To determine the value of dual-energy CT (DECT) and combined information of perfusion and angiography in diagnosing coronary artery disease (CAD), with single photon emission computed tomography (SPECT) and quantitative coronary angiography (QCA) as a reference standard. Thirty-four patients were enrolled in this study. DECT was used as a contrast-enhanced retrospectively ECG-gated scan protocol during the rest state and tubes were set at 140/100 kV. DECT angiography (DE-CTA) and DECT perfusion (DE-CTP) were calculated from two kV images. DE-CTP results were compared with SPECT and DE-CTA with QCA, respectively. The combined DE-CTP with DE-CTA data were compared to QCA in diagnosis of obstructive CAD (stenosis ≥ 50%). DECT showed diagnostic image quality in 31 patients. Using SPECT as a reference, DE-CTP had sensitivity of 68%, specificity of 93%, and sensitivity of 81%, and specificity of 92% for identifying any type of perfusion deficits on the segment- and territory-based analysis, respectively. Using QCA as a reference standard, DE-CTA showed sensitivity of 82%, specificity of 91% and accuracy of 86% for detecting ≥50% coronary stenosis on the vessel-based analysis, whereas the combination of DE-CTA and DE-CTP gave sensitivity of 90%, specificity of 86% and accuracy of 88% for detecting ≥50% coronary stenosis, respectively. Combination of DE-CTP and DE-CTA may improve diagnostic performance compared to CTA alone for the diagnosis of significant coronary stenosis.
The automatic recognition of micro-expression has been boosted ever since the successful introduction of deep learning approaches. As researchers working on such topics are moving to learn from the nature of micro-expression, the practice of using deep learning techniques has evolved from processing the entire video clip of micro-expression to the recognition on apex frame. Using the apex frame is able to get rid of redundant video frames, but the relevant temporal evidence of micro-expression would be thereby left out. This paper proposes a novel Apex-Time Network (ATNet) to recognize micro-expression based on spatial information from the apex frame as well as on temporal information from the respective-adjacent frames. Through extensive experiments on three benchmarks, we demonstrate the improvement achieved by learning such temporal information. Specially, the model with such temporal information is more robust in cross-dataset validations.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.