Current and Future Applications of Artificial Intelligence in Cardiac CT

PURPOSE OF REVIEW

In this review, we aim to summarize state-of-the-art artificial intelligence (AI) approaches applied to cardiovascular CT and their future implications.

RECENT FINDINGS

Recent studies have shown that deep learning networks can be applied for rapid automated segmentation of coronary plaque from coronary CT angiography, with AI-enabled measurement of total plaque volume predicting future heart attack. AI has also been applied to automate assessment of coronary artery calcium on cardiac and ungated chest CT and to automate the measurement of epicardial fat. Additionally, AI-based prediction models integrating clinical and imaging parameters have been shown to improve prediction of cardiac events compared to traditional risk scores. Artificial intelligence applications have been applied in all aspects of cardiovascular CT - in image acquisition, reconstruction and denoising, segmentation and quantitative analysis, diagnosis and decision assistance and to integrate prognostic risk from clinical data and images. Further incorporation of artificial intelligence in cardiovascular imaging holds important promise to enhance cardiovascular CT as a precision medicine tool.

Great debates in cardiac computed tomography: OPINION: "Artificial intelligence and the future of cardiovascular CT - Managing expectation and challenging hype"

This manuscript has been written as a follow-up to the "AI/ML great debate" featured at the 2021 Society of Cardiovascular Computed Tomography (SCCT) Annual Scientific Meeting. In debate style, we highlighti the need for expectation management of AI/ML, debunking the hype around current AI techniques, and countering the argument that in its current day format AI/ML is the "silver bullet" for the interpretation of daily clinical CCTA practice.

Hemodynamic impact of coronary stenosis using computed tomography: comparison between noninvasive fractional flow reserve and 3D fusion of coronary angiography with stress myocardial perfusion

Vasodilator-stress CT perfusion imaging in addition to CT coronary angiography (CTCA) may provide a single-test alternative to nuclear stress testing, commonly used to assess hemodynamic significance of stenosis. Another alternative is fractional flow reserve (FFR) calculated from cardiac CT images. We studied the concordance between these two approaches and their relationship to outcomes. We prospectively studied 150 patients with chest pain, who underwent CTCA and regadenoson CT. CTCA images were interpreted for presence and severity of stenosis. Fused 3D displays of subendocardial X-ray attenuation with coronary arteries were created to detect stress perfusion defects (SPD) in each coronary territory. In patients with stenosis > 25%, CT-FFR was quantified. Significant stenosis was determined by: (1) combination of stenosis > 50% with an SPD, (2) CT-FFR ≤ 0.80. Patients were followed-up for 36 ± 25 months for death, myocardial infarction or revascularization. After excluding patients with normal arteries and technical/quality issues, in final analysis of 76 patients, CTCA depicted stenosis > 70% in 13/224 arteries, 50-70% in 24, and < 50% in 187. CT-FFR ≤ 0.80 was found in 41/224 arteries, and combination of SPD with > 50% stenosis in 31/224 arteries. Inter-technique agreement was 89%. Despite high incidence of abnormal CT-FFR (30/76 patients), only 7 patients experienced adverse outcomes; 6/7 also had SPDs. Only 1/9 patients with CT-FFR ≤ 0.80 but normal perfusion had an event. Fusion of CTCA and stress perfusion can help determine the hemodynamic impact of stenosis in one test, in good agreement with CT-FFR. Adding stress CT perfusion analysis may help risk-stratify patients with abnormal CT-FFR.

Image reconstruction in cardiovascular CT: Part 2 - Iterative reconstruction; potential and pitfalls

The use of IR in CT previously has been prohibitively complicated and time consuming, however improvements in computer processing power now make it possible on almost all CT scanners. Due to its potential to allow scanning at lower doses, IR has received a lot of attention in the medical literature and has become a successful commercial product. Its use in cardiovascular CT has been driven in part due to concerns about radiation dose and image quality. This manuscript discusses the various vendor permutations of iterative reconstruction (IR) in detail and critically appraises the current clinical research available on the various IR techniques used in cardiovascular CT.

Non-invasive assessment of the haemodynamic significance of coronary stenosis using fusion of cardiac computed tomography and 3D echocardiography

Aims

Abnormal computed tomography coronary angiography (CTCA) often leads to stress testing to determine haemodynamic significance of stenosis. We hypothesized that instead, this could be achieved by fusion imaging of the coronary anatomy with 3D echocardiography (3DE)-derived resting myocardial deformation.

Methods and results

We developed fusion software that creates combined 3D displays of the coronary arteries with colour maps of longitudinal strain and tested it in 28 patients with chest pain, referred for CTCA (256 Philips scanner) who underwent 3DE (Philips iE33) and regadenoson stress CT. To obtain a reference for stenosis significance, coronaries were also fused with colour maps of stress myocardial perfusion. 3D displays were used to detect stress perfusion defect (SPD) and/or resting strain abnormality (RSA) in each territory. CTCA showed 56 normal arteries, stenosis <50% in 17, and >50% in 8 arteries. Of the 81 coronary territories, SPDs were noted in 20 and RSAs in 29. Of the 59 arteries with no stenosis >50% and no SPDs, considered as normal, 12 (20%) had RSAs. Conversely, with stenosis >50% and SPDs (haemodynamically significant), RSAs were considerably more frequent (5/6 = 83%). Overall, resting strain and stress perfusion findings were concordant in 64/81 arteries (79% agreement).

