Share Email Print

Proceedings Paper

Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: role of databases on performance
Author(s): Mandar Kale; Sudipta Mukhopadhyay; Jatindra K. Dash; Mandeep Garg; Niranjan Khandelwal
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper Abstract

Interstitial lung disease (ILD) is complicated group of pulmonary disorders. High Resolution Computed Tomography (HRCT) considered to be best imaging technique for analysis of different pulmonary disorders. HRCT findings can be categorised in several patterns viz. Consolidation, Emphysema, Ground Glass Opacity, Nodular, Normal etc. based on their texture like appearance. Clinician often find it difficult to diagnosis these pattern because of their complex nature. In such scenario computer-aided diagnosis system could help clinician to identify patterns. Several approaches had been proposed for classification of ILD patterns. This includes computation of textural feature and training /testing of classifier such as artificial neural network (ANN), support vector machine (SVM) etc. In this paper, wavelet features are calculated from two different ILD database, publically available MedGIFT ILD database and private ILD database, followed by performance evaluation of ANN and SVM classifiers in terms of average accuracy. It is found that average classification accuracy by SVM is greater than ANN where trained and tested on same database. Investigation continued further to test variation in accuracy of classifier when training and testing is performed with alternate database and training and testing of classifier with database formed by merging samples from same class from two individual databases. The average classification accuracy drops when two independent databases used for training and testing respectively. There is significant improvement in average accuracy when classifiers are trained and tested with merged database. It infers dependency of classification accuracy on training data. It is observed that SVM outperforms ANN when same database is used for training and testing.

Paper Details

Date Published: 24 March 2016
PDF: 6 pages
Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97852Z (24 March 2016); doi: 10.1117/12.2216743
Show Author Affiliations
Mandar Kale, Indian Institute of Technology Kharagpur (India)
Sudipta Mukhopadhyay, Indian Institute of Technology Kharagpur (India)
Jatindra K. Dash, Indian Institute of Technology Kharagpur (India)
National Institute of Science and Technology, Berhampur (India)
Mandeep Garg, Postgraduate Institute of Medical Education & Research (India)
Niranjan Khandelwal, Postgraduate Institute of Medical Education & Research (India)

Published in SPIE Proceedings Vol. 9785:
Medical Imaging 2016: Computer-Aided Diagnosis
Georgia D. Tourassi; Samuel G. Armato III, Editor(s)

© SPIE. Terms of Use
Back to Top