Anatomical feature extraction for registration of multiple modalities of brain MR

Timothy S. Newman; James D. Leonard

doi:10.1117/12.275530

16 June 1997 Anatomical feature extraction for registration of multiple modalities of brain MR

Timothy S. Newman, James D. Leonard

Proceedings Volume 2976, Biomedical Sensing, Imaging, and Tracking Technologies II; (1997) https://doi.org/10.1117/12.275530
Event: BiOS '97, Part of Photonics West, 1997, San Jose, CA, United States

Abstract

This paper introduces techniques for the extraction of anatomical structures from magnetic resonance (MR) images of the head. The goal of the work is to extract features that are useful for registration of different modalities of tomographic datasets of a patient. These features must therefore be present in multiple modalities of the datasets. Three such features that can be extracted are the location of the eyes, the longitudinal fissure, and the lateral ventricles. In this paper, we present our methods for extracting these features. The techniques exploit geometric shape characteristics to aid in the extraction process, chiefly through the use of Hough-based accumulations for location of the eyes and longitudinal fissure. An approach consisting of volume-growing followed by a locally adaptive histogramming is used for extraction of the ventricles.

Citation Download Citation

Timothy S. Newman and James D. Leonard "Anatomical feature extraction for registration of multiple modalities of brain MR", Proc. SPIE 2976, Biomedical Sensing, Imaging, and Tracking Technologies II, (16 June 1997); https://doi.org/10.1117/12.275530

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