Fast and effective characterization of 3D region of interest in medical image data

Despina Kontos; Vasileios Megalooikonomou

doi:10.1117/12.534459

12 May 2004 Fast and effective characterization of 3D region of interest in medical image data

Despina Kontos, Vasileios Megalooikonomou

Proceedings Volume 5370, Medical Imaging 2004: Image Processing; (2004) https://doi.org/10.1117/12.534459
Event: Medical Imaging 2004, 2004, San Diego, California, United States

Abstract

We propose a framework for detecting, characterizing and classifying spatial Regions of Interest (ROIs) in medical images, such as tumors and lesions in MRI or activation regions in fMRI. A necessary step prior to classification is efficient extraction of discriminative features. For this purpose, we apply a characterization technique especially designed for spatial ROIs. The main idea of this technique is to extract a k-dimensional feature vector using concentric spheres in 3D (or circles in 2D) radiating out of the ROI's center of mass. These vectors form characterization signatures that can be used to represent the initial ROIs. We focus on classifying fMRI ROIs obtained from a study that explores neuroanatomical correlates of semantic processing in Alzheimer's disease (AD). We detect a ROI highly associated with AD and apply the feature extraction technique with different experimental settings. We seek to distinguish control from patient samples. We study how classification can be performed using the extracted signatures as well as how different experimental parameters affect classification accuracy. The obtained classification accuracy ranged from 82% to 87% (based on the selected ROI) suggesting that the proposed classification framework can be potentially useful in supporting medical decision-making.

Citation Download Citation

Despina Kontos and Vasileios Megalooikonomou "Fast and effective characterization of 3D region of interest in medical image data", Proc. SPIE 5370, Medical Imaging 2004: Image Processing, (12 May 2004); https://doi.org/10.1117/12.534459

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