scholarly journals Recent Trends in Artificial Intelligence-Assisted Coronary Atherosclerotic Plaque Characterization

2021 ◽  
Vol 18 (19) ◽  
pp. 10003
Author(s):  
Anjan Gudigar ◽  
Sneha Nayak ◽  
Jyothi Samanth ◽  
U Raghavendra ◽  
Ashwal A J ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Atherosclerotic Plaque ◽  
Performance Metrics ◽  
Invasive Coronary Angiography ◽  
Computed Tomographic Angiography ◽  
Plaque Characterization ◽  
Technical Literature ◽  
Computed Tomographic ◽  
Vulnerable Plaques ◽  
Coronary Events

Coronary artery disease is a major cause of morbidity and mortality worldwide. Its underlying histopathology is the atherosclerotic plaque, which comprises lipid, fibrous and—when chronic—calcium components. Intravascular ultrasound (IVUS) and intravascular optical coherence tomography (IVOCT) performed during invasive coronary angiography are reference standards for characterizing the atherosclerotic plaque. Fine image spatial resolution attainable with contemporary coronary computed tomographic angiography (CCTA) has enabled noninvasive plaque assessment, including identifying features associated with vulnerable plaques known to presage acute coronary events. Manual interpretation of IVUS, IVOCT and CCTA images demands scarce physician expertise and high time cost. This has motivated recent research into and development of artificial intelligence (AI)-assisted methods for image processing, feature extraction, plaque identification and characterization. We performed parallel searches of the medical and technical literature from 1995 to 2021 focusing respectively on human plaque characterization using various imaging modalities and the use of AI-assisted computer aided diagnosis (CAD) to detect and classify atherosclerotic plaques, including their composition and the presence of high-risk features denoting vulnerable plaques. A total of 122 publications were selected for evaluation and the analysis was summarized in terms of data sources, methods—machine versus deep learning—and performance metrics. Trends in AI-assisted plaque characterization are detailed and prospective research challenges discussed. Future directions for the development of accurate and efficient CAD systems to characterize plaque noninvasively using CCTA are proposed.

Abstract 6101: Cost Effectiveness of Cardiac Computed Tomography Compared to Myocardial Perfusion Imaging (MPI) as an Effective Gatekeeper to Cardiac Catheterization in the Evaluation of Asymptomatic Firefighters with an Abnormal Treadmill Test

Circulation ◽  
2008 ◽  
Vol 118 (suppl_18) ◽  
Author(s):  
Matthew Budoff ◽  
Robert Karwasky ◽  
Naser Ahmadi MD Ahmadi ◽  
Cyrus A Nasserian ◽  
William W Chang ◽  
...  
Keyword(s):  
Los Angeles ◽  
Care Pathway ◽  
Cardiac Computed Tomography ◽  
Clinical Care ◽  
Invasive Coronary Angiography ◽  
Calcium Score ◽  
Computed Tomographic Angiography ◽  
Sensitivity Analyses ◽  
Computed Tomographic ◽  
Clinical Care Pathway

To identify CAD among patients who fail treadmill tests, the traditional clinical care pathway is MPI, then invasive coronary angiography (ICA). In a retrospective cohort study, we compared the direct costs for detecting CAD using the traditional clinical care pathway and an alternative that incorporates MDCT, with coronary calcium score (CCS) followed by computed tomographic angiography (CTA) and ICA. Over a 2-year period, 3,950 Los Angeles, CA Firefighters underwent wellness/fitness exams at 6 contracted medical facilities. A total of 495 cases had abnormal treadmill tests and were referred for follow-up cardiology evaluation. All cases received CCS, followed by CTA for calcium scores >10, and ICA for abnormal CTA (>50% obstruction in at least one vessel). MPI results were estimated based on the prior year’s experience, with abnormal MPI receiving ICA. Costs to detect CAD were calculated for both the MPI and MDCT pathways based on results for the cohort and current Medicare reimbursement costs. Sensitivity analyses were performed by varying each of the clinical and cost components of the model to “low” and “high” levels and computing net costs. Most model inputs were varied by ±50% of baseline values to gauge the robustness of the results. Among 495 cases with abnormal treadmill tests, 146 (29.5%) would have required ICA due to abnormal MPI tests; 131 (26.9%) had abnormal CCS (>10) and went to CTA; 40 (8.1%) had abnormal CTA (>50% stenosis) and went to ICA. ICA showed 38 (7.7%) cases of CAD. The computed cost to detect CAD was $1,376 per case for the traditional route with MPI as gatekeeper and $503 per case for CCS as gatekeeper. All sensitivity analyses showed lower costs for the MDCT compared to MPI pathways. The net cost to ICA-confirmed diagnosis of CAD is substantially lower with MDCT compared to MPI as gatekeeper to ICA.

