As the cornerstone of modern medical diagnosis, pathology is facing multiple challenges such as workforce shortages, strong diagnostic subjectivity, and inefficient workflows. With advantages in image recognition, pattern analysis, and big data processing, artificial intelligence (AI) is increasingly being integrated into the field of pathological diagnosis, driving its transition toward digitization and intelligence. This article systematically reviews the development of AI in pathology, from early supervised learning validation to weakly supervised learning overcoming annotation bottlenecks, and the recent rise of self-supervised and multimodal foundation models. It demonstrates the broad applications of AI in improving diagnostic consistency, optimizing workflows, and predicting molecular features and prognoses. AI not only enhances the objectivity and efficiency of pathological diagnosis but also promotes the development of emerging interdisciplinary fields such as computational pathomics, providing strong support for precision medicine. Although challenges such as data standardization and regulatory approval remain in clinical implementation, the deep integration of AI and pathology is ushering in a new era of human-machine collaboration and intelligent diagnostics.