Related Experiment Video
Updated: May 10, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
MEF-Net: Multi-scale and edge feature fusion network for intracranial hemorrhage segmentation in CT images
Xiufeng Zhang1, Shichen Zhang1, Yunfei Jiang1
1Mechanical and Electrical Engineering, Dalian Minzu University, Liaohe West Road 18, Dalian, China.
Insights
Early diagnosis of intracranial hemorrhage (ICH) is vital. A new MEF-Net model accurately segments brain bleeds in CT scans, improving diagnostic support and patient outcomes.
Area of Science:
- Medical Imaging
- Artificial Intelligence
- Neurology
Background:
- Intracranial hemorrhage (ICH) is a critical condition requiring timely diagnosis.
- Delayed diagnosis of cerebral bleeding leads to severe disability or death.
- Accurate segmentation of hematomas in CT scans aids diagnosis and treatment.
Purpose of the Study:
- To develop an automated method for precise intracranial hemorrhage segmentation in CT images.
- To improve diagnostic efficiency and accuracy for ICH using deep learning.
- To address challenges in segmenting ICH with multi-scale, multi-target, and blurred-edge characteristics.
Main Methods:
- Proposed a Multi-scale and Edge Feature Fusion Network (MEF-Net) for ICH segmentation.
- Utilized an encoder for multi-scale feature extraction and an edge detection module.
- Incorporated a multi-kernel attention module to enhance multi-target recognition.
Main Results:
- MEF-Net achieved average DICE scores of 0.7508 and 0.7443 on two public datasets.
- The proposed method outperformed several existing advanced medical image segmentation techniques.
- Demonstrated significant improvement in the accuracy of intracranial hemorrhage segmentation.
Conclusions:
- MEF-Net effectively extracts and fuses multi-scale and edge features for accurate ICH segmentation.
- The network enhances diagnostic support for clinicians by improving segmentation accuracy.
- This automated approach holds promise for better patient outcomes in managing intracranial hemorrhage.
Abstract:
Intracranial Hemorrhage (ICH) refers to cerebral bleeding resulting from ruptured blood vessels within the brain. Delayed and inaccurate diagnosis and treatment of ICH can lead to fatality or disability. Therefore, early and precise diagnosis of intracranial hemorrhage is crucial for protecting patients' lives. Automatic segmentation of hematomas in CT images can provide doctors with essential diagnostic support and improve diagnostic efficiency. CT images of intracranial hemorrhage exhibit characteristics such as multi-scale, multi-target, and blurred edges. This paper proposes a Multi-scale and Edge Feature Fusion Network (MEF-Net) to effectively extract multi-scale and edge features and fully fuse these features through a fusion mechanism. The network first extracts the multi-scale features and edge features of the image through the encoder and the edge detection module respectively, then fuses the deep information, and employs the multi-kernel attention module to process the shallow features, enhancing the multi-target recognition capability. Finally, the feature maps from each module are combined to produce the segmentation result. Experimental results indicate that this method has achieved average DICE scores of 0.7508 and 0.7443 in two public datasets respectively, surpassing those of several advanced methods in medical image segmentation currently available. The proposed MEF-Net significantly improves the accuracy of intracranial hemorrhage segmentation.
