Background: Spinocerebellar ataxia type 3 (SCA3) is the most common autosomal dominant hereditary ataxia, and, thus far, effective treatment remains low. Repetitive transcranial magnetic stimulation (rTMS) can improve the symptoms of spinal cerebellar ataxia, but the mechanism is unclear; in addition, whether any improvement in the symptoms is related to cerebellar metabolism has not yet been investigated. Therefore, the purpose of this study was to investigate the effects of low-frequency rTMS on local cerebellar metabolism in patients with SCA3 and the relationship between the improvement in the symptoms and cerebellar metabolism.Methods: A double-blind, prospective, randomized, sham-controlled trial was carried out among 18 SCA3 patients. The participants were randomly assigned to the real stimulation group (n = 9) or sham stimulation group (n = 9). Each participant in both the groups underwent 30 min of 1 Hz rTMS stimulation (a total of 900 pulses), differing only in terms of stimulator placement, for 15 consecutive days. To separately compare pre- and post-stimulation data (magnetic resonance spectroscopy (MRS) data and the International Cooperative Ataxia Rating Scale (ICARS) score) in the real and sham groups, paired-sample t-tests and Wilcoxon’s signed-rank tests were used in the analyses. The differences in the ICARS and MRS data between the two groups were analyzed with independent t-tests and covariance. To explore the association between the changes in the concentration of cerebellar metabolism and ICARS, we applied Pearson’s correlation analysis.Results: After 15 days of treatment, the ICARS scores significantly decreased in both the groups, while the decrease was more significant in the real stimulation group compared to the sham stimulation group (p < 0.001). The analysis of covariance further confirmed that the total ICARS scores decreased more dramatically in the real stimulation group after treatment compared to the sham stimulation group (F = 31.239, p < 0.001). The values of NAA/Cr and Cho/Cr in the cerebellar vermis, bilateral dentate nucleus, and bilateral cerebellar hemisphere increased significantly in the real stimulation group (p < 0.05), but no significant differences were found in the sham stimulation group (p > 0.05). The analysis of covariance also confirmed the greater change in the real stimulation group. This study also demonstrated that there was a negative correlation between NAA/Cr in the right cerebellar hemisphere and ICARS in the real stimulation group (r = − 0.831, p = 0.02).Conclusion: The treatment with rTMS over the cerebellum was found to induce changes in the cerebellar local metabolism and microenvironment in the SCA3 patients. The alterations may contribute to the improvement of the symptoms of ataxia in SCA3 patients.

Objectives: Spinocerebellar ataxia type 3 is a disorder within the brain network. However, the relationship between the brain network and disease severity is still unclear. This study aims to investigate changes in the white matter (WM) structural motor network, both in preclinical and ataxic stages, and its relationship with disease severity.Methods: For this study, 20 ataxic, 20 preclinical SCA3 patients, and 20 healthy controls were recruited and received MRI scans. Disease severity was quantified using the SARA and ICARS scores. The WM motor structural network was created using probabilistic fiber tracking and was analyzed using graph theory and network‐based statistics at global, nodal, and edge levels. In addition, the correlations between network topological measures and disease duration or clinical scores were analyzed.Results: Preclinical patients showed increasing assortativity of the motor network, altered subnetwork including 12 edges of 11 nodes, and 5 brain regions presenting reduced nodal strength. In ataxic patients assortativity of the motor network also increased, but global efficiency, global strength, and transitivity decreased. Ataxic patients showed a wider altered subnetwork and a higher number of reduced nodal strengths. A negative correlation between the transitivity of the motor network and SARA and ICARS scores was observed in ataxic patients.Interpretation: Changes to the WM motor network in SCA3 start before ataxia onset, and WM motor network involvement increases with disease progression. Global network topological measures of the WM motor network appear to be a promising image biomarker for disease severity. This study provides new insights into the pathophysiology of disease in SCA3/MJD.

Objective: To develop a machine learning (ML)-based classifier for discriminating between low-grade (ISUP I-II) and high-grade (ISUP III-IV) clear cell renal cell carcinomas (ccRCCs) using MRI textures.Materials and Methods: We retrospectively evaluated a total of 99 patients (with 61 low-grade and 38 high-grade ccRCCs), who were randomly divided into a training set (n = 70) and a validation set (n = 29). Regions of interest (ROIs) of all tumors were manually drawn three times by a radiologist at the maximum lesion level of the cross-sectional CMP sequence images. The quantitative texture analysis software, MaZda, was used to extract texture features, including histograms, co-occurrence matrixes, run-length matrixes, gradient models, and autoregressive models. Reproducibility of the texture features was assessed with the intra-class correlation coefficient (ICC). Features were chosen based on their importance coefficients in a random forest model, while the multi-layer perceptron algorithm was used to build a classifier on the training set, which was later evaluated with the validation set.Results: The ICCs of 257 texture features were equal to or higher than 0.80 (0.828–0.998. Six features, namely Kurtosis, 135dr_RLNonUni, Horzl_GLevNonU, 135dr_GLevNonU, S(4,4)Entropy, and S(0,5)SumEntrp, were chosen to develop the multi-layer perceptron classifier. A three-layer perceptron model, which has 229 nodes in the hidden layer, was trained on the training set. The accuracy of the model was 95.7% with the training set and 86.2% with the validation set. The areas under the receiver operating curves were 0.997 and 0.758 for the training and validation sets, respectively.Conclusions: A machine learning-based grading model was developed that can aid in the clinical diagnosis of clear cell renal cell carcinoma using MRI images.