AI-based volumetric six-tissue body composition quantification from CT cardiac attenuation scans for mortality prediction: a multicentre study

Abstract

Background: CT attenuation correction (CTAC) scans are routinely obtained during cardiac perfusion imaging, but currently only used for attenuation correction and visual calcium estimation. We aimed to develop a novel artificial intelligence (AI)-based approach to obtain volumetric measurements of chest body composition from CTAC scans and to evaluate these measures for all-cause mortality risk stratification.

Methods: We applied AI-based segmentation and image-processing techniques on CTAC scans from a large international image-based registry at four sites (Yale University, University of Calgary, Columbia University, and University of Ottawa), to define the chest rib cage and multiple tissues. Volumetric measures of bone, skeletal muscle, subcutaneous adipose tissue, intramuscular adipose tissue (IMAT), visceral adipose tissue (VAT), and epicardial adipose tissue (EAT) were quantified between automatically identified T5 and T11 vertebrae. The independent prognostic value of volumetric attenuation and indexed volumes were evaluated for predicting all-cause mortality, adjusting for established risk factors and 18 other body composition measures via Cox regression models and Kaplan-Meier curves.

Findings: The end-to-end processing time was less than 2 min per scan with no user interaction. Between 2009 and 2021, we included 11 305 participants from four sites participating in the REFINE SPECT registry, who underwent single-photon emission computed tomography cardiac scans. After excluding patients who had incomplete T5-T11 scan coverage, missing clinical data, or who had been used for EAT model training, the final study group comprised 9918 patients. 5451 (55%) of 9918 participants were male and 4467 (45%) of 9918 participants were female. Median follow-up time was 2·48 years (IQR 1·46-3·65), during which 610 (6%) patients died. High VAT, EAT, and IMAT attenuation were associated with an increased all-cause mortality risk (adjusted hazard ratio 2·39, 95% CI 1·92-2·96; p<0·0001, 1·55, 1·26-1·90; p<0·0001, and 1·30, 1·06-1·60; p=0·012, respectively). Patients with high bone attenuation were at reduced risk of death (0·77, 0·62-0·95; p=0·016). Likewise, high skeletal muscle volume index was associated with a reduced risk of death (0·56, 0·44-0·71; p<0·0001).

Interpretation: CTAC scans obtained routinely during cardiac perfusion imaging contain important volumetric body composition biomarkers that can be automatically measured and offer important additional prognostic value.

Funding: The National Heart, Lung, and Blood Institute, National Institutes of Health.

Figure 1.. Study design: artificial intelligence-derived computed tomography attenuation correction (CTAC)-based body composition analysis.

We integrated fully automated segmentation of skeletal muscles, bone, subcutaneous, intramuscular, and visceral adipose tissues with our previously validated deep-learning model for epicardial adipose tissue segmentation to predict all-cause mortality in patients undergoing myocardial perfusion imaging (MPI). SPECT – single-photon emission computed tomography.

Figure 2.. Study flowchart.

Abbreviations: CTAC - computed tomography attenuation correction, EAT – epicardial adipose tissue, T – thoracic.

Figure 3.. Nonlinear relation between hazard ratio and body composition parameter.

A: bone attenuation, B: EAT – epicardial adipose tissue attenuation, C: IMAT – intramuscular adipose tissue attenuation, D: VAT – visceral adipose tissue attenuation, E: SAT – subcutaneous adipose tissue attenuation, F: SM – skeletal muscle volume index. Solid vertical line specifies the Youden index cutoff while the blue lines show continuous unadjusted hazard ratio across all thresholds with 95% confidence interval (dashed lines), and the dashed horizontal red line specifies hazard ratio 1.

Figure 4.. Kaplan-Meier curves stratified by body composition measures.

A: epicardial adipose tissue (high attenuation: > −63 HU), B: intramuscular adipose tissue (high attenuation: > −68 HU), C: visceral adipose tissue (high attenuation: > −80 HU), D: subcutaneous adipose tissue (high attenuation: > −101 HU), E: bone (high attenuation: > 250 HU), F: skeletal muscle (high volume index: > 597.16 cm³/m²). Hazard ratios (HR) are shown (both unadjusted and adjusted for 11 clinical and imaging variables and other 18 body composition measures).

Figure 5.

Example of body composition segmentation from computed tomography attenuation correction (CTAC) scans in a 73-year-old male patient with a body mass index of 26.4 kg/m².

Figure 6.

Example of body composition segmentation from computed tomography attenuation correction (CTAC) scans in a 65-year-old female patient with a body mass index of 25.8 kg/m².