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

An algorithm for automatic segmentation and classification of magnetic resonance brain images

B J Erickson1, R T Avula

  • 1Department of Diagnostic Radiology, Mayo Foundation, Rochester MN 55905, USA.

Journal of Digital Imaging
|June 3, 1998
PubMed
Summary

An automated algorithm accurately segments and classifies brain tissues, including cerebrospinal fluid (CSF), gray matter (GM), and white matter (WM), with high precision and reproducibility in magnetic resonance imaging (MRI). This tool aids in analyzing brain structures and pathologies.

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

Generative Adversarial Networks for Brain MRI Synthesis: Impact of Training Set Size on Clinical Application.

Journal of imaging informatics in medicine·2024
Same author

Does having a rotator cuff repair prior to reverse total shoulder arthroplasty influence the outcome?

The bone & joint journal·2019
Same author

Comparative outcomes of outpatient and inpatient total shoulder arthroplasty: an analysis of the Medicare dataset.

The bone & joint journal·2017
Same author

In-hospital mortality risk of intertrochanteric hip fractures: a comprehensive review of the US Medicare database from 2005 to 2010.

Musculoskeletal surgery·2017
Same author

Biomechanical testing of the reconstructed ulnar collateral ligament: a systematic review of the literature.

Musculoskeletal surgery·2016
Same author

Bioceramic bone graft substitute for treatment of unicameral bone cysts.

Journal of orthopaedic surgery (Hong Kong)·2016

Area of Science:

  • Neuroimaging
  • Medical Image Analysis
  • Biomedical Engineering

Background:

  • Accurate segmentation and classification of intracranial tissues are crucial for neurological research and clinical diagnosis.
  • Existing methods may lack automation, reproducibility, or accuracy in distinguishing normal tissues from pathologies like those found in multiple sclerosis (MS).

Purpose of the Study:

  • To develop and validate an automated algorithm for segmenting brain from extracranial tissues.
  • To classify intracranial tissues into cerebrospinal fluid (CSF), gray matter (GM), white matter (WM), and pathology.
  • To assess the accuracy and reproducibility of the algorithm.

Main Methods:

  • Acquisition of multi-sequence magnetic resonance (MR) images (T1, dual echo, FLAIR) from 100 normal and 9 MS patients.

Related Experiment Videos

  • Superimposition of synthetic MS-like lesions onto normal scans for precise accuracy measurement.
  • Application of the algorithm to repeated scans of MS patients to evaluate reproducibility.
  • Validation using known classifications from synthetic lesions and comparing repeated scans.

    • Main Results:

    • The algorithm achieved 96% accuracy in labeling normal intradural tissue voxels (GM, WM, CSF).
    • Pathological tissues were classified with 94% accuracy.
    • The algorithm demonstrated high reproducibility with a mean coefficient of variation (COV) of 4.1% for tissue and pathology measurements.

    Conclusions:

    • A fully automated algorithm accurately and reproducibly segments and classifies intracranial tissues.
    • The developed algorithm shows significant potential for quantitative analysis in neurological studies and clinical practice.
    • This automated approach enhances the reliability of brain tissue analysis from MR images.