Related Experiment Video
Updated: Aug 23, 2025
06:48
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
Published on: January 7, 2019
9.0K
Segmentation Algorithm of Magnetic Resonance Imaging Glioma under Fully Convolutional Densely Connected Convolutional
Jie Dong1, Yueying Zhang1, Yun Meng2
1School of Information Engineering, North China University of Water Resources and Electric Power, Zhengzhou 450045, China.
Stem Cells International
|October 27, 2022
Summary
A new algorithm, cerebral gliomas semantic segmentation network (CGSSNet), enhances magnetic resonance imaging (MRI) segmentation for glioma diagnosis. This deep learning approach shows improved accuracy and potential for clinical application.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neuro-oncology
Background:
- Accurate segmentation of brain tumors in MRI is crucial for glioma diagnosis and treatment planning.
- Existing segmentation algorithms face challenges in precision and efficiency.
- Deep learning models, particularly convolutional neural networks, show promise in medical image analysis.
Purpose of the Study:
- To develop and evaluate a novel automatic semantic segmentation method for glioma MRI images.
- To assess the application value of the proposed method in clinical practice.
- To compare the performance of the new algorithm against existing methods.
Main Methods:
- Development of the cerebral gliomas semantic segmentation network (CGSSNet) based on the fully convolutional DenseNet (FCDNN) architecture.
- Application of CGSSNet to segment glioma MRI images using the BraTS public dataset.
- Quantitative comparison of CGSSNet with other algorithms using Dice Similarity Coefficient (DSC), sensitivity, and Hausdorff Distance (HD).
Main Results:
- CGSSNet significantly improved the segmentation accuracy of glioma MRI images.
- Achieved DSC, sensitivity, and HD values of 0.937, 0.811, and 1.201, respectively.
- Demonstrated superior performance across different iteration times compared to other algorithms.
Conclusions:
- The CGSSNet model, leveraging DenseNet, enhances segmentation accuracy for glioma MRI.
- The algorithm shows significant potential for practical application in clinical glioma diagnosis.
- This deep learning approach offers a valuable tool for neuro-oncology image analysis.
