BOA: A CT-Based Body and Organ Analysis for Radiologists at the Point of Care.
Journal
Investigative radiology
ISSN: 1536-0210
Titre abrégé: Invest Radiol
Pays: United States
ID NLM: 0045377
Informations de publication
Date de publication:
21 Nov 2023
21 Nov 2023
Historique:
medline:
23
11
2023
pubmed:
23
11
2023
entrez:
23
11
2023
Statut:
aheadofprint
Résumé
The study aimed to develop the open-source body and organ analysis (BOA), a comprehensive computed tomography (CT) image segmentation algorithm with a focus on workflow integration. The BOA combines 2 segmentation algorithms: body composition analysis (BCA) and TotalSegmentator. The BCA was trained with the nnU-Net framework using a dataset including 300 CT examinations. The CTs were manually annotated with 11 semantic body regions: subcutaneous tissue, muscle, bone, abdominal cavity, thoracic cavity, glands, mediastinum, pericardium, breast implant, brain, and spinal cord. The models were trained using 5-fold cross-validation, and at inference time, an ensemble was used. Afterward, the segmentation efficiency was evaluated on a separate test set comprising 60 CT scans. In a postprocessing step, a tissue segmentation (muscle, subcutaneous adipose tissue, visceral adipose tissue, intermuscular adipose tissue, epicardial adipose tissue, and paracardial adipose tissue) is created by subclassifying the body regions. The BOA combines this algorithm and the open-source segmentation software TotalSegmentator to have an all-in-one comprehensive selection of segmentations. In addition, it integrates into clinical workflows as a DICOM node-triggered service using the open-source Orthanc research PACS (Picture Archiving and Communication System) server to make the automated segmentation algorithms available to clinicians. The BCA model's performance was evaluated using the Sørensen-Dice score. Finally, the segmentations from the 3 different tools (BCA, TotalSegmentator, and BOA) were compared by assessing the overall percentage of the segmented human body on a separate cohort of 150 whole-body CT scans. The results showed that the BCA outperformed the previous publication, achieving a higher Sørensen-Dice score for the previously existing classes, including subcutaneous tissue (0.971 vs 0.962), muscle (0.959 vs 0.933), abdominal cavity (0.983 vs 0.973), thoracic cavity (0.982 vs 0.965), bone (0.961 vs 0.942), and an overall good segmentation efficiency for newly introduced classes: brain (0.985), breast implant (0.943), glands (0.766), mediastinum (0.880), pericardium (0.964), and spinal cord (0.896). All in all, it achieved a 0.935 average Sørensen-Dice score, which is comparable to the one of the TotalSegmentator (0.94). The TotalSegmentator had a mean voxel body coverage of 31% ± 6%, whereas BCA had a coverage of 75% ± 6% and BOA achieved 93% ± 2%. The open-source BOA merges different segmentation algorithms with a focus on workflow integration through DICOM node integration, offering a comprehensive body segmentation in CT images with a high coverage of the body volume.
Identifiants
pubmed: 37994150
doi: 10.1097/RLI.0000000000001040
pii: 00004424-990000000-00176
doi:
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Informations de copyright
Copyright © 2023 Wolters Kluwer Health, Inc. All rights reserved.
Déclaration de conflit d'intérêts
Conflicts of interest and sources of funding: J.H. received financial support from the German Research Foundation (DFG) funded by the Clinician Scientist Academy of the University Hospital Essen (FU 356/12-2). The authors declare no other conflict of interest.
Références
Schwartz FR, Samei E, Marin D. Exploiting the potential of photon-counting CT in abdominal imaging. Investig Radiol. 2023;58:488–498.
Li H, Zhang H, Johnson H, et al. Longitudinal subcortical segmentation with deep learning. Proc SPIE Int Soc Opt Eng. 2021;11596:115960D.
Wong J, Huang V, Wells D, et al. Implementation of deep learning-based auto-segmentation for radiotherapy planning structures: a workflow study at two cancer centers. Radiat Oncol. 2021;16:101.
Lenchik L, Heacock L, Weaver AA, et al. Automated segmentation of tissues using CT and MRI: a systematic review. Acad Radiol. 2019;26:1695–1706.
Koitka S, Gudlin P, Theysohn JM, et al. Fully automated preoperative liver volumetry incorporating the anatomical location of the central hepatic vein. Sci Rep. 2022;12:16479.
