Coronary CTA With AI-QCT Interpretation: Comparison With Myocardial Perfusion Imaging for Detection of Obstructive Stenosis Using Invasive Angiography as Reference Standard.

BACKGROUND. Deep learning frameworks have been applied to interpretation of coronary CTA performed for coronary artery disease (CAD) evaluation. OBJECTIVE. The purpose of our study was to compare the diagnostic performance of myocardial perfusion imaging (MPI) and coronary CTA with artificial intelligence quantitative CT (AI-QCT) interpretation for detection of obstructive CAD on invasive angiography and to assess the downstream impact of including coronary CTA with AI-QCT in diagnostic algorithms. METHODS. This study entailed a retrospective post hoc analysis of the derivation cohort of the prospective 23-center Computed Tomographic Evaluation of Atherosclerotic Determinants of Myocardial Ischemia (CREDENCE) trial. The study included 301 patients (88 women and 213 men; mean age, 64.4 ± 10.2 [SD] years) recruited from May 2014 to May 2017 with stable symptoms of myocardial ischemia referred for nonemergent invasive angiography. Patients underwent coronary CTA and MPI before angiography with quantitative coronary angiography (QCA) measurements and fractional flow reserve (FFR). CTA examinations were analyzed using an FDA-cleared cloud-based software platform that performs AI-QCT for stenosis determination. Diagnostic performance was evaluated. Diagnostic algorithms were compared. RESULTS. Among 102 patients with no ischemia on MPI, AI-QCT identified obstructive (≥ 50%) stenosis in 54% of patients, including severe (≥ 70%) stenosis in 20%. Among 199 patients with ischemia on MPI, AI-QCT identified nonobstructive (1-49%) stenosis in 23%. AI-QCT had significantly higher AUC (all p < .001) than MPI for predicting ≥ 50% stenosis by QCA (0.88 vs 0.66), ≥ 70% stenosis by QCA (0.92 vs 0.81), and FFR < 0.80 (0.90 vs 0.71). An AI-QCT result of ≥ 50% stenosis and ischemia on stress MPI had sensitivity of 95% versus 74% and specificity of 63% versus 43% for detecting ≥ 50% stenosis by QCA measurement. Compared with performing MPI in all patients and those showing ischemia undergoing invasive angiography, a scenario of performing coronary CTA with AIQCT in all patients and those showing ≥ 70% stenosis undergoing invasive angiography would reduce invasive angiography utilization by 39%; a scenario of performing MPI in all patients and those showing ischemia undergoing coronary CTA with AI-QCT and those with ≥ 70% stenosis on AI-QCT undergoing invasive angiography would reduce invasive angiography utilization by 49%. CONCLUSION. Coronary CTA with AI-QCT had higher diagnostic performance than MPI for detecting obstructive CAD. CLINICAL IMPACT. A diagnostic algorithm incorporating AI-QCT could substantially reduce unnecessary downstream invasive testing and costs. TRIAL REGISTRATION. Clinicaltrials.gov NCT02173275.

Diabetes, Atherosclerosis, and Stenosis by AI.

OBJECTIVE: This study evaluates the relationship between atherosclerotic plaque characteristics (APCs) and angiographic stenosis severity in patients with and without diabetes. Whether APCs differ based on lesion severity and diabetes status is unknown. RESEARCH DESIGN AND METHODS: We retrospectively evaluated 303 subjects from the Computed TomogRaphic Evaluation of Atherosclerotic Determinants of Myocardial IsChEmia (CREDENCE) trial referred for invasive coronary angiography with coronary computed tomographic angiography (CCTA) and classified lesions as obstructive (≥50% stenosed) or nonobstructive using blinded core laboratory analysis of quantitative coronary angiography. CCTA quantified APCs, including plaque volume (PV), calcified plaque (CP), noncalcified plaque (NCP), low-density NCP (LD-NCP), lesion length, positive remodeling (PR), high-risk plaque (HRP), and percentage of atheroma volume (PAV; PV normalized for vessel volume). The relationship between APCs, stenosis severity, and diabetes status was assessed. RESULTS: Among the 303 patients, 95 (31.4%) had diabetes. There were 117 lesions in the cohort with diabetes, 58.1% of which were obstructive. Patients with diabetes had greater plaque burden (P = 0.004). Patients with diabetes and nonobstructive disease had greater PV (P = 0.02), PAV (P = 0.02), NCP (P = 0.03), PAV NCP (P = 0.02), diseased vessels (P = 0.03), and maximum stenosis (P = 0.02) than patients without diabetes with nonobstructive disease. APCs were similar between patients with diabetes with nonobstructive disease and patients without diabetes with obstructive disease. Diabetes status did not affect HRP or PR. Patients with diabetes had similar APCs in obstructive and nonobstructive lesions. CONCLUSIONS: Patients with diabetes and nonobstructive stenosis had an association to similar APCs as patients without diabetes who had obstructive stenosis. Among patients with nonobstructive disease, patients with diabetes had more total PV and NCP.

