On using the computer linguistic models in the classification of biomedical images

Computer linguistic models have become widespread in the field of natural language processing and have recently been actively used to solve various computer vision problems. In this article, computer studies have been carried out aimed to identify the effectiveness of the use of transformer models in the task of classifying X-ray images of the lungs. The studies used pre-trained models of transformers with different sizes ViT-B(16/32), ViT-L(16/32), which were then fine-tuned on a set of X-ray images of lung. Computer studies of the use of convolutional neural networks VGG-16, Inception V3, ResNet50, EfficientNetV2, DenseNet121 have also been conducted. A comparative analysis of the classification results of the studied X-ray images showed that the ViT-B/32 transformer model has the best accuracy metrics accuracy=97.56%, AUC=99%.