Diagnostic performance of deep learning to exclude coronary stenosis on CT angiography in TAVI patients.

We evaluated the diagnostic performance of a deep-learning model (DLM) (CorEx®, Spimed-AI, Paris, France) designed to automatically detect > 50% coronary stenosis on coronary computed tomography angiography (CCTA) images. We studied inter-observer variability as an additional aim. CCTA images obtained before transcatheter aortic valve implantation (TAVI) were assessed by two radiologists and the DLM, and the results were compared to those of invasive coronary angiography (ICA) used as the reference standard. 165 consecutive patients underwent both CCTA and ICA as part of their TAVI work-up. We excluded the 42 (25.5%) patients with a history of stenting or bypass grafting and the 23 (13.9%) patients with low-quality images. We retrospectively subjected the CCTA images from the remaining 100 patients to evaluation by the DLM and compared the DLM and ICA results. All 25 patients with > 50% stenosis by ICA also had > 50% stenosis by DLM evaluation of CCTA: thus, the DLM had 100% sensitivity and 100% negative predictive value. False-positive DLM results were common, yielding a positive predictive value of only 39% (95% CI, 27-51%). Two radiologists with 3 and 25 years' experience, respectively, performed similarly to the DLM in evaluating the CCTA images; thus, accuracy did not differ significantly between each reader and the DLM (p = 0.625 and p = 0.375, respectively). The DLM had 100% negative predictive value for > 50% stenosis and performed similarly to experienced radiologists. This tool may hold promise for identifying the up to one-third of patients who do not require ICA before TAVI.

[Benefits and drawbacks of CT scan as a triple rule-out exam in acute chest pain to exclude acute coronary syndrome, pulmonary embolism and aortic dissection]. / Le scanner thoracique injecté « triple-rule-out ¼ a-t-il un intérêt dans le bilan des douleurs thoraciques aiguës pour éliminer le syndrome coronaire aigu, l'embolie pulmonaire et la dissection aortique ?

Chest pain is one of the major causes for admission in the Emergency Room in most countries and one of the principal reasons for urgent consultation with a cardiologist or a general practitioner. After clinical examination and initial biological measurements, substantial patients require further explorations. CT scan allows the search for pulmonary embolism in the early stage of pulmonary arteries iodine contrast exploration. During the same exam at the systemic arterial phase, the search for aortic dissection or coronary artery disease is possible while exploring the later contrast in the aortic artery. This triple rule-out exam allows correct diagnosis in case of acute chest pain with suspected pulmonary embolism, aortic dissection and other acute aortic syndromes or acute coronary syndrome. But X-rays are substantially increased as well as iodine contrast agent quantity while exam quality is globally decreased. Artificial intelligence may play an important role in the development of this protocol.

MDCT planning of trans catheter aortic valve implantation (TAVI): determination of optimal c-arm angulation.

A fluoroscopic view perpendicular to the aortic valve annulus is required during transcatheter aortic valve implantation (TAVI) for obtaining an optimal deployment of the bioprosthesis. By predicting c-arm angulation, pre-procedural MDCT could decrease the number of aortograms, shorten the time of the procedure and reduce the amount of intra-arterial contrast agent. The aim of our study was to assess the accuracy of MDCT in predicting c-arm angulation at the cath. lab. In this single center study, we investigated MDCT prediction of c-arm angulation in patients having undergone a TAVI procedure using SAPIEN 3® (Edwards Lifesciences, USA). Prior to the procedure, an experienced radiologist had reported the angulation using dedicated software (CTreport). After the procedure, a blinded experienced radiologist retrospectively measured the angles using the same method (CTstudy). Interobserver variability was drawn from the comparison between CTreport and CTstudy. Then, the mean angular difference between the predicted MDCT angles (CTstudy) was compared to the working view recorded at the cath. lab. Seventy-nine patients (M/F = 0.65; mean age: 85.2 years ± 5.3) were included. Interobserver variability was 5.9 ± 6.1°. The mean absolute difference between MDCT and fluoroscopy was 8.8 ± 7.1°. The present study showed that MDCT could predict the coplanar fluoroscopic angles prior to TAVI using a balloon-expandable bioprosthesis Sapien 3® placed via a transfemoral approach with a mean angular difference of 8.8 ± 7.1°. Reproducibility was considered good as the mean difference between two independent measures was 5.9 ± 6.1°.