Relation of Gender to Atherosclerotic Plaque Characteristics by Differing Angiographic Stenosis Severity.

It is unknown whether gender influences the atherosclerotic plaque characteristics (APCs) of lesions of varying angiographic stenosis severity. This study evaluated the imaging data of 303 symptomatic patients from the derivation arm of the CREDENCE (Computed TomogRaphic Evaluation of Atherosclerotic Determinants of Myocardial IsChEmia) trial, all of whom underwent coronary computed tomographic angiography and clinically indicated nonemergent invasive coronary angiography upon study enrollment. Index tests were interpreted by 2 blinded core laboratories, one of which performed quantitative coronary computed tomographic angiography using an artificial intelligence application to characterize and quantify APCs, including percent atheroma volume (PAV), low-density noncalcified plaque (LD-NCP), noncalcified plaque (NCP), calcified plaque (CP), lesion length, positive arterial remodeling, and high-risk plaque (a combination of LD-NCP and positive remodeling ≥1.10); the other classified lesions as obstructive (≥50% diameter stenosis) or nonobstructive (<50% diameter stenosis) based on quantitative invasive coronary angiography. The relation between APCs and angiographic stenosis was further examined by gender. The mean age of the study cohort was 64.4 ± 10.2 years (29.0% female). In patients with obstructive disease, men had more LD-NCP PAV (0.5 ± 0.4 vs 0.3 ± 0.8, p = 0.03) and women had more CP PAV (11.7 ± 1.6 vs 8.0 ± 0.8, p = 0.04). Obstructive lesions had more NCP PAV compared with their nonobstructive lesions in both genders, however, obstructive lesions in women also demonstrated greater LD-NCP PAV (0.4 ± 0.5 vs 1.0 ± 1.8, p = 0.03), and CP PAV (17.4 ± 16.5 vs 25.9 ± 18.7, p = 0.03) than nonobstructive lesions. Comparing the composition of obstructive lesions by gender, women had more CP PAV (26.3 ± 3.4 vs 15.8 ± 1.5, p = 0.005) whereas men had more NCP PAV (33.0 ± 1.6 vs 26.7 ± 2.5, p = 0.04). Men had more LD-NCP PAV in nonobstructive lesions compared with women (1.2 ± 0.2 vs 0.6 ± 0.2, p = 0.02). In conclusion, there are gender-specific differences in plaque composition based on stenosis severity.

Interobserver variability among expert readers quantifying plaque volume and plaque characteristics on coronary CT angiography: a CLARIFY trial sub-study.

BACKGROUND: The difference between expert level (L3) reader and artificial intelligence (AI) performance for quantifying coronary plaque and plaque components is unknown. OBJECTIVE: This study evaluates the interobserver variability among expert readers for quantifying the volume of coronary plaque and plaque components on coronary computed tomographic angiography (CCTA) using an artificial intelligence enabled quantitative CCTA analysis software as a reference (AI-QCT). METHODS: This study uses CCTA imaging obtained from 232 patients enrolled in the CLARIFY (CT EvaLuation by ARtificial Intelligence For Atherosclerosis, Stenosis and Vascular MorphologY) study. Readers quantified overall plaque volume and the % breakdown of noncalcified plaque (NCP) and calcified plaque (CP) on a per vessel basis. Readers categorized high risk plaque (HRP) based on the presence of low-attenuation-noncalcified plaque (LA-NCP) and positive remodeling (PR; ≥1.10). All CCTAs were analyzed by an FDA-cleared software service that performs AI-driven plaque characterization and quantification (AI-QCT) for comparison to L3 readers. Reader generated analyses were compared among readers and to AI-QCT generated analyses. RESULTS: When evaluating plaque volume on a per vessel basis, expert readers achieved moderate to high interobserver consistency with an intra-class correlation coefficient of 0.78 for a single reader score and 0.91 for mean scores. There was a moderate trend between readers 1, 2, and 3 and AI with spearman coefficients of 0.70, 0.68 and 0.74, respectively. There was high discordance between readers and AI plaque component analyses. When quantifying %NCP v. %CP, readers 1, 2, and 3 achieved a weighted kappa coefficient of 0.23, 0.34 and 0.24, respectively, compared to AI with a spearman coefficient of 0.38, 0.51, and 0.60, respectively. The intra-class correlation coefficient among readers for plaque composition assessment was 0.68. With respect to HRP, readers 1, 2, and 3 achieved a weighted kappa coefficient of 0.22, 0.26, and 0.17, respectively, and a spearman coefficient of 0.36, 0.35, and 0.44, respectively. CONCLUSION: Expert readers performed moderately well quantifying total plaque volumes with high consistency. However, there was both significant interobserver variability and high discordance with AI-QCT when quantifying plaque composition.

