Fusion of GoogleNet and Capsule Neural Network models for improving bone tumor classification

Combining the strengths of GoogleNet and Capsule Neural Network (CNN) models represents a novel approach to enhance the categorization of bone cancers, a critical aspect for accurate diagnosis and effective therapy planning. Current classification techniques often encounter challenges in achieving both resilience and high accuracy. In this study, we address these issues by leveraging the distinct features extracted from bone tumor images using the GoogleNet model. These features are subsequently fed into the Capsule CNN model, known for its proficiency in capturing complex spatial correlations within data. The proposed fusion strategy aims to improve precision and resilience in bone tumor categorization by synergistically utilizing these two models. The efficacy of this approach is evaluated on a publicly available bone tumor dataset, revealing a notable accuracy of 96.7%. Comparative analysis against state-of-the-art techniques underscores the superior performance of the integrated model. In conclusion, the amalgamation of GoogleNet and Capsule CNN models presents a promising avenue for advancing bone tumor classification, potentially leading to more accurate diagnoses and effective treatment plans for individuals with these conditions.