Automated detection of pneumoconiosis with multilevel deep features learned from chest X-Ray radiographs. (February 2021)

• Record Type: Journal Article
• Authors: Devnath, Liton; Luo, Suhuai; Summons, Peter; Wang, Dadong
• Is Part Of: Computers in biology and medicine. Volume 129(2021)
• Publication Date: 2021-02
• Subjects: Coal workers' pneumoconiosis (CWP) -- Computer-aided diagnosis -- Black lung -- Deep transfer learning -- Support vector machine -- X-rays; Medicine -- Data processing -- Periodicals; Biology -- Data processing -- Periodicals; 610.285
• DOI: 10.1016/j.compbiomed.2020.104125
• Languages: English
• ISSNs: 0010-4825

Abstract

Abstract: Early detection of pneumoconiosis in X-Rays has been a challenging task that leads to high inter- and intra-reader variability. Motivated by the success of deep learning in general and medical image classification, this paper proposes an approach to automatically detect pneumoconiosis using a deep feature based binary classifier. The features are extracted from X-rays using deep transfer learning, comprising both low and high-level feature sets. For this, a CNN model pre-trained with a transfer learning from a CheXNet model was initially used to extract deep features from the X-Ray images, then the deep features were mapped to higher-dimensional feature spaces for classification using Support Vector Machine (SVM) and CNN based feature aggregation methods. In order to cross validate the proposed method, the training and testing images were randomly split into three folds before each experiment. Nine evaluation metrics were employed to compare the performance of the proposed method and state-of-the-art methods from the literature that used the same datasets. The experimental results show that the proposed framework outperformed others, achieving an accuracy of 92.68% in the automated detection of pneumoconiosis. Highlights: A multilevel deep feature-based classifier is proposed to automatically detect pneumoconiosis in chest x-ray radiographs. Transfer learning of CheXNet is employed to extract different dimensional of low and high-level features from X-rays. A framework is proposed to combine multi-dimensional CNN features with SVM and feature aggregation methods in a novel way. The results of the integrated framework and some state-of-art traditional and advanced deep learning methods are compared. With an accuracy of 92.68%, the proposed technique has outperformed CXR in detecting pneumoconiosis.