Octree Representation Improves Data Fidelity of Cardiac CT Images and Convolutional Neural Network Semantic Segmentation of Left Atrial and Ventricular Chambers.
Kunal GuptaNitesh SekharDavis M VigneaultAnderson R ScottBrendan ColvertAmanda CraineAdhithi RaghavanFrancisco J ContijochPublished in: Radiology. Artificial intelligence (2021)
Octree-based representations can reduce the memory footprint and improve segmentation border accuracy.Keywords CT, Cardiac, Segmentation, Supervised Learning, Convolutional Neural Network (CNN), Deep Learning Algorithms, Machine Learning Algorithms© RSNA, 2021.
Keyphrases
- convolutional neural network
- deep learning
- machine learning
- left ventricular
- left atrial
- artificial intelligence
- big data
- image quality
- catheter ablation
- computed tomography
- mitral valve
- dual energy
- contrast enhanced
- working memory
- atrial fibrillation
- heart failure
- positron emission tomography
- magnetic resonance imaging
- magnetic resonance