Utility of Normalized Body Composition Areas, Derived From Outpatient Abdominal CT Using a Fully Automated Deep Learning Method, for Predicting Subsequent Cardiovascular Events

Magudia, Kirti; Bridge, Christopher P.; Bay, Camden; Farah, Subrina; Babić, Ana; Fintelmann, Florian J.; Brais, Lauren K.; Andriole, Katherine P.; Wolpin, Brian M.; Rosenthal, Michael H.

doi:10.2214/ajr.22.27977

Cited by 12 publications

(3 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Models such as the ones proposed in this study could increase the diagnostic and prognostic value of medical images by providing risk assessment in addition to answering the primary clinical question such as the etiology of a patient’s acute symptoms. Magudia et al predicted myocardial infarction using population-normalized BC metrics (muscle, VAT and SAT area z-scores) in outpatient adults without a major cardiovascular or oncologic diagnosis undergoing routine abdominal CT 49 . They found after controlling for BMI and other cardiovascular risk factors, only VAT area was associated with subsequent infarction risk.…”

Section: Discussionmentioning

confidence: 99%

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach

Zambrano Chaves,

Wentland,

Desai

et al. 2023

Sci Rep

View full text Add to dashboard Cite

Current risk scores using clinical risk factors for predicting ischemic heart disease (IHD) events—the leading cause of global mortality—have known limitations and may be improved by imaging biomarkers. While body composition (BC) imaging biomarkers derived from abdominopelvic computed tomography (CT) correlate with IHD risk, they are impractical to measure manually. Here, in a retrospective cohort of 8139 contrast-enhanced abdominopelvic CT examinations undergoing up to 5 years of follow-up, we developed multimodal opportunistic risk assessment models for IHD by automatically extracting BC features from abdominal CT images and integrating these with features from each patient’s electronic medical record (EMR). Our predictive methods match and, in some cases, outperform clinical risk scores currently used in IHD risk assessment. We provide clinical interpretability of our model using a new method of determining tissue-level contributions from CT along with weightings of EMR features contributing to IHD risk. We conclude that such a multimodal approach, which automatically integrates BC biomarkers and EMR data, can enhance IHD risk assessment and aid primary prevention efforts for IHD. To further promote research, we release the Opportunistic L3 Ischemic heart disease (OL3I) dataset, the first public multimodal dataset for opportunistic CT prediction of IHD.

show abstract

Section: Discussionmentioning

confidence: 99%

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach

Zambrano Chaves,

Wentland,

Desai

et al. 2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…2,[5][6][7] Studies have shown that automatic epicardial adipose tissue (EAT) derived from CTAC can provide additional information and improve mortality prediction. 8 Existing deep learning-based approaches for body composition segmentation have been developed for pre-selected abdominal CT slice, 2,7,9 and only one study so far utilized selected three slices from CT. 5 Until now, the full predictive value of CTAC in cardiometabolic screening remains unexplored.…”

Section: Introductionmentioning

confidence: 99%

AI-based volumetric six-tissue body composition quantification from CT cardiac attenuation scans enhances mortality prediction: multicenter study