Quantitative plaque analysis with A.I.-augmented CCTA in end-stage renal disease and complex CAD.

BACKGROUND: Adverse cardiovascular events are a significant cause of mortality in end-stage renal disease (ESRD) patients. High-risk plaque anatomy may be a significant contributor. However, their atherosclerotic phenotypes have not been described. We sought to define atherosclerotic plaque characteristics (APC) in dialysis patients using artificial-intelligence augmented CCTA. METHODS: We retrospectively analyzed ESRD patients referred for CCTA using an FDA approved artificial-intelligence augmented-CCTA program (Cleerly). Coronary lesions were evaluated for APCs by CCTA. APCs included percent atheroma volume(PAV), low-density non-calcified-plaque (LD-NCP), non-calcified-plaque (NCP), calcified-plaque (CP), length, and high-risk-plaque (HRP), defined by LD-NCP and positive arterial remodeling >1.10 (PR). RESULTS: 79 ESRD patients were enrolled, mean age 65.3 years, 32.9% female. Disease distribution was non-obstructive (65.8%), 1-vessel disease (21.5%), 2-vessel disease (7.6%), and 3-vessel disease (5.1%). Mean total plaque volume (TPV) was 810.0 mm3, LD-NCP 16.8 mm3, NCP 403.1 mm3, and CP 390.1 mm3. HRP was present in 81.0% patients. Patients with at least one >50% stenosis, or obstructive lesions, had significantly higher TPV, LD-NCP, NCP, and CP. Patients >65 years had more CP and higher PAV. CONCLUSION: Our study provides novel insight into ESRD plaque phenotypes and demonstrates that artificial-intelligence augmented CCTA analysis is feasible for CAD characterization despite severe calcification. We demonstrate elevated plaque burden and stenosis caused by predominantly non-calcified-plaque. Furthermore, the quantity of calcified-plaques increased with age, with men exhibiting increased number of 2-feature plaques and higher plaque volumes. Artificial-intelligence augmented CCTA analysis of APCs may be a promising metric for cardiac risk stratification and warrants further prospective investigation.

The effect of scan and patient parameters on the diagnostic performance of AI for detecting coronary stenosis on coronary CT angiography.

OBJECTIVES: To determine whether coronary computed tomography angiography (CCTA) scanning, scan preparation, contrast, and patient based parameters influence the diagnostic performance of an artificial intelligence (AI) based analysis software for identifying coronary lesions with ≥50% stenosis. BACKGROUND: CCTA is a noninvasive imaging modality that provides diagnostic and prognostic benefit to patients with coronary artery disease (CAD). The use of AI enabled quantitative CCTA (AI-QCT) analysis software enhances our diagnostic and prognostic ability, however, it is currently unclear whether software performance is influenced by CCTA scanning parameters. METHODS: CCTA and quantitative coronary CT (QCT) data from 303 stable patients (64 ± 10 years, 71% male) from the derivation arm of the CREDENCE Trial were retrospectively analyzed using an FDA-cleared cloud-based software that performs AI-enabled coronary segmentation, lumen and vessel wall determination, plaque quantification and characterization, and stenosis determination. The algorithm's diagnostic performance measures (sensitivity, specificity, and accuracy) for detecting coronary lesions of ≥50% stenosis were determined based on concordance with QCA measurements and subsequently compared across scanning parameters (including scanner vendor, model, single vs dual source, tube voltage, dose length product, gating technique, timing method), scan preparation technique (use of beta blocker, use and dose of nitroglycerin), contrast administration parameters (contrast type, infusion rate, iodine concentration, contrast volume) and patient parameters (heart rate and BMI). RESULTS: Within the patient cohort, 13% demonstrated ≥50% stenosis in 3 vessel territories, 21% in 2 vessel territories, 35% in 1 vessel territory while 32% had <50% stenosis in all vessel territories evaluated by QCA. Average AI analysis time was 10.3 ± 2.7 min. On a per vessel basis, there were significant differences only in sensitivity for ≥50% stenosis based on contrast type (iso-osmolar 70.0% vs non isoosmolar 92.1% p = 0.0345) and iodine concentration (<350 mg/ml 70.0%, 350-369 mg/ml 90.0%, 370-400 mg/ml 90.0%, >400 mg/ml 95.2%; p = 0.0287) in the context of low injection flow rates. On a per patient basis there were no significant differences in AI diagnostic performance measures across all measured scanner, scan technique, patient preparation, contrast, and individual patient parameters. CONCLUSION: The diagnostic performance of AI-QCT analysis software for detecting moderate to high grade stenosis are unaffected by commonly used CCTA scanning parameters and across a range of common scanning, scanner, contrast and patient variables. CONDENSED ABSTRACT: An AI-enabled quantitative CCTA (AI-QCT) analysis software has been validated as an effective tool for the identification, quantification and characterization of coronary plaque and stenosis through comparison to blinded expert readers and quantitative coronary angiography. However, it is unclear whether CCTA screening parameters related to scanner parameters, scan technique, contrast volume and rate, radiation dose, or a patient's BMI or heart rate at time of scan affect the software's diagnostic measures for detection of moderate to high grade stenosis. AI performance measures were unaffected across a broad range of commonly encountered scanner, patient preparation, scan technique, intravenous contrast and patient parameters.

