{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T12:20:03Z","timestamp":1774009203478,"version":"3.50.1"},"reference-count":37,"publisher":"MDPI AG","issue":"3","license":[{"start":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T00:00:00Z","timestamp":1773792000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["J. Imaging"],"abstract":"<jats:p>Computed tomography (CT) at the third lumbar vertebra (L3) is widely used for muscle quantification, but manual segmentation is labor intensive. This study externally validates an AI model, trained on a public dataset, for automated L3 muscle segmentation using an independent cohort, including a subgroup analysis of subject characteristics (e.g., age and a history of cancer). The AI model was trained on 900 CT scans with expert annotations from a publicly available repository. Validation was performed on 232 PET CT scans from the University Hospital Brussels, each manually segmented by an expert. Segmentation post-processing employed a density-based clustering algorithm to discard arm muscles and Hounsfield unit (HU) thresholding to refine the muscle segmentation. Performance was assessed using the Dice Similarity Coefficient (DSC) and Segmentation Surface Error (SSE). The model achieved a median DSC of 0.978 and a median SSE of 3.863 cm2 across the validation set. At lower BMI values, the model was more prone to overestimation of muscle surface area. Most segmentation errors occurred in the abdominal wall muscles. Analysis showed no significant difference between arm positioning above the head and alongside the body, indicating robustness to minor artifacts from arm positioning. The AI model delivers accurate, automated L3 muscle segmentation, supporting larger-scale body composition studies. However, diminished accuracy at low BMI values and limited demographic diversity of the data highlight the need for broader validation.<\/jats:p>","DOI":"10.3390\/jimaging12030135","type":"journal-article","created":{"date-parts":[[2026,3,18]],"date-time":"2026-03-18T10:11:12Z","timestamp":1773828672000},"page":"135","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["External Validation of an Open-Source Model for Automated Muscle Segmentation in CT Imaging of Cancer Patients"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9029-576X","authenticated-orcid":false,"given":"Hendrik","family":"Erenstein","sequence":"first","affiliation":[{"name":"Department of Medical Imaging and Radiation Therapy, Hanze University of Applied Sciences, 9714 CA Groningen, The Netherlands"},{"name":"Department of Radiotherapy, University of Groningen, University Medical Centre Groningen, 9713 GZ Groningen, The Netherlands"},{"name":"Research Group Healthy Ageing, Allied Health Care and Nursing, Hanze University of Applied Sciences, 9747 AC Groningen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jona","family":"Van den Broeck","sequence":"additional","affiliation":[{"name":"Experimental Anatomy Research Group, Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education and Physiotherapy, Vrije Universiteit Brussel, 1050 Brussels, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Annemieke","family":"van der Heij-Meijer","sequence":"additional","affiliation":[{"name":"Department of Medical Imaging and Radiation Therapy, Hanze University of Applied Sciences, 9714 CA Groningen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wim P.","family":"Krijnen","sequence":"additional","affiliation":[{"name":"Research Group Healthy Ageing, Allied Health Care and Nursing, Hanze University of Applied Sciences, 9747 AC Groningen, The Netherlands"},{"name":"Bernoulli Institute for Mathematics, Computer Science and Artificial Intelligence, University of Groningen, 9700 AK Groningen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9692-9513","authenticated-orcid":false,"given":"Aldo","family":"Scafoglieri","sequence":"additional","affiliation":[{"name":"Experimental Anatomy Research Group, Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education and Physiotherapy, Vrije Universiteit Brussel, 1050 Brussels, Belgium"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3928-8075","authenticated-orcid":false,"given":"Harri\u00ebt","family":"Jager-Wittenaar","sequence":"additional","affiliation":[{"name":"Research