X-ray coronary angiography is a primary imaging technique for diagnosing coronary diseases. Although quantitative coronary angiography (QCA) provides morphological information of coronary arteries with objective quantitative measures, considerable training is required to identify the target vessels and understand the tree structure of coronary arteries. Despite the use of computer-aided tools, such as the edge-detection method, manual correction is necessary for accurate segmentation of coronary vessels. In the present study, we proposed a robust method for major vessel segmentation using deep learning models with fully convolutional networks. When angiographic images of 3302 diseased major vessels from 2042 patients were tested, deep learning networks accurately identified and segmented the major vessels in X-ray coronary angiography. The average F1 score reached 0.917, and 93.7% of the images exhibited a high F1 score > 0.8. The most narrowed region at the stenosis was distinctly captured with high connectivity. Robust predictability was validated for the external dataset with different image characteristics. For major vessel segmentation, our approach demonstrated that prediction could be completed in real time with minimal image preprocessing. By applying deep learning segmentation, QCA analysis could be further automated, thereby facilitating the use of QCA-based diagnostic methods.

To compare the diagnostic accuracy of on-site computed tomography (CT)-derived fractional flow reserve (FFR) and stress CT myocardial perfusion (CTP) in patients with coronary artery disease. Using a prospective CTP registry, 72 patients with invasive FFR were enrolled. CT-derived FFR was computed on-site using rest-phase CTP data. The diagnostic accuracies of coronary CT angiography (CCTA), CT-derived FFR, and stress CTP were evaluated using an area under the receiver-operating characteristic curve (AUC) with invasive FFR as a reference standard. Logistic regression and the net reclassification index (NRI) were used to evaluate incremental differences in CT-derived FFR or CTP compared with CCTA alone. The per-vessel prevalence of haemodynamically significant stenosis (FFR ≤ 0.80) was 39% (54/138). Per-vessel sensitivity and specificity were 94 and 66% for CCTA, 87 and 77% for CT-derived FFR, and 79 and 91% for CTP, respectively. There was no significant difference in the AUC values of CT-derived FFR and CTP (P = 0.845). The diagnostic performance of CCTA (AUC = 0.856) was improved by combining it with CT-derived FFR (AUC = 0.919, P = 0.004, NRI = 1.01) or CTP (AUC = 0.913, P = 0.004, NRI = 0.66). CT-derived FFR values had a moderate correlation with invasive FFR (r = 0.671, P < 0.001). On-site CT-derived FFR combined with CCTA provides an incremental diagnostic improvement over CCTA alone in identifying haemodynamically significant stenosis defined by invasive FFR, with a diagnostic accuracy comparable with CTP.

In percutaneous intervention for treatment of coronary plaques, guidewire navigation is a primary procedure for stent delivery. Steering a flexible guidewire within coronary arteries requires considerable training, and the non-linearity between the control operation and the movement of the guidewire makes precise manipulation difficult. Here, we introduce a deep reinforcement learning (RL) framework for autonomous guidewire navigation in a robot-assisted coronary intervention. Using Rainbow, a segment-wise learning approach is applied to determine how best to accelerate training using human demonstrations, transfer learning, and weight initialization. ‘State’ for RL is customized as a focus window near the guidewire tip, and subgoals are placed to mitigate a sparse reward problem. The RL agent improves performance, eventually enabling the guidewire to reach all valid targets in ‘stable’ phase. For the last 300 out of 1000 episodes, the success rates of the guidewire navigation to the distal-main and side targets were 98% and 99% in 2D and 3D phantoms, respectively. Our framework opens a new direction in the automation of robot-assisted intervention, providing guidance on RL in physical spaces involving mechanical fatigue.

Purpose The present study aims to improve precision of four-dimensional (4D) phase-contrast (PC) MRI technique by using multiple velocity encoding (VENC) parameters. Theory and Methods The 3D flow fields in an in vitro stenosis phantom and an in vivo ascending aorta were determined using a 4D PC-MRI sequence with multiple VENC values. The velocity field obtained for large VENC was combined with that from small VENC, unless velocity data were lost by phase aliasing and phase dispersion. Noise levels of the combined velocity fields were compared with the increasing overlapping number of VENC parameters. Results The phantom measurement showed that the multi-VENC acquisition reduced the noise levels in radial and axial velocities (> 24 cm/s at VENC = 300 cm/s) down to 0.80 ± 0.45 cm/s and 5.60 ± 2.63 cm/s, respectively. This increased the velocity-to-noise ratio (VNR) by approximately two-fold to six-fold depending on the locations. As a result, the multi-VENC measurement could visualize the low-velocity recirculating flows more clearly. Conclusion The multi-VENC measurement of 4D PC-MRI sequence increased the VNR distribution by reducing velocity noise. The improved VNR can be beneficial for investigating blood flow structures in a flow field with a high velocity dynamic range. Magn Reson Med 75:1909–1919, 2016.

We investigate the behavior of sectional lift coefficient of a flapping wing of a fruit-fly in hovering motion. Through three-dimensional numerical simulations, we show that during the stroke, the sectional lift coefficient significantly varies in time as well as in the spanwise direction owing to complex interactions between the wing and vortices in the wake. However, the time-averaged sectional lift force coefficient is inversely proportional to the spanwise distance from the rotation center except very near the wing-tip region. This is because the wing-tip vortex significantly decreases the lift force on the wing-tip region during and after midstroke.