AI Article Synopsis
- An improved adaptive multi-dictionary learning method is introduced to enhance the quality of super-resolution (SR) reconstructed medical images by integrating information from both medical images and a database of natural images.
- The method employs an image pyramid, using upper layer images derived from the self-similarity of low-resolution images during the training phase, and takes the top layer image for initial reconstruction.
- Experimental results demonstrate that this approach effectively utilizes both similar information at the same scale and different scales, leading to significant improvements in medical image SR reconstruction.
Article Abstract
To improve the quality of the super-resolution (SR) reconstructed medical images, an improved adaptive multi-dictionary learning method is proposed, which uses the combined information of medical image itself and the natural images database. In training dictionary section, it uses the upper layer images of pyramid which are generated by the self-similarity of low resolution images. In reconstruction section, the top layer image of pyramid is taken as the initial reconstruction image, and medical image's SR reconstruction is achieved by regularization term which is the non-local structure self-similarity of the image. This method can make full use of the same scale and different scale similar information of medical images. Simulation experiments are carried out on natural images and medical images, and the experimental results show the proposed method is effective for improving the effect of medical image SR reconstruction.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1080/24699322.2018.1560092 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Want AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!