File Download
There are no files associated with this item.
Supplementary
-
Citations:
- Appears in Collections:
Conference Paper: Adaptive Multi-contrast MR Image Denoising based on a Residual U-Net using Noise Level Map
Title | Adaptive Multi-contrast MR Image Denoising based on a Residual U-Net using Noise Level Map |
---|---|
Authors | |
Issue Date | 2021 |
Publisher | International Society of Magnetic Resonance Imaging (ISMRM) . |
Citation | Proceedings of the 29th Annual Meeting & Exhibition of the International Society for Magnetic Resonance in Medicine (ISMRM), Virtual Conference, Vancouver, BC, Canada, 15-20 May 2021, paper no. 1243 How to Cite? |
Abstract | Multi-contrast MRI offers us images with complementary diagnostic information. Despite the dramatic difference in contrast, multi-contrast images often share highly correlated structure information. A deep learning (DL) based strategy is proposed to denoise multi-contrast MR images with flexible noise-levels using residual U-Net. This method utilizes the structural similarities across contrasts by simultaneously denoising multiple contrasts while existing single-contrast MRI denoising methods neglect the analogous structure information. The proposed method outperforms BM3D in terms of better noise reduction and details preservation. More importantly, we introduce a noise-level map that can be manually set to fit the different noise levels. |
Description | Digital Posters Session D-40: Parent Session: Novel & Multicontrast Approaches - Multicontrast Methods - no. 1243 |
Persistent Identifier | http://hdl.handle.net/10722/304350 |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Hu, J | - |
dc.contributor.author | Liu, Y | - |
dc.contributor.author | Yi, Z | - |
dc.contributor.author | Zhao, Y | - |
dc.contributor.author | Chen, F | - |
dc.contributor.author | Wu, EX | - |
dc.date.accessioned | 2021-09-23T08:58:49Z | - |
dc.date.available | 2021-09-23T08:58:49Z | - |
dc.date.issued | 2021 | - |
dc.identifier.citation | Proceedings of the 29th Annual Meeting & Exhibition of the International Society for Magnetic Resonance in Medicine (ISMRM), Virtual Conference, Vancouver, BC, Canada, 15-20 May 2021, paper no. 1243 | - |
dc.identifier.uri | http://hdl.handle.net/10722/304350 | - |
dc.description | Digital Posters Session D-40: Parent Session: Novel & Multicontrast Approaches - Multicontrast Methods - no. 1243 | - |
dc.description.abstract | Multi-contrast MRI offers us images with complementary diagnostic information. Despite the dramatic difference in contrast, multi-contrast images often share highly correlated structure information. A deep learning (DL) based strategy is proposed to denoise multi-contrast MR images with flexible noise-levels using residual U-Net. This method utilizes the structural similarities across contrasts by simultaneously denoising multiple contrasts while existing single-contrast MRI denoising methods neglect the analogous structure information. The proposed method outperforms BM3D in terms of better noise reduction and details preservation. More importantly, we introduce a noise-level map that can be manually set to fit the different noise levels. | - |
dc.language | eng | - |
dc.publisher | International Society of Magnetic Resonance Imaging (ISMRM) . | - |
dc.relation.ispartof | ISMRM (International Society of Magnetic Resonance Imaging) Virtual Conference & Exhibition, 2021 | - |
dc.title | Adaptive Multi-contrast MR Image Denoising based on a Residual U-Net using Noise Level Map | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Wu, EX: ewu@eee.hku.hk | - |
dc.identifier.authority | Wu, EX=rp00193 | - |
dc.identifier.hkuros | 325458 | - |
dc.identifier.spage | 1243 | - |
dc.identifier.epage | 1243 | - |