P2722Optimizing diagnosis of obstrutive coronary artery disease by CT angiography and ischemia test: a randomized clinical trial

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
J P Dias Ferreira Reis ◽  
R Ramos ◽  
P Modas Daniel ◽  
S Rosa Aguiar ◽  
L Almeida Morais ◽  
...  
Keyword(s):  
Coronary Artery Disease ◽  
Clinical Trial ◽  
Coronary Artery ◽  
Coronary Angiography ◽  
Invasive Coronary Angiography ◽  
Computed Tomographic Angiography ◽  
Functional Test ◽  
Computed Tomographic ◽  
Artery Disease ◽  
Tomographic Angiography

Abstract Aim In patients with suspected coronary artery disease (CAD), computed tomographic angiography (CTA) may improve patient selection for invasive coronary angiography (ICA) as alternative to functional testing. However, the role of CTA in symptomatic patients after abnormal functional test is incompletely defined. Methods and results This randomized clinical trial conducted in single academic tertiary center selected 218 symptomatic patients (pts) with mild to moderately abnormal functional test referred to invasive coronary to receive either the originally intended ICA (n=103) or CTA (n=115). CTA interpretation and subsequent care decisions were made by the clinical team. Patients with high risk features on functional tests, previous acute coronary syndrome, previously documented CAD, chronic kidney disease (GFR <60 ml/min/1.73m2) or persistent atrial fibrillation were excluded. The primary endpoint was the percentage of ICA with no significant obstructive CAD (no stenosis ≥50%) in each group. Diagnostic and revascularization yields of ICA in either group were also assessed. Subjects averaged 68±9 years of age, 60% were male, 29% were diabetic. Nuclear perfusion stress test was used in 33.9% in CTA group and 31.1% in control group (p=0.655). Mean post (functional) test probability of obstructive CAD was 34%. Overall prevalence of obstructive CAD was 32.1%. In the CTA group, ICA angiography was cancelled by referring physicians in 83 of the pts (72.2%) after receiving CTA results. For those undergoing ICA, nonobstructive CAD was found in 5 pts (15.6%) in the CTA-guided arm and 60 (58.3%) in the usual care arm (P<0.001). Mean cumulative radiation exposure related to diagnostic work up was similar in both groups (6±14 vs 5±14mSv, P=0.152), but a greater cumulative contrast dose in the CTA-guided group (87.5±21 vs 77±40, p=0.026) was observed. Both diagnostic (84.4% vs 41.7, p<0.001) and revascularization (71.9% vs 38.8%, p=0.001) yields were significantly higher for CTA-guided ICA as compared to standard functional test-guided ICA. Conclusions In patients with suspected CAD and mild to moderately abnormal functional test, a diagnostic strategy including computed tomographic angiography as gatekeeper is effective and significantly improves diagnostic and revascularization yields of invasive coronary angiography.

4182Sex specific patterns in the onset and manifestation of coronary atherosclerotic plaque; insights from the multi-center CCTA CONFIRM registry

2019 ◽  
Vol 40 (Supplement_1) ◽  
Author(s):  
A R Van Rosendael ◽  
F Y Lin ◽  
H Gransar ◽  
I J Van Den Hoogen ◽  
U Gianni ◽  
...  
Keyword(s):  
Atherosclerotic Plaque ◽  
Coronary Atherosclerosis ◽  
Age Of Onset ◽  
Hazard Analysis ◽  
Computed Tomographic Angiography ◽  
Left Main ◽  
Computed Tomographic ◽  
Increased Risk ◽  
Coronary Atherosclerotic Plaque ◽  
Mixed Plaque

