Modeling Deep Feature for Lung Disease Classification in Chest X-ray Images

An accurate method of diagnosis is needed as lung disease spreads around the globe. Since the virus spreads so quickly, diagnosing lung disease can be challenging for medical professionals. Accurate diagnosis and treatment are what set clinical diagnosis apart because they typically depend on a doctor's skill and knowledge. This is the most challenging aspect of diagnosing COVID-19 and pneumonia patients. Therefore, for the time being, this technology's major objective is to create a way to detect lung problems early and stop the virus from spreading quickly. This system offers a categorization framework for a challenging image analysis task in the medical field, where chest X-ray images are assessed. The pre-trained Alex Net is utilized to generate the feature map that was taken from the x-ray image. The LSTM model models the extracted feature map to extract a feature vector for a Support Vector Machine (SVM) classifier to categorize lung diseases. In the method of convolutional neural network (CNN) classification, a large number of layers, values, thresholds, and parameters are required to be defined for classification. Since the pre-trained Alex Net is used in our proposed framework, the parameter values for CNN don’t need to be defined, reducing processing time effectively. This paper proposes the modeling of feature maps using LSTM and the application of machine learning techniques gave the accuracy of 98.8% for the categorization of lung diseases in the form of 10-fold cross validation. Three diseases are distinguished in the proposed framework: normal, viral pneumonia, and COVID-19. In experiments, accuracy, true positive, false negative, positive predictive, and false discovery rates are used to evaluate classifier performance.