The integration of Computer-Aided Diagnosis (CAD) systems in histopathology has significantly enhanced the accuracy and efficiency of cancer diagnosis. The work provides an overview of various methods already implemented in histopathology for different cancer types, highlighting the technological advancements and methodologies that have shaped the current landscape. The key areas of focus include preprocessing techniques to improve image quality, advanced segmentation methods for accurate delineation of pathological regions, feature extraction techniques to capture relevant diagnostic information, and classification methods leveraging machine learning algorithms for precise diagnosis. Emphasizing the importance of collaboration between medical specialists and computer vision researchers, this review aims to develop robust and clinically relevant CAD systems. This review paper also focuses on the application of CAD systems in bone cancer due to its complex nature and the diagnostic challenges it presents. Through comprehensive coverage of standard methods in digital histopathology for bone cancer diagnosis, this review underscores the potential of automated tools to transform medical diagnostics. By offering timely and precise assessments, these tools can lead to better treatment outcomes, significantly enhancing patient care and management.