Chronic Lower Respiratory Diseases detection based on Deep Recursive Convolutional Neural Network

Abstract

Recently, symptoms of Chronic Obstructive Pulmonary Disease (COPD) have been identified concerning long-term continuous treatment. Furthermore, predicting the life probability of patients with COPD is crucial for formative ensuing treatment and conduct plans. Additionally, it plays a vital role in providing complementary solutions using technologies such as Deep Learning (DL) to address experiments in the medical field. Early and timely analysis of clinical images can improve prognostic accuracy. These include COPD, pneumonia, asthma, tuberculosis and fibrosis. Conventional methods of diagnosing COPD often rely on physical exams and tests such as spirometers, chest and genetic analysis. However, respiratory diseases pose an enormous comprehensive health burden for many patients. Thus these methods are not always accurate or obtainable. However, succeeding in their accuracy involves a nonspecific diagnosis rate, time-consuming manual procedures, and extensive clinical imaging knowledge of the radiologist. To solve this problem, we use a Deep Recursive Convolutional Neural Network (DRCNN) method to detect chronic lower respiratory disease. Initially, we collected the images from the Kaggle repository, and evaluate the result based on the following stage. The first stage is pre-processing using a Gaussian filter to reduce noise and detect the edges. The second stage is segmentation used on Image Threshold Based Segmentation (ITBS), used for counting the binary image and separating the regions. In the third stage, we use the chi-square test to select the best features and evaluate the image values for each feature and threshold. Finally, classification using DRCNN detects CLRD classifying better than the previous method. In synthesis, CLRD can be detected by many staging measures, such as sensitivity, specificity, accuracy, precision, and Recall