Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Meng, Yucong, Yang, Zhiwei, Shi, Yonghong, Song, Zhijian
Natura: Preprint
Pubblicazione: 2024
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866913611597742080
author Meng, Yucong
Yang, Zhiwei
Shi, Yonghong
Song, Zhijian
author_facet Meng, Yucong
Yang, Zhiwei
Shi, Yonghong
Song, Zhijian
contents The accelerated MRI reconstruction process presents a challenging ill-posed inverse problem due to the extensive under-sampling in k-space. Recently, Vision Transformers (ViTs) have become the mainstream for this task, demonstrating substantial performance improvements. However, there are still three significant issues remain unaddressed: (1) ViTs struggle to capture high-frequency components of images, limiting their ability to detect local textures and edge information, thereby impeding MRI restoration; (2) Previous methods calculate multi-head self-attention (MSA) among both related and unrelated tokens in content, introducing noise and significantly increasing computational burden; (3) The naive feed-forward network in ViTs cannot model the multi-scale information that is important for image restoration. In this paper, we propose FPS-Former, a powerful ViT-based framework, to address these issues from the perspectives of frequency modulation, spatial purification, and scale diversification. Specifically, for issue (1), we introduce a frequency modulation attention module to enhance the self-attention map by adaptively re-calibrating the frequency information in a Laplacian pyramid. For issue (2), we customize a spatial purification attention module to capture interactions among closely related tokens, thereby reducing redundant or irrelevant feature representations. For issue (3), we propose an efficient feed-forward network based on a hybrid-scale fusion strategy. Comprehensive experiments conducted on three public datasets show that our FPS-Former outperforms state-of-the-art methods while requiring lower computational costs.
format Preprint
id arxiv_https___arxiv_org_abs_2412_10776
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification
Meng, Yucong
Yang, Zhiwei
Shi, Yonghong
Song, Zhijian
Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
The accelerated MRI reconstruction process presents a challenging ill-posed inverse problem due to the extensive under-sampling in k-space. Recently, Vision Transformers (ViTs) have become the mainstream for this task, demonstrating substantial performance improvements. However, there are still three significant issues remain unaddressed: (1) ViTs struggle to capture high-frequency components of images, limiting their ability to detect local textures and edge information, thereby impeding MRI restoration; (2) Previous methods calculate multi-head self-attention (MSA) among both related and unrelated tokens in content, introducing noise and significantly increasing computational burden; (3) The naive feed-forward network in ViTs cannot model the multi-scale information that is important for image restoration. In this paper, we propose FPS-Former, a powerful ViT-based framework, to address these issues from the perspectives of frequency modulation, spatial purification, and scale diversification. Specifically, for issue (1), we introduce a frequency modulation attention module to enhance the self-attention map by adaptively re-calibrating the frequency information in a Laplacian pyramid. For issue (2), we customize a spatial purification attention module to capture interactions among closely related tokens, thereby reducing redundant or irrelevant feature representations. For issue (3), we propose an efficient feed-forward network based on a hybrid-scale fusion strategy. Comprehensive experiments conducted on three public datasets show that our FPS-Former outperforms state-of-the-art methods while requiring lower computational costs.
title Boosting ViT-based MRI Reconstruction from the Perspectives of Frequency Modulation, Spatial Purification, and Scale Diversification
topic Image and Video Processing
Artificial Intelligence
Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.10776