A machine learning approach for classification of anatomical coverage in CT

Xiaoyong Wang; Pechin Lo; Bharath Ramakrishna; Johnathan Goldin; Matthew Brown

doi:10.1117/12.2216259

24 March 2016 A machine learning approach for classification of anatomical coverage in CT

Xiaoyong Wang, Pechin Lo, Bharath Ramakrishna, Johnathan Goldin, Matthew Brown

Proceedings Volume 9785, Medical Imaging 2016: Computer-Aided Diagnosis; 97853P (2016) https://doi.org/10.1117/12.2216259
Event: SPIE Medical Imaging, 2016, San Diego, California, United States

Abstract

Automatic classification of anatomical coverage of medical images is critical for big data mining and as a pre-processing step to automatically trigger specific computer aided diagnosis systems. The traditional way to identify scans through DICOM headers has various limitations due to manual entry of series descriptions and non-standardized naming conventions. In this study, we present a machine learning approach where multiple binary classifiers were used to classify different anatomical coverages of CT scans. A one-vs-rest strategy was applied. For a given training set, a template scan was selected from the positive samples and all other scans were registered to it. Each registered scan was then evenly split into k × k × k non-overlapping blocks and for each block the mean intensity was computed. This resulted in a 1 × k³ feature vector for each scan. The feature vectors were then used to train a SVM based classifier. In this feasibility study, four classifiers were built to identify anatomic coverages of brain, chest, abdomen-pelvis, and chest-abdomen-pelvis CT scans. Each classifier was trained and tested using a set of 300 scans from different subjects, composed of 150 positive samples and 150 negative samples. Area under the ROC curve (AUC) of the testing set was measured to evaluate the performance in a two-fold cross validation setting. Our results showed good classification performance with an average AUC of 0.96.

Citation Download Citation

Xiaoyong Wang, Pechin Lo, Bharath Ramakrishna, Johnathan Goldin, and Matthew Brown "A machine learning approach for classification of anatomical coverage in CT", Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97853P (24 March 2016); https://doi.org/10.1117/12.2216259

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