Group Healthy Ageing, Allied Health Care and Nursing, Hanze University of Applied Sciences, 9747 AC Groningen, The Netherlands"},{"name":"Experimental Anatomy Research Group, Department of Physiotherapy, Human Physiology and Anatomy, Faculty of Physical Education and Physiotherapy, Vrije Universiteit Brussel, 1050 Brussels, Belgium"},{"name":"Radboud university medical center, Department of Gastroenterology and Hepatology, Dietetics, 6525 GA Nijmegen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0782-8498","authenticated-orcid":false,"given":"Martine","family":"Sealy","sequence":"additional","affiliation":[{"name":"Research Group Healthy Ageing, Allied Health Care and Nursing, Hanze University of Applied Sciences, 9747 AC Groningen, The Netherlands"},{"name":"Radboud university medical center, Department of Gastroenterology and Hepatology, Dietetics, 6525 GA Nijmegen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8995-1210","authenticated-orcid":false,"given":"Peter","family":"van Ooijen","sequence":"additional","affiliation":[{"name":"Department of Radiotherapy, University of Groningen, University Medical Centre Groningen, 9713 GZ Groningen, The Netherlands"},{"name":"Data Science Center in Health (DASH), University Medical Centre Groningen, 9713 GZ Groningen, The Netherlands"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,3,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"601","DOI":"10.1093\/ageing\/afz046","article-title":"Sarcopenia: Revised European consensus on definition and diagnosis","volume":"48","author":"Bahat","year":"2019","journal-title":"Age Ageing"},{"key":"ref_2","doi-asserted-by":"crossref","unstructured":"Beaudart, C., Zaaria, M., Pasleau, F., Reginster, J., and Bruy\u00e8re, O. (2017). Health Outcomes of Sarcopenia: A Systematic Review and Meta-Analysis. PLoS ONE, 12.","DOI":"10.1371\/journal.pone.0169548"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"645","DOI":"10.1002\/ncp.10787","article-title":"Structured presurgery prehabilitation for aged patients undergoing elective surgery significantly improves surgical outcomes and reduces cost: A nonrandomized sequential comparative prospective cohort study","volume":"37","author":"Koh","year":"2022","journal-title":"Nutr. Clin. Pract."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1155\/2024\/3018760","article-title":"Exploring the Potential of Treating Sarcopenia through Dietary Interventions","volume":"2024","author":"Srivastava","year":"2024","journal-title":"J. Food Biochem."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"S576","DOI":"10.1016\/j.clnesp.2021.09.103","article-title":"Correlation of skeletal muscle area and muscle attenuation between l3, c3, and t4 level in patients with cancer: Results from the body-convert study group","volume":"46","author":"Sealy","year":"2021","journal-title":"Clin. Nutr. ESPEN"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"112553","DOI":"10.1016\/j.nut.2024.112553","article-title":"Variations in vertebral muscle mass and muscle quality in adult patients with different types of cancer","volume":"128","author":"Sealy","year":"2024","journal-title":"Nutrition"},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"501","DOI":"10.1016\/j.clnu.2019.02.029","article-title":"Low muscle mass is associated with early termination of chemotherapy related to toxicity in patients with head and neck cancer","volume":"39","author":"Sealy","year":"2020","journal-title":"Clin. Nutr."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"115","DOI":"10.1152\/jappl.1998.85.1.115","article-title":"Cadaver validation of skeletal muscle measurement by magnetic resonance imaging and computerized tomography","volume":"85","author":"Mitsiopoulos","year":"1998","journal-title":"J. Appl. Physiol."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"24","DOI":"10.1007\/s00421-005-0061-0","article-title":"Prediction and validation of total and regional skeletal muscle mass by ultrasound in Japanese adults","volume":"96","author":"Sanada","year":"2006","journal-title":"Eur. J. Appl. Physiol."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"997","DOI":"10.1139\/H08-075","article-title":"A practical and precise approach to quantification of body composition in cancer patients using computed tomography images acquired during routine care","volume":"33","author":"Mourtzakis","year":"2008","journal-title":"Appl. Physiol. Nutr. Metab."