Deep Learning to Automate Reference-Free Image Quality Assessment of Whole-Heart MR Images.
Davide PicciniRobin DemesmaekerJohn HeerfordtJérôme YerlyLorenzo Di SopraPier Giorgio MasciJuerg SchwitterD Van De VilleJonas RichiardiTobias KoberMatthias StuberPublished in: Radiology. Artificial intelligence (2020)
The proposed IQ-DCNN was trained to mimic expert visual image quality assessment of 3D whole-heart MR images. The results from the IQ-DCNN were in good agreement with human expert reading, and the network was capable of automatically comparing different reconstructed volumes.Supplemental material is available for this article.© RSNA, 2020.
Keyphrases
- deep learning
- convolutional neural network
- artificial intelligence
- heart failure
- endothelial cells
- contrast enhanced
- clinical practice
- machine learning
- magnetic resonance
- atrial fibrillation
- induced pluripotent stem cells
- working memory
- pluripotent stem cells
- magnetic resonance imaging
- resistance training
- computed tomography