A Deep Learning-Based Approach to Reduce Rescan and Recall Rates in Clinical MRI Examinations.

A Sreekumari D Shanbhag Desmond Teck Beng Yeo Thomas K F Foo Julie Georgia Pilitsis J Polzin U Patil Ailish C Coblentz Anish N Kapadia J Khinda Alexandre Boutet John D Port Ileana Hancu

Published in: AJNR. American journal of neuroradiology (2019)

Fast, automated deep learning-based image-quality rating can decrease rescan and recall rates, while rendering them technologist-independent. It was estimated that decreasing rescans and recalls from the technologists' values to the values of deep learning could save hospitals $24,000/scanner/year.

Keyphrases

deep learning
image quality
artificial intelligence
convolutional neural network
computed tomography
machine learning
magnetic resonance imaging
healthcare
contrast enhanced
magnetic resonance
dual energy
diffusion weighted imaging