Medical Image Classification using CMT and FTGD Layer

Medical image classification is a critical task in the field of healthcare, as it enables the accurate diagnosis and treatment of several diseases. Here, we propose a novel approach for medical image classification by incorporating a Fully Trainable Gaussian Derivative Convolutional (FTGD) layer, on Convolutional Neural Networks Meets Vision Transformer (CMT) model. Our results illustrates the usefulness of the proposed approach for medical image classification and highlight the potential of combining CNNs with the ViT architecture and FTGD layer for improved performance in healthcare applications. We evaluate our proposed approach on a COVID-19 dataset and achieve an accuracy of 85%, outperforming existing methods and also reduces the number of parameters. The proposed method has the potential to assist healthcare professionals in accurately diagnosing and treating various diseases, including COVID-19.