In clinical diagnosis of brain tumors, accurate segmentation based on multimodal magnetic resonance imaging (MRI) is essential for determining tumor type, extent, and spatial boundaries. However, differences in imaging mechanisms, information emphasis, and feature distributions among multimodal MRI data have posed significant challenges for precise tumor modeling and fusion-based segmentation. In recent years, fusion neural networks have provided effective strategies for integrating multimodal information and have become a major research focus in multimodal brain tumor segmentation. This review systematically summarized relevant studies on fusion neural networks for multimodal brain tumor segmentation published since 2019. First, the fundamental concepts of multimodal data fusion and model fusion were introduced. Then, existing methods were categorized into three types according to fusion levels: prediction fusion models, feature fusion models, and stage fusion models, and their structural characteristics and segmentation performance were comparatively analyzed. Finally, current limitations were discussed, and potential development trends of fusion neural networks for multimodal MRI brain tumor segmentation were summarized. This review aims to provide references for the design and optimization of future multimodal brain tumor segmentation models.
ObjectiveAnalysis prophylactic anti-epileptic drugs (AEDs) therapy in patients with brain tumor-related epilepsy (BTE) to observe whether seizures occurance, frequency will decrease, and the adverse reactions risk assessment of the patient's after using AEDs in 3 months and 12 month.
MethodsRetrospective analysis of the cases and follow-up data of patients with the diagnosis of brain tumors in the Second Affiliated Hospital of Chongqing Medical University in June 2011 to February 2015. Through the strict inclusion criteria and exclusion criteria review, the sixty-eight standard patients were divided into two groups:treatment group (44 cases) and control group (24 cases), and compared in the incidence of epilepsy and seizure frequency two groups of patients, and observe the adverse reactions after using AEDs. And analyzed the outcome of patients with brain tumors at 3 months and 2 months.
ResultsThrough at least 1 year follow up, compared the data of patients in the two groups with seizure incidence at 3 months and with seizures frequency≥3 times at 12 months, the difference was statistically significant (P < 0.05).In the treatment group, however, 7 patients experienced mild adverse reactions, such as dizziness, fatigue, nausea and vomiting, mild white blood cell reduction, mild liver damage, menstrual cycle changes, mental and behavioral abnormalities, etc.A patient discontinued due to mental disorder, and a patient change AEDs due to menstrual cycle change. All patients had no serious adverse reactions.
Conclusions①prophylactic use of AEDs can significantly reduce the incidence of seizures at 3 months; ②Although prophylactic use of AEDs did not reduce the incidence of seizures at 12 months, but can reduce the frequency of seizures; ③The risk of adverse reactions of prophylactic use of AEDs in patients with BTE is relatively low.
