Artificial intelligence-aided CT segmentation for body composition analysis: a validation study

Abstract

Background: Body composition is associated with survival outcome in oncological patients, but it is not routinely calculated. Manual segmentation of subcutaneous adipose tissue (SAT) and muscle is time-consuming and therefore limited to a single CT slice. Our goal was to develop an artificial-intelligence (AI)-based method for automated quantification of three-dimensional SAT and muscle volumes from CT images.

Methods: Ethical approvals from Gothenburg and Lund Universities were obtained. Convolutional neural networks were trained to segment SAT and muscle using manual segmentations on CT images from a training group of 50 patients. The method was applied to a separate test group of 74 cancer patients, who had two CT studies each with a median interval between the studies of 3 days. Manual segmentations in a single CT slice were used for comparison. The accuracy was measured as overlap between the automated and manual segmentations.

Results: The accuracy of the AI method was 0.96 for SAT and 0.94 for muscle. The average differences in volumes were significantly lower than the corresponding differences in areas in a single CT slice: 1.8% versus 5.0% (p < 0.001) for SAT and 1.9% versus 3.9% (p < 0.001) for muscle. The 95% confidence intervals for predicted volumes in an individual subject from the corresponding single CT slice areas were in the order of ± 20%.

Conclusions: The AI-based tool for quantification of SAT and muscle volumes showed high accuracy and reproducibility and provided a body composition analysis that is more relevant than manual analysis of a single CT slice.

Keywords: Body composition; Muscles; Neural networks (computer); Subcutaneous fat; Tomography (x-ray; computed).

Fig. 1

Manual and AI-based segmentations of SAT and muscle. Left: segmentation on a CT slice at L3 level: manual (a) and AI-based (b). Coronal slice showing the AI-based 3D segmentation from T11 to the hip bone (c). Measurements: manual areas, 186 cm² (SAT) and 170 cm² (muscle); AI-based areas, 184 cm² (SAT) and 158 cm² (muscle); AI-based volumes 6,832 cm³ (SAT) and 8,253 cm³ (muscle). AI Artificial intelligence, SAT Subcutaneous fat

Fig. 2

Relation between AI-based 3D volume and L3 slice 2D area for SAT (a) and muscle (b) for 148 computed tomography studies in 74 patients. 2D Two-dimensional, 3D Three-dimensional, AI Artificial intelligence, SAT Subcutaneous fat