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

Brain Imaging01:14

Brain Imaging

280
Brain imaging technologies provide critical insights into both the structure and function of the human brain, enabling medical professionals and researchers to diagnose, study, and treat neurological disorders or psychiatric disorders more effectively.
These technologies include computerized axial tomography (CAT or CT scans), positron-emission tomography (PET scans),  magnetic resonance imaging (MRI),  functional magnetic resonance imaging (fMRI), and Transcranial Magnetic...
280
Organization of the Brain01:30

Organization of the Brain

949
The brain is an integral component of the nervous system and serves as the center for processing sensory inputs, making decisions, and directing bodily actions. This complex organ is organized into three primary sections: the hindbrain, midbrain, and forebrain, each responsible for a range of vital functions.
Hindbrain
The hindbrain, located at the base of the brain, plays a vital role in regulating automatic processes that sustain life. It includes the medulla oblongata, which is essential for...
949

You might also read

Related Articles

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

Sort by
Same author

A tri-modal contrastive learning framework for protein representation learning.

Cell reports methods·2026
Same author

scLong: a billion-parameter foundation model for capturing long-range gene context in single-cell transcriptomics.

Nature communications·2026
Same author

AI-Driven Tacrolimus Dosing in Transplant Care: Cohort Study.

JMIR AI·2025
Same author

TapWeight: Reweighting Pretraining Objectives for Task-Adaptive Pretraining.

Transactions on machine learning research·2025
Same author

Transformer Architecture Search for Improving Out-of-Domain Generalization in Machine Translation.

Transactions on machine learning research·2025
Same author

Downstream Task Guided Masking Learning in Masked Autoencoders Using Multi-Level Optimization.

Transactions on machine learning research·2025

Related Experiment Video

Updated: Aug 22, 2025

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery
09:53

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Published on: July 5, 2021

3.7K

Brain tumor classification based on neural architecture search.

Shubham Chitnis1, Ramtin Hosseini2, Pengtao Xie3

  • 1Department of Chemical Engineering, Indian Institute of Technology Bombay, Mumbai, India.

Scientific Reports
|November 10, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning method, Learning-by-Self-Explanation (LeaSE), to automatically design neural architectures for brain tumor classification from MRI scans. LeaSE achieves superior accuracy and efficiency compared to manual designs, aiding diagnosis in underserved regions.

More Related Videos

Author Spotlight: Streamlined Brain and Skull Modeling for Enhanced Neurosurgical Planning in NHP Research
06:33

Author Spotlight: Streamlined Brain and Skull Modeling for Enhanced Neurosurgical Planning in NHP Research

Published on: February 9, 2024

1.3K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.7K

Related Experiment Videos

Last Updated: Aug 22, 2025

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery
09:53

Role of Diffusion MRI Tractography in Endoscopic Endonasal Skull Base Surgery

Published on: July 5, 2021

3.7K
Author Spotlight: Streamlined Brain and Skull Modeling for Enhanced Neurosurgical Planning in NHP Research
06:33

Author Spotlight: Streamlined Brain and Skull Modeling for Enhanced Neurosurgical Planning in NHP Research

Published on: February 9, 2024

1.3K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.7K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Biology

Background:

  • Brain tumors are a significant global health concern, with accurate diagnosis from Magnetic Resonance Imaging (MRI) crucial for effective treatment.
  • A shortage of expert radiologists in underserved regions necessitates advanced diagnostic tools for brain tumor detection and classification.
  • Current deep learning approaches rely on manually designed neural architectures, which are time-consuming and labor-intensive.

Purpose of the Study:

  • To develop an automated method for discovering high-performance neural network architectures for brain tumor classification from MRI data.
  • To address the limitations of manual neural architecture design in terms of time, labor, and performance.
  • To improve the accuracy and efficiency of brain tumor diagnosis using artificial intelligence.

Main Methods:

  • Proposed a Learning-by-Self-Explanation (LeaSE) framework, an automated neural architecture search method.
  • LeaSE utilizes an explainer model to guide architecture search based on explanation fidelity, evaluated by an audience model.
  • The method was applied to a dataset of 3264 MRI images for classifying glioma, meningioma, pituitary tumors, and healthy tissues.

Main Results:

  • The LeaSE method automatically designed neural architectures that outperformed manually designed networks in brain tumor classification accuracy.
  • Achieved a test accuracy of 90.6% and an Area Under the Curve (AUC) of 95.6% with 3.75M parameters.
  • Outperformed ResNet101 (84.5% accuracy, 90.1% AUC, 42.56M parameters) and other state-of-the-art neural architecture search methods.

Conclusions:

  • Automated neural architecture search using LeaSE offers a promising approach for developing efficient and accurate AI tools for brain tumor diagnosis.
  • The method demonstrates potential for improving diagnostic capabilities in regions with limited access to expert radiologists.
  • LeaSE provides a more efficient and effective alternative to manual deep learning model design for medical image analysis.