AI-based tool can measure plaque burden, stenosis severity on CCTA
USA: A recent study showed that in patients with stable chest pain, an artificial intelligence (AI)-based tool can rapidly and accurately measure plaque volume and stenosis severity from the images of coronary CT angiography (CCTA). Also, it has the potential for better prediction of future myocardial infarction (MI) as it agrees closely with expert readers and intravascular ultrasound. The study appears in the journal Lancet: Digital Health.
Coronary CT angiography is the first-line test for the evaluation of coronary artery stenosis severity. AI algorithms are increasingly being applied to CCTAfor improving the efficiency and accuracy of image analysis, demonstrating high performance when compared with expert readers. Deep learning is a type of AI that uses artificial neural networks for generating automated predictions directly from image data.
Quantification of Atherosclerotic plaque from CCTA enables accurate assessment of coronary artery disease burden and prognosis. Andrew Lin, Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, CA, USA, and colleagues sought to develop and validate a deep learning system for CCTA-derived measures of plaque volume and stenosis severity in an international, multicentre study.
The study included nine cohorts of patients undergoing CCTA at 11 sites. They were assigned to training and test sets. Data were retrospectively collected on patients with a wide range of clinical presentations of coronary artery disease who underwent CCTA between Nov 18, 2010, and Jan 25, 2019.
The researchers trained a novel deep learning convolutional neural network to segment coronary plaque in 921 patients (5045 lesions). Then, the deep learning network was applied to an independent test set that included an external validation cohort of 175 patients (1081 lesions) and 50 patients (84 lesions). This was assessed by intravascular ultrasound within 1 month of CCTA.
The prognostic value of deep learning-based plaque measurements was evaluated for fatal or non-fatal myocardial infarction (primary outcome) in 1611 patients from the prospective SCOT-HEART trial.
The study led to the following findings:
· In the overall test set, there was excellent or good agreement, respectively, between deep learning and expert reader measurements of total plaque volume (intraclass correlation coefficient [ICC] 0·964) and percent diameter stenosis (ICC 0·879).
· When compared with intravascular ultrasound, there was an excellent agreement for deep learning total plaque volume (ICC 0·949) and minimal luminal area (ICC 0·904).
· The mean per-patient deep learning plaque analysis time was 5·65 s versus 25·66 min taken by experts.
· Over a median follow-up of 4·7 years, myocardial infarction occurred in 41 (2·5%) of 1611 patients from the SCOT-HEART trial.
· A deep learning-based total plaque volume of 238·5 mm3 or higher was associated with an increased risk of myocardial infarction (hazard ratio [HR] 5·36) after adjustment for the presence of deep learning-based obstructive stenosis (HR 2·49) and the ASSIGN clinical risk score (HR 1·01).
"Our novel, externally validated deep learning system provides rapid measurements of plaque volume and stenosis severity from CCTA," the authors concluded. "This agrees closely with expert readers and intravascular ultrasound and could have prognostic value for future myocardial infarction."
The study titled, "Deep learning-enabled coronary CT angiography for plaque and stenosis quantification and cardiac risk prediction: an international multicentre study," was published in the journal Lancet: Digital Health.
KEYWORDS: Lancet, artificial intelligence, coronary CT angiography, CCTA, AI, deep learning, myocardial infarction, Andrew Lin, stenosis, coronary plaque, computed tomography
Medha Baranwal joined Medical Dialogues as an Editor in 2018 for Speciality Medical Dialogues. She covers several medical specialties including Cardiac Sciences, Dentistry, Diabetes and Endo, Diagnostics, ENT, Gastroenterology, Neurosciences, and Radiology. She has completed her Bachelors in Biomedical Sciences from DU and then pursued Masters in Biotechnology from Amity University. She has a working experience of 5 years in the field of medical research writing, scientific writing, content writing, and content management. She can be contacted at firstname.lastname@example.org. Contact no. 011-43720751