Objective To observe the value of synthetic MRI(SynMRI)and diffusion tensor imaging(DTI)for evaluating grade and isocitrate dehydrogenase-1(IDH-1)status of adult gliomas.Methods Totally 115 patients with adult glioma were retrospectively enrolled and divided into adult low-grade glioma(aLGG)group(n=44)and adult high-grade glioma(aHGG)group(n=71)according to WHO classification.There were 30 cases of IDH-1 mutant type,2 cases of wild type and 12 cases of undetermined gliomas in aLGG group,whereas 26 cases of IDH-1 mutant type,24 cases of wild type and 21 cases undetermined gliomas in aHGG group,respectively.SynMRI and DTI parameters,including T1 value,T2 value,proton density(PD),apparent diffusion coefficient(ADC)and fractional anisotropy(FA)were compared between groups,and the efficacy of each parameter for distinguishing aLGG and aHGG,as well as IDH-1 mutant type and wild type was analyzed.Results Significant differences of T1 value,T2 value,ADC and FA were found between groups,also between IDH-1 mutant type and wild type gliomas within aHGG group(all P＜0.05).The area under the curve(AUC)of the above parameters for distinguishing aLGG and aHGG was 0.731,0.686,0.930 and 0.710,respectively,while for distinguishing IDH-1 mutant type and wild type in aHGG group was 0.775,0.729,0.817 and 0.705,respectively,among which ADC had the highest AUC(all P＜0.05).Conclusion SynMRI and DTI parameters such as T1 value,T2 value,ADC and FA were helpful for distinguishing aLGG and aHGG,IDH-1 mutant type and wild type,among which ADC had the highest efficacy.

Objective:To investigate the value of a deep learning model based on diffusion-weighted imaging (DWI) in quick identification of the TOAST etiology classification in patients with acute ischemic stroke (AIS).Methods:In this cross-sectional study, imaging and clinical data of 504 patients with AIS admitted to the First Affiliated Hospital of Xinjiang Medical University from March 2023 to February 2024 were retrospectively reviewed. Using the TOAST etiology classification, there were 252 large artery atherosclerosis type and 252 small-artery occlusion type. The 504 cases were divided into a training set ( n=302), a validation set ( n=101) and a test set ( n=101) using stratified randomization in the ratio of 6∶2∶2. All cases had DWI data. A DenseNet network framework was used to construct DenseNet models by optimizing the model configurations of different layers. Three DenseNet models with different layers (121, 169, 201) were constructed, named DenseNet169 model, DenseNet121 model, and DenseNet201 model. The data enhancement, Adam optimizer and cross-entropy loss function methods were used to improve the convergence speed and robustness of the model, and to balance the positive and negative sample imbalance problem. Independent sample t-test or χ2 was used to compare the clinical data of patients with large artery atherosclerosis type and small-artery occlusion type AIS. Receiver operating characteristic curves and area under the curve (AUC) were performed to evaluate the efficacy of each model in identification of patients with large artery atherosclerosis type and small-artery occlusion type AIS. Results:There were statistically significant differences in age, National Institutes of Health Stroke Scale score at admission, and stenosis or occlusion of large vessels between patients with large artery atherosclerosis type and small-artery occlusion (all P<0.05). In the test set, the AUC, sensitivity, accuracy, and F1 score values of the DenseNet201 model for discriminating patients with large artery atherosclerosis type AIS and small-artery occlusion type AIS (0.826, 0.902, 0.743, 0.780, respectively) were higher than those of DenseNet121 (0.801, 0.647, 0.723, 0.702, respectively) and DenseNet169 model (0.778, 0.882, 0.733, 0.769). Conclusions:The deep learning models based DWI constructed in this study can help with the TOAST etiology classification of AIS cases. DenseNet201 model shows the best and stable performance in the deep learning-based classification.