Identifying pneumonia in chest X-rays: A deep learning approach. (October 2019)

• Record Type: Journal Article
• Authors: Jaiswal, Amit Kumar; Tiwari, Prayag; Kumar, Sachin; Gupta, Deepak; Khanna, Ashish; Rodrigues, Joel J.P.C.
• Is Part Of: Measurement. Volume 145(2019)
• Page Start: 511
• Page End: 518
• Publication Date: 2019-10
• Subjects: 00-01 -- 99-00; Chest X-ray -- Medical imaging -- Object detection -- Segmentation; Weights and measures -- Periodicals; Measurement -- Periodicals; Measurement; Weights and measures; Periodicals; 530.8
• DOI: 10.1016/j.measurement.2019.05.076
• Languages: English
• ISSNs: 0263-2241

Abstract

Highlights: Detecting pneumonia in the critical stage of diagnosis can be life threatening. Deep learning techniques ease the process of pneumonia identification process. Radiologists find it beneficial to distinguish chest X-ray images among absence or presence of pneumonia. Mask-RCNN configures regional context which helps finding accurate results. Abstract: The rich collection of annotated datasets piloted the robustness of deep learning techniques to effectuate the implementation of diverse medical imaging tasks. Over 15% of deaths include children under age five are caused by pneumonia globally. In this study, we describe our deep learning based approach for the identification and localization of pneumonia in Chest X-rays (CXRs) images. Researchers usually employ CXRs for the diagnostic imaging study. Several factors such as positioning of the patient and depth of inspiration can change the appearance of the chest X-ray, complicating interpretation further. Our identification model (https://github.com/amitkumarj441/identify_pneumonia ) is based on Mask-RCNN, a deep neural network which incorporates global and local features for pixel-wise segmentation. Our approach achieves robustness through critical modifications of the training process and a novel post-processing step which merges bounding boxes from multiple models. The proposed identification model achieves better performances evaluated on chest radiograph dataset which depict potential pneumonia causes.