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"317","DOI":"10.1093\/gerona\/gls168","article-title":"Variations of CT-Based Trunk Muscle Attenuation by Age, Sex, and Specific Muscle","volume":"68","author":"Anderson","year":"2013","journal-title":"J. Gerontol. Ser. A Biol. Sci. Med. Sci."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"109943","DOI":"10.1016\/j.ejrad.2021.109943","article-title":"Methodology, clinical applications, and future directions of body composition analysis using computed tomography (CT) images: A review","volume":"145","author":"Tolonen","year":"2021","journal-title":"Eur. J. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","unstructured":"Elhakim, T., Trinh, K., Mansur, A., Bridge, C., and Daye, D. (2023). Role of Machine Learning-Based CT Body Composition in Risk Prediction and Prognostication: Current State and Future Directions. Diagnostics, 13.","DOI":"10.3390\/diagnostics13050968"},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/j.compmedimag.2019.04.007","article-title":"Muscle segmentation in axial computed tomography (CT) images at the lumbar (L3) and thoracic (T4) levels for body composition analysis","volume":"75","author":"Dabiri","year":"2019","journal-title":"Comput. Med. Imaging Graph."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"e363","DOI":"10.1016\/j.crad.2022.01.036","article-title":"Fully automated deep-learning section-based muscle segmentation from CT images for sarcopenia assessment","volume":"77","author":"Islam","year":"2022","journal-title":"Clin. Radiol."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"1973","DOI":"10.1002\/jcsm.13310","article-title":"A systematic review of automated segmentation of 3D computed-tomography scans for volumetric body composition analysis","volume":"14","author":"Mai","year":"2023","journal-title":"J. Cachexia Sarcopenia Muscle"},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"110218","DOI":"10.1016\/j.ejrad.2022.110218","article-title":"Artificial intelligence for body composition and sarcopenia evaluation on computed tomography: A systematic review and meta-analysis","volume":"149","author":"Bedrikovetski","year":"2022","journal-title":"Eur. J. Radiol."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"1807","DOI":"10.21873\/invivo.12896","article-title":"Deep-learning-based Segmentation of Skeletal Muscle Mass in Routine Abdominal CT Scans","volume":"36","author":"Kreher","year":"2022","journal-title":"In Vivo"},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"112592","DOI":"10.1016\/j.nut.2024.112592","article-title":"Evaluation of a fully automated computed tomography image segmentation method for fast and accurate body composition measurements","volume":"129","author":"Dietz","year":"2025","journal-title":"Nutrition"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"109622","DOI":"10.1016\/j.compbiomed.2024.109622","article-title":"Multilabel segmentation and analysis of skeletal muscle and adipose tissue in routine abdominal CT scans","volume":"186","author":"Kreher","year":"2025","journal-title":"Comput. Biol. Med."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Isensee, F., Wald, T., Ulrich, C., Baumgartner, M., Roy, S., Maier-Hein, K., and Jaeger, P.F. (2024). nnU-Net Revisited: A Call for Rigorous Validation in 3D Medical Image Segmentation. arXiv.","DOI":"10.1007\/978-3-031-72114-4_47"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"203","DOI":"10.1038\/s41592-020-01008-z","article-title":"nnU-Net: A self-configuring method for deep learning-based biomedical image segmentation","volume":"18","author":"Isensee","year":"2021","journal-title":"Nat. Methods"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"483","DOI":"10.1038\/s41597-024-03337-6","article-title":"SAROS: A dataset for whole-body region and organ segmentation in CT imaging","volume":"11","author":"Koitka","year":"2024","journal-title":"Sci. Data"},{"key":"ref_24","unstructured":"Koitka, S., Baldini, G., Kroll, L., van Landeghem, N., Haubold, J., Sung Kim, M., Kleesiek, J., Nensa, F., and Hosch, R. (2023, December 28). SAROS\u2014A Large, Heterogeneous, and Sparsely Annotated Segmentation Dataset on CT Imaging Data. Available online: https:\/\/www.cancerimagingarchive.net\/analysis-result\/saros\/."