Format

Send to

Choose Destination
Abdom Radiol (NY). 2019 Aug;44(8):2921-2928. doi: 10.1007/s00261-019-02014-2.

Automated segmentation and quantification of aortic calcification at abdominal CT: application of a deep learning-based algorithm to a longitudinal screening cohort.

Author information

1
E3/311 Clinical Science Center, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave., Madison, WI, 53792-3252, USA.
2
Radiology & Imaging Sciences, National Institutes of Health Clinical Center, Bethesda, MD, USA.
3
Department of Radiology, Medical College of Wisconsin, Milwaukee, WI, USA.
4
E3/311 Clinical Science Center, University of Wisconsin School of Medicine and Public Health, 600 Highland Ave., Madison, WI, 53792-3252, USA. ppickhardt2@uwhealth.org.

Abstract

OBJECTIVE:

To investigate an automated aortic calcium segmentation and scoring tool at abdominal CT in an adult screening cohort.

METHODS:

Using instance segmentation with convolutional neural networks (Mask R-CNN), a fully automated vascular calcification algorithm was applied to a data set of 9914 non-contrast CT scans from 9032 consecutive asymptomatic adults (mean age, 57.5 ± 7.8 years; 4467 M/5447F) undergoing colonography screening. Follow-up scans were performed in a subset of 866 individuals (mean interval, 5.4 years). Automated abdominal aortic calcium volume, mass, and Agatston score were assessed. In addition, comparison was made with a separate validated semi-automated approach in a subset of 812 cases.

RESULTS:

Mean values were significantly higher in males for Agatston score (924.2 ± 2066.2 vs. 564.2 ± 1484.2, p < 0.001), aortic calcium mass (222.2 ± 526.0 mg vs. 144.5 ± 405.4 mg, p < 0.001) and volume (699.4 ± 1552.4 ml vs. 426.9 ± 1115.5 HU, p < 0.001). Overall age-specific Agatston scores increased an average of 10%/year for the entire cohort; males had a larger Agatston score increase between the ages of 40 to 60 than females (91.2% vs. 75.1%, p < 0.001) and had significantly higher mean Agatston scores between ages 50 and 80 (p < 0.001). For the 812-scan subset with both automated and semi-automated methods, median difference in Agatston score was 66.4 with an r2 agreement value of 0.84. Among the 866-patient cohort with longitudinal follow-up, the average Agatston score change was 524.1 ± 1317.5 (median 130.9), reflecting a mean increase of 25.5% (median 73.6%).

CONCLUSION:

This robust, fully automated abdominal aortic calcification scoring tool allows for both individualized and population-based assessment. Such data could be automatically derived at non-contrast abdominal CT, regardless of the study indication, allowing for opportunistic assessment of cardiovascular risk.

KEYWORDS:

Aortic calcium; Artificial intelligence; Cardiovascular disease; Deep learning; Fully automated

PMID:
30976827
DOI:
10.1007/s00261-019-02014-2

Supplemental Content

Full text links

Icon for Springer
Loading ...
Support Center