⚠ Official Notice: www.ijisrt.com is the official website of the International Journal of Innovative Science and Research Technology (IJISRT) Journal for research paper submission and publication. Please beware of fake or duplicate websites using the IJISRT name.



AI-Based Brain Tumor Detection, Classification and Segmentation Using EfficientNet-B0, VNet, Grad-CAM and Medical Chatbot


Authors : S. Abhignya; D. Shubhang; Dr. D. Sujatha

Volume/Issue : Volume 11 - 2026, Issue 7 - July


Google Scholar : https://tinyurl.com/2a8jpyta

DOI : https://doi.org/10.38124/ijisrt/26jul963

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.


Abstract : In this paper, an efficient deep learning-based system is designed to detect brain tumors from MRI images. This system uses a multi-class classification approach, which can classify brain tumors into categories such as Glioma, Meningioma, Pituitary Tumor, and No Tumor cases using a model built upon EfficientNet-B0. To ensure transparency, Grad-CAM is applied in this study to visualize the portions of the input image that help to make predictions, thus making the results easily interpretable in terms of locating a brain tumor. Moreover, besides classification, tumor segmentation is carried out for Glioma brain tumors through the use of V-Net model built upon the BraTS 2020 Dataset. Finally, tumor coverage calculation and automated medical reports are provided by the developed system.

Keywords : Brain Tumor Detection, Deep Learning, MRI Analysis, EfficientNet-B0, V-Net, Grad-CAM, Segmentation, Tumor Classification.

References :

  1. E. F. Gomes et al., “Deep Learning Approaches for Brain Tumor Classification and Imaging,” Applied Sciences, 2026.
  2. A. Angelina et al., “Advancing Brain Tumor Diagnosis Using Deep Learning,” medRxiv, 2026.
  3. N. Shatnawi et al., “Attention-Based Deep Residual CNN for Brain Tumor Classification,” 2026.
  4. N. JS et al., “Multiscale Attention U-Net with EfficientNet for Brain Tumor Segmentation,” Nature Scientific Reports, 2025.
  5. C. N. Devi et al., “Hybrid Res2Net-UNet Model for Brain Tumor Segmentation,” 2025.
  6. A. Pourmahboubi et al., “Transfer Learning-Based Brain Tumor Segmentation Using MRI,” 2025.
  7. B. M. Jebin et al., “Brain Tumor Detection and Classification Using CNN and U-Net,” 2025.
  8. E. Hassan et al., “EfficientNet-Based Brain Tumor Classification Framework,” 2025.
  9. N. A. Babar et al., “Attention-Guided Deep Learning Model for Brain Tumor Classification,” 2025.
  10. T. R. Mahesh et al., “Explainable AI-Based EfficientNet Framework for Brain Tumor Classification,” 2024.
  11. A. M. Mostafa et al., “Brain Tumor Segmentation Using Deep Learning on MRI,” 2023.
  12. B. Babu Vimala et al., “EfficientNet-Based Brain Tumor Classification Using Transfer Learning,” 2023.
  13. M. F. Ahamed et al., “Review on Brain Tumor Segmentation Using Deep Learning,” 2023.

In this paper, an efficient deep learning-based system is designed to detect brain tumors from MRI images. This system uses a multi-class classification approach, which can classify brain tumors into categories such as Glioma, Meningioma, Pituitary Tumor, and No Tumor cases using a model built upon EfficientNet-B0. To ensure transparency, Grad-CAM is applied in this study to visualize the portions of the input image that help to make predictions, thus making the results easily interpretable in terms of locating a brain tumor. Moreover, besides classification, tumor segmentation is carried out for Glioma brain tumors through the use of V-Net model built upon the BraTS 2020 Dataset. Finally, tumor coverage calculation and automated medical reports are provided by the developed system.

Keywords : Brain Tumor Detection, Deep Learning, MRI Analysis, EfficientNet-B0, V-Net, Grad-CAM, Segmentation, Tumor Classification.

Paper Submission Last Date
31 - October - 2026

SUBMIT YOUR PAPER CALL FOR PAPERS
Video Explanation for Published paper

Never miss an update from Papermashup

Get notified about the latest tutorials and downloads.

Subscribe by Email

Get alerts directly into your inbox after each post and stay updated.
Subscribe
OR

Subscribe by RSS

Add our RSS to your feedreader to get regular updates from us.
Subscribe