Edge-guided and Cross-scale Feature Fusion Network for Efficient Multi-contrast MRI Super-Resolution
| Title: | Edge-guided and Cross-scale Feature Fusion Network for Efficient Multi-contrast MRI Super-Resolution |
|---|---|
| Authors: | Yang, Zhiyuan, Zhang, Bo, Zeng, Zhiqiang, Yeo, Si Yong |
| Publication Year: | 2024 |
| Subject Terms: | Electrical Engineering and Systems Science - Image and Video Processing |
| More Details: | In recent years, MRI super-resolution techniques have achieved great success, especially multi-contrast methods that extract texture information from reference images to guide the super-resolution reconstruction. However, current methods primarily focus on texture similarities at the same scale, neglecting cross-scale similarities that provide comprehensive information. Moreover, the misalignment between features of different scales impedes effective aggregation of information flow. To address the limitations, we propose a novel edge-guided and cross-scale feature fusion network, namely ECFNet. Specifically, we develop a pipeline consisting of the deformable convolution and the cross-attention transformer to align features of different scales. The cross-scale fusion strategy fully integrates the texture information from different scales, significantly enhancing the super-resolution. In addition, a novel structure information collaboration module is developed to guide the super-resolution reconstruction with implicit structure priors. The structure information enables the network to focus on high-frequency components of the image, resulting in sharper details. Extensive experiments on the IXI and BraTS2020 datasets demonstrate that our method achieves state-of-the-art performance compared to other multi-contrast MRI super-resolution methods, and our method is robust in terms of different super-resolution scales. We would like to release our code and pre-trained model after the paper is accepted. Comment: submitted to ICPR2024 |
| Document Type: | Working Paper |
| Access URL: | http://arxiv.org/abs/2407.05307 |
| Accession Number: | edsarx.2407.05307 |
| Database: | arXiv |
| FullText | Text: Availability: 0 CustomLinks: – Url: http://arxiv.org/abs/2407.05307 Name: EDS - Arxiv Category: fullText Text: View this record from Arxiv MouseOverText: View this record from Arxiv – Url: https://resolver.ebsco.com/c/xy5jbn/result?sid=EBSCO:edsarx&genre=article&issn=&ISBN=&volume=&issue=&date=20240707&spage=&pages=&title=Edge-guided and Cross-scale Feature Fusion Network for Efficient Multi-contrast MRI Super-Resolution&atitle=Edge-guided%20and%20Cross-scale%20Feature%20Fusion%20Network%20for%20Efficient%20Multi-contrast%20MRI%20Super-Resolution&aulast=Yang%2C%20Zhiyuan&id=DOI: Name: Full Text Finder (for New FTF UI) (s8985755) Category: fullText Text: Find It @ SCU Libraries MouseOverText: Find It @ SCU Libraries |
|---|---|
| Header | DbId: edsarx DbLabel: arXiv An: edsarx.2407.05307 RelevancyScore: 1098 AccessLevel: 3 PubType: Report PubTypeId: report PreciseRelevancyScore: 1098.05627441406 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Edge-guided and Cross-scale Feature Fusion Network for Efficient Multi-contrast MRI Super-Resolution – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Yang%2C+Zhiyuan%22">Yang, Zhiyuan</searchLink><br /><searchLink fieldCode="AR" term="%22Zhang%2C+Bo%22">Zhang, Bo</searchLink><br /><searchLink fieldCode="AR" term="%22Zeng%2C+Zhiqiang%22">Zeng, Zhiqiang</searchLink><br /><searchLink fieldCode="AR" term="%22Yeo%2C+Si+Yong%22">Yeo, Si Yong</searchLink> – Name: DatePubCY Label: Publication Year Group: Date Data: 2024 – Name: Subject Label: Subject Terms Group: Su Data: <searchLink fieldCode="DE" term="%22Electrical+Engineering+and+Systems+Science+-+Image+and+Video+Processing%22">Electrical Engineering and Systems Science - Image and Video Processing</searchLink> – Name: Abstract Label: Description Group: Ab Data: In recent years, MRI super-resolution techniques have achieved great success, especially multi-contrast methods that extract texture information from reference images to guide the super-resolution reconstruction. However, current methods primarily focus on texture similarities at the same scale, neglecting cross-scale similarities that provide comprehensive information. Moreover, the misalignment between features of different scales impedes effective aggregation of information flow. To address the limitations, we propose a novel edge-guided and cross-scale feature fusion network, namely ECFNet. Specifically, we develop a pipeline consisting of the deformable convolution and the cross-attention transformer to align features of different scales. The cross-scale fusion strategy fully integrates the texture information from different scales, significantly enhancing the super-resolution. In addition, a novel structure information collaboration module is developed to guide the super-resolution reconstruction with implicit structure priors. The structure information enables the network to focus on high-frequency components of the image, resulting in sharper details. Extensive experiments on the IXI and BraTS2020 datasets demonstrate that our method achieves state-of-the-art performance compared to other multi-contrast MRI super-resolution methods, and our method is robust in terms of different super-resolution scales. We would like to release our code and pre-trained model after the paper is accepted.<br />Comment: submitted to ICPR2024 – Name: TypeDocument Label: Document Type Group: TypDoc Data: Working Paper – Name: URL Label: Access URL Group: URL Data: <link linkTarget="URL" linkTerm="http://arxiv.org/abs/2407.05307" linkWindow="_blank">http://arxiv.org/abs/2407.05307</link> – Name: AN Label: Accession Number Group: ID Data: edsarx.2407.05307 |
| PLink | https://login.libproxy.scu.edu/login?url=https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&scope=site&db=edsarx&AN=edsarx.2407.05307 |
| RecordInfo | BibRecord: BibEntity: Subjects: – SubjectFull: Electrical Engineering and Systems Science - Image and Video Processing Type: general Titles: – TitleFull: Edge-guided and Cross-scale Feature Fusion Network for Efficient Multi-contrast MRI Super-Resolution Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Yang, Zhiyuan – PersonEntity: Name: NameFull: Zhang, Bo – PersonEntity: Name: NameFull: Zeng, Zhiqiang – PersonEntity: Name: NameFull: Yeo, Si Yong IsPartOfRelationships: – BibEntity: Dates: – D: 07 M: 07 Type: published Y: 2024 |
| ResultId | 1 |