Variational Autoencoders with a Structural Similarity Loss in Time of Flight MRAs

• Published in: arXiv.org
• Main Authors: Timmins, Kimberley M, Irene C van der Schaaf, Ruigrok, Ynte M, Velthuis, Birgitta K, Kuijf, Hugo J
• Format: Paper Journal Article
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 20.01.2021
• Subjects: Abnormalities; Aneurysms; Anomalies; Arteries; Artificial neural networks; Blood vessels; Computer Science - Computer Vision and Pattern Recognition; Computer Science - Learning; Datasets; Image quality; Image reconstruction; Image segmentation; Magnetic resonance; Optimization; Performance evaluation; Signal to noise ratio; Similarity

Time-of-Flight Magnetic Resonance Angiographs (TOF-MRAs) enable visualization and analysis of cerebral arteries. This analysis may indicate normal variation of the configuration of the cerebrovascular system or vessel abnormalities, such as aneurysms. A model would be useful to represent normal cere...