Quantitative Susceptibility Mapping using Deep Neural Network: QSMnet

Iron, Myelin, and the Brain: Neuroimaging Meets Neurobiology.

The influence of brain iron and myelin on magnetic susceptibility and effective transverse relaxation - A biochemical and histological validation study.

https://vbn.aau.dk/ws/files/300737701/1_s2.0_S1053811919302605_main.pdf

DeepQSM - using deep learning to solve the dipole inversion for quantitative susceptibility mapping.

A growing body of evidence suggests that the dysregulation of neuronal iron may play a critical role in Alzheimer's disease. Recent MRI studies have established a relationship between iron accumulation and amyloid-β aggregation. The present study provides further insight demonstrating a relationship between iron and tau accumulation using magnetic resonance-based quantitative susceptibility mapping and tau-PET in n = 236 subjects with amyloid-β pathology (from the Swedish BioFINDER-2 study). Both voxel-wise and regional analyses showed a consistent association between differences in bulk magnetic susceptibility, which can be primarily ascribed to an increase in iron content, and tau-PET signal in regions known to be affected in Alzheimer's disease. Subsequent analyses revealed that quantitative susceptibility specifically mediates the relationship between tau-PET and cortical atrophy measures, thus suggesting a modulatory effect of iron burden on the disease process. We also found evidence suggesting the relationship between quantitative susceptibility and tau-PET is stronger in younger participants (age ≤ 65). Together, these results provide in vivo evidence of an association between iron deposition and both tau aggregation and neurodegeneration, which help advance our understanding of the role of iron dysregulation in the Alzheimer's disease aetiology.

/pdf/relationship-between-cortical-iron-and-tau-aggregation-in-42rxh23hp1.pdf

Relationship between cortical iron and tau aggregation in Alzheimer’s disease

Purpose
The aim of the 2016 quantitative susceptibility mapping (QSM) reconstruction challenge was to test the ability of various QSM algorithms to recover the underlying susceptibility from phase data faithfully.

Methods
Gradient-echo images of a healthy volunteer acquired at 3T in a single orientation with 1.06 mm isotropic resolution. A reference susceptibility map was provided, which was computed using the susceptibility tensor imaging algorithm on data acquired at 12 head orientations.

Susceptibility maps calculated from the single orientation data were compared against the reference susceptibility map. Deviations were quantified using the following metrics: root mean squared error (RMSE), structure similarity index (SSIM), high-frequency error norm (HFEN), and the error in selected white and gray matter regions.

Results
Twenty-seven submissions were evaluated. Most of the best scoring approaches estimated the spatial frequency content in the ill-conditioned domain of the dipole kernel using compressed sensing strategies. The top 10 maps in each category had similar error metrics but substantially different visual appearance.

Conclusion
Because QSM algorithms were optimized to minimize error metrics, the resulting susceptibility maps suffered from over-smoothing and conspicuity loss in fine features such as vessels. As such, the challenge highlighted the need for better numerical image quality criteria. Magn Reson Med, 2017. © 2017 International Society for Magnetic Resonance in Medicine.

https://onlinelibrary.wiley.com/doi/pdf/10.1002/mrm.26830

Jinsuh Kim

Papers

Quantitative susceptibility mapping: Report from the 2016 reconstruction challenge.