Search research articles

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

Comparative effectiveness of low-dose versus high-dose vitamin D on bone metabolic markers in preterm infants: a retrospective cohort study.

Translational pediatrics·2026

Same author

An updated inventory of rock glaciers in the Eastern Himalaya.

Scientific data·2026

Same author

Observation of Structural Transition and Metallization in a van der Waals Diamagnet ZnPS<sub>3</sub> via Pressure Manipulation.

ACS omega·2026

Same author

High circular dichroism response predicted by deep learning in chiral metasurfaces.

Applied optics·2026

Same author

Endothelial SP1 lactylation promotes bronchopulmonary dysplasia via regulation of Cdkn1a expression.

Scientific reports·2026

Same author

RuleScope: Semantic-Aware Authoring of Data Validation Rules.

IEEE transactions on visualization and computer graphics·2026

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jul 4, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

An MRI brain tumor segmentation method based on improved U-Net.

Jiajun Zhu¹, Rui Zhang¹, Haifei Zhang¹

¹School of Computer and Information Engineering, Nantong Institute of Technology, Nantong 226600, China.

Mathematical Biosciences and Engineering : MBE

|February 2, 2024

Summary

This summary is machine-generated.

This study introduces an enhanced U-Net model for improved MRI brain tumor segmentation. The novel approach significantly boosts segmentation accuracy, aiding in diagnosis and treatment planning.

Keywords:

CBAM MRI U-Net brain tumor segmentation semantic segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

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

Published on: January 7, 2019

Related Experiment Videos

Last Updated: Jul 4, 2025

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

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

Published on: January 7, 2019

Area of Science:

Medical Imaging
Artificial Intelligence
Computer Vision

Background:

Convolutional Neural Networks (CNNs) can lose feature information during brain tumor image segmentation.
Existing U-Net models may not fully capture critical features for accurate segmentation.

Purpose of the Study:

To develop an enhanced U-Net architecture for improved MRI brain tumor segmentation.
To address feature information loss and class imbalance issues in CNN-based segmentation.

Main Methods:

Utilized ResNet50 as the backbone for enhanced feature extraction in U-Net.
Integrated the Convolutional Block Attention Module (CBAM) into residual modules for feature refinement.
Combined cross-entropy loss and Dice similarity coefficient to handle class imbalance and improve segmentation.

Main Results:

The enhanced U-Net achieved an average Intersection over Union (IoU) of 86.64%.
The Dice score reached 87.47%, outperforming original U-Net and R-Unet models.
Demonstrated significant improvements of 3.13% (IoU) and 2.06% (Dice) over baseline models.

Conclusions:

The proposed enhanced U-Net model significantly improves MRI brain tumor segmentation efficacy.
The method offers valuable technical support for clinical MRI diagnosis and treatment.
Attention mechanisms and combined loss functions enhance segmentation performance and robustness.