Utility of Fully Automated Body Composition Measures on Pretreatment Abdominal CT for Predicting Survival in Patients With Colorectal Cancer

Aug 24, 2022AJR. American journal of roentgenology

Automated Body Composition Analysis from Abdominal CT Scans Predicts Survival in Colorectal Cancer Patients

AI simplified

GLP-1 Therapies on OpenScience ↗PubMed ↗DOI ↗

Abstract

A total of 1766 patients with colorectal cancer were included in the analysis of automated body composition measures for survival prediction.

Patients who died had significantly lower median muscle attenuation (19.2 vs 26.2 HU) and smaller subcutaneous adipose tissue (SAT) area (168.4 cm vs 197.6 cm) compared to those who survived.
The highest 5-year area under the curve (AUC) for predicting survival was observed for muscle attenuation (0.666 without metastases; 0.701 with metastases) and aortic calcium (0.677 without metastases; 0.689 with metastases).
A combination of muscle attenuation, SAT area, and aortic calcium yielded improved 5-year AUCs of 0.758 and 0.732 in patients without and with metastases, respectively.
Risk of death was significantly increased in patients in the lowest quartile for muscle attenuation (hazard ratio [HR] = 1.55) and SAT area (HR = 1.81).
Conversely, patients in the highest quartile for visceral adipose tissue area had a decreased risk of death (HR = 0.79).
Body mass index (BMI) did not significantly predict death in the subset of patients assessed.

AI simplified

CT examinations contain opportunistic body composition data with potential prognostic utility. Previous studies have primarily used manual or semiautomated tools to evaluate body composition in patients with colorectal cancer (CRC).The purpose of this article is to assess the utility of fully automated body composition measures derived from pretreatment CT examinations in predicting survival in patients with CRC.This retrospective study included 1766 patients (mean age, 63.7 ± 14.4 [SD] years; 862 men, 904 women) diagnosed with CRC between January 2001 and September 2020 who underwent pretreatment abdominal CT. A panel of fully automated artificial intelligence-based algorithms was applied to portal venous phase images to quantify skeletal muscle attenuation at the L3 lumbar level, visceral adipose tissue (VAT) area and subcutaneous adipose tissue (SAT) area at L3, and abdominal aorta Agatston score (aortic calcium). The electronic health record was reviewed to identify patients who died of any cause (= 848). ROC analyses and logistic regression analyses were used to identify predictors of survival, with attention to highest- and lowest-risk quartiles.Patients who died, compared with patients who survived, had lower median muscle attenuation (19.2 vs 26.2 HU,< .001), SAT area (168.4 cmvs 197.6 cm,< .001), and aortic calcium (620 vs 182,< .001). Measures with highest 5-year AUCs for predicting survival in patients without (= 1303) and with (= 463) metastatic disease were muscle attenuation (0.666 and 0.701, respectively) and aortic calcium (0.677 and 0.689, respectively). A combination of muscle attenuation, SAT area, and aortic calcium yielded 5-year AUCs of 0.758 and 0.732 in patients without and with metastases, respectively. Risk of death was increased (< .05) in patients in the lowest quartile for muscle attenuation (hazard ratio [HR] = 1.55) and SAT area (HR = 1.81) and in the highest quartile for aortic calcium (HR = 1.37) and decreased (< .05) in patients in the highest quartile for VAT area (HR = 0.79) and SAT area (HR = 0.76). In 423 patients with available BMI, BMI did not significantly predict death (= .75).Fully automated CT-based body composition measures including muscle attenuation, SAT area, and aortic calcium predict survival in patients with CRC.Routine pretreatment body composition evaluation could improve initial risk stratification of patients with CRC. BACKGROUND. OBJECTIVE. METHODS. RESULTS. CONCLUSION. CLINICAL IMPACT. n p p p n n p p p2 2

Full Text

Full text is available at the source.

View full text ↗

Utility of Fully Automated Body Composition Measures on Pretreatment Abdominal CT for Predicting Survival in Patients With Colorectal Cancer

Abstract

Full Text

You found one interesting study. We’ll send the next 7.

what lands in your inbox each week:

Recent issues from the glp-1 therapies brief