No abstract

Artificial Intelligence (AI) has impacted every aspect of clinical medicine, and is predicted to revolutionise diagnosis, treatment and patient care. Through novel machine learning (ML) and deep learning (DL) techniques, AI has made significant grounds in cardiology and cardiac investigations, including echocardiography. Echocardiography is a ubiquitous tool that remains first-line for the evaluation of many cardiovascular diseases, with large data sets, objective parameters, widespread availability and an excellent safety profile, it represents the perfect candidate for AI advancement. As such, AI has firmly made its stamp on echocardiography, showing great promise in training, image acquisition, interpretation and analysis, diagnostics, prognostication and phenotype development. However, there remain significant barriers in real-world clinical application and uptake of AI derived algorithms in echocardiography, most importantly being the lack of clinical outcome studies. While AI has been shown to match or even best its human counterparts, an improvement in real world outcomes remains to be established. There are also legal and ethical concerns that hinder its progress. Large outcome focused trials and a collaborative multi-disciplinary effort will be necessary to push AI into the clinical workspace. Despite this, current and emerging trials suggest that these systems will undoubtedly transform echocardiography, improving clinical utility, efficiency and training.

Introduction Coronary computed tomography angiography (CCTA) has emerged as a reliable non-invasive modality to assess coronary artery stenosis (CAS) severity and vulnerable plaque (VP). However, comprehensive CCTA assessment, especially VP, is time-consuming and dependent on reader expertise, limiting CCTA's true potential. Purpose In this study, we aim to develop and validate a deep learning (DL) based system capable of evaluating CAS severity and characterising VP on CCTA. Methods A DL system was trained to assess CAS severity on 3909 expert annotated vessels. A subset of 824 vessels was used to train the model to assess for the presence of VP. The model was based on a 2D U-Net and 3D convolutional neural network architecture. The system automatically performed vessel tracking and segmentation to quantify stenosis severity and characterise the presence of VP. CAS severity was categorised as 0%, 1–49% and ≥50%. VP was defined as: low attenuation plaque (LAP; ≤30 Hounsfield units), positive remodelling (PR; ≥10% diameter) and spotty calcification (SC; <3mm). The model was then tested on 1435 vessels for CAS (mean calcium score 197±502) and a subset of 365 vessels for VP (mean calcium score 419±551), and its diagnostic performance compared with expert readers. Results The CAS testing data had a prevalence of 75% (1080/1435), 18% (257/1435) and 6.8% (98/1435) for 0%, 1–49% and ≥50% stenosis, respectively. VP was present in 20% (72/365) in the respective dataset with 44% (32/72) LAP, 19% (14/72) PR and 36% (26/72) SC. Average analysis time for CAS severity and VP was 3.7±2.0s and 3.5±1.8s, respectively. Diagnostic performance of our system is summarised in Tables 1 (CAS severity) and 2 (VP characteristics). Conclusions We developed an DL based system capable of rapidly evaluating CAS severity and characterising VP on CCTA. Our system demonstrated high specificity and accuracy for both CAS severity and VP quantification when compared with expert readers. Funding Acknowledgement Type of funding sources: None.

No abstract