Related Experiment Video
Updated: Jul 26, 2025
04:48
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
Published on: November 30, 2022
2.8K
CT medical image segmentation algorithm based on deep learning technology.
Tongping Shen1,2, Fangliang Huang1, Xusong Zhang2
1School of Information Engineering, Anhui University of Chinese Medicine, Hefei, 230012, China.
Mathematical Biosciences and Engineering : MBE
|June 16, 2023
Summary
This study introduces an improved deep neural network for medical image segmentation, enhancing accuracy for complex lesions. The novel approach effectively addresses challenges like blurred edges and noise interference in medical imaging.
Area of Science:
- Medical Imaging
- Computer Vision
- Artificial Intelligence
Background:
- Medical image segmentation faces challenges including blurred edges, uneven backgrounds, and noise.
- Accurate segmentation is crucial for diagnosing and monitoring various medical conditions.
Purpose of the Study:
- To develop a robust medical image segmentation algorithm using deep neural network technology.
- To improve segmentation accuracy for complex lesions and challenging image artifacts.
Main Methods:
- A deep neural network with a U-Net-like encoder-decoder structure was employed.
- Residual and convolutional structures were used for feature extraction.
- An attention mechanism module was integrated into network jump connections to enhance spatial perception and reduce channel redundancy.
Main Results:
- The proposed model achieved high performance across multiple datasets (DRIVE, ISIC2018, COVID-19 CT).
- Demonstrated Dice scores of 0.7826, 0.8904, and 0.8069, and IOU scores of 0.9683, 0.9537, and 0.9462, respectively.
- Significantly improved segmentation accuracy for medical images with complex lesion shapes and adhesions.
Conclusions:
- The developed deep neural network algorithm effectively enhances medical image segmentation.
- The integration of attention mechanisms improves the handling of complex lesions and noisy data.
- The model shows promise for clinical applications requiring precise medical image analysis.
