Correlation of HbA1c levels with CT-based body composition biomarkers in diabetes mellitus and metabolic syndrome

Abstract

Diabetes mellitus and metabolic syndrome are closely linked with visceral body composition, but clinical assessment is limited to external measurements and laboratory values including hemoglobin A1c (HbA1c). Modern deep learning and AI algorithms allow automated extraction of biomarkers for organ size, density, and body composition from routine computed tomography (CT) exams. Comparing visceral CT biomarkers across groups with differing glycemic control revealed significant, progressive CT biomarker changes with increasing HbA1c. For example, in the unenhanced female cohort, mean changes between normal and poorly-controlled diabetes showed: 53% increase in visceral adipose tissue area, 22% increase in kidney volume, 24% increase in liver volume, 6% decrease in liver density (hepatic steatosis), 16% increase in skeletal muscle area, and 21% decrease in skeletal muscle density (myosteatosis) (all p < 0.001). The multisystem changes of metabolic syndrome can be objectively and retrospectively measured using automated CT biomarkers, with implications for diabetes, metabolic syndrome, and GLP-1 agonists.

Fig. 1

Distributions and statistical analysis of visceral adipose tissue (VAT) area at the L3 level between groups. For this and all similar figures, women are the top row and men the bottom; CT without IV contrast in the left column and CT with IV contrast in the right column. Box and whisker plots show the median, interquartile range, and the whiskers extend to the 5th and 95th percentile. All four subplots are shown on a consistent Y axis range. Statistically significant findings from the Kruskal-Wallis test are indicated with red font. Except as otherwise noted, all distributions are highly significantly different (p < 0.001). The pattern of significantly increasing VAT with increasing HbA1c to the diabetic category is consistent.

Fig. 2

Distributions and statistical analysis of segmented kidney volume in cubic centimeters (= mL) between groups. Except as otherwise noted, all distributions are highly significantly different (p < 0.001). The overall pattern is increasing kidney volume with increasing HbA1c group. From a statistical standpoint this does not plateau above the diabetic range in all groups and continues to significantly increase in the CT exam groups with contrast. While there is a statistical plateau in the unenhanced CT groups, the median does continue to increase but the range broadens slightly.

Fig. 3

Distributions and statistical analysis of segmented liver volume in cubic centimeters between groups. The pattern is increasing liver volume with increasing HbA1c. Except as otherwise noted, all distributions are highly significantly different (p < 0.001). In all groups there is a highly statistically significant difference between normal and prediabetic groups versus diabetic and poorly controlled diabetic levels of glycemic control. Only in women with contrast-enhanced CT exams was there also a significant increase in liver volume comparing normal to pre-diabetic groups. Only in men with contrast-enhanced CT exams was there a significant increase in liver volume from the diabetic to poorly- controlled diabetic range.

Fig. 4

Distributions and statistical analysis of the median segmented liver density in Hounsfield Units between groups. Except as otherwise noted, all distributions are highly significantly different (p < 0.001). The overall trend is decreasing density of the liver, which is likely due to increasing hepatic steatosis. This is statistically clearer on CT exams with intravenous contrast, owing in part to the decreased enhancement of steatotic livers.

Fig. 5

Distributions and statistical analysis of the muscle area in square centimeters at the representative slice from the L3 vertebral level between groups. Except as otherwise noted, all distributions are highly significantly different (p < 0.001). The overall trend is increasing muscle area, though not all individual subgroups are significant. In all groups this appears to plateau at the diabetic level of glycemic control, with the muscle area in poorly controlled diabetes not statistically higher than in the diabetic group.

Fig. 6

Distributions and statistical analysis of the median segmented muscle density in Hounsfield Units from the L3 vertebral level between groups. The trend is decreased muscular density with increasing Hb A1c, reflecting increased myosteatosis.

Fig. 7

Histogram of the nearest Hb A1c value to CT scan in our cohort of over 10,000 adults, color coded by the four categories named “Normal” (n = 1984), “Pre-Diabetes” (n = 2948), “Diabetes” (n = 2595), and “Poorly Controlled” (n = 2838). The distribution has an expected peak near the upper limit of normal and pre-diabetic range, reflecting the pre-test probability for ordering Hb A1c in routine practice.

Fig. 8

Representative images illustrating the AI algorithm segmentation and body composition extraction from routine CT exams. For this figure, contrast-enhanced CTs of female patients from each HbA1c category were selected (rows) and segmented axial images with color overlay from the L1 level (left column), L3 level (middle column), and maximum intensity projection (MIP) images in coronal projection (right column) are shown. Color code: Blue is superficial fat, yellow is visceral fat, red is skeletal muscle, brown is liver, orange is spleen, and green is vertebral trabecular region. Progressive changes related to visceral fat and liver volume are most visually apparent from this composite figure.