Abstract: The incidence of bladder cancer is increasing annually, and the gold standard for its diagnosis relies on histopathological biopsy. Whole-slide digitization technology can produce thousands of high-resolution captured pathological images and has greatly promoted the development of digital pathology. Deep learning, as a new method of artificial intelligence, has achieved remarkable results in the analysis of pathological images for tumor diagnosis, molecular typing, and prediction of prognosis and recurrence of bladder cancer. Traditional pathology relies heavily on the professional level and experience of pathologists; as such, it is highly subjective and has poor reproducibility. Deep learning can automatically extract image features. It can also improve diagnostic efficiency and repeatability and reduce missed and misdiagnosed rates when used to assist pathologists in making decisions. This technology cannot only alleviate the pressure of the current shortage of skilled workforce and uneven medical resources but also promote the development of precision medicine. This article reviews the latest research progress and prospects of deep learning in pathological image analysis of bladder cancer.