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 Concept Videos

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

9.1K
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...
9.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Loss of the calorie restriction response protein DEPP1 worsens diet-induced obesity.

Endocrinology·2026
Same author

An advanced framework for predicting pollen outbreaks using multi-input multi-output temporal convolutional networks and firefly algorithm.

Scientific reports·2026
Same author

Low resource federated learning for classification of nail disease by deploying cross-silo and heterogeneously dataset distributions.

Scientific reports·2026
Same author

Firefly algorithm and DNN for improved contactless heart rate measurement from videos.

Scientific reports·2026
Same author

Proposed dense variational autoencoder model integrated with contrastive learning for foot ulcer classification.

Scientific reports·2026
Same author

Efficient Multiscale Gradient-Domain Filtering for Image and Video Dehazing with Enhanced Temporal Coherence.

Journal of visualized experiments : JoVE·2025

Related Experiment Video

Updated: Jan 17, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.4K

Convolutional Neural Network-based Framework for Brain Tumor Classification and Segmentation using Magnetic Resonance

Ambuj Kathuria1, Deepali Gupta2, Mudita Uppal2

  • 1Chitkara University Institute of Engineering and Technology, Chitkara University; ambujkathuria@yahoo.co.in.

Journal of Visualized Experiments : Jove
|September 22, 2025
PubMed
Summary

This study introduces a deep learning framework for brain tumor segmentation and classification from MRI scans. The system achieves high accuracy in identifying tumor types and grades, enabling automated clinical reporting.

More Related Videos

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.3K
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

Related Experiment Videos

Last Updated: Jan 17, 2026

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.4K
Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

49.3K
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

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Oncology

Background:

  • Early brain tumor diagnosis is crucial for patient prognosis and treatment planning.
  • Accurate segmentation and classification of brain tumors from MRI scans are challenging yet essential.
  • Advancements in MRI and computer vision necessitate effective deep learning models for brain tumor analysis.

Purpose of the Study:

  • To develop and evaluate a deep learning-based framework for segmenting and classifying brain tumors from MRI data.
  • To compare the performance of different deep learning models for tumor classification and grading.
  • To integrate hybrid models with GPT-4.0 for automated clinical report generation.

Main Methods:

  • Utilized nine image augmentation techniques for preprocessing MRI scans.
  • Employed a U-Net model for brain tumor segmentation.
  • Developed classification models using InceptionV3, DenseNet201, and Inception-ResNet-v2 for tumor type and grade identification.
  • Integrated hybrid models with GPT-4.0 for automated report generation.

Main Results:

  • InceptionV3 achieved 99.15% accuracy in classifying tumor types (Glioma, Meningioma, Pituitary), outperforming DenseNet201 (98.75%).
  • Inception-ResNet-v2 accurately classified tumor grades (HGG/LGG) with 96.64% accuracy.
  • The integrated system demonstrated potential for autonomous identification and reporting of brain tumors.

Conclusions:

  • The proposed deep learning framework effectively segments and classifies brain tumors from MRI scans.
  • The hybrid model integrating U-Net, InceptionV3/DenseNet201, Inception-ResNet-v2, and GPT-4.0 offers a promising solution for automated clinical analysis.
  • This novel framework has the potential to significantly aid clinicians in the early and accurate diagnosis of brain tumors.