Selectively Probing the Magnetic Resonance Signals of γ-Aminobutyric Acid in Human Brains In Vivo

BACKGROUND

Gamma-aminobutyric acid (GABA) is an inhibitory neurotransmitter in human brains, playing a role in the pathogenesis of various psychiatric disorders. Current methods have some non-neglectable shortcomings and noninvasive and accurate detection of GABA in human brains is long-term challenge.

PURPOSE

To develop a pulse sequence capable of selectively detecting and quantifying the 1 H signal of GABA in human brains based on optimal controlled spin singlet order.

STUDY TYPE

Prospective.

SUBJECTS/PHANTOM

A phantom of GABA (pH = 7.3 ± 0.1) and 11 healthy subjects (5 females and 6 males, body mass index: 21 ± 3 kg/m2 , age: 25 ± 4 years).

FIELD STRENGTH/SEQUENCE

7 Tesla, 3 Tesla, GABA-targeted magnetic resonance spectroscopy (GABA-MRS-7 T, GABA-MRS-3 T), magnetization prepared two rapid acquisition gradient echoes sequence.

ASSESSMENT

By using the developed pulse sequences applied on the phantom and healthy subjects, the signals of GABA were successfully selectively probed. Quantification of the signals yields the concentration of GABA in the dorsal anterior cingulate cortex (dACC) in human brains.

STATISTICAL TESTS

Frequency.

RESULTS

The 1 H signals of GABA in the phantom and in the human brains of healthy subjects were successfully detected. The concentration of GABA in the dACC of human brains was 3.3 ± 1.5 mM.

DATA CONCLUSION

The developed pulse sequences can be used to selectively probe the 1 H MR signals of GABA in human brains in vivo.

EVIDENCE LEVEL

1 TECHNICAL EFFICACY STAGE: 1.

An automatic interpretable deep learning pipeline for accurate Parkinson's disease diagnosis using quantitative susceptibility mapping and T1-weighted images

Parkinson's disease (PD) diagnosis based on magnetic resonance imaging (MRI) is still challenging clinically. Quantitative susceptibility maps (QSM) can potentially provide underlying pathophysiological information by detecting the iron distribution in deep gray matter (DGM) nuclei. We hypothesized that deep learning (DL) could be used to automatically segment all DGM nuclei and use relevant features for a better differentiation between PD and healthy controls (HC). In this study, we proposed a DL-based pipeline for automatic PD diagnosis based on QSM and T1-weighted (T1W) images. This consists of (1) a convolutional neural network model integrated with multiple attention mechanisms which simultaneously segments caudate nucleus, globus pallidus, putamen, red nucleus, and substantia nigra from QSM and T1W images, and (2) an SE-ResNeXt50 model with an anatomical attention mechanism, which uses QSM data and the segmented nuclei to distinguish PD from HC. The mean dice values for segmentation of the five DGM nuclei are all >0.83 in the internal testing cohort, suggesting that the model could segment brain nuclei accurately. The proposed PD diagnosis model achieved area under the the receiver operating characteristic curve (AUCs) of 0.901 and 0.845 on independent internal and external testing cohorts, respectively. Gradient-weighted class activation mapping (Grad-CAM) heatmaps were used to identify contributing nuclei for PD diagnosis on patient level. In conclusion, the proposed approach can potentially be used as an automatic, explainable pipeline for PD diagnosis in a clinical setting.