Quantification of periventricular lesions from MR brain images /

average Mahalanobis distance and neural network, are

Bibliographic Details
Main Author: Madhavan, Sridhar
Format: Thesis eBook
Language:English
Published: [Place of publication not identified] : [publisher not identified] ; 1996.
Subjects:
Online Access:Link to OAKTrust copy
Description
Summary:average Mahalanobis distance and neural network, are
clinically usable software environment.
evaluated as part of the region growing algorithm. The
for the medical community to quantify periventricular lesions
generated and then used as the homogeneity criterion in a
Graphical-User-Interface is designed in order to have a
growing with the neural network stopping criterion provides
lesions for the purpose of studying ways to prevent or
Magnetic Resonance brain images of Acquired Immunodeficiency
Periventricular lesions are associated with hyperintensity in
Provisions are made for a radiologist to input lesion
region growing algorithm. Two different stopping criteria,
results obtained indicate that the perpendicular region
reverse this disease. Basically this work has led to a tool
seedpoints interactively. A comprehensive feature vector is
Syndrome patients. The objective of this research has been
the closest match to the manual segmentation of lesions. A
the development of a user-friendly software to quantify such
which are currently assessed in a qualitative manner.
Item Description:"Major subject: Electrical Engineeering".
Vita.
Physical Description:xi, 72 leaves : illustrations ; 28 cm.
Also available online.
Issued also on microfiche from Lange Micrographics.
Bibliography:Includes bibliographical references: pages 58-62.