Relationship of age, atherosclerosis and angiographic stenosis using artificial intelligence.

OBJECTIVE: The study evaluates the relationship of coronary stenosis, atherosclerotic plaque characteristics (APCs) and age using artificial intelligence enabled quantitative coronary computed tomographic angiography (AI-QCT). METHODS: This is a post-hoc analysis of data from 303 subjects enrolled in the CREDENCE (Computed TomogRaphic Evaluation of Atherosclerotic Determinants of Myocardial IsChEmia) trial who were referred for invasive coronary angiography and subsequently underwent coronary computed tomographic angiography (CCTA). In this study, a blinded core laboratory analysing quantitative coronary angiography images classified lesions as obstructive (≥50%) or non-obstructive (<50%) while AI software quantified APCs including plaque volume (PV), low-density non-calcified plaque (LD-NCP), non-calcified plaque (NCP), calcified plaque (CP), lesion length on a per-patient and per-lesion basis based on CCTA imaging. Plaque measurements were normalised for vessel volume and reported as % percent atheroma volume (%PAV) for all relevant plaque components. Data were subsequently stratified by age <65 and ≥65 years. RESULTS: The cohort was 64.4±10.2 years and 29% women. Overall, patients >65 had more PV and CP than patients <65. On a lesion level, patients >65 had more CP than younger patients in both obstructive (29.2 mm3 vs 48.2 mm3; p<0.04) and non-obstructive lesions (22.1 mm3 vs 49.4 mm3; p<0.004) while younger patients had more %PAV (LD-NCP) (1.5% vs 0.7%; p<0.038). Younger patients had more PV, LD-NCP, NCP and lesion lengths in obstructive compared with non-obstructive lesions. There were no differences observed between lesion types in older patients. CONCLUSION: AI-QCT identifies a unique APC signature that differs by age and degree of stenosis and provides a foundation for AI-guided age-based approaches to atherosclerosis identification, prevention and treatment.

Performance goals and endpoint assessments for clinical trials of femoropopliteal bare nitinol stents in patients with symptomatic peripheral arterial disease.

OBJECTIVE: This analysis proposes safety and performance goals for prospective single-arm trials of bare nitinol stents to treat patients with debilitating claudication associated with femoropopliteal (FP) atherosclerotic lesions. BACKGROUND: To date there have been no analyses of clinical trials data to set efficacy and safety benchmarks for new bare nitinol stents in the treatment of claudication from FP disease. Industry has been reluctant to sponsor studies of nitinol stents due to logistical barriers. METHODS: VIVA Physician's, Inc. (VPI) analyzed subject-level data from the PTA control arm of three randomized FDA device trials conducted by industry. Subjects with Rutherford category 2-4 claudication and FP lesion lengths 4-15 cm with 12 month duplex ultrasound (DUS) assessment were identified. These data were combined with the results of a survey of the medical literature (1990-2006) for similar subjects. RESULTS: Analysis of the industry derived control arm PTA data identified 116 patients (mean lesion length 8.7 cm) with a 12 month DUS defined FP patency of 28%. A similar cohort of 191 patients was identified from the medical literature in which the 12-month vessel patency equaled 37%; from these combined patient cohorts, expected vessel patency for PTA was estimated to equal 33%. CONCLUSION: Based on the PTA performance efficacy rate of 33% derived from industry clinical trial data and the medical literature, and the requirement that the bare nitinol stent 12-month efficacy performance goal be set to equal twice this rate, the patency efficacy goal equals 66%. Additional information is provided on safety and other reporting standards and stent integrity evaluation for bare metal stents.