Meeting Banner
Abstract #1283

Microstructure Quantification by Q-Space Trajectory Imaging via Unrolled Neural Networks: Exploring Model Generalizability

Jinyang Yu1,2, Oliver Gödicke1,3, Frederik B. Laun4, Mark E. Ladd1,3,5, and Tristan Anselm Kuder1,3
1Medical Physics in Radiology, German Cancer Research Center (DKFZ), Heidelberg, Germany, 2Faculty of Engineering Sciences, Heidelberg University, Heidelberg, Germany, 3Faculty of Physics and Astronomy, Heidelberg University, Heidelberg, Germany, 4Institute of Radiology, Universitätsklinikum Erlangen, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany, 5Medical Faculty Heidelberg, Heidelberg University, Heidelberg, Germany

Synopsis

Keywords: Microstructure, Diffusion Analysis and Visualization, Brain, Q-Space Trajectory Imaging, Algorithm Unrolling, Model Generalization

Motivation: Existing machine learning models for microparameter estimation in Q-Space Trajectory Imaging (QTI) suffer from limited generalizability, particularly when the q-space encoding varies between acquisition protocols.

Goal(s): To develop deep learning models that enhance computational efficiency and model generalization compared to voxel-wise training using multi-layer perceptrons.

Approach: We developed a convolutional neural network by unrolling the iterative hard-thresholding algorithm and applied a novel training strategy that involves random permutation (RP) of diffusion measurements.

Results: The new framework demonstrated superior efficiency and performance across evaluation metrics, with the RP strategy enabling effective learning on perturbated training data across variable q-space encoding schemes.

Impact: The developed network accelerates model training with higher fidelity than state-of-the-art machine learning methods. The RP approach enhances model robustness and supports generalizability, facilitating on-the-fly QTI microstructural estimation across different acquisition protocols, which may improve clinical utility.

How to access this content:

For one year after publication, abstracts and videos are only open to registrants of this annual meeting. Registrants should use their existing login information. Non-registrant access can be purchased via the ISMRM E-Library.

After one year, current ISMRM & ISMRT members get free access to both the abstracts and videos. Non-members and non-registrants must purchase access via the ISMRM E-Library.

After two years, the meeting proceedings (abstracts) are opened to the public and require no login information. Videos remain behind password for access by members, registrants and E-Library customers.

Click here for more information on becoming a member.

Keywords