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

Brain tumor classification using hybrid spinal-EfficientNet using MRI images.

Ponlatha Sambandham1, Someswari Perla2, Ramachandro Majji3

  • 1Department of ECE, Mahendra Engineering College, Tamilnadu, India.

Journal of Neuroimmunology
|May 7, 2026
PubMed
Summary
This summary is machine-generated.

Related Concept Videos

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

You might also read

Related Articles

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

Sort by
Same author

Brain tumor detection using HyGSNet and feature extraction with DWT-based GDP.

Journal of neuroimmunology·2026
Same author

Deep Belief VGG-16 Hybrid Model for Brain Tumor Classification Using MRI Images.

NMR in biomedicine·2025
Same author

Smart IoT in Breast Cancer Detection Using Optimal Deep Learning.

Journal of digital imaging·2023
Same author

Jaya Ant lion optimization-driven Deep recurrent neural network for cancer classification using gene expression data.

Medical & biological engineering & computing·2021
Same author

Online Neonatal Training and Orientation Programme in India (ONTOP-IN)--the way forward for distance education in developing countries.

Journal of tropical pediatrics·2012
Same journal

Clinical features, imaging findings, and treatment outcomes of optic neuritis associated with anti-CRMP5 antibodies: a systematic review.

Journal of neuroimmunology·2026
Same journal

Serum IDO1 and β-catenin levels in patients with multiple sclerosis with and without atherosclerosis: A case-control study.

Journal of neuroimmunology·2026
Same journal

Neurological sequelae of Long COVID: Pathophysiological mechanisms, diagnostic advances, and therapeutic perspectives.

Journal of neuroimmunology·2026
Same journal

Clinical characteristics of IgG4-related hypertrophic pachymeningitis with and without serum ANCA positivity.

Journal of neuroimmunology·2026
Same journal

Chronic neuroinflammation after acute SARS-Cov-2 infection induces retinal damage in the hACE2 transgenic mouse model.

Journal of neuroimmunology·2026
Same journal

Myasthenia gravis misdiagnosis in the era of innovative therapies: Uncovering pitfalls and patterns.

Journal of neuroimmunology·2026
See all related articles

A new hybrid framework, Spinal-EfficientNet, improves brain tumor classification accuracy and speed. This method enhances early detection and clinical decisions by overcoming limitations of traditional approaches.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Biology

Background:

  • Traditional brain tumor classification methods face challenges like inefficiency, class imbalance, and high computational costs, delaying clinical decisions.
  • Magnetic Resonance Imaging (MRI) is crucial for brain tumor diagnosis, but accurate and efficient classification remains a significant hurdle.

Purpose of the Study:

  • To introduce Spinal-EfficientNet, a novel hybrid framework designed to enhance brain tumor classification accuracy and processing speed.
  • To address the limitations of existing methods in terms of efficiency and accuracy for brain tumor identification.

Main Methods:

  • Utilized Magnetic Resonance Imaging (MRI) brain scans from the BRATS 2018 dataset.
  • Employed wavelet-domain filtering for preprocessing, SegNet for tumor segmentation, and image augmentation techniques.
Keywords:
Brain tumorEfficientNetMagnetic resonance imagingSpinalNetWavelet-domain filtering

Related Experiment Videos

  • Extracted texture and statistical features, then classified tumors using the hybrid Spinal-EfficientNet architecture combining EfficientNet and SpinalNet.

    • Main Results:

    • Spinal-EfficientNet achieved high performance metrics: 92.5% specificity, 92.9% sensitivity, 92.5% accuracy, and 91.6% F1-score via k-fold cross-validation.
    • Demonstrated significant accuracy improvements over various existing methods, including CNN-SVM, VGG-SCNet, UL-BTD, AFDNN, ResNet50-EWS, EfficientNet-B0, and SpinalNet.

    Conclusions:

    • The Spinal-EfficientNet framework offers a reliable and effective approach for complex brain tumor classification tasks.
    • The proposed model shows notable gains in accuracy and processing speed, paving the way for more timely and accurate clinical decision-making.