Scan-specific k-space interpolation using deep Koopman autoencoders
Wassim Ben Salah, Jon Cleary, Sarah McElroy, Raphael Tomi-Tricot, Antoine Naegel, Sebastien Ourselin, Jonathan Shapey, Christos Bergeles, Radhouene Neji
Abstract
Purpose: To develop a scan-specific, interpretable k-space interpolation technique for the reconstruction of accelerated MRI data. Methods: A deep Koopman autoencoder for nonlinear k-space interpolation was developed consisting of an encoder, a linear layer for interpolation and a decoder. The resulting network is implemented using mean square error loss function on k-space neighbourhoods derived from the autocalibration signals (ACS), combining a prediction loss and an autoencoding loss. The approach was compared to GRAPPA and RAKI in 281 retrospectively undersampled brain datasets, using quantitative reconstruction metrics. In a subset of 52 randomly selected images, a clinical reader study compared the proposed approach and RAKI in a forced choice scenario and using a five-point ordinal scoring, assessing sharpness, SNR, aliasing and overall image quality. Additionally, the effect of varying parameters such as the number of autocalibration signals, the contribution of the autoencoding loss, the kernel size, and the latent space dimension for the proposed technique was studied. Results: The proposed approach showed improved quantitative metrics compared to GRAPPA and RAKI. Visually, the method showed higher resilience to noise amplification and improved preservation of sharp details. In the clinical reader study, the proposed approach was preferred overall to RAKI and yielded higher scores than GRAPPA and RAKI. The proposed method showed robustness to parameter variations. Conclusion: Deep Learning based k-space interpolation can be achieved using a Koopman autoencoder for k-space neighbourhoods. Keywords: Parallel imaging, Koopman autoencoder, nonlinear mapping, k-space interpolation, deep learning reconstruction
Create a lesson
Related papers
Towards consensus on practical probabilistic evaluation metrics for clinical decision making in radiotherapy
Jenneke I. de Jong, Steven J. M. Habraken, Erik W. Korevaar et al.
Unmyelinated axons alter the biological interpretation of MRI biomarkers of demyelination
Ali Abdollahzadeh, Ricardo Coronado-Leija, Elizabeth Chasen et al.
Impact-Based Analysis Method (IBAM) to evaluate the primary stability of the pedicle screw: A proof of concept
Julie Gabriel, Yvan Petit, Giuseppe Rosi et al.
Geometry-bridge flow matching for blind rigid-motion correction in head cone-beam CT
Sungho Yun, Seungryong Cho
The relationship between junctional zone, smooth muscle tone and intra-uterine pressure
Nicolas R. Chevalier, Emilie Huon, Julie Poujol et al.
A Soft Sponge-Pillar Electrode Platform for Motion-Tolerant Ambulatory EEG and Sleep Monitoring
Chansoo Kim, Weilun Li, Ryan Andersen et al.