Generative adversarial network based data augmentation to improve cervical cell classification model.

The survival rate of cervical cancer can be improved by the early screening. However, the screening is a heavy task for pathologists. Thus, automatic cervical cell classification model is proposed to assist pathologists in screening. In cervical cell classification, the number of abnormal cells is small, meanwhile, the ratio between the number of abnormal cells and the number of normal cells is small too. In order to deal with the small sample and class imbalance problem, a generative adversarial network (GAN) trained by images of abnormal cells is proposed to obtain the generated images of abnormal cells. Using both generated images and real images, a convolutional neural network (CNN) is trained. We design four experiments, including 1) training the CNN by under-sampled images of normal cells and the real images of abnormal cells, 2) pre-training the CNN by other dataset and fine-tuning it by real images of cells, 3) training the CNN by generated images of abnormal cells and the real images, 4) pre-training the CNN by generated images of abnormal cells and fine-tuning it by real images of cells. Comparing these experimental results, we find that 1) GAN generated images of abnormal cells can effectively solve the problem of small sample and class imbalance in cervical cell classification; 2) CNN model pre-trained by generated images and fine-tuned by real images achieves the best performance whose AUC value is 0.984.