A Deep Feature Learning Model for Pneumonia Detection Applying a Combination of mRMR Feature Selection and Machine Learning Models

• Published in: Ingénierie et recherche biomédicale Vol. 41; no. 4; pp. 212 - 222
• Main Authors: Toğaçar, M., Ergen, B., Cömert, Z., Özyurt, F.
• Format: Journal Article
• Language: English
• Published: Elsevier Masson SAS 01.08.2020
• Subjects: Biomedical image processing; Convolutional neural network; Diagnosis system; Feature selection; Pneumonia; Diagnosis system; Pneumonia; Feature selection; Biomedical image processing; Convolutional neural network
• ISSN: 1959-0318
• DOI: 10.1016/j.irbm.2019.10.006

•This study applied deep learning models to detect pneumonia through the chest images.•Image augmentation technique was applied to ensure balance between classes.•We have extracted and combined features from the equivalent layers of CNN models.•We have reduced combined features with the feature selection method (mRMR).•We achieved the best result using various classifiers. Pneumonia is one of the diseases that people may encounter in any period of their lives. Approximately 18% of infectious diseases are caused by pneumonia. This disease may result in death in the following stages. In order to diagnose pneumonia as a medical condition, lung X-ray images are routinely examined by the field experts in the clinical practice. In this study, lung X-ray images that are available for the diagnosis of pneumonia were used. The convolutional neural network was employed as feature extractor, and some of existing convolutional neural network models that are AlexNet, VGG-16 and VGG-19 were utilized so as to realize this specific task. Then, the number of deep features was reduced from 1000 to 100 by using the minimum redundancy maximum relevance algorithm for each deep model. Accordingly, we achieved 100 deep features from each deep model, and we combined these features so as to provide an efficient feature set consisting of totally 300 deep features. In this step of the experiment, this feature set was given as an input to the decision tree, k-nearest neighbors, linear discriminant analysis, linear regression, and support vector machine learning models. Finally, all models ensured promising results, especially linear discriminant analysis yielded the most efficient results with an accuracy of 99.41%. Consequently, the results point out that the deep features provided robust and consistent features for pneumonia detection, and minimum redundancy maximum relevance method was found a beneficial tool to reduce the dimension of the feature set.