Improving Radiological Interpretation through Optimization of Radiographs using Vision Transformers

After the great success that artificial intelligence models such as Chat-GPT have achieved, we began to investigate the core behind this model, it was Transformers, mainly used for Natural Language Processing, but we discovered that it had a version that could be used with images, called Vision Transformers. On computer vision, one field we are interested on is medical imaging, and how a model of Vision Transformers could help healthcare professionals on reducing their workload and helping them to get results of radiology faster. We aim to create a functional model that combines the best of Convolutional Neural Networks(CNN) and Vision Transformers to provide a high precision detection of diseases through radiological images.