Conclusions

Fusion of CTCA and 3DE-derived data allows direct visualization of each coronary artery and strain in its territory. In this feasibility study, resting strain showed good agreement with stress perfusion, indicating that it may be potentially used to assess haemodynamic impact of coronary stenosis, as an alternative to stress testing that entails additional radiation exposure.

Fusion of Three-Dimensional Echocardiographic Regional Myocardial Strain with Cardiac Computed Tomography for Noninvasive Evaluation of the Hemodynamic Impact of Coronary Stenosis in Patients with Chest Pain

BACKGROUND

Combined evaluation of coronary stenosis and the extent of ischemia is essential in patients with chest pain. Intermediate-grade stenosis on computed tomographic coronary angiography (CTCA) frequently triggers downstream nuclear stress testing. Alternative approaches without stress and/or radiation may have important implications. Myocardial strain measured from echocardiographic images can be used to detect subclinical dysfunction. The authors recently tested the feasibility of fusion of three-dimensional (3D) echocardiography-derived regional resting longitudinal strain with coronary arteries from CTCA to determine the hemodynamic significance of stenosis. The aim of the present study was to validate this approach against accepted reference techniques.

METHODS

Seventy-eight patients with chest pain referred for CTCA who also underwent 3D echocardiography and regadenoson stress computed tomography were prospectively studied. Left ventricular longitudinal strain data (TomTec) were used to generate fused 3D displays and detect resting strain abnormalities (RSAs) in each coronary territory. Computed tomographic coronary angiographic images were interpreted for the presence and severity of stenosis. Fused 3D displays of subendocardial x-ray attenuation were created to detect stress perfusion defects (SPDs). In patients with stenosis >25% in at least one artery, fractional flow reserve was quantified (HeartFlow). RSA as a marker of significant stenosis was validated against two different combined references: stenosis >50% on CTCA and SPDs seen in the same territory (reference standard A) and fractional flow reserve < 0.80 and SPDs in the same territory (reference standard B).

RESULTS

Of the 99 arteries with no stenosis >50% and no SPDs, considered as normal, 19 (19%) had RSAs. Conversely, with stenosis >50% and SPDs, RSAs were considerably more frequent (17 of 24 [71%]). The sensitivity, specificity, and accuracy of RSA were 0.71, 0.81, and 0.79, respectively, against reference standard A and 0.83, 0.81, and 0.82 against reference standard B.

CONCLUSIONS

Fusion of CTCA and 3D echocardiography-derived resting myocardial strain provides combined displays, which may be useful in determination of the hemodynamic or functional impact of coronary abnormalities, without additional ionizing radiation or stress testing.

Three-dimensional quantification of myocardial perfusion during regadenoson stress computed tomography

BACKGROUND

There is no accepted methodology for CT-based vasodilator stress myocardial perfusion imaging and analysis. We developed a technique for quantitative 3D analysis of CT images, which provides several indices of myocardial perfusion. We sought to determine the ability of these indices during vasodilator stress to identify segments supplied by coronary arteries with obstructive disease and to test the accuracy of the detection of perfusion abnormalities against SPECT.

METHODS

We studied 93 patients referred for CT coronary angiography (CTCA) who underwent regadenoson stress. 3D analysis of stress CT images yielded segmental perfusion indices: mean X-ray attenuation, severity of defect and relative defect volume. Each index was averaged for myocardial segments, grouped by severity of stenosis: 0%, <50%, 50-70%, and >70%. Objective detection of perfusion abnormalities was optimized in 47 patients and then independently tested in the remaining 46 patients.

RESULTS

CTCA depicted normal coronary arteries or non-obstructive disease in 62 patients and stenosis of >50% in 31. With increasing stenosis, segmental attenuation showed a 7% decrease, defect severity increased 11%, but relative defect volume was 7-fold higher in segments with obstructive disease (p<0.001). In the test group, detection of perfusion abnormalities associated with stenosis >50% showed sensitivity 0.78, specificity 0.54, accuracy 0.59. When compared to SPECT in a subset of 21 patients (14 with abnormal SPECT), stress CT perfusion analysis showed sensitivity 0.79, specificity 0.71, accuracy 0.76.

CONCLUSIONS

3D analysis of vasodilator stress CT images provides quantitative indices of myocardial perfusion, of which relative defect volume was most robust in identifying segments supplied by arteries with obstructive disease. This study may have implications on how CT stress perfusion imaging is performed and analyzed.

Takeuchi repair of anomalous left coronary artery from the pulmonary artery

Anomalous left coronary artery from the pulmonary artery (ALCAPA) is a rare form of congenital heart disease that has been successfully palliated for decades. Prior to coronary reimplantation, the Takeuchi repair was the most common operative palliation. The Takeuchi repair is still seen today at less experienced congenital centers or when reimplantation is not possible. Patients who have had the Takeuchi repair are at risk of having subsequent complications related to this repair. Unfortunately, due to the surgical rarity, the post surgical anatomy is often poorly understood by cardiologists leading to inadequate risk factor assessment and compromised patient care. Coronary computed tomography angiography is a useful imaging modality to follow patients who have had the Takeuchi repair.