Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Tissue segmentation and classification of MRSI data using canonical correlation analysis.

Teresa Laudadio1, Pieter Pels, Lieven De Lathauwer

  • 1Department of Electrical Engineering, Division ESAT-SCD, Katholieke Universiteit Leuven, Leuven-Heverlee, Belgium. laudadio@esat.kuleuven.ac.be

Magnetic Resonance in Medicine
|November 9, 2005
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Deconver: A Deconvolutional Network for Medical Image Segmentation.

IEEE journal of biomedical and health informatics·2025
Same author

DeepISLES: a clinically validated ischemic stroke segmentation model from the ISLES'22 challenge.

Nature communications·2025
Same author

AI-enabled detection of QRS fragmentation from 12-lead electrocardiogram and its clinical relevance for predicting malignant arrhythmia onset.

Frontiers in cardiovascular medicine·2024
Same author

Resting state electroencephalographic brain activity in neonates can predict age and is indicative of neurodevelopmental outcome.

Clinical neurophysiology : official journal of the International Federation of Clinical Neurophysiology·2024
Same author

Coupling between Regional Oxygen Saturation of the Brain and Vital Signs during Immediate Transition after Birth.

Neonatology·2024
Same author

A unified framework for multi-lead ECG characterization using Laplacian Eigenmaps.

Physiological measurement·2023

This study introduces a new Magnetic Resonance Spectroscopic Imaging (MRSI) tissue typing technique using Canonical Correlation Analysis (CCA). CCA offers accurate and efficient tissue characterization by integrating spectral and spatial data for improved analysis.

Area of Science:

  • Biomedical Engineering
  • Medical Imaging Analysis
  • Statistical Bioinformatics

Background:

  • Accurate tissue typing is crucial for diagnosing and monitoring various medical conditions.
  • Magnetic Resonance Spectroscopic Imaging (MRSI) provides rich spectral and spatial data for tissue characterization.
  • Existing methods for MRSI data analysis may not fully exploit the available information.

Purpose of the Study:

  • To develop and validate an accurate and efficient technique for tissue typing using MRSI data.
  • To adapt Canonical Correlation Analysis (CCA) for simultaneous spectral and spatial information exploitation in MRSI.
  • To compare the performance of CCA against ordinary correlation analysis for MRSI data.

Main Methods:

  • The study employed Canonical Correlation Analysis (CCA), a statistical method, for processing MRSI data.

Related Experiment Videos

  • CCA was adapted to simultaneously leverage both spectral and spatial information inherent in MRSI datasets.
  • The technique was validated using simulated and in vivo prostate MRSI data.

    • Main Results:

    • The proposed CCA-based technique demonstrated high accuracy, robustness, and efficiency in tissue typing.
    • Extensive studies confirmed the superior performance of CCA compared to ordinary correlation analysis.
    • CCA effectively retrieved tissue types by integrating spectral and spatial MRSI data.

    Conclusions:

    • Canonical Correlation Analysis provides an accurate and efficient method for tissue typing with MRSI data.
    • The integration of spectral and spatial information via CCA enhances the robustness of tissue characterization.
    • This technique holds significant potential for improving diagnostic capabilities in medical imaging.