Related Experiment Video
Updated: Jul 31, 2025
14:08
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
42.7K
Intracerebral hemorrhage CT scan image segmentation with HarDNet based transformer
Zhegao Piao1, Yeong Hyeon Gu2, Hailin Jin1
1Department of Computer Science and Engineering, Sejong University, Seoul, South Korea.
Scientific Reports
|May 3, 2023
Summary
This study introduces TransHarDNet, a new model for segmenting brain hemorrhage on CT scans. It improves efficiency and speed over U-Net models for better intracerebral hemorrhage diagnosis.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Computer Vision
Background:
- U-Net models for hemorrhage segmentation have limitations in parameter efficiency, model size, and speed.
- Existing encoder-decoder architectures struggle with efficient information transfer.
Purpose of the Study:
- To propose TransHarDNet, an improved image segmentation model for diagnosing intracerebral hemorrhage from CT scans.
- To enhance efficiency and inference speed while maintaining high performance in hemorrhage segmentation.
Main Methods:
- Integrating HarDNet blocks into the U-Net architecture.
- Connecting the encoder and decoder using a transformer block.
- Training and testing on a large dataset of 82,636 CT scan images with five hemorrhage types.
Main Results:
- TransHarDNet achieved a Dice coefficient of 0.712 and an IoU of 0.597 on a test set of 1200 hemorrhage images.
- Demonstrated superior performance compared to U-Net, U-Net++, SegNet, PSPNet, and HarDNet.
- Achieved an inference speed of 30.78 frames per second (FPS), faster than most encoder-decoder models.
Conclusions:
- TransHarDNet offers reduced network complexity and improved inference speed for brain hemorrhage segmentation.
- The proposed model maintains high performance, outperforming conventional segmentation models.
- TransHarDNet presents a viable and efficient solution for the automated diagnosis of intracerebral hemorrhage.
