Related Experiment Video
Updated: Aug 22, 2025
Neuronavigation-guided Repetitive Transcranial Magnetic Stimulation for Aphasia
Published on: May 6, 2016
High-resolution medical image reconstruction based on residual neural network for diagnosis of cerebral aneurysm
1Department of Neurosurgery, The Second Affiliated Hospital of Guizhou Medical University, Kaili, China.
Insights
This study introduces a new lightweight super-resolution algorithm for CT angiography (CTA) images to enhance cerebral aneurysm visualization. The developed residual neural network model improves image clarity, aiding in more accurate diagnosis of this critical cerebrovascular disease.
Area of Science:
- Medical Imaging
- Computer Vision
- Biomedical Engineering
Background:
- Cerebral aneurysms are life-threatening cerebrovascular diseases requiring accurate diagnosis.
- CT angiography (CTA) is crucial for diagnosis, but patient movement hinders image quality.
- Improving the resolution of CTA images is essential for better clinical judgment.
Purpose of the Study:
- To develop a novel 3D medical image super-resolution algorithm for cerebral aneurysms.
- To address limitations of existing super-resolution methods, such as poor performance and long reconstruction times.
- To enhance the clarity and diagnostic utility of cerebral aneurysm images.
Main Methods:
- Designed a lightweight super-resolution network utilizing a residual neural network architecture.
- Modified residual blocks by removing the Batch Normalization (B.N.) layer to mitigate gradient problems.
- Incorporated a channel domain attention mechanism to improve network performance and information fidelity.
- Utilized a new dataset of cerebral aneurysms obtained via CTA imaging.
Main Results:
- The proposed model achieved superior performance compared to traditional methods (SRCNN, ESPCN, FSRCNN) on a cerebral aneurysm dataset.
- Objective evaluations showed improved Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) scores at 2x and 4x magnification.
- The model demonstrated higher robustness, accuracy, and intuition in practical application, assisting doctors in diagnosis.
Conclusions:
- The developed residual neural network-based super-resolution model significantly enhances high-resolution image reconstruction for cerebral aneurysms.
- This method offers a promising auxiliary diagnostic tool to improve the accuracy of cerebral aneurysm diagnosis.
- Its effectiveness is expected to grow with wider clinical application of CTA imaging.
Objective:
Cerebral aneurysms are classified as severe cerebrovascular diseases due to hidden and critical onset, which seriously threaten life and health. An effective strategy to control intracranial aneurysms is the regular diagnosis and timely treatment by CT angiography (CTA) imaging technology. However, unpredictable patient movements make it challenging to capture sub-millimeter-level ultra-high resolution images in a CTA scan. In order to improve the doctor's judgment, it is necessary to improve the clarity of the cerebral aneurysm medical image algorithm.
Methods:
This paper mainly focuses on researching a three-dimensional medical image super-resolution algorithm applied to cerebral aneurysms. Although some scholars have proposed super-resolution reconstruction methods, there are problems such as poor effect and too much reconstruction time. Therefore, this paper designs a lightweight super-resolution network based on a residual neural network. The residual block structure removes the B.N. layer, which can effectively solve the gradient problem. Considering the high-resolution reconstruction needs to take the complete image as the research object and the fidelity of information, this paper selects the channel domain attention mechanism to improve the performance of the residual neural network.
Results:
The new data set of cerebral aneurysms in this paper was obtained by CTA imaging technology of patients in the Department of neurosurgery, the second affiliated of Guizhou Medical University Hospital. The proposed model was evaluated from objective evaluation, model effect, model performance, and detection comparison. On the brain aneurysm data set, we tested the PSNR and SSIM values of 2 and 4 magnification factors, and the scores of our method were 33.01, 28.39, 33.06, and 28.41, respectively, which were better than those of the traditional SRCNN, ESPCN and FSRCNN. Subsequently, the model is applied to practice in this paper, and the effect, performance index and diagnosis of auxiliary doctors are obtained. The experimental results show that the high-resolution image reconstruction model based on the residual neural network designed in this paper plays a more influential role than other image classification methods. This method has higher robustness, accuracy and intuition.
Conclusion:
With the wide application of CTA images in the clinical diagnosis of cerebral aneurysms and the increasing number of application samples, this method is expected to become an additional diagnostic tool that can effectively improve the diagnostic accuracy of cerebral aneurysms.
