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 Video

Updated: Jan 18, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K

Explainable deep learning framework for brain tumor detection: Integrating LIME, Grad-CAM, and SHAP for enhanced

Abdurrahim Akgündoğdu1, Şerife Çelikbaş2

  • 1Electrical Electronics Engineering, Istanbul University-Cerrahpaşa, Istanbul, 34093, Istanbul, Turkey.

Medical Engineering & Physics
|September 9, 2025
PubMed
Summary
This summary is machine-generated.

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

Diagnosis of renal failure disease using Adaptive Neuro-Fuzzy Inference System.

Journal of medical systems·2010
Same author

3D image analysis and artificial intelligence for bone disease classification.

Journal of medical systems·2010
Same journal

Development and experimental characterization of a cadaveric stance simulator for residual limb biomechanics.

Medical engineering & physics·2026
Same journal

Rapid personalized computational modeling of the wrist.

Medical engineering & physics·2026
Same journal

SHAP-enabled explainable AI framework for clinical interpretation of valvular heart diseases via digital acoustic features.

Medical engineering & physics·2026
Same journal

Three-dimensional motion analysis of a total wrist prosthesis during the dart-throwing motion: a cadaveric study.

Medical engineering & physics·2026
Same journal

Patient-specific left ventricular hypertrophy under severe hypertension: mechanistic insights from Hill-type computational simulations.

Medical engineering & physics·2026
Same journal

Enabling laboratory-based personalization of musculoskeletal spine models: a standardized rail-guided ultrasound method.

Medical engineering & physics·2026
See all related articles

Explainable AI (XAI) techniques like LIME, Grad-CAM, and SHAP significantly improved deep learning models for brain tumor detection. This enhanced model accuracy from 97.20% to 99.40% on the BRATS2019 dataset.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computer Science

Background:

  • Deep learning enhances disease diagnosis but often lacks transparency.
  • AI decision systems require improved interpretability for clinical trust.
  • Brain tumor detection is a critical application for AI in healthcare.

Purpose of the Study:

  • To enhance the explainability and training performance of deep learning models for brain tumor detection.
  • To integrate explainable artificial intelligence (XAI) techniques into a convolutional neural network (CNN).
  • To validate the effectiveness of XAI in improving diagnostic accuracy and model reliability.

Main Methods:

  • A two-stage training approach was employed for a CNN model.
  • Explainable AI (XAI) methods including Local Interpretable Model-Agnostic Explanations (LIME), Gradient-weighted Class Activation Mapping (Grad-CAM), and Shapley Additive Explanations (SHAP) were utilized.
Keywords:
Explainable artificial intelligenceGradient-weighted class activation mappingLocal interpretable model-agnostic explanationsShapley additive explanations

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K

Related Experiment Videos

Last Updated: Jan 18, 2026

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.4K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.3K
  • Generated XAI masks were used to augment the dataset for improved training.

    • Main Results:

    • The initial CNN model achieved 97.20% accuracy on the BRATS2019 dataset.
    • Integration of LIME, Grad-CAM, and SHAP masks improved accuracy to 99.40%, with sensitivity at 99.20%, specificity at 99.60%, and ROC-AUC at 99.90%.
    • The model demonstrated generalizability, with accuracy increasing from 96.80% to 99.80% on the BR35H dataset.

    Conclusions:

    • XAI techniques significantly enhance the performance and interpretability of deep learning models for brain tumor detection.
    • The proposed method offers a reliable and stable strategy for improving AI diagnostic accuracy in medical imaging.
    • The integration of XAI is crucial for developing trustworthy and effective AI-driven clinical decision support systems.