Share Email Print

Proceedings Paper

A machine learning approach for classification of anatomical coverage in CT
Author(s): Xiaoyong Wang; Pechin Lo; Bharath Ramakrishna; Johnathan Goldin; Matthew Brown
Format Member Price Non-Member Price
PDF $17.00 $21.00

Paper 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.

Paper Details

Date Published: 24 March 2016
PDF: 6 pages
Proc. SPIE 9785, Medical Imaging 2016: Computer-Aided Diagnosis, 97853P (24 March 2016); doi: 10.1117/12.2216259
Show Author Affiliations
Xiaoyong Wang, Univ. of California, Los Angeles (United States)
Pechin Lo, Univ. of California, Los Angeles (United States)
Bharath Ramakrishna, Univ. of California, Los Angeles (United States)
Johnathan Goldin, Univ. of California, Los Angeles (United States)
Matthew Brown, Univ. of California, Los Angeles (United States)

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
Sign in to read the full article
Create a free SPIE account to get access to
premium articles and original research
Forgot your username?