Open Access. Powered by Scholars. Published by Universities.®
Articles 1 - 6 of 6
Full-Text Articles in Radiology
Automated Assessment Of Cardiothoracic Ratios On Chest Radiographs Using Deep Learning, Varun Danda, Paras Lakhani, Md
Automated Assessment Of Cardiothoracic Ratios On Chest Radiographs Using Deep Learning, Varun Danda, Paras Lakhani, Md
Phase 1
Introduction: The cardiothoracic ratio (CTR) is a quantitative measure of cardiac size that can measured from chest radiography (CXR). Although radiologists using digital workstations possess the ability to calculate CTR, clinical demands prevent calculation for every case. In this study, the efficacy of a deep convolutional neural network (dCNN) to assess CTR was evaluated.
Methods: 611 HIPAA-compliant de-identified CXRs were obtained from [institution blinded] and public databases. Using ImageJ, a board-certified radiologist (reader #1) and a medical student (reader #2), measured the CTR by marking four pixels on all CXRs: the right- and left-most chest wall, the right- and left-most …
Effect Of Contrast-Enhanced Echocardiograms On The Prognosis Of Infective Endocarditis, D. Arias, E. Halpern, F. Forsberg, J. R. Eisenbrey
Effect Of Contrast-Enhanced Echocardiograms On The Prognosis Of Infective Endocarditis, D. Arias, E. Halpern, F. Forsberg, J. R. Eisenbrey
Phase 1
Objective - Infective endocarditis (IE) is an infectious disease of the cardiac valves where bacteria colonize the valves; typically, via the formation of vegetations. Recent research has shown that the microbubbles in a contrast-enhanced ultrasound (CEUS) examination can move and dislodge bacterial vegetations in vitro. This study investigated whether CEUS resulted in faster resolution of IE in vivo by dislodging the vegetations.
Methods - This IRB approved retrospective study reviewed 36 patients who were diagnosed with IE via echocardiography. Data was sourced from patients within the Jefferson University Hospital’s Cardiology EMR system by searching for contrast and vegetation from …
What Is The Effect Of Iodine Contrast Agents On The Subharmonic Signal Generated From Ultrasound Contrast Agents?, Neal Kalantri, Cara Esposito, Jaydev Dave
What Is The Effect Of Iodine Contrast Agents On The Subharmonic Signal Generated From Ultrasound Contrast Agents?, Neal Kalantri, Cara Esposito, Jaydev Dave
Phase 1
Subharmonic-aided pressure estimation (SHAPE) is a technique utilizing subharmonic signals from microbubble-based ultrasound contrast agents (UCA’s) to noninvasively record pressures. Cardiac applications of SHAPE have been demonstrated in canines where low errors (0.19-2.5mmHg) were observed in canine ventricle pressures between the SHAPE technique and pressure catheter measurements. Validation of SHAPE involves simultaneous measurements by a pressure catheter (iodine contrast is used to guide catheter placement) and by SHAPE using UCAs. The goal of this experiment is to determine if mixing Visipaque (iodine contrast, GE Healthcare, Oslo, Norway) and UCAs effects the subharmonic signal.
The study was performed in an in …
Hepatocellular Carcinoma Treated With Microwave Ablation Prior To Liver Transplantation, Nicole Wagner, Amanda Smolock, Michael Markovitz, Varun Danda, Christopher Neely, Warren Maley, Jesse Civan, Colette Shaw
Hepatocellular Carcinoma Treated With Microwave Ablation Prior To Liver Transplantation, Nicole Wagner, Amanda Smolock, Michael Markovitz, Varun Danda, Christopher Neely, Warren Maley, Jesse Civan, Colette Shaw
Phase 1
Introduction: Ablation is a minimally invasive procedure that limits local liver tumor progression and prolongs patients’ transplantation eligibility. Microwave ablation (MWA) utilizes higher temperatures than the standard of care, radiofrequency ablation (RFA), which increases efficiency. Meta-analyses compared MWA with RFA for the treatment of HCC and showed similar efficacy and safety between these modalities. However, limited pathologic data exists determining whether explanted tumors remained viable after MWA.
Methods: Our database was reviewed retrospectively for patients with HCC who underwent MWA prior to liver transplantation between 2013 and 2019. Patient demographics, etiology of disease, tumor size, procedure details, bilirubin, MELD, …
Assessment Of Dobhoff Tube Malposition On Radiographs Using Deep Learning, Kevin George, Paras Lakhani, Md
Assessment Of Dobhoff Tube Malposition On Radiographs Using Deep Learning, Kevin George, Paras Lakhani, Md
Phase 1
Introduction: Dobhoff tubes (DHT) are narrow-bore flexible devices that deliver enteral nutrition for critically ill patients. Tracheobronchial insertion of DHTs presents a significant risk for pulmonary complications. Thus, DHT insertion requires radiologist confirmation of correct placement with chest x-ray (CXR), increasing clinical delays. To address this, we demonstrate the novel application of Deep Convolutional Neural Networks (DCNNs) to automatically and accurately identify DHTs in CXRs in real time.
Methods: 141 de-identified HIPAA compliant frontal view chest radiographs containing DHTs in various positions were obtained. The DHTs were first manually segmented and verified by a board certified radiologist. Images were split …
3d Convolutional Neural Networks For The Diagnosis Of 6 Unique Pathologies On Head Ct, Travis Clarke, Paras Lakhani, Md
3d Convolutional Neural Networks For The Diagnosis Of 6 Unique Pathologies On Head Ct, Travis Clarke, Paras Lakhani, Md
Phase 1
Introduction: Head CT scans are a standard first-line tool used by physicians in the diagnosis of neurological pathologies. Recently, the development of deep learning models such as convolutional neural networks (CNNs) has allowed the rapid identification of bleeds and other pathologies on CT scans. This study aims to show that by training 3D CNNs with a larger, curated dataset, a more comprehensive list of potential diagnoses can be included in the detailed model.
Methods: A retrospective study was performed using a dataset of 66,000 head CT studies from the Thomas Jefferson University health system. Studies were acquired using a natural …