Surgical workflow image generation based on generative adversarial networks

In the medical field, the labeling of surgical video data requires Expert knowledge, collecting enough numbers of marked surgical video data is difficult and time-consuming. The insufficient video data (labeled data) leads to the low generalization ability of the training model and the low accuracy of recognition. It has been recently shown that Generative Adversarial Networks (GANs) can produce synthetic images of exceptional visual fidelity. In this work, the authors propose the GAN-based method for automatic Surgical Workflow images. The theory and methodology of this paper are validated on real three surgery video datasets. It can generative effective surgical workflow images. The technology studied in this paper has broad application prospects in computer-aided surgical systems and is a core component of the artificial intelligence medical operating room in the future.