Open Access. Powered by Scholars. Published by Universities.®

Medicine and Health Sciences Commons

Open Access. Powered by Scholars. Published by Universities.®

Articles 1 - 4 of 4

Full-Text Articles in Medicine and Health Sciences

Institutional Strategies To Maintain And Grow Imaging Research During The Covid-19 Pandemic, Mai-Lan Ho, Corey W Arnold, Summer J Decker, John D Hazle, Elizabeth A Krupinski, David A Mankoff Apr 2023

Institutional Strategies To Maintain And Grow Imaging Research During The Covid-19 Pandemic, Mai-Lan Ho, Corey W Arnold, Summer J Decker, John D Hazle, Elizabeth A Krupinski, David A Mankoff

Student and Faculty Publications

Understanding imaging research experiences, challenges, and strategies for academic radiology departments during and after COVID-19 is critical to prepare for future disruptive events. We summarize key insights and programmatic initiatives at major academic hospitals across the world, based on literature review and meetings of the Radiological Society of North America Vice Chairs of Research (RSNA VCR) group. Through expert discussion and case studies, we provide suggested guidelines to maintain and grow radiology research in the postpandemic era.


Pocketnet: A Smaller Neural Network For Medical Image Analysis, Adrian Celaya, Jonas A Actor, Rajarajesawari Muthusivarajan, Evan Gates, Caroline Chung, Dawid Schellingerhout, Beatrice Riviere, David Fuentes Apr 2023

Pocketnet: A Smaller Neural Network For Medical Image Analysis, Adrian Celaya, Jonas A Actor, Rajarajesawari Muthusivarajan, Evan Gates, Caroline Chung, Dawid Schellingerhout, Beatrice Riviere, David Fuentes

Student and Faculty Publications

Medical imaging deep learning models are often large and complex, requiring specialized hardware to train and evaluate these models. To address such issues, we propose the PocketNet paradigm to reduce the size of deep learning models by throttling the growth of the number of channels in convolutional neural networks. We demonstrate that, for a range of segmentation and classification tasks, PocketNet architectures produce results comparable to that of conventional neural networks while reducing the number of parameters by multiple orders of magnitude, using up to 90% less GPU memory, and speeding up training times by up to 40%, thereby allowing …


Recent Trends In Soft-Tissue Infection Imaging., Nicholas Petruzzi, Md, Nylla Shanthly, Mbbs, Drm, Mathew L. Thakur, Phd Mar 2009

Recent Trends In Soft-Tissue Infection Imaging., Nicholas Petruzzi, Md, Nylla Shanthly, Mbbs, Drm, Mathew L. Thakur, Phd

Department of Radiation Oncology Faculty Papers

This article discusses the current techniques and future directions of infection imaging with particular attention to respiratory, central nervous system, abdominal, and postoperative infections. The agents currently in use localize to areas of infection and inflammation. An infection-specific imaging agent would greatly improve the utility of scintigraphy in imaging occult infections. The superior spatial resolution of (18)F-fluorodeoxyglucose positron emission tomography ((18)F-FDG-PET) and its lack of reliance on a functional immune system, gives this agent certain advantages over the other radiopharmaceuticals. In respiratory tract infection imaging, an important advancement would be the ability to quantitatively delineate lung inflammation, allowing one to …


Long-Distance Three-Color Neuronal Tracing In Fixed Tissue Using Neurovue Dyes, Heather Jensen Smith, Brian Gray, Katharine Muirhead, Betsy Ohlsson-Wilhelm, Bernd Fritzsch Jan 2007

Long-Distance Three-Color Neuronal Tracing In Fixed Tissue Using Neurovue Dyes, Heather Jensen Smith, Brian Gray, Katharine Muirhead, Betsy Ohlsson-Wilhelm, Bernd Fritzsch

Journal Articles: Eppley Institute

Dissecting development of neuronal connections is critical for understanding neuronal function in both normal and diseased states. Charting the development of the multitude of connections is a monumental task, since a given neuron typically receives hundreds of convergent inputs from other neurons and provides divergent outputs for hundreds of other neurons. Although progress is being made utilizing various mutants and/or genetic constructs expressing fluorescent proteins like GFP, substantial work remains before a database documenting the development and final location of the neuronal pathways in an adult animal is completed. The vast majority of developing neurons cannot be specifically labeled with …