Share Email Print
cover

Proceedings Paper

Two-stage deep learning architecture for pneumonia detection and its diagnosis in chest radiographs
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Approximately two million pediatric deaths occur every year due to Pneumonia. Detection and diagnosis of Pneumonia plays an important role in reducing these deaths. Chest radiography is one of the most commonly used modalities to detect pneumonia. In this paper, we propose a novel two-stage deep learning architecture to detect pneumonia and classify its type in chest radiographs. This architecture contains one network to classify images as either normal or pneumonic, and another deep learning network to classify the type as either bacterial or viral. In this paper, we study and compare the performance of various stage one networks such as AlexNet, ResNet, VGG16 and Inception-v3 for detection of pneumonia. For these networks, we employ transfer learning to exploit the wealth of information available from prior training. For the second stage, we find that transfer learning with these same networks tends to overfit the data. For this reason we propose a simpler CNN architecture for classification of pneumonic chest radiographs and show that it overcomes the overfitting problem. We further enhance the performance of our system in a novel way by incorporating lung segmentation using a U-Net architecture. We make use of a publicly available dataset comprising 5856 images (1583 – Normal, 4273 – Pneumonic). Among the pneumonia patients, 2780 patients are identified as bacteria type and the rest belongs to virus category. We test our proposed algorithm(s) on a set of 624 images and we achieve an area under the receiver operating characteristic curve of 0.996 for pneumonia detection. We also achieve an accuracy of 97.8% for classification of pneumonic chest radiographs thereby setting a new benchmark for both detection and diagnosis. We believe the proposed two-stage classification of chest radiographs for pneumonia detection and its diagnosis would enhance the workflow of radiologists.

Paper Details

Date Published: 2 March 2020
PDF: 10 pages
Proc. SPIE 11318, Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications, 113180G (2 March 2020); doi: 10.1117/12.2547635
Show Author Affiliations
Barath Narayanan Narayanan, Univ. of Dayton (United States)
Univ. of Dayton Research Institute (United States)
Venkata Salini Priyamvada Davuluru, Univ. of Dayton (United States)
Russell C. Hardie, Univ. of Dayton (United States)


Published in SPIE Proceedings Vol. 11318:
Medical Imaging 2020: Imaging Informatics for Healthcare, Research, and Applications
Po-Hao Chen; Thomas M. Deserno, Editor(s)

© SPIE. Terms of Use
Back to Top
PREMIUM CONTENT
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?
close_icon_gray