Chest X-ray Image View Classification

Author

Zhiyun Xue ; Daekeun You ; Candemir, Sema ; Jaeger, Stefan ; Antani, Sameer ; Long, L. Rodney ; Thoma, George R.

Author_Institution

Nat. Libr. of Med., Lister Hill Nat. Center for Biomed. Commun., Bethesda, MD, USA

fYear

2015

fDate

22-25 June 2015

Firstpage

66

Lastpage

71

Abstract

The view information of a chest X-ray (CXR), such as frontal or lateral, is valuable in computer aided diagnosis (CAD) of CXRs. For example, it helps for the selection of atlas models for automatic lung segmentation. However, very often, the image header does not provide such information. In this paper, we present a new method for classifying a CXR into two categories: frontal view vs. lateral view. The method consists of three major components: image pre-processing, feature extraction, and classification. The features we selected are image profile, body size ratio, pyramid of histograms of orientation gradients, and our newly developed contour-based shape descriptor. The method was tested on a large (more than 8,200 images) CXR dataset hosted by the National Library of Medicine. The very high classification accuracy (over 99% for 10-fold cross validation) demonstrates the effectiveness of the proposed method.

Keywords

diagnostic radiography; feature extraction; feature selection; image classification; medical image processing; CAD; CXR; CXR dataset; atlas models; automatic lung segmentation; chest X-ray image view classification; computer aided diagnosis; contour-based shape descriptor; feature extraction; feature selection; image preprocessing; pyramid-of-histogram-of-orientation gradients; Accuracy; Feature extraction; Image segmentation; Lungs; Radiography; Shape; X-ray imaging; chest radiograph; contourbased shape feature; view classification;

fLanguage

English

Publisher

ieee

Conference_Titel

Computer-Based Medical Systems (CBMS), 2015 IEEE 28th International Symposium on

Conference_Location

Sao Carlos

Type

conf

DOI

10.1109/CBMS.2015.49

Filename

7167459