Fully automatic detection and measurement of abdominal aortic aneurysm using artificial intelligence

Abstract

Background Abdominal aortic aneurysm (AAA) is a life-threatening disease, and the decision to treat relies on the exact detection and size of AAA, which is time-consuming and prone to high inter-reader variability. Artificial intelligence (AI) has revealed new insights into the management of AAA, but it needs large amounts of contrast-enhanced CT data. Moreover, there has been few studies about the fully automatic detection and measurement of AAA. Purpose The aim of this study is to evaluate the accuracy of AI for the detection and measurement of AAA using small amounts of non-contrast CT. Methods We retrospectively collected 145 non-contrast CT scans of suspected AAA. The first step was to manually segment the 30 non-contrast CT scans to create training data for the AI, and the second step was to improve accuracy using 9 of non-contrast CT scans. Image processing is used to identify the AAA area and automatically measure the size. The AAA region was identified from the amount of change in the minor-axis, and the maximum minor-axis diameter was calculated using elliptical fitting. To evaluate the diagnostic utility of AI for the detection of AAA, the sensitivity and positive predictive value were calculated referred for the diagnostic report. The reproducibility in the size of AAA was assessed using intraclass correlation coefficients (ICCs) between the diagnostic report and AI. Results Among 145 of non-contrast CT scans, 111 had AAA. The sensitivity and positive predictive value of AI for the detection of AAA were 94.6% and 53.8%, respectively (Picture 1). The size of AAA calculated by the AI (42.5±8.8 mm) showed a strong correlation with the those of diagnostic reports (44.6±8.4 mm; ICCs = 0.97) (Picture 2). Conclusions AI represents a useful tool in the fully automatic detection and measurement of AAA using small amounts of non-contrast CT. Funding Acknowledgement Type of funding sources: None. Picture 1Picture 2

Diagnostic Accuracy of AI for Opportunistic Screening of Abdominal Aortic Aneurysm in CT: A Systematic Review and Narrative Synthesis

“…This made the quantitative estimation of the sensitivity, specificity, and accuracy impossible. One study [ 36 ] computed the sensitivity and positive predictive value by dividing a single case into two parts. The whole set consisted of 145 noncontrast CT scans of which 111 had AAA.…”

“… Domain Question Almuntashri A. (2012) [ 32 ] Fujiwara J. F. (2021) [ 36 ] Habijan M. (2020) [ 31 ] Hosseini B. (2010) [ 33 ] Kossioris G. T. (2008) [ 34 ] Lu J.-T. (2019) [ 30 ] Mohhamadi S. (2019) [ 23 ] Schei T. R. (2003) [ 35 ] D1 Were the data (training and testing sets) balanced by the severity (including the absence) of the target pathology?…”

“… Study 1st Author (Year) D1 D2 D3 D4 Overall Weight (%) Study 1 Almuntashri A. (2012) [ 32 ] high low some concerns low high 3 Study 2 Fujiwara J. F. (2021) [ 36 ] high some concerns some concerns some concerns high 11 Study 3 Habijan M. (2020) [ 31 ] high low low low low 31.6 Study 4 Hosseini B. (2010) [ 33 ] high low some concerns low high 12.9 Study 5 Kossioris G. T. (2008) [ 34 ] high low …”

Artificial intelligence in atherosclerotic disease: Applications and trends

“…The authors employ label-free CTs, avoiding possible complications associated with the intravenous use of contrast, such as renal failure or allergic reactions. In a dataset of 145 label-free CT scans (n = 111 with AAA), the proposed approach achieved a sensitivity of 94.6% for AAA detection and a good estimation of the AAA size (42.5 ± 8.8 mm) compared to those of diagnostic reports (44.6 ± 8.4 mm) (123).…”