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 explainable multi-stage framework for brain tumor classification using hybrid feature fusion and EfficientNetB5

Imran Qureshi1, Muhammad Zaheer Sajid2, Ayman Youssef3

  • 1College of Computer and Information Sciences, Imam Mohammad Ibn Saud Islamic University (IMSIU), 11432, Riyadh, Saudi Arabia. iqureshi@imamu.edu.sa.

Scientific Reports
|May 21, 2026
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

The Cutting Edge: Interventional Strategies for Pain Management.

Physical medicine and rehabilitation clinics of North America·2026
Same author

Lightweight and Energy-Aware Intrusion Detection for Industrial IoT Using TinyML and Edge AI.

Scientific reports·2026
Same author

Privacy-aware distributed intelligence with tokenized trust for low-latency task offloading in 6G vehicular edge networks.

Scientific reports·2026
Same author

Cardio-Dense: Diagnosis of Cardiac Abnormalities Based on Phonocardiogram Using Improved Swin Transformer Through Lightweight Dense Blocks.

Diagnostics (Basel, Switzerland)·2026
Same author

A gated task-attentive multi-task network for unified retinal image analysis.

Scientific reports·2026
Same author

Characteristics and Outcomes of Patients With Malignancies Prior to Colorectal Cancer: A Propensity Score Matched Analysis.

Journal of gastrointestinal cancer·2026

Accurate brain tumor classification is crucial for patient care. A new HyFusion-Net model combines handcrafted and deep learning features for superior accuracy and clinical interpretability in brain tumor detection.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Accurate brain tumor (BT) severity classification is vital for effective clinical decision-making.
  • Manual assessment of brain tumors is time-consuming and labor-intensive for medical experts.
  • Current deep learning (DL) models show potential but often lack feature diversity for robust classification.

Purpose of the Study:

  • To introduce HyFusion-Net, a novel and explainable DL framework for brain tumor classification.
  • To enhance classification accuracy by fusing handcrafted and deep features.
  • To provide clinical interpretability through explainability maps for better radiologist understanding.

Main Methods:

  • Developed HyFusion-Net, a DL framework integrating handcrafted features (SIFT, LBP, HoG, Canny) with deep features from DenseNet201.
Keywords:
Brain tumorDeep learningFeature fusionMagnetic resonance imageOcclusion map

Related Experiment Videos

  • Employed an EfficientNetB5 classifier for superior performance.
  • Integrated occlusion map-based explainability to identify critical tumor regions for classification decisions.

    • Main Results:

    • The HyFusion-Net model achieved superior classification accuracy compared to other DL methods.
    • Demonstrated robust performance across variations in MRI data.
    • Generated explainability heatmaps that align with radiological markers, enhancing clinical interpretability.

    Conclusions:

    • The HyFusion-Net model is suitable for clinical application in brain tumor diagnosis.
    • The framework offers a transparent diagnostic rate and aids radiologists in understanding classification rationale.
    • This approach improves upon existing DL methods by offering both high accuracy and explainability.