Experimental dataset for deep learning based simultaneous measurement of flow-wall dynamics (DL-SFW)

Several pathological phenomena are closely associated with mechanical properties of vessel and interactions of blood flow–wall dynamics. However, conventional techniques cannot easily measure these features. In this study, new deep learning-based simultaneous measurement of flow–wall dynamics (DL-SFW) is proposed by devising integrated neural network for super-resolved localization and vessel wall segmentation and combining with tissue motion measurement technique and flow velocimetry. The performance of DL-SFW is verified by comparing with conventional techniques for tissue-mimicking phantoms. DL-SFW improves relative errors in measurements of velocity, wall shear stress (WSS), and strain with up to 4.6-fold, 15.1-fold, and 22.2-fold, respectively. After performance verification, in vivo feasibility is demonstrated by applying DL-SFW to murine carotid artery with different pathological conditions: aging and diabetes mellitus (DM). Mean flow velocities and WSS values of the DM group decrease by 30% and 20% of those of the control group, respectively. The mean flow velocity and WSS of the aging group are slightly smaller than those of the control group. However, the strain values of the aging and DM groups are much smaller than that of the control group (p < 0.005). These results coincide with those from other flow velocimetry and elastography. The mutual comparison of flow–wall dynamics and histological analysis shows correlation between immunoreactive region and abnormal flow–wall dynamics interactions.This study elucidates excellent performance of DL-SFW in the simultaneous measurements of vascular stiffness and complicated flow–wall dynamics. These results provide useful information with high-resolution and accurate diagnosis of cardiovascular diseases.