Hierarchical stochastic neighbor embedding as a tool for visualizing the encoding capability of magnetic resonance fingerprinting dictionaries

TL;DR

This paper demonstrates how Hierarchical Stochastic Neighbor Embedding (HSNE) can visualize and compare the encoding capabilities of different Magnetic Resonance Fingerprinting (MRF) sequences, aiding in understanding their effectiveness.

Contribution

The study introduces HSNE as a novel tool for visualizing high-dimensional MRF dictionaries, enabling detailed comparison of sequence encoding capabilities and effects of transmit field variations.

Findings

HSNE effectively visualizes MRF dictionary encoding capabilities.

Differences between sequences are clearly distinguishable in HSNE embeddings.

HSNE results align with traditional MRF matching simulations.

Abstract

In Magnetic Resonance Fingerprinting (MRF) the quality of the estimated parameter maps depends on the encoding capability of the variable flip angle train. In this work we show how the dimensionality reduction technique Hierarchical Stochastic Neighbor Embedding (HSNE) can be used to obtain insight into the encoding capability of different MRF sequences. Embedding high-dimensional MRF dictionaries into a lower-dimensional space and visualizing them with colors, being a surrogate for location in low-dimensional space, provides a comprehensive overview of particular dictionaries and, in addition, enables comparison of different sequences. Dictionaries for various sequences and sequence lengths were compared to each other, and the effect of transmit field variations on the encoding capability was assessed. Clear differences in encoding capability were observed between different sequences, and HSNE results accurately reflect those obtained from an MRF matching simulation.