Kart T, Fischer M, Küstner T, et al. Deep learning-based automated abdominal organ segmentation in the UK biobank and German National Cohort Magnetic Resonance Imaging Studies. Investig Radiol. 2021;56:401–408.
Neves CA, Tran ED, Kessler IM, et al. Fully automated preoperative segmentation of temporal bone structures from clinical CT scans. Sci Rep. 2021;11:116.
Meddeb A, Kossen T, Bressem KK, et al. Evaluation of a deep learning algorithm for automated spleen segmentation in patients with conditions directly or indirectly affecting the spleen. Tomogr Ann Arbor Mich. 2021;7:950–960.
Senthilvelan J, Jamshidi N. A pipeline for automated deep learning liver segmentation (PADLLS) from contrast enhanced CT exams. Sci Rep. 2022;12:15794.
Jodogne S. The Orthanc ecosystem for medical imaging. J Digit Imaging. 2018;31:341–352.
Koitka S, Kroll L, Malamutmann E, et al. Fully automated body composition analysis in routine CT imaging using 3D semantic segmentation convolutional neural networks. Eur Radiol. 2021;31:1795–1804.
Wasserthal J, Breit H-C, Meyer MT, et al. TotalSegmentator: robust segmentation of 104 anatomic structures in CT images. Radiol Artif Intell. 2023;e230024.
Isensee F, Jaeger PF, Kohl SAA, et al. nnU-net: a self-configuring method for deep learning-based biomedical image segmentation. Nat Methods. 2021;18:203–211.
Kroll L, Mathew A, Baldini G, et al. CT-derived body composition analysis could possibly replace DXA and BIA to monitor NET-patients. Sci Rep. 2022;12:13419.
Surov A, Strobel A, Borggrefe J, et al. Low skeletal muscle mass predicts treatment response in oncology: a meta-analysis. Eur Radiol. 2023;33:6426–6437.
Hosch R, Kattner S, Berger MM, et al. Biomarkers extracted by fully automated body composition analysis from chest CT correlate with SARS-CoV-2 outcome severity. Sci Rep. 2022;12:16411.
Li X, Zhang N, Hu C, et al. CT-based radiomics signature of visceral adipose tissue for prediction of disease progression in patients with Crohn's disease: a multicentre cohort study. eClinicalMedicine. 2023;56:101805. Available at: https://www.thelancet.com/journals/eclinm/article/PIIS2589-5370(22)00534-X/fulltext. Accessed July 19, 2023.
Iacobellis G. Epicardial adipose tissue in contemporary cardiology. Nat Rev Cardiol. 2022;19:593–606.
Alatzides GL, Haubold J, Steinberg HL, et al. Adipopenia in body composition analysis: a promising imaging biomarker and potential predictive factor for patients undergoing transjugular intrahepatic portosystemic shunt placement. Br J Radiol. 2023;96:20220863.
Savjani R. nnU-Net: further automating biomedical image autosegmentation. Radiol Imaging Cancer. 2021;3:e209039.
Lin D, Wang Z, Li H, et al. Automated measurement of pancreatic fat deposition on Dixon MRI using nnU-net. J Magn Reson Imaging JMRI. 2023;57:296–307.
Pettit RW, Marlatt BB, Corr SJ, et al. nnU-Net deep learning method for segmenting parenchyma and determining liver volume from computed tomography images. Ann Surg Open Perspect Surg Hist Educ Clin Approaches. 2022;3:e155.
Anon. celery/celery. 2023. Available at: https://github.com/celery/celery. Accessed July 18, 2023.
Anon. RabbitMQ: easy to use, flexible messaging and streaming—RabbitMQ. Available at: https://www.rabbitmq.com/. Accessed July 18, 2023.
NVIDIA Corporation. Triton inference server: an optimized cloud and edge inferencing solution. 2023. Available at: https://github.com/triton-inference-server/server. Accessed July 18, 2023.
Koitka S, Metz C, et al; Leo. razorx89/pydicom-seg: 0.4.1. 2023. Available at: https://zenodo.org/record/7646115. Accessed July 18, 2023.
Ziegler E, Urban T, Brown D, et al. Open health imaging foundation viewer: an extensible open-source framework for building Web-based imaging applications to support cancer research. JCO Clin Cancer Inform. 2020;4:336–345. Available at: https://ascopubs.org/doi/10.1200/CCI.19.00131. Accessed August 25, 2023.
doi: 10.1200/CCI.19.00131.
Dice LR. Measures of the amount of ecologic association between species. Ecology. 1945;26:297–302.
