End-to-end automated body composition analyses with integrated quality control for opportunistic assessment of sarcopenia in CT.

OBJECTIVES: To develop a pipeline for automated body composition analysis and skeletal muscle assessment with integrated quality control for large-scale application in opportunistic imaging. METHODS: First, a convolutional neural network for extraction of a single slice at the L3/L4 lumbar level was developed on CT scans of 240 patients applying the nnU-Net framework. Second, a 2D competitive dense fully convolutional U-Net for segmentation of visceral and subcutaneous adipose tissue (VAT, SAT), skeletal muscle (SM), and subsequent determination of fatty muscle fraction (FMF) was developed on single CT slices of 1143 patients. For both steps, automated quality control was integrated by a logistic regression model classifying the presence of L3/L4 and a linear regression model predicting the segmentation quality in terms of Dice score. To evaluate the performance of the entire pipeline end-to-end, body composition metrics, and FMF were compared to manual analyses including 364 patients from two centers. RESULTS: Excellent results were observed for slice extraction (z-deviation = 2.46 ± 6.20 mm) and segmentation (Dice score for SM = 0.95 ± 0.04, VAT = 0.98 ± 0.02, SAT = 0.97 ± 0.04) on the dual-center test set excluding cases with artifacts due to metallic implants. No data were excluded for end-to-end performance analyses. With a restrictive setting of the integrated segmentation quality control, 39 of 364 patients were excluded containing 8 cases with metallic implants. This setting ensured a high agreement between manual and fully automated analyses with mean relative area deviations of ΔSM = 3.3 ± 4.1%, ΔVAT = 3.0 ± 4.7%, ΔSAT = 2.7 ± 4.3%, and ΔFMF = 4.3 ± 4.4%. CONCLUSIONS: This study presents an end-to-end automated deep learning pipeline for large-scale opportunistic assessment of body composition metrics and sarcopenia biomarkers in clinical routine. KEY POINTS: • Body composition metrics and skeletal muscle quality can be opportunistically determined from routine abdominal CT scans. • A pipeline consisting of two convolutional neural networks allows an end-to-end automated analysis. • Machine-learning-based quality control ensures high agreement between manual and automatic analysis.

Fully Automated Segmentation of Connective Tissue Compartments for CT-Based Body Composition Analysis: A Deep Learning Approach.

OBJECTIVE: Body composition comprises prognostic information in patients with various malignancies and can be opportunistically determined from routine computed tomography (CT) scans. However, accurate assessment of patients with alterations, for example, due to ascites or anasarca, and accurate identification of intermuscular fat remain challenging. In this study, we aimed to develop a fully automated and highly accurate segmentation tool for connective tissue compartments from abdominal CT scans using the open-source Convolutional Neural Network (CNN) DeepMedic. MATERIALS AND METHODS: In this retrospective study, a CNN was developed using data of 1143 consecutive patients undergoing either preinterventional CT for transcatheter aortic valve implantation (TAVI) (82%) or diagnostic CT for liver cirrhosis with portosystemic shunting (PTSS) (18%). All analyses were performed on single-slice images at the L3/L4 level. The data were subdivided into subsets of training (70%), validation (15%), and test data (15%), balanced for TAVI and PTSS patients. To demonstrate the generalizability of the applied method with respect to nonspecific clinical routine data, the model with the highest performance in TAVI and PTSS patients was further tested on 100 randomly selected patients who underwent CT for routine diagnostic purposes at a hospital of maximum care, including critically ill patients. The applicability of the method to native CT examinations was additionally tested on 50 patients. RESULTS: Compared with the ground truth of the test data, the presented method achieved highly accurate segmentation results (subcutaneous adipose tissue [SAT], Dice score [DSC]: 0.98 ± 0.01; visceral adipose tissue [VAT], DSC: 0.96 ± 0.04; skeletal muscles [SM], DSC: 0.95 ± 0.02) and showed excellent generalizability on the routine CT diagnostic patients (SAT, DSC: 0.97 ± 0.04; VAT, DSC: 0.95 ± 0.05; SM, DSC: 0.95 ± 0.04) and also on native CT scans (SAT, DSC: 0.99 ± 0.01; VAT, DSC: 0.97 ± 0.03; SM, DSC: 0.97 ± 0.02). CONCLUSIONS: Fully automated determination of body composition based on CT can be performed with excellent results using the open-source CNN DeepMedic. The trained model is made usable for research by a deployable and sharable application.