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

Enhancing brain tumor detection through deep learning and explainable AI techniques.

Shaymaa A Hassan1, Anfal Hathah2, Omar E Elnokity2

  • 1Dept. of Electronics and Communications Engineering, Zagazig University, P.O. 44519, Zagazig, Egypt. shafayad@zu.edu.eg.

Scientific Reports
|July 4, 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

Machine learning-assisted validation of a high-isolation THz MIMO antenna for 6G communication and IoT application.

Scientific reports·2026
Same author

Graphene based terahertz MIMO antenna with machine learning regression for 6G communications.

Scientific reports·2026
Same author

SHARP-AODV: An Intelligent Adaptive Routing Protocol for Highly Mobile Autonomous Aerial Vehicle (AAV) Networks.

Sensors (Basel, Switzerland)·2025
Same author

High-performance quatrefoil-slotted THz MIMO antenna for 6G applications with regression-based machine learning validation.

Scientific reports·2025
Same author

Smart antenna with reconfigurable polarization for future generation of mm-wave communication.

Scientific reports·2025
Same author

Improving bovine disease detection through multilabel classification.

Scientific reports·2025
Same journal

MT-MRI for detection of renal interstitial fibrosis in renovascular disease.

Scientific reports·2026
Same journal

Detection of underground objects from GPR data using a lightweight YOLO-based approach.

Scientific reports·2026
Same journal

Early systemic inflammatory-metabolic trajectory phenotypes are associated with survival outcomes in metastatic renal cell carcinoma treated with nivolumab.

Scientific reports·2026
Same journal

Water balance components in a dry-seeded rice-wheat system: Untangling the effects of tillage and mulching practices.

Scientific reports·2026
Same journal

Topological approaches to quantum tensor train compression via ZX-calculus and SVD.

Scientific reports·2026
Same journal

determinants of flood impacts and adaptive capacity among market vendors in Walukuba-Masese, Jinja city, Uganda.

Scientific reports·2026
See all related articles
This summary is machine-generated.

This study developed a deep learning framework for brain tumor detection, achieving 98.3% accuracy. The AI model provides reliable, explainable results for medical imaging, enhancing trustworthy artificial intelligence in oncology.

Area of Science:

  • Medical Imaging and Artificial Intelligence
  • Oncology and Neuroscience
  • Computer Science and Machine Learning

Background:

  • Brain tumors are a significant cause of cancer mortality, with manual MRI analysis being time-consuming and subjective.
  • Deep learning (DL) offers automated brain tumor detection, but clinical adoption is hindered by limited data and lack of interpretability.
  • Developing robust and transparent AI tools is crucial for advancing medical diagnostics.

Purpose of the Study:

  • To introduce a deep learning (DL) framework for automated brain tumor detection.
  • To address challenges of limited dataset availability and lack of interpretability in medical AI.
  • To validate the framework's performance and clinical relevance through rigorous testing and explainable AI (XAI) analysis.

Main Methods:

Keywords:
Brain tumorDeep learningExplainable AI (XAI)External validationMRIPatient-wise cross-validation

Related Experiment Videos

  • Utilized InceptionV3 optimized with Nadam architecture for brain tumor detection.
  • Employed patient-wise stratified fivefold cross-validation with data augmentation and oversampling on 90% of data.
  • Validated the model on internal (10%) and external (3000 images) test sets, incorporating quantitative explainable AI (XAI) analyses.

Main Results:

  • Achieved 98.3% accuracy during cross-validation and perfect metrics (100% accuracy) on the internal test set.
  • Demonstrated strong generalizability on an external dataset with 96% accuracy.
  • Quantitative XAI confirmed high faithfulness, causal importance, and specificity, supporting model transparency.

Conclusions:

  • The proposed DL framework offers a rigorous and transparent solution for data-limited medical imaging, particularly for brain tumor detection.
  • The model achieves high diagnostic performance with clinically aligned explanations, establishing a foundation for trustworthy AI.
  • This approach enhances the reliability and interpretability of AI in medical diagnostics, paving the way for clinical translation.