Mulitmedia Library
Validation of deep-learning image reconstruction for coronary computed tomography angiography: Impact on noise, image quality and diagnostic accuracy
The present study evaluated the impact of deep-learning image reconstruction (DLIR) on noise, image quality, and diagnostic accuracy. In 43 patients who underwent clinically indicated coronary CT angiography and invasive coronary angiography, image quality was improved by up to 62% at similar noise levels. In addition, DLIR-H yielded the highest noise reduction (up to 43%) and best image quality (improvement of up to 138%). More importantly, sensitivity (92% vs. 88%), specificity (73% vs. 73%) and diagnostic accuracy (82% vs. 80%) of DLIR were at least non-inferior to ASiR-V.Artificial intelligence machine learning-based coronary CT fractional flow reserve (CT-FFRML): Impact of iterative and filtered back projection reconstruction techniques
The influence of computed tomography (CT) reconstruction algorithms on the performance of machine-learning-based CT-derived fractional flow reserve (CT-FFRML) has not been investigated. CT-FFRML values and processing time of two reconstruction algorithms were compared using an on-site workstation.
