Image processing and algorithms for medical applications
Image degradation is a significant issue in medical imaging, as it may obscure the fine details of anatomical structures and organizations. This not only reduces the usability of the images thus increasing the time and monetary costs associated with diagnostic procedures, but also significantly impa...
Saved in:
| 主要作者: | |
|---|---|
| 其他作者: | |
| 格式: | Thesis-Master by Coursework |
| 語言: | English |
| 出版: |
Nanyang Technological University
2024
|
| 主題: | |
| 在線閱讀: | https://hdl.handle.net/10356/175599 |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| 機構: | Nanyang Technological University |
| 語言: | English |
| 總結: | Image degradation is a significant issue in medical imaging, as it may obscure the fine details of anatomical structures and organizations. This not only reduces the usability of the images thus increasing the time and monetary costs associated with diagnostic procedures, but also significantly impact the accuracy of subsequent image analysis and interpretation. Noise and blur are are the two most common types of degradation. This project evaluates and compares the effectiveness of several image filtering methods, including Gaussian filter, Median filter, DWT filter, NLM filter, BM3D method, U-Net and Restormer model in restoring medical images with various levels and types of synthetic noise or blur to highlight the performance of deep learning based methods like U-Net and their great potential for application in medical image processing.
Keywords: Medical image processing, Medical image denoising, Medical image deblurring, Medical image filtering, Deep learning, U-Net |
|---|