Hybrid 3D/2D Convolutional Neural Network for Hemorrhage Evaluation on Head CT.

Peter Chang Edward Kuoy Jack Grinband Brent D Weinberg M Thompson Richelle L Homo Jefferson W Chen H Abcede Mohammad Shafie Leo P Sugrue Christopher G Filippi Min-Ying Lydia Su Wengui Yu Christopher P Hess Daniel S Chow

Published in: AJNR. American journal of neuroradiology (2018)

A customized deep learning tool is accurate in the detection and quantification of hemorrhage on NCCT. Demonstrated high performance on prospective NCCTs ordered from the emergency department suggests the clinical viability of the proposed deep learning tool.

Keyphrases

deep learning
convolutional neural network
emergency department
artificial intelligence
machine learning
computed tomography
contrast enhanced
image quality
dual energy
high resolution
loop mediated isothermal amplification
label free
positron emission tomography
magnetic resonance
adverse drug
pet ct