9, 1
  36. DingW LiL ZhuangX HuangL.Cross‐modality multi‐atlas segmentation using deep neural networks. Published online August 14 2020. · DOI
  37. 10.1136/bmjopen-2019-031018 · doi:10.1136/bmjopen-2019-031018
  38. 10.1016/j.euf.2021.03.013 · DOI
  39. 10.1055/s-0039-3400267 · DOI
  40. 10.2214/AJR.22.27749 · DOI · Paper page
  41. 10.21037/qims-21-370 · DOI
  42. 10.1111/j.1745-3984.1971.tb00916.x · DOI
  43. 10.1111/codi.15621 · DOI
  44. 10.1016/j.clnu.2022.03.016 · DOI
  45. 10.1016/j.jocd.2013.08.007 · DOI · Paper page
  46. 10.1002/crt2.53 · DOI
  47. 10.3389/fneur.2018.00679 · DOI · Paper page
  48. 10.1038/s41598-018-31911-7 · DOI · Paper page
  49. 10.3389/fonc.2022.772403 · DOI
  50. 10.1016/j.compbiomed.2021.104497 · DOI
  51. 10.1152/jappl.2000.89.2.599 · DOI
  52. 10.1016/S2589-7500(19)30123-2 · DOI · Paper page
  53. 10.1038/s41597-020-00715-8 · DOI
  54. 10.1016/j.media.2017.06.015 · DOI · Paper page
  55. Mesguich C, 2022, 18F‐FDG PET/CT and MRI in the management of multiple myeloma: a comparative review, Front Nucl Med, 12
  56. 10.1002/mp.15821 · DOI
  57. 10.1038/s41598-020-79471-z · DOI
  58. 10.1159/000480407 · DOI
  59. 10.1245/s10434-016-5385-y · DOI
  60. 10.1002/bjs.10063 · DOI · Paper page

Metadata

Authors
Mai, D. V. C., Drami, I., Pring, E. T., Gould, L. E., Lung, P., Popuri, K., Chow, V., Beg, M. F., Athanasiou, T., Jenkins, J. T., & the BiCyCLE Research Group
Affiliations
  • Department of Surgery St Mark's Academic Institute, St Mark's Hospital London UK
  • Department of Computer Science Memorial University of Newfoundland St Johns Canada
  • School of Engineering Science Simon Fraser University Burnaby Canada
  • Department of Surgery and Cancer Imperial College London UK
Venue
Journal of Cachexia, Sarcopenia and Muscle
Publisher
Wiley
Published
2023-08-10
Volume
14
Issue
5
Pages
1973-1986
ISSN
  • 2190-5991
  • 2190-6009
Cited by
78
References
15
Language
en

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: A systematic review of automated segmentation of 3D computed-tomography scans for volumetric body composition analysis. https://app.cochat.ai/papers/10.1002/jcsm.13310
The paper
Mai, D. V. C., Drami, I., Pring, E. T., Gould, L. E., Lung, P., Popuri, K., Chow, V., Beg, M. F., Athanasiou, T., Jenkins, J. T., & the BiCyCLE Research Group. (2023). A systematic review of automated segmentation of 3D computed-tomography scans for volumetric body composition analysis. Journal of Cachexia, Sarcopenia and Muscle. https://doi.org/10.1002/jcsm.13310

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.