Background: Encephalitis is a common central nervous system inflammatory disease that seriously endangers human health owing to the lack of effective diagnostic methods, which leads to a high rate of misdiagnosis and mortality. Glutamate is implicated closely in microglial activation, and activated microglia are key players in encephalitis. Hence, using glutamate chemical exchange saturation transfer (GluCEST) imaging for the early diagnosis of encephalitis holds promise. Methods: The sensitivity of GluCEST imaging with different concentrations of glutamate and other major metabolites in the brain was validated in phantoms. Twenty-seven Sprague-Dawley (SD) rats with encephalitis induced by Staphylococcus aureus infection were used for preclinical research of GluCEST imaging in a 7.0-Tesla scanner. For the clinical study, six patients with encephalitis, six patients with lacunar infarction, and six healthy volunteers underwent GluCEST imaging in a 3.0-Tesla scanner. Results: The number of amine protons on glutamate that had a chemical shift of 3.0 ppm away from bulk water and the signal intensity of GluCEST were concentrationdependent. Under physiological conditions, glutamate is the main contributor to the GluCEST signal. Compared with normal tissue, in both rats and patients with encephalitis, the encephalitis areas demonstrated a hyper-intense GluCEST signal, while the lacunar infarction had a decreased GluCEST signal intensity. After intravenous immunoglobulin therapy, patients with encephalitis lesions showed a decrease in GluCEST signal, and the results were significantly different from the pre-treatment signal (1.34 ± 0.31 vs 5.0 ± 0.27%, respectively; p = 0.000).

This study aimed to analyse cerebral grey matter changes in mild cognitive impairment (MCI) using voxel-based morphometry and to diagnose early Alzheimer's disease using deep learning methods based on convolutional neural networks (CNNs) evaluating these changes. Participants (111 MCI, 73 normal cognition) underwent 3-T structural magnetic resonance imaging. The obtained images were assessed using voxel-based morphometry, including extraction of cerebral grey matter, analyses of statistical differences, and correlation analyses between cerebral grey matter and clinical cognitive scores in MCI. The CNN-based deep learning method was used to extract features of cerebral grey matter images. Compared to subjects with normal cognition, participants with MCI had grey matter atrophy mainly in the entorhinal cortex, frontal cortex, and bilateral frontotemporal lobes (p < 0.0001). This atrophy was significantly correlated with the decline in cognitive scores (p < 0.01). The accuracy, sensitivity, and specificity of the CNN model for identifying participants with MCI were 80.9%, 88.9%, and 75%, respectively. The area under the curve of the model was 0.891. These findings demonstrate that research based on brain morphology can provide an effective way for the clinical, non-invasive, objective evaluation and identification of early Alzheimer's disease.

No abstract