Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity
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 im...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2019-02-01
|
| Series: | Computer Assisted Surgery |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/24699322.2018.1557906 |
| _version_ | 1811305839231762432 |
|---|---|
| author | Fang Zhang Yue Wu Zhitao Xiao Lei Geng Jun Wu Jia Wen Wen Wang Ping Liu |
| author_facet | Fang Zhang Yue Wu Zhitao Xiao Lei Geng Jun Wu Jia Wen Wen Wang Ping Liu |
| author_sort | Fang Zhang |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-04-13T08:33:39Z |
| format | Article |
| id | doaj.art-a7c5ac9844a04035a27116b07f428579 |
| institution | Directory Open Access Journal |
| issn | 2469-9322 |
| language | English |
| last_indexed | 2024-04-13T08:33:39Z |
| publishDate | 2019-02-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | Computer Assisted Surgery |
| spelling | doaj.art-a7c5ac9844a04035a27116b07f4285792022-12-22T02:54:10ZengTaylor & Francis GroupComputer Assisted Surgery2469-93222019-02-01001810.1080/24699322.2018.15579061557906Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarityFang Zhang0Yue Wu1Zhitao Xiao2Lei Geng3Jun Wu4Jia Wen5Wen Wang6Ping Liu7Tianjin Key Laboratory of Optoelectronic Detection Technology and SystemsTianjin Polytechnic UniversityTianjin Key Laboratory of Optoelectronic Detection Technology and SystemsTianjin Key Laboratory of Optoelectronic Detection Technology and SystemsTianjin Key Laboratory of Optoelectronic Detection Technology and SystemsTianjin Key Laboratory of Optoelectronic Detection Technology and SystemsTianjin Key Laboratory of Optoelectronic Detection Technology and SystemsTianjin Polytechnic UniversityTo 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.http://dx.doi.org/10.1080/24699322.2018.1557906Super-resolution reconstructionmedical imageimproved adaptive multi-dictionary learningnon-local structural similarity |
| spellingShingle | Fang Zhang Yue Wu Zhitao Xiao Lei Geng Jun Wu Jia Wen Wen Wang Ping Liu Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity Computer Assisted Surgery Super-resolution reconstruction medical image improved adaptive multi-dictionary learning non-local structural similarity |
| title | Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity |
| title_full | Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity |
| title_fullStr | Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity |
| title_full_unstemmed | Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity |
| title_short | Super resolution reconstruction for medical image based on adaptive multi-dictionary learning and structural self-similarity |
| title_sort | super resolution reconstruction for medical image based on adaptive multi dictionary learning and structural self similarity |
| topic | Super-resolution reconstruction medical image improved adaptive multi-dictionary learning non-local structural similarity |
| url | http://dx.doi.org/10.1080/24699322.2018.1557906 |
| work_keys_str_mv | AT fangzhang superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity AT yuewu superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity AT zhitaoxiao superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity AT leigeng superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity AT junwu superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity AT jiawen superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity AT wenwang superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity AT pingliu superresolutionreconstructionformedicalimagebasedonadaptivemultidictionarylearningandstructuralselfsimilarity |