Sugarcane, a vital global crop, faces significant challenges from various diseases that threaten its yield and quality. This paper presents a comprehensive review of recent advancements in sugarcane plant disease detection and classification methodologies. The escalating demand for efficient and accurate disease management has driven substantial progress in this field. The review encompasses a wide array of techniques, including image processing, machine learning, and deep learning, tailored specifically for sugarcane diseases. Noteworthy improvements in data acquisition, feature extraction, and model architectures are discussed, addressing the unique characteristics of sugarcane leaves. Additionally, challenges such as dataset scarcity, cross-species generalization, and real-time implementation in sugarcane fields are addressed. The paper concludes by outlining potential avenues for future research, emphasizing the integration of emerging technologies and the need for standardized evaluation metrics. This review serves as a valuable resource for researchers, practitioners, and stakeholders invested in the sustainable management of sugarcane diseases, thereby contributing to the resilience and productivity of global sugarcane agriculture.