Huttenlocher DP, Klanderman GA, Rucklidge WJ. Comparing images using the Hausdorff distance. IEEE Trans Pattern Anal Mach Intell. 1993;15:850–863.
Dubuisson M-P, Jain AK. A modified Hausdorff distance for object matching. Proc 12th Int Conf Pattern Recognit. 1994;1:566–568. Available at: http://ieeexplore.ieee.org/document/576361/. Accessed September 3, 2023.
Yeghiazaryan V, Voiculescu I. Family of boundary overlap metrics for the evaluation of medical image segmentation. J Med Imaging (Bellingham). 2018;5:015006. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5817231/. Accessed September 1, 2023.
Yang M, Colak C, Chundru KK, et al. Automated knee cartilage segmentation for heterogeneous clinical MRI using generative adversarial networks with transfer learning. Quant Imaging Med Surg. 2022;12:2620633–2622633. Available at: https://qims.amegroups.org/article/view/89910. Accessed September 1, 2023.
Jin J, Zhu H, Zhang J, et al. Multiple U-net-based automatic segmentations and radiomics feature stability on ultrasound images for patients with ovarian cancer. Front Oncol. 2021;10:614201. Available at: https://www.frontiersin.org/articles/10.3389/fonc.2020.614201. Accessed September 1, 2023.
doi: 10.3389/fonc.2020.614201.
Kavur AE, Gezer NS, Barış M, et al. CHAOS challenge—combined (CT-MR) healthy abdominal organ segmentation. Med Image Anal. 2021;69:101950. Available at: https://www.sciencedirect.com/science/article/pii/S1361841520303145. Accessed September 1, 2023.
Shapiro SS, Wilk MB. An analysis of variance test for normality (complete samples)†. Biometrika. 1965;52(3–4):591–611.
Ross A, Willson VL. Paired samples t-test. In: Ross A, Willson VL, eds. Basic and Advanced Statistical Tests: Writing Results Sections and Creating Tables and Figures. Rotterdam, the Netherlands: SensePublishers; 2017:17–19. Available at: https://doi.org/10.1007/978-94-6351-086-8_4. Accessed September 4, 2023.
McKnight PE, Najab J. Mann-Whitney U test. In: The Corsini Encyclopedia of Psychology. John Wiley & Sons, Ltd; 2010:1–1. Available at: https://onlinelibrary.wiley.com/doi/abs/10.1002/9780470479216.corpsy0524. Accessed July 18, 2023.
Virtanen P, Gommers R, Oliphant TE, et al. SciPy 1.0: fundamental algorithms for scientific computing in Python. Nat Methods. 2020;17:261–272.
Anon. Cinematic rendering in medical imaging. Available at: https://www.siemens-healthineers.com/digital-health-solutions/cinematic-rendering. Accessed July 18, 2023.
Sun M, Lu L, Hameed IA, et al. Detecting small anatomical structures in 3D knee MRI segmentation by fully convolutional networks. Appl Sci. 2022;12:283. Available at: https://www.mdpi.com/2076-3417/12/1/283. Accessed August 25, 2023.
Kwon K, Hwang D, Oh D, et al. CT-free quantitative SPECT for automatic evaluation of %thyroid uptake based on deep-learning. EJNMMI Phys. 2023;10:20. Available at: https://doi.org/10.1186/s40658-023-00536-9. Accessed August 25, 2023.
doi: 10.1186/s40658-023-00536-9.
Hussein S, Green A, Watane A, et al. Automatic segmentation and quantification of white and brown adipose tissues from PET/CT scans. IEEE Trans Med Imaging. 2017;36:734–744.
Lee SJ, Liu J, Yao J, et al. Fully automated segmentation and quantification of visceral and subcutaneous fat at abdominal CT: application to a longitudinal adult screening cohort. Br J Radiol. 2018;91:20170968. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6223139/. Accessed August 25, 2023.
Nowak S, Faron A, Luetkens JA, et al. Fully automated segmentation of connective tissue compartments for CT-based body composition analysis: a deep learning approach. Investig Radiol. 2020;55:357–366.
Nowak S, Theis M, Wichtmann BD, et al. End-to-end automated body composition analyses with integrated quality control for opportunistic assessment of sarcopenia in CT. Eur Radiol. 2022;32:3142–3151. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9038788/. Accessed August 25, 2023.
Castagnoli F, Doran S, Lunn J, et al. Splenic volume as a predictor of treatment response in patients with non-small cell lung cancer receiving immunotherapy. PLoS One. 2022;17:e0270950.
