Showing 6 Abstracts.
Convolutional neural networks (CNNs) have proven to be valuable in the fields of image processing and computer vision. Our work applies complex-valued CNNs to magnetic resonance imaging (MRI) to reduce scan times. The reduction of scan times has widespread pediatric benefits. A typical scan requires that patients remain still for up to an hour to produce a clear image, which is difficult for children without inducing anesthesia, which carries risks. A need exists for greatly improved MRI scan times without the loss of diagnostic accuracy. This scan time can be reduced by subsampling in k-space. We use CNNs to reconstruct images from these undersampled acquisitions. Our work investigates complex-valued CNNs for image reconstruction in lieu of two-channel real-valued CNNs. Read More
Meeting name: SPR 2019 Annual Meeting & Postgraduate Course , 2019
Authors: Cole Elizabeth, Pauly John, Vasanawala Shreyas, Cheng Joseph
Keywords: Magnetic Resonance Imaging, deep learning, Neural network
Though first line evaluation of bone lesions is projection radiography (XR), this is often supplemented by both computed tomography (CT), with attendant ionizing radiation, and MRI for associated marrow and soft-tissue assessment. However, if bone can be evaluated on MRI as well, then a CT may be obviated. Thus, we aim to assess an isotropic Zero Echo Time (ZTE) MRI sequence. Read More
Meeting name: SPR 2020 Annual Meeting & Postgraduate Course , 2020
Authors: Sandberg Jesse, Yuan Jianmin, Wishah Fidaa, Vasanawala Shreyas
To assess the image quality and clinical performance of a novel accelerated, free-breathing 2D cine cardiac MR sequence with DCNN reconstruction in comparison to conventional breath-held 2D cine balanced steady-state free precession (bSSFP). Read More
Meeting name: SPR 2020 Annual Meeting & Postgraduate Course , 2020
Authors: Zucker Evan, Sandino Christopher, Kino Aya, Lai Peng, Vasanawala Shreyas
Keywords: Cardiac, MRI, Deep Learning
The purpose of this study is to develop a method of training pediatric patients in effective breathing during magnetic resonance imaging (MRI). Read More
Meeting name: IPR 2016 Conjoint Meeting & Exhibition , 2016
Authors: Alford Raphael, Jain Shreyan, Cheng Joseph, Zhang Tao, Vasanawala Shreyas
Keywords: Biofeedback, Non-sedated MRI, Respiratory Training
To evaluate by CCTA the prevalence and morphology of pediatric LAD MBs (coronary segments that contact or tunnel within myocardium), which are common and usually incidental in adults but only sporadically reported in children. Read More
Meeting name: SPR 2020 Annual Meeting & Postgraduate Course , 2020
Authors: Zucker Evan, Kino Aya, Vasanawala Shreyas, Newman Beverley, Barth Richard, Chan Frandics
Keywords: Myocardial Bridge, Coronary CTA, Coronary
Diffusion weighted (DW) imaging is a standard component of many MRI exams. For musculoskeletal examinations, DW is used as a tool for assessing malignant and infectious/inflammatory processes. A recently developed novel silent and distortionless DWI sequence (DW-SD) has been previously shown to have less distortion and noise as well as having equivalent diffusion contrast and ADC values in normal tissues to standard echo-planar DW imaging (DW-EPI). We aim in this study to validate and assess this novel DW-SD method in pediatric extremity pathology cases. Read More
Meeting name: SPR 2020 Annual Meeting & Postgraduate Course , 2020
Authors: Sandberg Jesse, Yuan Jianmin, Hu Yuxin, Sandino Christopher, Menini Anne, Hargreaves Brian, Vasanawala Shreyas