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

You might also read

Related Articles

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

Sort by
Same author

Pro-515 of the dynamin-like GTPase MxB contributes to HIV-1 inhibition by regulating MxB oligomerization and binding to HIV-1 capsid.

The Journal of biological chemistry·2020
Same author

Efficient solar hydrogen production coupled with organics degradation by a hybrid tandem photocatalytic fuel cell using a silicon-doped TiO<sub>2</sub> nanorod array with enhanced electronic properties.

Journal of hazardous materials·2020
Same author

Ribitol enhances matriglycan of α-dystroglycan in breast cancer cells without affecting cell growth.

Scientific reports·2020
Same author

RUNX3 Inhibits the Invasion and Metastasis of Human Colon Cancer HT-29 Cells by Upregulating MMP-2/9.

Evidence-based complementary and alternative medicine : eCAM·2020
Same author

Observation of changes in the number of myocardial capillaries in rabbits after treatment of acute myocardial infarction by Tongxinluo superfine powder.

Journal of traditional Chinese medicine = Chung i tsa chih ying wen pan·2020
Same author

Circulating Factors in Trauma Plasma Activate Specific Human Immune Cell Subsets.

Injury·2020

Related Experiment Video

Updated: Oct 18, 2025

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

3.0K

Multi-Task Deep Supervision on Attention R2U-Net for Brain Tumor Segmentation.

Shiqiang Ma1, Jijun Tang1,2,3, Fei Guo4

  • 1School of Computer Science and Technology, College of Intelligence and Computing, Tianjin University, Tianjin, China.

Frontiers in Oncology
|October 4, 2021
PubMed
Summary

This study introduces an attention R2U-Net model with multi-task deep supervision (MTDS) for precise brain tumor segmentation. The novel approach enhances accuracy and efficiency in medical image analysis.

Keywords:
attention mechanismbrain tumor segmentationdeep supervisionmulti-scale feature fusionmulti-task learningsemi-supervised learning

More Related Videos

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

3.1K
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

43.0K

Related Experiment Videos

Last Updated: Oct 18, 2025

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

3.0K
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

3.1K
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

43.0K

Area of Science:

  • Medical image analysis
  • Artificial intelligence in oncology
  • Neuroimaging

Background:

  • Accurate brain tumor segmentation is crucial for diagnosis and treatment.
  • Existing deep learning models struggle with precise tumor localization and boundary delineation.
  • Challenges include extracting rich semantic information and preventing overfitting.

Purpose of the Study:

  • To develop an advanced 2D end-to-end model for accurate automatic brain tumor segmentation.
  • To improve the localization of tumor areas and the precision of segmentation boundaries.
  • To address limitations of simple deep learning models in medical image segmentation.

Main Methods:

  • Proposed a novel attention R2U-Net model integrated with multi-task deep supervision (MTDS).
  • Introduced the attention pre-activation residual module (APR) for enhanced tumor area localization using multi-scale fusion.
  • Evaluated the model on the BraTS 2020 validation dataset (125 cases).

Main Results:

  • Achieved competitive brain tumor segmentation results on the BraTS 2020 dataset.
  • The MTDS model effectively extracts semantic information and refines segmentation boundaries.
  • The APR module aids in accurate tumor localization.
  • Demonstrated a small parameter count and low computational cost compared to state-of-the-art methods.

Conclusions:

  • The proposed attention R2U-Net with MTDS offers an effective solution for automatic brain tumor segmentation.
  • The model achieves high accuracy while maintaining computational efficiency.
  • This technology holds promise for improving clinical diagnosis and treatment planning for brain tumors.