K
Kevin Ho-Shon
Researcher at Macquarie University
Publications - 23
Citations - 236
Kevin Ho-Shon is an academic researcher from Macquarie University. The author has contributed to research in topics: Medicine & Deep learning. The author has an hindex of 6, co-authored 20 publications receiving 138 citations. Previous affiliations of Kevin Ho-Shon include Royal Prince Alfred Hospital & University of Sydney.
Papers
More filters
Journal ArticleDOI
A comparison of 4D flow MRI-derived wall shear stress with computational fluid dynamics methods for intracranial aneurysms and carotid bifurcations — A review
Jeremy Szajer,Kevin Ho-Shon +1 more
TL;DR: Pooled analysis suggests that WSS magnitudes obtained by 4D flow MRI are underestimated, while the relative distribution is reasonably accurate, the latter being an important factor for determining the natural history of intracranial aneurysms and other cerebrovascular diseases.
Journal ArticleDOI
Preoperative progressive pneumoperitoneum complementing chemical component relaxation in complex ventral hernia repair
Kristen E. Elstner,John W. Read,Omar Rodriguez-Acevedo,Kevin Ho-Shon,John Magnussen,Nabeel Ibrahim +5 more
TL;DR: PPP is a useful adjunct in the repair of complex ventral hernia, and helps to minimize the risks of postoperative abdominal compartment syndrome and the sequelae of fascial closure under tension, however, its benefits must be carefully weighed with the risk of serious complications.
Journal ArticleDOI
Convolutional neural networks for prostate magnetic resonance image segmentation
TL;DR: To improve the FCNN performance for prostate MRI segmentation, various structures of shortcut connections together with the size of a deep network are analyzed and eight different FCNNs-based deep 2D network structures for automatic MRI prostate segmentation are suggested.
Journal ArticleDOI
Optimized sampling and parameter estimation for quantification in whole body PET
TL;DR: The results show that estimates of MRGlu using sparse data and the optimized Bayesian approach are comparable with those obtained by standard methods and fully sampled data.
Proceedings ArticleDOI
From Chest X-Rays to Radiology Reports: A Multimodal Machine Learning Approach
TL;DR: An encoder-decoder based framework that can automatically generate radiology reports from medical images is proposed that uses a Convolutional Neural Network as an encoder coupled with a multi-stage Stacked Long Short-Term Memory as a decoder to generate reports.