The application of artificial intelligence (AI) in cancer pathology has shown significant potential to enhance diagnostic accuracy, streamline workflows, and support precision oncology. This review examines the current applications of AI across various cancer types, including breast, lung, prostate, and colorectal cancer, where AI aids in tissue classification, mutation detection, and prognostic predictions. The key technologies driving these advancements include machine learning, deep learning, and computer vision, which enable automated analysis of histopathological images and multi-modal data integration. Despite these promising developments, challenges persist, including ensuring data privacy, improving model interpretability, and meeting regulatory standards. Furthermore, this review explores future directions in AI-driven cancer pathology, including real-time diagnostics, explainable AI, and global accessibility, emphasizing the importance of collaboration between AI and pathologists. Addressing these challenges and leveraging AI’s full potential could lead to a more efficient, equitable, and personalized approach to cancer care.

Chronic Mucocutaneous Candidiasis (CMC) is a rare immunodeficiency disease characterized by chronic or recurrent superficial Candida infections on the skin, nail, and mucous membranes. Here, we present four Chinese patients with CMC who manifested oral mucosal leukoplakia and nail thickening during early childhood, all displaying fissured tongue lines. The causative pathogens isolated from their oral mucosa and nails were identified as C. albicans and C. parapsilosis through morphology and molecular sequencing. Notably, among the four patients, one presented with vitiligo, while another had hypothyroidism. We have also conducted a review of reported cases of CMC in China and worldwide over the last five years, highlighting potential approaches for diagnosis and treatment. The current molecular evidence in the literature suggests potential for the development of early diagnosis methods, such as screening genetic variables on STAT1 and STAT3. Additionally, potential treatment avenues, including gene-targeted analogues and GM-CSF analogues, could be explored in conjunction with traditional antifungal therapy.