External validation of a deep learning model for automatic segmentation of skeletal muscle and adipose tissue on abdominal CT images
British Journal of Radiology, vol. 97, pp. 2015–2023
Abstract
OBJECTIVES: Body composition assessment using CT images at the L3-level is increasingly applied in cancer research and has been shown to be strongly associated with long-term survival. Robust high-throughput automated segmentation is key to assess large patient cohorts and to support implementation of body composition analysis into routine clinical practice. We trained and externally validated a deep learning neural network (DLNN) to automatically segment L3-CT images. METHODS: Expert-drawn segmentations of visceral and subcutaneous adipose tissue (VAT/SAT) and skeletal muscle (SM) of L3-CT-images of 3187 patients undergoing abdominal surgery were used to train a DLNN. The external validation cohort was comprised of 2535 patients with abdominal cancer. DLNN performance was evaluated with (geometric) dice similarity (DS) and Lin's concordance correlation coefficient. RESULTS: There was a strong concordance between automatic and manual segmentations with median DS for SM, VAT, and SAT of 0.97 (IQR: 0.95-0.98), 0.98 (IQR: 0.95-0.98), and 0.95 (IQR: 0.92-0.97), respectively. Concordance correlations were excellent: SM 0.964 (0.959-0.968), VAT 0.998 (0.998-0.998), and SAT 0.992 (0.991-0.993). Bland-Altman metrics indicated only small and clinically insignificant systematic offsets; SM radiodensity: 0.23 Hounsfield units (0.5%), SM: 1.26 cm2.m-2 (2.8%), VAT: -1.02 cm2.m-2 (1.7%), and SAT: 3.24 cm2.m-2 (4.6%). CONCLUSION: A robustly-performing and independently externally validated DLNN for automated body composition analysis was developed. ADVANCES IN KNOWLEDGE: This DLNN was successfully trained and externally validated on several large patient cohorts. The trained algorithm could facilitate large-scale population studies and implementation of body composition analysis into clinical practice.
Authors 29
-
David P.J. van Dijk corresponding
Maastricht University Medical Centre · Maastricht University · Zuyderland Medisch Centrum
Affiliation as printed
Department of Surgery, Maastricht University Medical Center , Maastricht, 6200 MD,
Department of Surgery, Zuyderland Medical Centre , Geleen, 6162 BG,
NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University , Maastricht, 6229 ER,
-
Affiliation as printed
Department of Radiotherapy (MAASTRO), Maastricht University , Maastricht, Maastricht, 6229 ET,
GROW School for Oncology and Reproduction, Maastricht University , Maastricht, 6229 ER,
-
Maastricht University Medical Centre · Maastricht University
Affiliation as printed
Department of Surgery, Maastricht University Medical Center , Maastricht, 6200 MD,
NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University , Maastricht, 6229 ER,
-
Maastricht University Medical Centre · Maastricht University
Affiliation as printed
Department of Radiology, Maastricht University Medical Center , Maastricht, Maastricht, 6200 MD,
GROW School for Oncology and Reproduction, Maastricht University , Maastricht, 6229 ER,
-
Glasgow Royal Infirmary · University of Glasgow
Affiliation as printed
Academic Unit of Surgery, School of Medicine, University of Glasgow, Glasgow Royal Infirmary , Glasgow, Glasgow, G31 2ER,
-
Glasgow Royal Infirmary · University of Glasgow
Affiliation as printed
West of Scotland Pancreatic Unit, Glasgow Royal Infirmary , Glasgow, Glasgow, G12 0YN,
Wolfson Wohl Cancer Research Centre, School of Cancer Sciences, University of Glasgow , Glasgow, Glasgow, G61 1BD,
-
Glasgow Royal Infirmary · University of Glasgow
Affiliation as printed
West of Scotland Pancreatic Unit, Glasgow Royal Infirmary , Glasgow, Glasgow, G12 0YN,
Wolfson Wohl Cancer Research Centre, School of Cancer Sciences, University of Glasgow , Glasgow, Glasgow, G61 1BD,
-
Glasgow Royal Infirmary · University of Glasgow
Affiliation as printed
Academic Unit of Surgery, School of Medicine, University of Glasgow, Glasgow Royal Infirmary , Glasgow, Glasgow, G31 2ER,
-
Affiliation as printed
Department of Surgery, Zuyderland Medical Centre , Geleen, 6162 BG,
-
Affiliation as printed
Academic Unit of Cancer Sciences, Faculty of Medicine, University of Southampton , Southampton, Southampton, SO16 6YD,
-
Maastricht University Medical Centre · Maastricht University
Affiliation as printed
Department of Surgery, Maastricht University Medical Center , Maastricht, 6200 MD,
NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University , Maastricht, 6229 ER,
-
Affiliation as printed
Department of Radiotherapy (MAASTRO), Maastricht University , Maastricht, Maastricht, 6229 ET,
GROW School for Oncology and Reproduction, Maastricht University , Maastricht, 6229 ER,
-
Affiliation as printed
Department of Radiotherapy (MAASTRO), Maastricht University , Maastricht, Maastricht, 6229 ET,
GROW School for Oncology and Reproduction, Maastricht University , Maastricht, 6229 ER,
-
Maastricht University Medical Centre · Maastricht University · Universitätsklinikum Aachen
Affiliation as printed
Department of General, Visceral and Transplant Surgery, University Hospital Aachen , Aachen, 52074,
Department of Surgery, Maastricht University Medical Center , Maastricht, 6200 MD,
NUTRIM School of Nutrition and Translational Research in Metabolism, Maastricht University , Maastricht, 6229 ER,
Cited by 22 stored of 22
No patents citing this paper on Lens.org (checked 2026-10-06).