Yi,

Michalowska,

Shanbhag

et al. 2024

Preprint

View full text Add to dashboard Cite

BackgroundComputed tomography attenuation correction (CTAC) scans are routinely obtained during cardiac perfusion imaging, but currently only utilized 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 evaluate these measures for all-cause mortality (ACM) risk stratification.MethodsWe applied AI-based segmentation and image-processing techniques on CTAC scans from a large international image-based registry (four sites), to define chest rib cage and multiple tissues. Volumetric measures of bone, skeletal muscle (SM), subcutaneous, intramuscular (IMAT), visceral (VAT), and epicardial (EAT) adipose tissues were quantified between automatically-identified T5 and T11 vertebrae. The independent prognostic value of volumetric attenuation, and indexed volumes were evaluated for predicting ACM, adjusting for established risk factors and 18 other body compositions measures via Cox regression models and Kaplan-Meier curves.FindingsEnd-to-end processing time was <2 minutes/scan with no user interaction. Of 9918 patients studied, 5451(55%) were male. During median 2.5 years follow-up, 610 (6.2%) patients died. High VAT, EAT and IMAT attenuation were associated with increased ACM risk (adjusted hazard ratio (HR) [95% confidence interval] for VAT: 2.39 [1.92, 2.96], p<0.0001; EAT: 1.55 [1.26, 1.90], p<0.0001; IMAT: 1.30 [1.06, 1.60], p=0.0124). Patients with high bone attenuation were at lower risk of death as compared to subjects with lower bone attenuation (adjusted HR 0.77 [0.62, 0.95], p=0.0159). Likewise, high SM volume index was associated with a lower risk of death (adjusted HR 0.56 [0.44, 0.71], p<0.0001).InterpretationsCTAC scans obtained routinely during cardiac perfusion imaging contain important volumetric body composition biomarkers which can be automatically measured and offer important additional prognostic value.Research in contextEvidence before this studyFully automated volumetric body composition analysis of chest computed tomography attenuation correction (CTAC) can be obtained in patients undergoing myocardial perfusion imaging. This new information has potential to significantly improve risk stratification and patient management. However, the CTAC scans have not been utilized for body composition analysis to date. We searched PubMed and Google Scholar for existing body composition related literature on June 5, 2024, using the search term (“mortality”) AND (“risk stratification” OR “survival analysis” OR “prognostic prediction” OR “prognosis”) AND (“body composition quantification” OR “body composition analysis” OR “body composition segmentation”). We identified 34 articles either exploring body composition segmentation or evaluating clinical value of body composition quantification. However, to date, all the prognostic evaluation is performed for quantification of three or fewer types of body composition tissues. Within the prognostic studies, only one used chest CT scans but utilized only a few specified slices selected from the scans, and not a standardized volumetric analysis. None of these previous efforts utilized CTAC scans, and none included epicardial adipose tissue in comprehensive body composition analysis.Added value of this studyIn this international multi-center study, we demonstrate a novel artificial intelligence-based annotation-free approach for segmenting six key body composition tissues (bone, skeletal muscle, subcutaneous adipose tissue, intramuscular adipose tissue, epicardial adipose tissue, and visceral adipose tissue) from low-dose ungated CTAC scans, by exploiting existing CT segmentation models and image processing techniques. We evaluate the prognostic value of metrics derived from volumetric quantification of CTAC scans obtained during cardiac imaging, for all-cause mortality prediction in a large cohort of patients. We reveal strong and independent associations between several volumetric body composition metrics and all-cause mortality after adjusting for existing clinical factors, and available cardiac perfusion and atherosclerosis biomarkers.Implications of all the available evidenceThe comprehensive body composition analysis can be routinely performed, at the point of care, for all cardiac perfusion scans utilizing CTAC. Automatically-obtained volumetric body composition quantification metrics provide added value over existing risk factors, using already-obtained scans to significantly improve the risk stratification of patients and clinical decision-making.

show abstract

“…Particularly, abdominal obesity is associated with medical conditions such as hypertension, dyslipidemia, and type 2 diabetes in people of all ages, including young adults and children [ 5 ]. Abdominal adipose tissue distribution and body composition may also predict cardiovascular risk and subsequent events [ 6 ].…”

Section: Introductionmentioning

confidence: 99%

A Combined Region- and Pixel-Based Deep Learning Approach for Quantifying Abdominal Adipose Tissue in Adolescents Using Dixon Magnetic Resonance Imaging

et al. 2023

View full text Add to dashboard Cite

Background: The development of adipose tissue during adolescence may provide valuable insights into obesity-associated diseases. We propose an automated convolutional neural network (CNN) approach using Dixon-based magnetic resonance imaging (MRI) to quantity abdominal subcutaneous adipose tissue (SAT) and visceral adipose tissue (VAT) in children and adolescents. Methods: 474 abdominal Dixon MRI scans of 136 young healthy volunteers (aged 8–18) were included in this study. For each scan, an axial fat-only Dixon image located at the L2–L3 disc space and another image at the L4–L5 disc space were selected for quantification. For each image, an outer and an inner region around the abdomen wall, as well as SAT and VAT pixel masks, were generated by expert readers as reference standards. A standard U-Net CNN architecture was then used to train two models: one for region segmentation and one for fat pixel classification. The performance was evaluated using the dice similarity coefficient (DSC) with fivefold cross-validation, and by Pearson correlation and the Student’s t-test against the reference standards. Results: For the DSC results, means and standard deviations of the outer region, inner region, SAT, and VAT comparisons were 0.974 ± 0.026, 0.997 ± 0.003, 0.981 ± 0.025, and 0.932 ± 0.047, respectively. Pearson coefficients were 1.000 for both outer and inner regions, and 1.000 and 0.982 for SAT and VAT comparisons, respectively (all p = NS). Conclusion: These results show that our method not only provides excellent agreement with the reference SAT and VAT measurements, but also accurate abdominal wall region segmentation. The proposed combined region- and pixel-based CNN approach provides automated abdominal wall segmentation as well as SAT and VAT quantification with Dixon MRI and enables objective longitudinal assessment of adipose tissues in children during adolescence.

show abstract

Utility of Normalized Body Composition Areas, Derived From Outpatient Abdominal CT Using a Fully Automated Deep Learning Method, for Predicting Subsequent Cardiovascular Events

Cited by 12 publications

References 28 publications

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach

Opportunistic assessment of ischemic heart disease risk using abdominopelvic computed tomography and medical record data: a multimodal explainable artificial intelligence approach

AI-based volumetric six-tissue body composition quantification from CT cardiac attenuation scans enhances mortality prediction: multicenter study

A Combined Region- and Pixel-Based Deep Learning Approach for Quantifying Abdominal Adipose Tissue in Adolescents Using Dixon Magnetic Resonance Imaging

Contact Info

Product

Resources

About