Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: role of databases on performance

Mandar Kale; Sudipta Mukhopadhyay; Jatindra K. Dash; Mandeep Garg; Niranjan Khandelwal

doi:10.1117/12.2216743

24 March 2016 Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: role of databases on performance

Mandar Kale, Sudipta Mukhopadhyay, Jatindra K. Dash, Mandeep Garg, Niranjan Khandelwal

Author Affiliations +

Proceedings Volume 9785, Medical Imaging 2016: Computer-Aided Diagnosis; 97852Z (2016) https://doi.org/10.1117/12.2216743
Event: SPIE Medical Imaging, 2016, San Diego, California, United States

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.

Citation Download Citation

Mandar Kale, Sudipta Mukhopadhyay, Jatindra K. Dash, Mandeep Garg, and Niranjan Khandelwal "Differentiation of several interstitial lung disease patterns in HRCT images using support vector machine: role of databases on performance", Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97852Z (24 March 2016); https://doi.org/10.1117/12.2216743

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available