Abstract: Due to the extremely similar imaging manifestations and location of onset between meningiomas and acoustic neuromas in the CPA(Cerebellopontine angle) region of the human body, clinical diagnosis is prone to misdiagnosis. Establishing an automatic tumor detection model using deep learning methods can effectively reduce the subjectivity of manual diagnosis, decrease missed diagnosis rates, and improve work efficiency. The diversity of the dataset and superiority of image quality largely determine the performance of the detection model. This paper proposes a DCGAN (Deep convolutional generative adversarial networks) with improved loss function for data augmentation of meningioma and acoustic neuroma detection models to address the issues of scarce medical image datasets, imbalanced number of categories and poor imaging quality. Compared with traditional dataset augmentation methods, the results showed that after optimizing the dataset with DCGAN, the accuracy, specificity, and mAP (Mean average precision) of the brain tumor detection model increased by 1.5%, 2%, and 3% respectively compared to the original dataset, rising to 0.9328, 0.8986, and 0.9300. The experimental results show that optimizing the dataset through DCGAN can improve the detection performance of the brain tumor detection model better, and more reliably assist clinical medical diagnosis.

Key words: Brain tumors, Detection model, Dataset augmentation, DCGAN