Enhanced swin transformer based tuberculosis classification with segmentation using chest X-ray

BACKGROUND: Tuberculosis disease is the disease that causes significant morbidity and mortality worldwide. Thus, early detection of the disease is crucial for proper treatment and controlling the spread of Tuberculosis disease. Chest X-ray imaging is one of the most widely used diagnostic tools for detecting the Tuberculosis, which is time-consuming, and prone to errors. Nowadays, deep learning model provides the automated classification of medical images with promising outcome. OBJECTIVE: Thus, this research introduced a deep learning based segmentation and classification model. Initially, the Adaptive Gaussian Filtering based pre-processing and data augmentation is performed to remove artefacts and biased outcome. Then, Attention UNet (AUNet) based segmentation is proposed for segmenting the required region of Chest X-ray. METHODS: Using the segmented outcome, Enhanced Swin Transformer (EnSTrans) model based Tuberculosis classification model is designed with Residual Pyramid Network based Multi-layer perceptron (MLP) layer for enhancing the classification accuracy. RESULTS: Enhanced Lotus Effect Optimization (EnLeO) Algorithm is employed for the loss function optimization of the EnSTrans model. CONCLUSIONS: The proposed methods acquired the Accuracy, Recall, Precision, F-score, and Specificity of 99. 0576%, 98. 9459%, 99. 145%, 98. 96%, and 99. 152% respectively.