A software tool for automatic classification and segmentation of 2D/3D medical images

Modern medical diagnosis utilizes techniques of visualization of human internal organs (CT, MRI) or of its metabolism (PET). However, evaluation of acquired images made by human experts is usually subjective and qualitative only. Quantitative analysis of MR data, including tissue classification and...

Full description

Saved in:
Bibliographic Details
Published in:Nuclear instruments & methods in physics research. Section A, Accelerators, spectrometers, detectors and associated equipment Vol. 702; pp. 137 - 140
Main Authors: Strzelecki, Michal, Szczypinski, Piotr, Materka, Andrzej, Klepaczko, Artur
Format: Journal Article
Language:English
Published: Elsevier B.V 21.02.2013
Subjects:
Classification
Data classification
Image analysis and processing software
Magnetic resonance imaging
Medical imaging
Positron emission
Segmentation
Surface layer
Texture
Texture analysis
Three dimensional
Tomography
Data classification
Texture analysis
Image analysis and processing software
Magnetic resonance imaging
ISSN:0168-9002, 1872-9576
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Modern medical diagnosis utilizes techniques of visualization of human internal organs (CT, MRI) or of its metabolism (PET). However, evaluation of acquired images made by human experts is usually subjective and qualitative only. Quantitative analysis of MR data, including tissue classification and segmentation, is necessary to perform e.g. attenuation compensation, motion detection, and correction of partial volume effect in PET images, acquired with PET/MR scanners. This article presents briefly a MaZda software package, which supports 2D and 3D medical image analysis aiming at quantification of image texture. MaZda implements procedures for evaluation, selection and extraction of highly discriminative texture attributes combined with various classification, visualization and segmentation tools. Examples of MaZda application in medical studies are also provided.
Bibliography:ObjectType-Article-2
SourceType-Scholarly Journals-1
ObjectType-Feature-1
content type line 23
ISSN:0168-9002
1872-9576
DOI:10.1016/j.nima.2012.09.006