Show simple item record

dc.contributor.authorJaiswal, Amit Kumaren
dc.contributor.authorTiwari, Prayagen
dc.contributor.authorKumar, Sachinen
dc.contributor.authorGupta, Deepaken
dc.contributor.authorKhanna, Ashishen
dc.contributor.authorRodrigues, Joel J.P.C.en
dc.date.accessioned2020-01-21T13:52:46Z
dc.date.available2020-01-21T13:52:46Z
dc.date.issued2019-06-04
dc.identifier.citationJaiswal AK, Tiwari P, Kumar S, Gupta D, Khanna A, Rodrigues JJ (2019) 'Identifying pneumonia in chest X-rays: a deep learning approach', Measurement, 145 (), pp.511-518.en
dc.identifier.issn0263-2241
dc.identifier.doi10.1016/j.measurement.2019.05.076
dc.identifier.urihttp://hdl.handle.net/10547/623797
dc.description.abstractThe 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.
dc.language.isoenen
dc.publisherElsevieren
dc.relation.urlhttps://www.sciencedirect.com/science/article/pii/S0263224119305202en
dc.rightsGreen - can archive pre-print and post-print or publisher's version/PDF
dc.subjectchest X-rayen
dc.subjectmedical imagingen
dc.subjectobject detectionen
dc.subjectsegmentationen
dc.subjectB800 Medical Technologyen
dc.titleIdentifying pneumonia in chest X-rays: a deep learning approachen
dc.typeArticleen
dc.contributor.departmentUniversity of Bedfordshireen
dc.contributor.departmentUniversity of Padovaen
dc.contributor.departmentSouth Ural State Universityen
dc.contributor.departmentMaharaja Agrasen Institute of Technologyen
dc.contributor.departmentNational Institute of Telecommunications (Inatel), Brazilen
dc.contributor.departmentInstituto de Telecomunicações, Portugalen
dc.contributor.departmentFederal University of Piauí, Brazilen
dc.identifier.journalMeasurementen
dc.date.updated2020-01-21T13:49:34Z
html.description.abstractThe 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.


Files in this item

Thumbnail
Name:
Publisher version

This item appears in the following Collection(s)

Show simple item record