By providing automated and objective results, deep learning may reduce inter-observer variability and interpretative error among physicians
Deep learning offers significant promise in plaque quantification from CCTA and, when applied to CCTA scans, automatically detects and contours the heart arteries and underlying atherosclerotic plaques. This, Lin pointed out, enables rapid measurements of plaque volume and coronary artery stenosis directly from standard CCTA images, with high accuracy compared to expert readers and at a far faster rate than the usual analysis time. Lin also noted that deep learning from CCTA agreed with the invasive reference standard of intravascular ultrasound to measure total plaque volume and minimum luminal area.
He now believes a deep learning system that rapidly and accurately estimates coronary artery stenosis could become a ‘second reader’ and clinical decision support tool. ‘By providing automated and objective results, deep learning may reduce inter-observer variability and interpretative error among physicians. The system also could be used as pre-screen CCTA scans, flagging patients with obstructive disease to be prioritised for clinical reporting.’
In summation, CCTA could guide the use of preventive therapies, improve event-free survival, and reduce further unnecessary testing. AI-enabled image analysis might also improve the efficiency and speed of CCTA testing.
Dr Andrew Lin is a postdoctoral researcher in the Biomedical Imaging Research Institute, Cedars-Sinai Medical Center, Los Angeles, California, (Mentorship: Dr Damini Dey). His research focuses on the application of artificial intelligence and advanced analytics techniques to plaque imaging with CCTA.
Source: Healthcare in Europe