An Algorithm Based Method for Detecting Bone Tumour

Bone cancer detection poses significant challenges due to the complexity and variability of radiographic images. This project proposes a novel approach for the early detection of bone cancer utilizing the Capsule Network (Caps Net) algorithm combined with edge detection methods in MATLAB for image processing. The Caps Net algorithm is employed to analyze the hierarchical relationships in image features, which enhances the model's ability to recognize intricate patterns and variations associated with bone lesions. Initially, digital radiographic images of bone tissues are pre- processed using edge detection techniques to highlight relevant features while minimizing noise. Various edge detection methods, such as the Sobel and Canny algorithms, are implemented to extract critical outlines and textures of the bone structure. This pre- processed data is then fed into the Caps Net model, which leverages its unique capsule architecture to maintain spatial hierarchies and improve classification accuracy. A large dataset of photos classified into cancerous and noncancerous classifications is used to assess the effectiveness of the suggested method. Metrics such as accuracy, sensitivity, specificity, and F1 score are calculated to assess the model's effectiveness in identifying bone cancer. The results demonstrate a significant improvement over traditional methods, showcasing the robustness and efficiency of the Caps Net algorithm in medical image analysis. This innovative method not only enhances diagnostic capabilities but also contributes to the development of automated systems for clinical settings, potentially aiding radiologists in early detection and treatment planning. Future work will focus on further refining the model and exploring its applicability to other types of medical imaging for comprehensive cancer detection.