Abstract Background Pathobiologic data support varied atherosclerotic plaque characteristics which uniquely define risk in women as compared to men (i.e., plaque erosion versus rupture). The advent of noninvasive coronary computed tomographic angiography (CCTA) allows for further exploration as to a sex-specific signature of atherosclerotic plaque features unique to women and different from that of men. In this analysis, we compared sex differences in the age of onset of coronary atherosclerosis and varied plaque findings between women and men. Methods From the multicenter CONFIRM registry, the Leiden CCTA score (based on segmental plaque extent, location, severity, and composition) was calculated in women and men without prior CAD, with imputation for missing plaque data. First, women and men were matched on the Leiden CCTA score to allow assessment of differences in atherosclerotic profile. Second, the earliest age of women and men to display a median Leiden CCTA score >0, >2, >6, >8 was evaluated. Third, the prognostic value of previously established thresholds of the Leiden CCTA score was examined for all-cause mortality with Cox-proportional hazard analysis, and specifically a sex interaction. Results In total, 11,678 women (age 58.5±12.4 years) and 13,272 men (age 55.6±12.5 years) were included. Of the patient subset matched on Leiden CCTA score (10,266 women, score 4.1±6.0 and 10,266 men, Leiden score 4.1±6.0, P=0.589), women were characterized by less obstructive CAD (≥50% stenosis) (17.5% vs 19.1%, P=0.003), more frequent non-obstructive left main plaque (10.1% vs 8.9%, P=0.004) and a lower number of segments with non-calcified or mixed plaque, but an equal number of calcified plaques. The earliest age when women and men have a median Leiden CCTA score above 0, 2, 4, 6, or 8 was consistently 14 to 16 years later for women. A visual representation of the CAD development delay is shown in Figure 1. Adjusted for age, the hazard ratio for death (827 events) for a score 6–20, and >20 (compared with 0–6) was 1.95 (95% CI 1.56–2.42), and 3.44 (95% CI 2.40–4.93) for women, respectively, and 1.63 (95% CI 1.31–2.03), 2.22 (95% CI 1.64–3.00) for men, respectively (P-interaction 0.006). Despite the low number of events, women <50 years with a score >20 were at 12.8 (95% CI 3.58–45.73) times increased risk. Conclusion There is an approximate 15-year delay in onset of coronary atherosclerosis for women compared to men. The burden of atherosclerotic plaque is associated with a higher relative hazard for death among women than men. The pattern of more nonobstructive CAD, especially in the left main coronary artery, but also less non-calcified plaque supports a sex-specific plaque signature which may uniquely define risk among women as compared to men. Acknowledgement/Funding The research reported in this manuscript was funded, in part, by the National Institute of Health (Bethesda, MD, USA) under award number R01 HL115150.

Impact of Several Factors on the Diagnostic Interpretability of Coronary Computed Tomographic Angiography Using a 256-Detector Row CT Scanner

2021 ◽  
Vol 17 ◽  
Author(s):  
Lixue Xu ◽  
Nan Luo ◽  
Yi He ◽  
Zhenghan Yang
Keyword(s):  
Predictive Value ◽  
Signal To Noise Ratio ◽  
Invasive Coronary Angiography ◽  
Computed Tomographic Angiography ◽  
Ct Scanner ◽  
Logistic Regression Models ◽  
Computed Tomographic ◽  
Stenosis Severity ◽  
Calcium Load ◽  
The Impact

Purpose: To explore the impact of patient-related, vessel-related, image quality-related and cardiovascular risk factors on CCTA interpretability using 256-detector row Computed Tomography (CT). Methods: One hundred ten patients who underwent CCTA and Invasive Coronary Angiography (ICA) were consecutively retrospectively enrolled from January 2018 to October 2018. Using ICA as the reference standard, ≥50% diameter stenosis was defined as the cut-off criterion to detect the diagnostic performance of CCTA. Diagnostic reproducibility was investigated by calculating the interrater reproducibility of CCTA. Multiple logistic regression models were performed to evaluate the impact of 14 objective factors. Results: A total of 1019 segments were evaluated. The per-segment sensitivity, specificity, accuracy, positive predictive value, and negative predictive value of CCTA were 76.8%, 93.7%, 91.2%, 67.8% and 95.9%, respectively. The per-segment diagnostic reproducibility was 0.44 for CCTA. Regarding accuracy, a negative association was found for stenosis severity, calcium load and hyperlipidaemia. Regarding sensitivity, calcium load and diabetes mellitus (DM) were positively related. Regarding specificity, a negative correlation was observed between stenosis severity and calcium load. Regarding interrater reproducibility, stenosis severity and calcium load were negatively associated, whereas male sex and the signal-to-noise ratio (SNR) were positively related (all p<0.05). Conclusion: Per-segment 256-detector row CCTA performance was optimal in stenosis-free or occluded segments. Heavier calcium load was associated with poorer CCTA interpretability. On the one hand, our findings confirmed the rule-out value of CCTA; on the other hand, they suggested improvements in calcium subtractions and deep learning-based tools to improve CCTA diagnostic interpretability.

scholarly journals Atherosclerotic Plaque Characterization by 0.5-mm-Slice Multislice Computed Tomographic Imaging

2007 ◽  
Vol 71 (3) ◽  
pp. 363-366 ◽  
Author(s):  
Sadako Motoyama ◽  
Takeshi Kondo ◽  
Hirofumi Anno ◽  
Atsushi Sugiura ◽  
Yoshihiro Ito ◽  
...  
Keyword(s):  
Atherosclerotic Plaque ◽  
Tomographic Imaging ◽  
Plaque Characterization ◽  
Computed Tomographic ◽  
Computed Tomographic Imaging
Sign in / Sign up

Export Citation Format

Share Document