Enhancing Gastrointestinal Image Classification: A Fusion of CNN and Vision Trasformers

In order to meet the pressing demand for early diagnosis in healthcare, we proposed a unique hybrid architecture in this study that is intended for the categorization of gastrointestinal (GI) illnesses. With fewer trainable parameters, faster training times, and less storage needed for model weights, our suggested architecture prioritizes efficiency achieves an impressive 94% accuracy. To effectively diagnose GI disorders, this design combines convolutional neural networks (CNNs) with Transformers. The creation of this hybrid architecture, which boasts excellent accuracy in illness categorization, decreased storage requirements, and efficiency in training, is one of the research's accomplishments. Our proposed model demonstrates its flexibility for many uses, encouraging simple implementation and expandability. Extensive tests performed on a large dataset of endoscopic images highlight our hybrid architecture's better performance over current techniques. With this study, diagnostics for gastrointestinal diseases have advanced significantly, opening the door to future diagnostic systems that will be more precise and effective. The proposed architecture has outperformed the traditional pre-trained models both in classification accuracy and time to train the model with no weights.