Hardin Espinoza (chordgreen1)

© 2020 IOP Publishing Ltd.Epicardial adipose tissue (EAT) is a visceral fat deposit, that's known for its association with factors, such as obesity, diabetes mellitus, age, and hypertension. Segmentation of the EAT in a fast and reproducible way is important for the interpretation of its role as an independent risk marker intricate. However, EAT has a variable distribution, and various diseases may affect the volume of the EAT, which can increase the complexity of the already time-consuming manual segmentation work. We propose a 3D deep attention U-Net method to automatically segment the EAT from coronary computed tomography angiography (CCTA). Five-fold cross-validation and hold-out experiments were used to evaluate the proposed method through a retrospective investigation of 200 patients. The automatically segmented EAT volume was compared with physician-approved clinical contours. Quantitative metrics used were the Dice similarity coefficient (DSC), sensitivity, specificity, Jaccard index (JAC), Hausdorff distance (HD), mean surface distance (MSD), residual mean square distance (RMSD), and the center of mass distance (CMD). For cross-validation, the median DSC, sensitivity, and specificity were 92.7%, 91.1%, and 95.1%, respectively, with JAC, HD, CMD, MSD, and RMSD are 82.9% ± 8.8%, 3.77 ± 1.86mm, 1.98 ± 1.50mm, 0.37 ± 0.24mm, and 0.65 ± 0.37mm, respectively. For the hold-out test, the accuracy of the proposed method remained high. We developed a novel deep learning-based approach for the automated segmentation of the EAT on CCTA images. We demonstrated the high accuracy of the proposed learning-based segmentation method through comparison with ground truth contour of 200 clinical patient cases using 8 quantitative metrics, Pearson correlation, and Bland-Altman analysis. Our automatic EAT segmentation results show the potential of the proposed method to be used in computer-aided diagnosis of coronary artery diseases (CADs) in clinical settings. © 2020 Institute of Physics and Engineering in Medicine.OBJECTIVE Instrumental identification of proximal scleroderma, which is necessary for the early diagnosis of systemic sclerosis (SSD), has not yet been developed. The aim of this study was to assess the potential diagnostic value of the imaging photoplethysmography (IPPG) method in patients with SSD. APPROACH The study enrolled 19 patients with SSD and 21 healthy subjects matched by age and sex with the patients. Spatial distribution of capillary-blood-flow parameters and their dynamics was estimated in the facial area of patients and subjects. In the IPPG system, a 40-s video of the subject's face illuminated by green polarized light was recorded with a monochrome digital camera in synchronization with the electrocardiogram. Experimental data were processed by using custom software allowing assessment of an arrival time of the blood pressure wave (PAT), an amplitude of pulsatile component (APC) of the photoplethysmographic waveform, and their variability. MAIN RESULTS Our study has revealed significant increase of PAT variability in patients with SSD compared to the control group 52±47 ms vs 24±13 ms (P = 0.01). Similarly, the variability of PPG-pulse shape was larger in patients with SSD 0.13±0.07 % vs 0.09±0.02 % (P less then 0.001). In addition, patients with scleroderma showed significantly greater degree of asymmetry of APC parameter than the control group 17.7±9.7 vs 7.9±5.0 (P less then 0.001). Metabolism inhibitor At the same time, no correlation was found between the photoplethysmographic waveform parameters and either the form or duration of the disease. No relationship between the characteristics of the PPG waveform and the modified Rodnan skin score was found, as well. SIGNIFICANCE Novel instrumental markers found in our pilot study showed that the IPPG method can be used for diagnosing the systemic sclerosis in the early stages of the disease. © 2020 Institute of Physics and Engineering in Medicine.3D bioprinti