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"32","DOI":"10.1002\/jpen.1440","article-title":"GLIM Criteria for the Diagnosis of Malnutrition: A Consensus Report from the Global Clinical Nutrition Community","volume":"43","author":"Jensen","year":"2019","journal-title":"J. Parenter. Enter. Nutr."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"159","DOI":"10.1016\/j.ejca.2019.11.015","article-title":"European consensus-based interdisciplinary guideline for melanoma. Part 2: Treatment\u2014Update 2019","volume":"126","author":"Garbe","year":"2020","journal-title":"Eur. J. Cancer"},{"key":"ref_27","first-page":"S289","article-title":"Esophageal cancer: Staging system and guidelines for staging and treatment","volume":"6","author":"Berry","year":"2014","journal-title":"J. Thorac. Dis."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e211S","DOI":"10.1378\/chest.12-2355","article-title":"Methods for staging non-small cell lung cancer: Diagnosis and management of lung cancer, 3rd ed: American College of Chest Physicians evidence-based clinical practice guidelines","volume":"143","author":"Silvestri","year":"2013","journal-title":"Chest"},{"key":"ref_29","first-page":"122","article-title":"Head and neck cancers\u2014Major changes in the American Joint Committee on cancer eighth edition cancer staging manual","volume":"67","author":"Lydiatt","year":"2017","journal-title":"CA Cancer J. Clin."},{"key":"ref_30","unstructured":"Scikit-Learn Developers (2024, December 17). Scikit-Learn (1.3.2) API Reference, DBSCAN. Available online: https:\/\/scikit-learn.org\/stable\/modules\/generated\/sklearn.cluster.DBSCAN.html."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"261","DOI":"10.1038\/s41592-019-0686-2","article-title":"SciPy 1.0: Fundamental algorithms for scientific computing in Python (1.10.1)","volume":"17","author":"Virtanen","year":"2020","journal-title":"Nat. Methods"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1038\/s41592-023-02150-0","article-title":"Understanding metric-related pitfalls in image analysis validation","volume":"21","author":"Reinke","year":"2024","journal-title":"Nat. Methods"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"195","DOI":"10.1038\/s41592-023-02150-0","article-title":"Metrics reloaded: Recommendations for image analysis validation","volume":"21","author":"Reinke","year":"2024","journal-title":"Nat. Methods"},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"1539","DOI":"10.1200\/JCO.2012.45.2722","article-title":"Cancer Cachexia in the Age of Obesity: Skeletal Muscle Depletion Is a Powerful Prognostic Factor, Independent of Body Mass Index","volume":"31","author":"Martin","year":"2013","journal-title":"J. Clin. Oncol."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"1635","DOI":"10.1007\/s00330-023-09911-7","article-title":"Adipose tissue composition determines its computed tomography radiodensity","volume":"34","author":"Zoabi","year":"2024","journal-title":"Eur. Radiol."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1111\/cpf.12422","article-title":"Skeletal muscle analyses: Agreement between non-contrast and contrast CT scan measurements of skeletal muscle area and mean muscle attenuation","volume":"38","author":"Werf","year":"2018","journal-title":"Clin. Physiol. Funct. Imaging"},{"key":"ref_37","first-page":"qxaf023","article-title":"Artificial intelligence in global health: An unfair future for health in Sub-Saharan Africa?","volume":"3","author":"Victor","year":"2025","journal-title":"Health Aff. Sch."}],"container-title":["Journal of Imaging"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/135\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T10:22:50Z","timestamp":1774002170000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2313-433X\/12\/3\/135"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,18]]},"references-count":37,"journal-issue":{"issue":"3","published-online":{"date-parts":[[2026,3]]}},"alternative-id":["jimaging12030135"],"URL":"https:\/\/doi.org\/10.3390\/jimaging12030135","relation":{},"ISSN":["2313-433X"],"issn-type":[{"value":"2313-433X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,18]]}}}