RESUMEN
Objective:To explore the value of a deep learning model based on MRI in predicting the methylation status of MGMT in WHO Ⅱ, Ⅲ gliomas.Methods:The clinical and imaging data of 121 patients with WHO grade Ⅱ, Ⅲ glioma confirmed by surgical pathology and molecular pathology in the Second Hospital of Lanzhou University from June 2016 to June 2020 were retrospectively analyzed. Among them, the MGMT promoter was methylated. A total of 78 cases were metabolized and 43 cases were unmethylated. T 2WI and T 1WI enhanced sequence images of 121 cases of WHO Ⅱ, Ⅲ gliomas were collected, and all the images of each patient including the lesion level were selected manually, and were randomly divided into training set and validation set according to 7∶3. The EfficientNet-B3 convolutional neural network was used to build independent prediction models (T 2-net, T 1C-net, TS-net) based on T 2WI, T 1WI enhancement, T 2WI combined with T 1WI enhancement, and the prediction performance of each model was evaluated separately through the ROC curve. Results:The T 2-net model in the validation set presented an accuracy of 72.3%, a sensitivity of 64.7%, a specificity of 73.3%, and an area under the curve (AUC) of 0.72 for predicting the methylation status of the MGMT promoter in WHO Ⅱ, Ⅲ gliomas. The T 1C-net model showed an accuracy of 66.8%, a sensitivity of 68.3%, a specificity of 66.9%, and an AUC of 0.72. The TS-net model showed an accuracy of 81.8%, a sensitivity of 63.1%, a specificity of 85.0%, and AUC of 0.78. Conclusions:The EfficientNet-B3 convolutional neural network based on MRI can predict the methylation status of the MGMT promoter of WHO Ⅱ, Ⅲ gliomas; the TS-net model has the best prediction performance.
RESUMEN
PURPOSE: Microcystic meningioma (MCM) appears similar to atypical meningioma(AM) as per conventional diagnostic imaging. However, considering their different recurrence rate and prognosis, accurate differential diagnosis is essential for determine the appropriate treatment strategy. The aim of the study was to differentiate MCM from AM by diffusion-weighted imaging (DWI), in order to provide the basis for accurate preoperative diagnosis. METHODS: The preoperative clinical data, conventional MRI and DWI data of 15 MCM and 30 AM cases were retrospectively analyzed. The average apparent diffusion coefficient (ADCmean), minimum ADC (ADCmin) and normalized ADC (nADC) between MCM and AM were compared using two sample t-tests. The value of ADCmean, ADCmin and nADC in the differential diagnosis of MCM and AM were calculated by the receiver operating curve (ROC) analysis. RESULTS: The ADCmean (1.06 ± 0.10 vs 0.80 ± 0.11 × 10-3 mm2/s; P < 0.001), ADCmin (0.99 ± 0.10 vs 0.74 ± 0.12 × 10-3 mm2/s; P < 0.001) and nADC (1.45 ± 0.17 vs 1.07 ± 0.17; P < .0001) were significantly higher in MCM compared to AM. ADCmean of 0.91 × 10-3 mm2/s showed an optimum area under the ROC curve of 0.967 ± 0.022, and distinguished between MCM and AM with 86.67% sensitivity, 100% specificity and 88.89% accuracy. In addition, its positive and negative predictive values were 96.29% and 77.78% respectively. CONCLUSIONS: DWI can differentially diagnose MCM and AM, and ADCmean is a potential quantitative tool that can improve preoperative diagnosis of both tumors.
