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

Advanced Deep Learning Architectures in MRI-Based Brain Tumor Classification: A Systematic Review Focused on

Naima Noor1,2, Clinton Turner3,4, Samantha J Holdsworth5,6

  • 1Auckland Bioengineering Institute, The University of Auckland, Auckland, 1010, New Zealand. naima.noor@auckland.ac.nz.

Journal of Imaging Informatics in Medicine
|July 7, 2026
PubMed
Summary

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

Deep Learning for Brain MRI Artifact Correction: Current Challenges and Future Directions.

Bioengineering (Basel, Switzerland)·2026
Same author

Machine learning approaches in automated infant General Movements Assessment: A scoping review.

Developmental medicine and child neurology·2026
Same author

Dysregulation of glycogen metabolism in cardiomyopathy caused by glycogenin-1 (GYG1) missense variants.

The Journal of clinical endocrinology and metabolism·2026
Same author

Development-related gene expression disruption in the human midcingulate cortex in Huntington's disease.

Journal of Huntington's disease·2026
Same author

Measurement and control of mechanics of cardiac trabeculae secured by light-curable hydrogel.

Experimental physiology·2025
Same author

Intracranial pulse wave velocity using 4D flow MRI: method comparison and covariate analysis.

Interface focus·2025
Same journal

DSGH-Net: Medical Image Segmentation via Dual-Statistical Dynamic Context and Graph-Convolutional Heterogeneous Decoder.

Journal of imaging informatics in medicine·2026
Same journal

Acceptance and Utilization of Picture Archiving and Communication Systems in Emergency Departments: A TAM-Based Study in Palestinian Governmental Hospitals.

Journal of imaging informatics in medicine·2026
Same journal

Gonial Angle Estimation on Dental Panoramic X-Rays Using Deep Learning: A Transfer Learning Approach for Keypoint Detection.

Journal of imaging informatics in medicine·2026
Same journal

MRI Radiomics for Preoperative Microvascular Invasion Stratification in Hepatocellular Carcinoma: Comparative Analysis of Intratumoral, Peritumoral, and Combined Intratumoral-Peritumoral Approaches-A Systematic Review and Meta-analysis.

Journal of imaging informatics in medicine·2026
Same journal

Cross-Center Online Generalization Algorithm with Unadversarial Consistency for Fetal Heart Ultrasound View Recognition.

Journal of imaging informatics in medicine·2026
Same journal

From Gram Stain to Decision Support: Performance of Multimodal Large Language Models in Blood Culture Microscopy.

Journal of imaging informatics in medicine·2026
See all related articles
This summary is machine-generated.

Deep learning models show promise for brain tumor classification from MRI, but clinical use is hindered by data bias and poor validation, especially for meningiomas. Improved reporting and diverse datasets are crucial for real-world application.

Area of Science:

  • Neuroimaging
  • Artificial Intelligence
  • Medical Diagnostics

Background:

  • Deep learning (DL) is increasingly used for automated brain tumor classification via MRI.
  • Clinical deployment is limited by tumor heterogeneity, dataset bias, and incomplete validation.
  • Meningioma classification is underrepresented in current AI research.

Purpose of the Study:

  • To systematically review advanced DL-based MRI brain tumor classification methods from 2016-2025.
  • To emphasize meningioma-focused classification and subtyping advancements.
  • To identify gaps and challenges hindering clinical translation.

Main Methods:

  • Systematic review of 56 eligible studies (2016-2025).
  • Categorization into five DL methodological groups: transformers, attention-enhanced CNNs, federated learning, etc.
Keywords:
Brain tumor classificationComputer-aided diagnosisConvolutional neural networksDeep learningFederated learningMRIMeningiomaTransformersTumor subtyping

Related Experiment Videos

  • Analysis of class-wise metrics, reporting practices, dataset usage, and interpretability.

    • Main Results:

    • Attention-enhanced CNNs and hybrid CNN-transformer models demonstrated high accuracy for meningiomas (F1-score 89.0%-99.0%).
    • A significant gap exists between general tumor classification and clinically actionable subtyping/grading, especially for meningiomas.
    • Reporting inconsistencies (e.g., missing MRI sequences, class imbalance) limit comparability and translation.

    Conclusions:

    • Standardized reporting, diverse datasets, and interpretability are needed for clinical readiness.
    • Clinically aligned meningioma evaluations are essential for effective translation.
    • Geographic concentration of research raises representativeness concerns.