Image Generation of Trichomonas Vaginitis Based on Mode Margin Generative Adversarial Networks

Using deep learning to screen for trichomoniasis vaginitis is an important method to assist doctors in diagnosis. However, scarce medical data always limits the ability of deep learning models, so in order to generate more diverse image data, a Mode Margin Generative Adversarial Network(MMGAN) is proposed. We design a new backbone Generative Adversarial Networks(GAN) and add a model mapping ratio term to it to increase the modes of the generated image, which effectively alleviates the model collapse phenomenon. The network is evaluated on self-built dataset. Experimental results show that the quality and diversity of images generated by MMGAN are better than GAN and WGAN. Moreover, we also provide a basic diagnostic model for trichomoniasis vaginitis and evaluate the effectiveness of the enhanced data in the actual diagnosis. The enhanced data improve the accuracy of the classification model.