DWT-LBP Descriptors for Chest X-Ray View Classification

In this paper, we have attempted the problem of chest X ray Image view classification. To do this, we have applied three steps pre-processing, feature computation and classification. Image enhancement based on histogram equalization is carried out in pre-processing. For computing the features hybrid method based on Discrete Wavelet Transform and Uniform Local Binary Pattern is developed and SVM used for classification. We have got encouraging results on NIH dataset with accuracy of 98.00% using 10 fold cross validation.

[1]  Kunio Doi,et al.  Development of a computerized method for identifying the posteroanterior and lateral views of chest radiographs by use of a template matching technique. , 2002, Medical physics.

[2]  Okeke Stephen,et al.  An Efficient Deep Learning Approach to Pneumonia Classification in Healthcare , 2019, Journal of healthcare engineering.

[3]  H. K. Huang,et al.  Orientation correction for chest images , 1992, Journal of Digital Imaging.

[4]  John M. Boone,et al.  Recognition of chest radiograph orientation for picture archiving and communications systems display using neural networks , 2009, Journal of Digital Imaging.

[5]  Daekeun You,et al.  Chest X-ray Image View Classification , 2015, 2015 IEEE 28th International Symposium on Computer-Based Medical Systems.

[6]  Clement J. McDonald,et al.  Automatic Tuberculosis Screening Using Chest Radiographs , 2014, IEEE Transactions on Medical Imaging.

[7]  Matti Pietikäinen,et al.  Multiresolution Gray-Scale and Rotation Invariant Texture Classification with Local Binary Patterns , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[8]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[9]  Laurent Wendling,et al.  Angular relational signature-based chest radiograph image view classification , 2018, Medical & Biological Engineering & Computing.

[10]  Thomas Martin Deserno,et al.  Automatic detection of the view position of chest radiographs , 2003, SPIE Medical Imaging.

[11]  Stéphane Mallat,et al.  A Theory for Multiresolution Signal Decomposition: The Wavelet Representation , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[12]  Chungnan Lee,et al.  Projection profile analysis for identifying different views of chest radiographs. , 2006, Academic radiology.

[13]  Ming-Chung Chou,et al.  A computerized method for automated identification of erect posteroanterior and supine anteroposterior chest radiographs. , 2011, Physics in medicine and biology.

[14]  Thomas Martin Deserno,et al.  Determining the View of Chest Radiographs , 2003, Journal of Digital Imaging.