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

Segmentation, feature extraction, and multiclass brain tumor classification.

Jainy Sachdeva1, Vinod Kumar, Indra Gupta

  • 1Biomedical Engineering Lab, Department of Electrical Engineering, Indian Institute of Technology Roorkee, 247667, Roorkee, Uttrakhand, India, jainysachdeva@gmail.com.

Journal of Digital Imaging
|May 7, 2013
PubMed
Summary

This study developed a PCA-ANN approach for multiclass brain tumor classification from MRI scans. The method achieved high accuracy, demonstrating its potential for computer-aided diagnosis in radiology.

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

Clinical, Neuroimaging, and Functional Profile of Children With Hemiplegic Cerebral Palsy: A Cross-Sectional Study From a Tertiary Care Center.

Journal of child neurology·2026
Same author

Incremental value of whole-body 18F-fluorodeoxyglucose PET/computed tomography in cavernous sinus syndrome: guiding biopsy and improving diagnostic outcome.

Nuclear medicine communications·2026
Same author

Invasive mould infections of the central nervous system in the Indian population: a cohort study (2004-2025).

The Lancet regional health. Southeast Asia·2026
Same author

Magnetic resonance vessel wall imaging is superior to MRA in assessing the extent of vascular involvement in patients with moyamoya disease.

Polish journal of radiology·2026
Same author

Clinical Manifestations.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same author

Biomarkers.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Multiclass brain tumor classification is crucial for effective treatment planning.
  • Accurate segmentation and feature extraction from MR images are challenging.
  • Existing methods may lack robustness in differentiating various tumor types.

Purpose of the Study:

  • To develop and evaluate a Principal Component Analysis-Artificial Neural Network (PCA-ANN) approach for multiclass brain tumor classification.
  • To assess the classification accuracy and robustness of the proposed PCA-ANN system using a diverse dataset of brain MR images.
  • To explore the potential of this system as a computer-aided diagnostic tool for radiologists.

Main Methods:

  • Utilized a dataset of 428 post-contrast T1-weighted MR images from 55 patients, encompassing astrocytoma, glioblastoma multiforme, medulloblastoma, meningioma, metastatic tumors, and normal regions.

Related Experiment Videos

  • Extracted 856 SROIs using a content-based active contour model and 218 intensity and texture features.
  • Applied Principal Component Analysis (PCA) for dimensionality reduction, followed by classification using an Artificial Neural Network (ANN).

    • Main Results:

    • The PCA-ANN approach demonstrated a significant increase in classification accuracy, reaching up to 91% in experiments with random sub-sampling.
    • High individual class accuracies were achieved, including 90.74% for Astrocytoma, 88.46% for Glioblastoma Multiforme, 96.67% for Metastatic tumors, and 93.78% for Normal Regions.
    • Even when data was partitioned to prevent patient overlap between training and testing sets, the system maintained robust performance with an overall accuracy of 85.23%.

    Conclusions:

    • The developed PCA-ANN approach is effective for multiclass brain tumor classification using MRI data.
    • The system shows promise as a computer-aided diagnostic tool, aiding radiologists in precise tumor localization and diagnosis.
    • Further development could enhance the accuracy and reliability of automated brain tumor classification systems.