Modified MixNet-Based Classification of Lung Diseases by Using a Noval Dataset

Abstract

The lungs are critical components of the respiratory system because they allow for the exchange of oxygen and carbon dioxide within our bodies. However, a variety of conditions can affect the lungs, resulting in serious health consequences. The goal of lung disease treatment is to control their severity, which is usually irreversible. The fundamental goal of this effort is to build a consistent method for automatically establishing the severity of lung illness. This paper describes MixNet-LD, a unique automated approach aimed to identify and categorize the severity of lung illnesses using an upgraded pre-trained MixNet model. One of the first steps in developing the MixNetLD system was to build a preprocessing strategy that uses CLAHE and MSR to decrease noise, highlight irregularities, and eventually improve the classification performance of lung illnesses. Data augmentation strategies were used to rectify the dataset's unbalanced distribution of classes and prevent overfitting. Furthermore, dense blocks were used to improve classification outcomes across the four severity categories of lung disorders. In practice, the MixNet-LD model achieves cutting-edge performance while keeping the model size and complexity manageable. The proposed approach was tested using a variety of datasets gathered from credible internet sources, as well as a novel private dataset known as Pak-Lungs. A pretrained model was used on the dataset to obtain important characteristics from lung disease images. The pictures were then categorized into categories such as Normal, COVID-19, Pneumonia, Tuberculosis, and Lung Cancer using a linear layer of the SVM classifier with a linear activation function. The MixNetLD system was tested in four distinct tests and achieved a remarkable accuracy of 98.5% on the difficult lung disease dataset. The acquired findings and comparisons clearly demonstrate the MixNet-LD system's improved performance and learning capabilities. These findings show that the proposed approach may effectively increase the accuracy of classification models in medicinal image investigation. This research helps to further the development of new strategies for effective medical image processing in clinical settings.