1. Magnetic Resonance Fingerprinting Reconstruction via Spatiotemporal Convolutional Neural Networks
- Author
-
Balsiger, Fabian, Konar, Amaresha Shridhar, Chikop, Shivaprasad, Chandran, Vimal, Scheidegger, Olivier, Geethanath, Sairam, and Reyes, Mauricio
- Subjects
Computer Science - Computer Vision and Pattern Recognition - Abstract
Magnetic resonance fingerprinting (MRF) quantifies multiple nuclear magnetic resonance parameters in a single and fast acquisition. Standard MRF reconstructs parametric maps using dictionary matching, which lacks scalability due to computational inefficiency. We propose to perform MRF map reconstruction using a spatiotemporal convolutional neural network, which exploits the relationship between neighboring MRF signal evolutions to replace the dictionary matching. We evaluate our method on multiparametric brain scans and compare it to three recent MRF reconstruction approaches. Our method achieves state-of-the-art reconstruction accuracy and yields qualitatively more appealing maps compared to other reconstruction methods. In addition, the reconstruction time is significantly reduced compared to a dictionary-based approach., Comment: Accepted for Machine Learning for Medical Image Reconstruction (MLMIR) workshop at MICCAI 2018. The revision corrects Amaresha's last name and Section 2.1 (scanner type and flip angles)
- Published
- 2018
- Full Text
- View/download PDF