Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 2 of 2
Full-Text Articles in Engineering
Differential Impact Of Blood Pressure Control Targets On Epicardial Coronary Flow After Transcatheter Aortic Valve Replacement, Brennan Vogl, Alejandra Chavez-Ponce, Adam Wentworth, Eric Erie, Pradeep Yadav, Vinod H. Thourani, Lakshmi Prasad Dasi, Brian Lindman, Mohamad Alkhouli, Hoda Hatoum
Differential Impact Of Blood Pressure Control Targets On Epicardial Coronary Flow After Transcatheter Aortic Valve Replacement, Brennan Vogl, Alejandra Chavez-Ponce, Adam Wentworth, Eric Erie, Pradeep Yadav, Vinod H. Thourani, Lakshmi Prasad Dasi, Brian Lindman, Mohamad Alkhouli, Hoda Hatoum
Michigan Tech Publications, Part 2
Background: The cause for the association between increased cardiovascular mortality rates and lower blood pressure (BP) after aortic valve replacement (AVR) is unclear. This study aims to assess how the epicardial coronary flow (ECF) after AVR varies as BP levels are changed in the presence of a right coronary lesion. Methods: The hemodynamics of a 3D printed aortic root model with a SAPIEN 3 26 deployed were evaluated in an in vitro left heart simulator under a range of varying systolic blood pressure (SBP) and diastolic blood pressure (DBP). ECF and the flow ratio index were calculated. Flow index value …
S-Net: A Multiple Cross Aggregation Convolutional Architecture For Automatic Segmentation Of Small/Thin Structures For Cardiovascular Applications, Nan Mu, Zonghan Lyu, Mostafa Rezaeitaleshmahalleh, Cassie Bonifas, Jordan Gosnell, Marcus Haw, Joseph Vettukattil, Jingfeng Jiang
S-Net: A Multiple Cross Aggregation Convolutional Architecture For Automatic Segmentation Of Small/Thin Structures For Cardiovascular Applications, Nan Mu, Zonghan Lyu, Mostafa Rezaeitaleshmahalleh, Cassie Bonifas, Jordan Gosnell, Marcus Haw, Joseph Vettukattil, Jingfeng Jiang
Michigan Tech Publications, Part 2
With the success of U-Net or its variants in automatic medical image segmentation, building a fully convolutional network (FCN) based on an encoder-decoder structure has become an effective end-to-end learning approach. However, the intrinsic property of FCNs is that as the encoder deepens, higher-level features are learned, and the receptive field size of the network increases, which results in unsatisfactory performance for detecting low-level small/thin structures such as atrial walls and small arteries. To address this issue, we propose to keep the different encoding layer features at their original sizes to constrain the receptive field from increasing as the network …