Khoshpouri P, Hazhirkarzar B, Ameli S, et al. Quantitative spleen and liver volume changes predict survival of patients with primary sclerosing cholangitis. Clin Radiol. 2019;74:734.e13–734.e20.
Surov A, Wienke A, Gutzmer R, et al. Time to include sarcopenia into the oncological routine. Eur J Cancer Oxf Engl 1990. 2023;190:112939.
Tezze C, Amendolagine FI, Nogara L, et al. A combination of metformin and galantamine exhibits synergistic benefits in the treatment of sarcopenia. JCI Insight. 2023;8:e168787.
Yoshida S, Shiraishi R, Nakayama Y, et al. Can nutrition contribute to a reduction in sarcopenia, frailty, and comorbidities in a super-aged society? Nutrients. 2023;15:2991.
Ito T, Tanemura A, Kuramitsu T, et al. Spleen volume is a predictor of posthepatectomy liver failure and short-term mortality for hepatocellular carcinoma. Langenbeck's Arch Surg. 2023;408:297.
Winder M, Owczarek AJ, Chudek J, et al. Are we overdoing it? Changes in diagnostic imaging workload during the years 2010-2020 including the impact of the SARS-CoV-2 pandemic. Healthc Basel Switz. 2021;9:1557.
Peng Y-C, Lee W-J, Chang Y-C, et al. Radiologist burnout: trends in medical imaging utilization under the national health insurance system with the universal code bundling strategy in an academic tertiary medical centre. Eur J Radiol. 2022;157:110596.
Sexauer R, Yang S, Weikert T, et al. Automated detection, segmentation, and classification of pleural effusion from computed tomography scans using machine learning. Investig Radiol. 2022;57:552–559.
Toda N, Hashimoto M, Arita Y, et al. Deep learning algorithm for fully automated detection of small (≤4 cm) renal cell carcinoma in contrast-enhanced computed tomography using a multicenter database. Investig Radiol. 2022;57:327–333.
Thomas MF, Kofler F, Grundl L, et al. Improving automated glioma segmentation in routine clinical use through artificial intelligence-based replacement of missing sequences with synthetic magnetic resonance imaging scans. Investig Radiol. 2022;57:187–193.
Edwards K, Chhabra A, Dormer J, et al. Abdominal muscle segmentation from CT using a convolutional neural network. Proc SPIE Int Soc Opt Eng. 2020;11317:113170L. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC7309562/. Accessed August 25, 2023.
Park HJ, Shin Y, Park J, et al. Development and validation of a deep learning system for segmentation of abdominal muscle and fat on computed tomography. Korean J Radiol. 2020;21:88–100.
Rister B, Yi D, Shivakumar K, et al. CT-ORG, a new dataset for multiple organ segmentation in computed tomography. Sci Data. 2020;7:381. Available at: https://www.nature.com/articles/s41597-020-00715-8. Accessed August 25, 2023.
Hänsch A, Schwier M, Gass T, et al. Evaluation of deep learning methods for parotid gland segmentation from CT images. J Med Imaging. 2019;6:011005. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6165912/. Accessed August 25, 2023.
Park J, Lee JS, Oh D, et al. Quantitative salivary gland SPECT/CT using deep convolutional neural networks. Sci Rep. 2021;11:7842. Available at: https://www.nature.com/articles/s41598-021-87497-0. Accessed August 25, 2023.
Benčević M, Habijan M, Galić I. Epicardial adipose tissue segmentation from CT images with a semi-3D neural network. In: 2021 International Symposium ELMAR. 2021:87–90.
Yang J, Veeraraghavan H, Armato SG, et al. Autosegmentation for thoracic radiation treatment planning: a grand challenge at AAPM 2017. Med Phys. 2018;45:4568–4581. Available at: https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6714977/. Accessed August 25, 2023.
Diniz JOB, Diniz PHB, Valente TLA, et al. Spinal cord detection in planning CT for radiotherapy through adaptive template matching, IMSLIC and convolutional neural networks. Comput Methods Prog Biomed. 2019;170:53–67. Available at: https://www.sciencedirect.com/science/article/pii/S0169260718313580. Accessed August 25, 2023.
Peng Z, Fang X, Yan P, et al. A method of rapid quantification of patient-specific organ doses for CT using deep-learning-based multi-organ segmentation and GPU-accelerated Monte Carlo dose computing. Med Phys. 2020;47:2526–2536.