Capsule-ConvKAN: A Hybrid Neural Approach to Medical Image Classification
This addresses classification challenges in biomedical imaging, though it appears incremental as it builds on existing architectures.
The study tackled medical image classification by proposing Capsule-ConvKAN, a hybrid neural network combining Capsule Network and Convolutional Kolmogorov-Arnold Network, which achieved 91.21% accuracy on a histopathological dataset.
This study conducts a comprehensive comparison of four neural network architectures: Convolutional Neural Network, Capsule Network, Convolutional Kolmogorov-Arnold Network, and the newly proposed Capsule-Convolutional Kolmogorov-Arnold Network. The proposed Capsule-ConvKAN architecture combines the dynamic routing and spatial hierarchy capabilities of Capsule Network with the flexible and interpretable function approximation of Convolutional Kolmogorov-Arnold Networks. This novel hybrid model was developed to improve feature representation and classification accuracy, particularly in challenging real-world biomedical image data. The architectures were evaluated on a histopathological image dataset, where Capsule-ConvKAN achieved the highest classification performance with an accuracy of 91.21%. The results demonstrate the potential of the newly introduced Capsule-ConvKAN in capturing spatial patterns, managing complex features, and addressing the limitations of traditional convolutional models in medical image classification.