Comprehensive Validation of Automated Whole Body Skeletal Muscle, Adipose Tissue, and Bone Segmentation from 3D CT images for Body Composition Analysis: Towards Extended Body Composition

Abstract

Background The latest advances in computer-assisted precision medicine are making it feasible to move from populationwide models that are useful to discover aggregate patterns that hold for group-based analysis to patient-specific models that can drive patient-specific decisions with regard to treatment choices, and predictions of outcomes of treatment. Body Composition is recognized as an important driver and risk factor for a wide variety of diseases, as well as a predictor of individual patient-specific clinical outcomes to treatment choices or surgical interventions. 3D CT images are routinely acquired in the oncological worklows and deliver accurate rendering of internal anatomy and therefore can be used opportunistically to assess the amount of skeletal muscle and adipose tissue compartments. Powerful tools of artificial intelligence such as deep learning are making it feasible now to segment the entire 3D image and generate accurate measurements of all internal anatomy. These will enable the overcoming of the severe bottleneck that existed previously, namely, the need for manual segmentation, which was prohibitive to scale to the hundreds of 2D axial slices that made up a 3D volumetric image. Automated tools such as presented here will now enable harvesting whole-body measurements from 3D CT or MRI images, leading to a new era of discovery of the drivers of various diseases based on individual tissue, organ volume, shape, and functional status. These measurements were hitherto unavailable thereby limiting the field to a very small and limited subset. These discoveries and the potential to perform individual image segmentation with high speed and accuracy are likely to lead to the incorporation of these 3D measures into individual specific treatment planning models related to nutrition, aging, chemotoxicity, surgery and survival after the onset of a major disease such as cancer.Methods We developed a whole-body 3D CT segmentation method for body composition analysis. This method delivers accurate 3D segmentation of the bony tissue, the skeletal muscle, subcutaneous and visceral fat.Results Evaluation on 50 volumes in the evaluation dataset achieved an average dice coefficients of 0.980 for bone, 0.974 for skeletal muscle, 0.986 for SAT, and 0.960 for VAT, demonstrating the accurate performance of the proposed whole-body 3D tissue segmentation algorithm.Conclusion The validation presented in this paper confirms the feasibility of going beyond 2D single-slice based tissue area measurements to full 3D measurements of volumes and texture for these tissues as well as other internal organ volumes, shape, location, texture and radiomic texture features in the body. Recent advances in machine/deep learning are capable of not only providing these measurements, but can also provide the necessary statistical models to learn the importance of each of these measurements in developing individual specific models of patient outcomes. This is a necessary step to unleash the full power of AI into supporting new and personali...

Nascent to novel methods to evaluate malnutrition and frailty in the surgical patient

“…Finally, a new approach is the fully automated, multiple-tissue, multiple-organ, three-dimensional segmentation and assessment by a commercially available software (Figure 8). 73 In this software program that runs locally on a desktop or laptop computer, all available crosssectional axial slices obtained from a CT image are analyzed and segmented, and each slice is annotated by its vertebral level. A complete automated analysis of the volume of all body composition components such as skeletal muscle, visceral adipose tissue, subcutaneous adipose tissue, and intramuscular adipose tissue by each F I G U R E 7 (A) Multivariate odds ratio from studies exploring the association of myosteatosis with poor clinical outcomes (excluding survival) in the surgical context.…”

“…F I G U R E 8 Three-dimensional, fully automated body composition imaging analysis from computerized tomography (CT) using DAFS-the data analysis facilitation suite by Voronoi Health Analytics Inc, Canada 73. DAFS can segment any field of view of CT images from head to toe from contrast and noncontrast images and low-dose and conventional-dose images in both adults and children.…”

Unsupervised Domain Adaptation for Vertebrae Detection and Identification in 3D CT Volumes Using a Domain Sanity Loss

“…Training such models in a supervised manner requires labels. Depending on the specific task, labeling a single 3D scan on the pixel level can take an expert up to two weeks [ 32 ]. Considering that many applications require several hundred samples, one can conclude that labeling a complete data set is almost prohibitively labor-intensive [ 33 , 34 ], setting harsh limits to AI democratization.…”

Automated CT Analysis of Body Composition as a Frailty Biomarker in Abdominal Surgery

“…Next, curated scans are processed via nonlinear machine learning algorithms to provide (1) multislice segmentation of multiple organs and tissues and (2) vertebral bone annotation in each image slice. 32 In prior validation against manual analysis, 32 average Dice similarity coefficients (spatial overlap index used for validation in image segmentation that quantifies overlap at the pixel or voxel level) were 0.97 for skeletal muscle, 0.99 for subcutaneous adipose tissue, and 0.96 for visceral adipose tissue, and errors in annotation of slice based on vertebral levels were small.…”