A Multiscale Deep Learning Method for Quantitative Visualization of Traumatic Hemoperitoneum at CT: Assessment of Feasibility and Comparison with Subjective Categorical Estimation.

David Dreizin Yuyin Zhou Shuhao Fu Yan Wang Guang Li Kathryn Champ Eliot L SiegelZe WangTina ChenAlan L Yuille

Published in: Radiology. Artificial intelligence (2020)

A multiscale deep learning method for traumatic hemoperitoneum quantitative visualization had improved diagnostic performance for predicting hemorrhage-control interventions and mortality compared with subjective volume estimation. Supplemental material is available for this article. © RSNA, 2020.

Keyphrases

machine learning
deep learning
artificial intelligence
spinal cord injury
convolutional neural network
high resolution
sleep quality
computed tomography
type diabetes
magnetic resonance imaging
contrast enhanced
dual energy
risk factors
cardiovascular disease
positron emission tomography
depressive symptoms