In the evolving landscape of cancer diagnosis, histopathological image analysis stands out as a critical tool, particularly for lung and colon cancers. This paper presents a novel approach that harnesses Artificial Intelligence (AI) to automate and enhance the interpretation of histopathological images. We developed a mobile application that enables users to upload or capture histopathological images, offering real-time analysis and a percentage likelihood of cancer presence. The study employs advanced machine learning models, specifically Convolutional Neural Networks (CNNs) and Support Vector Machines (SVMs), trained on a meticulously curated dataset of 25,000 images from both benign and malignant tissue types. By addressing the inherent subjectivity and time constraints associated with manual interpretations, our application aims to improve diagnostic accuracy and efficiency. This research not only contributes to the field of medical imaging but also promotes the integration of AI-driven tools in clinical practice, thereby enhancing patient outcomes in lung and colon cancer management. The findings underscore the potential of AI to revolutionize cancer diagnostics, paving the way for more personalized and timely treatment interventions.