Rationale and design of the EPLURIBUS Study (Evidence for a comPrehensive evaLUation of left ventRicle dysfnctIon By a whole-heart coverage cardiac compUted tomography Scanner)

A deep-learning approach for myocardial fibrosis detection in early contrast-enhanced cardiac CT images

Aims

Diagnosis of myocardial fibrosis is commonly performed with late gadolinium contrast-enhanced (CE) cardiac magnetic resonance (CMR), which might be contraindicated or unavailable. Coronary computed tomography (CCT) is emerging as an alternative to CMR. We sought to evaluate whether a deep learning (DL) model could allow identification of myocardial fibrosis from routine early CE-CCT images.

Methods and results

Fifty consecutive patients with known left ventricular (LV) dysfunction (LVD) underwent both CE-CMR and (early and late) CE-CCT. According to the CE-CMR patterns, patients were classified as ischemic (n = 15, 30%) or non-ischemic (n = 35, 70%) LVD. Delayed enhancement regions were manually traced on late CE-CCT using CE-CMR as reference. On early CE-CCT images, the myocardial sectors were extracted according to AHA 16-segment model and labeled as with scar or not, based on the late CE-CCT manual tracing. A DL model was developed to classify each segment. A total of 44,187 LV segments were analyzed, resulting in accuracy of 71% and area under the ROC curve of 76% (95% CI: 72%-81%), while, with the bull's eye segmental comparison of CE-CMR and respective early CE-CCT findings, an 89% agreement was achieved.

Conclusions

DL on early CE-CCT acquisition may allow detection of LV sectors affected with myocardial fibrosis, thus without additional contrast-agent administration or radiational dose. Such tool might reduce the user interaction and visual inspection with benefit in both efforts and time.

Comprehensive Evaluation of Left Ventricle Dysfunction by a New Computed Tomography Scanner: The E-PLURIBUS Study

BACKGROUND

Although cardiac magnetic resonance (CMR) is considered the gold standard for myocardial fibrosis detection, cardiac computed tomography (CCT) is emerging as a promising alternative.

OBJECTIVES

The purpose of this study was to assess feasibility and diagnostic accuracy of a comprehensive functional and anatomical evaluation with CCT as compared with CMR in patients with newly diagnosed left ventricular dysfunction (LVD).

METHODS

A total of 128 consecutive patients with newly diagnosed LVD were screened. Based on the exclusion criteria, 28 cases were excluded. CCT was performed within 10 days from CMR. Biventricular volumes and ejection fraction, and presence and pattern of delayed enhancement (DE), were determined, along with evaluation of coronary arteries among patients undergoing invasive angiography in the 6 months after CCT.

RESULTS

Six cases were excluded because of claustrophobia at CMR. Among the 94 patients who formed the study population, the concordance between CCT and CMR in suggesting the cause of the LVD was high (94.7%, 89/94 patients) in the overall population and was 100% for identifying ischemic cardiomyopathy. The CCT diagnostic rate for DE assessment was also high (96.7%, 1,544/1,598 territories) and similar to that of CMR (97.4%; P = 0.345, CCT vs CMR). Moreover, CCT showed high diagnostic accuracy in the detection of DE (94.8%, 95% CI: 93.6%-95.8%) in a territory-based analysis. Biventricular volumes and function parameters as measured by CCT and CMR were similar, without significant differences with the exception of a modest difference in RV volume. CCT was confirmed to be accurate for assessing arterial coronary circulation. The mean radiation exposure of the whole CCT was 7.78 ± 2.53 mSv (0.84 ± 0.24 mSv for DE).

CONCLUSIONS

CCT performed with low-dose whole-heart coverage scanner and high-concentration contrast agent appears an effective noninvasive tool for a comprehensive assessment of patients with newly diagnosed LVD.

The Potential Role of Cardiac CT in the Evaluation of Patients With Known or Suspected Cardiomyopathy: From Traditional Indications to Novel Clinical Applications

After 15 years from its advent in the clinical field, coronary computed tomography (CCTA) is now widely considered as the best first-step test in patients with low-to-moderate pre-test probability of coronary artery disease. Technological innovation was of pivotal importance for the extensive clinical and scientific interest in CCTA. Recently, the advent of last generation wide-coverage CT scans paved the way for new clinical applications of this technique beyond coronary arteries anatomy evaluation. More precisely, both biventricular volume and systolic function quantification and myocardial fibrosis identification appeared to be feasible with last generation CT. In the present review we would focus on potential applications of cardiac computed tomography (CCT), beyond CCTA, for a comprehensive assessment patients with newly diagnosed cardiomyopathy, from technical requirements to novel clinical applications.

State of the art paper: Cardiovascular CT for planning ventricular tachycardia ablation procedures

In the last 20 years coronary computed tomography angiography (CCTA) gained a pivotal role in the evaluation of patients with suspected coronary artery disease (CAD) as finally recognized by the ESC guidelines on stable CAD. Technological advances have progressively improved the temporal resolution of CT scanners, contemporary reducing acquisition time, radiation dose and contrast volume needed for the whole heart volume acquisition, further expanding the role of cardiac CT beyond coronary anatomy evaluation. Aim of the present review is to discuss use and benefit of cardiac CT for the planning and preparation of VT ablation.