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 1, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K

Brain Tumor Detection by Using Stacked Autoencoders in Deep Learning.

Javaria Amin1, Muhammad Sharif2, Nadia Gul3

  • 1Department of Computer Science, COMSATS University Islamabad, Wah Campus, Islamabad, Pakistan.

Journal of Medical Systems
|December 19, 2019
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

Sequential Transfer Learning for Multi-Domain Breast Image Segmentation Using a Transformer-Enhanced Hybrid U-Net.

Bioengineering (Basel, Switzerland)·2026
Same author

An Atypical Presentation of Tuberculous Ascites, Severe Hyponatremia, and Acute Kidney Injury in a Young Male.

Clinical case reports·2026
Same author

Targeting STE20-type kinase MST3 improves metabolic dysfunction-associated steatohepatitis without affecting hepatocellular carcinoma development in mice.

BMC medicine·2026
Same author

Advanced hybrid transformer CNN framework for improved skin lesion classification and segmentation.

Scientific reports·2026
Same author

Ageing promotes metastasis via activation of the integrated stress response.

Nature·2026
Same author

Amino acid restriction sensitizes lung cancer cells to ferroptosis via GCN2-dependent activation of the integrated stress response.

Redox biology·2026
This summary is machine-generated.

This study introduces a deep learning model for accurate brain tumor detection from MR images. The model enhances image quality and utilizes a stacked sparse autoencoder for improved tumor classification, demonstrating enhanced performance on benchmark datasets.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Computational Biology

Background:

  • Brain tumor detection is challenging due to variations in shape, size, and appearance.
  • Accurate segmentation and classification are crucial for effective diagnosis and treatment planning.

Purpose of the Study:

  • To develop and evaluate a deep learning model for automated brain tumor detection and classification from MR images.
  • To improve the accuracy and robustness of brain tumor identification using advanced image processing and machine learning techniques.

Main Methods:

  • Preprocessing involved high-pass and median filtering to enhance MR slice quality and highlight inhomogeneities.
  • A 4-connected seed growing algorithm was used for pixel-level segmentation based on image intensity.
Keywords:
GliomaHidden sizeMagnetic resonance imagesSoftmaxStacked sparse autoencoder

Related Experiment Videos

Last Updated: Jan 1, 2026

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.6K
  • A two-layer stacked sparse autoencoder (SSAE) model with 200 and 400 hidden units was fine-tuned for classification.
  • The model was trained and tested on multiple BRATS (Multimodal Brain Tumor Segmentation) datasets (2012-2015).

    • Main Results:

    • The proposed method demonstrated improved performance in brain tumor detection compared to existing approaches.
    • Image enhancement techniques effectively improved the visibility of tumor-related features.
    • The SSAE model achieved accurate classification of tumorous and non-tumorous regions.

    Conclusions:

    • The developed deep learning framework offers a promising approach for automated and accurate brain tumor detection.
    • The combination of image preprocessing, segmentation, and SSAE model provides a robust solution for clinical applications.
    • Further validation on diverse datasets can enhance the generalizability of the model.