Estimating 3-D whole-body composition from a chest CT scan

Abstract

Background: Estimating whole-body composition from limited region-computed tomography (CT) scans has many potential applications in clinical medicine; however, it is challenging.

Purpose: To investigate if whole-body composition based on several tissue types (visceral adipose tissue [VAT], subcutaneous adipose tissue [SAT], intermuscular adipose tissue [IMAT], skeletal muscle [SM], and bone) can be reliably estimated from a chest CT scan only.

Methods: A cohort of 97 lung cancer subjects who underwent both chest CT scans and whole-body positron emission tomography-CT scans at our institution were collected. We used our in-house software to automatically segment and quantify VAT, SAT, IMAT, SM, and bone on the CT images. The field-of-views of the chest CT scans and the whole-body CT scans were standardized, namely, from vertebra T1 to L1 and from C1 to the bottom of the pelvis, respectively. Multivariate linear regression was used to develop the computer models for estimating the volumes of whole-body tissues from chest CT scans. Subject demographics (e.g., gender and age) and lung volume were included in the modeling analysis. Ten-fold cross-validation was used to validate the performance of the prediction models. Mean absolute difference (MAD) and R-squared (R² ) were used as the performance metrics to assess the model performance.

Results: The R² values when estimating volumes of whole-body SAT, VAT, IMAT, total fat, SM, and bone from the regular chest CT scans were 0.901, 0.929, 0.900, 0.933, 0.928, and 0.918, respectively. The corresponding MADs (percentage difference) were 1.44 ± 1.21 L (12.21% ± 11.70%), 0.63 ± 0.49 L (29.68% ± 61.99%), 0.12 ± 0.09 L (16.20% ± 18.42%), 1.65 ± 1.40 L (10.43% ± 10.79%), 0.71 ± 0.68 L (5.14% ± 4.75%), and 0.17 ± 0.15 L (4.32% ± 3.38%), respectively.

Conclusion: Our algorithm shows promise in its ability to estimate whole-body compositions from chest CT scans. Body composition measures based on chest CT scans are more accurate than those based on vertebra third lumbar.

Keywords: body composition; chest; computed tomography; prediction models; whole-body.

FIGURE 1

Computed results of body tissues on a whole‐body positron emission tomography‐computed tomography (PET‐CT) scan: (a) the original CT image, (b) the manual annotations of the body tissues, and (c) the computerized/automated segmentations of the body tissues. (d) and (e) The three‐dimensional (3‐D) visualization of the five body tissues

FIGURE 2

The lung volume segmentation: (a) original computed tomography (CT) images, (b) the segmented right and left lung regions in overlay, and (c) the three‐dimensional (3‐D) visualization of the segmented lungs

FIGURE 3

Scatter plots of the five body tissue volumes ((a): SAT, (b): VAT, (c): IMAT, (d): total fat, (e) SM, and (f) bone) computed from whole‐body positron emission tomography‐computed tomography (PET‐CT) scans versus estimated volumes from the chest CT‐based models. IMAT, intermuscular adipose tissue; SAT, subcutaneous adipose tissue; SM, skeletal muscle; VAT, visceral adipose tissue

FIGURE 4

Scatter plots of the five body tissues ((a): SAT, (b): VAT, (c): IMAT, (d): total fat, (e) SM, and (f) bone) computed from whole‐body positron emission tomography‐computed tomography (PET‐CT) scans and body tissue areas predicted from the third lumbar (L3)‐based models. IMAT, intermuscular adipose tissue; SAT, subcutaneous adipose tissue; SM, skeletal muscle; VAT, visceral adipose tissue

FIGURE 5

The Bland–Altman plots showing the agreement between the measured values (unit: L) from the whole‐body computed tomography (CT) scans and the predicted values from the chest CT‐based model for different body tissues ((a): SAT, (b): VAT, (c): IMAT, (d): total fat, (e) SM, and (f) bone). The horizontal red line shows the mean of the differences (=bias) between the two methods. The green horizontal lines show the upper and lower 95% limits of agreement (=bias ± 1.96 × SD).

FIGURE 6

The Bland–Altman plots showing the agreement between the measured values (unit: L) from the whole‐body computed tomography (CT) scans and the predicted values (unit: L) from the third lumbar (L3)‐based model for different body ((a): SAT, (b): VAT, (c): IMAT, (d): total fat, (e) SM, and (f) bone). The horizontal red line shows the mean of the differences (=bias) between the two methods. The green horizontal lines show the upper and lower 95% limits of agreement (=bias ± 1.96 × SD).