With the continuous innovation of human science, medical diagnosis and treatment methods have become diverse. In recent years, the method of in-depth learning has made great achievements in the medical field. It relies on the advantages of today's big data to find rules from a large number of data, so as to simulate human learning and analysis capabilities. It solves the problem of the huge amount of data that is difficult to be solved by manpower. This article reviewed and analyzed the application of deep learning in the diagnosis and prognosis prediction of ovarian cancer, and explored the application value and research prospects of deep learning in the diagnosis and treatment of ovarian cancer.