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

被引:23
|
作者
Mai, Dinh Van Chi [1 ,2 ,7 ]
Drami, Ioanna T. [1 ,3 ]
Pring, Edward E. [1 ,2 ]
Gould, Laura [1 ,4 ]
Lung, Phillip [1 ,2 ]
Popuri, Karteek [5 ]
Chow, Vincent F. [6 ]
Beg, Mirza [6 ]
Athanasiou, Thanos T. [2 ]
Jenkins, John [1 ,2 ]
机构
[1] St Marks Hosp, St Marks Acad Inst, Dept Surg, London, England
[2] Imperial Coll, Dept Surg & Canc, London, England
[3] Imperial Coll, Dept Metab Digest & Reprod, London, England
[4] Univ Glasgow, Coll Med Vet & Life Sci, Sch Canc Sci, Glasgow, Scotland
[5] Mem Univ Newfoundland, Dept Comp Sci, St John, NF, Canada
[6] Simon Fraser Univ, Sch Engn Sci, Burnaby, BC, Canada
[7] Northwick Pk Hosp & Clin Res Ctr, St Marks Hosp, Dept Colorectal Surg, Harrow Rd, London HA1 3UJ, England
关键词
AI; Body composition measurement; Computed tomography; Deep learning; Sarcopenia; Segmentation; SUBCUTANEOUS ADIPOSE-TISSUE; SKELETAL-MUSCLE; ARTIFICIAL-INTELLIGENCE; SARCOPENIC OBESITY; PROGNOSTIC-FACTOR; CANCER; VALIDATION; IMAGES; PREDICTION; MORTALITY;
D O I
10.1002/jcsm.13310
中图分类号
R592 [老年病学]; C [社会科学总论];
学科分类号
03 ; 0303 ; 100203 ;
摘要
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.
引用
收藏
页码:1973 / 1986
页数:14
相关论文
共 50 条
  • [31] 3D deeply supervised network for automated segmentation of volumetric medical images
    Dou, Qi
    Yu, Lequan
    Chen, Hao
    Jin, Yueming
    Yang, Xin
    Qin, Jing
    Heng, Pheng-Ann
    MEDICAL IMAGE ANALYSIS, 2017, 41 : 40 - 54
  • [32] A device-agnostic shape model for automated body composition estimates from 3D optical scans
    Tian, Isaac Y.
    Wong, Michael C.
    Kennedy, Samantha
    Kelly, Nisa N.
    Liu, Yong E.
    Garber, Andrea K.
    Heymsfield, Steven B.
    Curless, Brian
    Shepherd, John A.
    MEDICAL PHYSICS, 2022, 49 (10) : 6395 - 6409
  • [33] MULTISPECTRAL COMPUTED-TOMOGRAPHY MICROSCOPE FOR 3-D MATERIAL ANALYSIS
    NAKAMURA, O
    KAWATA, S
    MINAMI, S
    APPLIED OPTICS, 1990, 29 (11): : 1671 - 1674
  • [34] Automated body composition estimation from device-agnostic 3D optical scans in pediatric populations
    Tian, Isaac Y.
    Wong, Michael C.
    Nguyen, William M.
    Kennedy, Samantha
    McCarthy, Cassidy
    Kelly, Nisa N.
    Liu, Yong E.
    Garber, Andrea K.
    Heymsfield, Steven B.
    Curless, Brian
    Shepherd, John A.
    CLINICAL NUTRITION, 2023, 42 (09) : 1619 - 1630
  • [35] 3d Lung Vessel Segmentation In Computed Tomography Angiography Images
    Ozkan, Haydar
    ISTANBUL UNIVERSITY-JOURNAL OF ELECTRICAL AND ELECTRONICS ENGINEERING, 2012, 12 (01): : 1437 - 1443
  • [36] Evaluation of a fully automated computed tomography image segmentation method for fast and accurate body composition measurements
    Dietz, Michelle, V
    Popuri, Karteek
    Janssen, Lars
    Ma, Da
    Chow, Vincent Tze Yang
    Lee, Hyunwoo
    Verhoef, Cornelis
    Madsen, Eva V. E.
    Beg, Mirza F.
    van Vugt, Jeroen L. A.
    NUTRITION, 2025, 129
  • [37] Quantitative Volumetric Breast Imaging with 3D Inverse Scatter Computed Tomography
    Andre, Michael
    Wiskin, James
    Borup, David
    Johnson, Steven
    Ojeda-Fournier, Haydee
    Olson, Linda
    2012 ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC), 2012, : 1110 - 1113
  • [38] DEMONSTRATION OF THE HILAR BILIARY CONFLUENCE USING 3D COMPUTED-TOMOGRAPHY CHOLANGIOGRAPHY
    SHINOHARA, Y
    MUNEMASA, R
    SEMINARS IN INTERVENTIONAL RADIOLOGY, 1995, 12 (02) : 138 - 145
  • [39] A machine learning approach relating 3D body scans to body composition in humans
    Pleuss, James D.
    Talty, Kevin
    Morse, Steven
    Kuiper, Patrick
    Scioletti, Michael
    Heymsfield, Steven B.
    Thomas, Diana M.
    EUROPEAN JOURNAL OF CLINICAL NUTRITION, 2019, 73 (02) : 200 - 208
  • [40] Automated 3D Reconstruction and Segmentation from Optical Coherence Tomography
    Eichel, Justin A.
    Bizheva, Kostadinka K.
    Clausi, David A.
    Fieguth, Paul W.
    COMPUTER VISION-ECCV 2010, PT III, 2010, 6313 : 44 - +