Multi-scale deformable transformer for multi-contrast knee MRI super-resolution

Zou, Beiji; Ji, Zexin; Zhu, Chengzhang; Dai, Yulan; Zhang, Wensheng; Kui, Xiaoyan

doi:10.1016/j.bspc.2022.104154

Cited by 17 publications

(5 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The use of DL for MRI reconstructions has the potential to reduce the examination time for TSE and FLAIR acquisitions. In recent years, a number of different approaches to deep learning (DL) have emerged, and a growing number of new developments in artificial networks have initiated a paradigm shift in the field of medical imaging [23][24][25][26].…”

Section: Discussionmentioning

confidence: 99%

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction

Gohla,

Hauser,

Bombach

et al. 2024

Cancers

View full text Add to dashboard Cite

A fully diagnostic MRI glioma protocol is key to monitoring therapy assessment but is time-consuming and especially challenging in critically ill and uncooperative patients. Artificial intelligence demonstrated promise in reducing scan time and improving image quality simultaneously. The purpose of this study was to investigate the diagnostic performance, the impact on acquisition acceleration, and the image quality of a deep learning optimized glioma protocol of the brain. Thirty-three patients with histologically confirmed glioblastoma underwent standardized brain tumor imaging according to the glioma consensus recommendations on a 3-Tesla MRI scanner. Conventional and deep learning-reconstructed (DLR) fluid-attenuated inversion recovery, and T2- and T1-weighted contrast-enhanced Turbo spin echo images with an improved in-plane resolution, i.e., super-resolution, were acquired. Two experienced neuroradiologists independently evaluated the image datasets for subjective image quality, diagnostic confidence, tumor conspicuity, noise levels, artifacts, and sharpness. In addition, the tumor volume was measured in the image datasets according to Response Assessment in Neuro-Oncology (RANO) 2.0, as well as compared between both imaging techniques, and various clinical–pathological parameters were determined. The average time saving of DLR sequences was 30% per MRI sequence. Simultaneously, DLR sequences showed superior overall image quality (all p < 0.001), improved tumor conspicuity and image sharpness (all p < 0.001, respectively), and less image noise (all p < 0.001), while maintaining diagnostic confidence (all p > 0.05), compared to conventional images. Regarding RANO 2.0, the volume of non-enhancing non-target lesions (p = 0.963), enhancing target lesions (p = 0.993), and enhancing non-target lesions (p = 0.951) did not differ between reconstruction types. The feasibility of the deep learning-optimized glioma protocol was demonstrated with a 30% reduction in acquisition time on average and an increased in-plane resolution. The evaluated DLR sequences improved subjective image quality and maintained diagnostic accuracy in tumor detection and tumor classification according to RANO 2.0.

show abstract

Section: Discussionmentioning

confidence: 99%

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction

Gohla,

Hauser,

Bombach

et al. 2024

Cancers

View full text Add to dashboard Cite

show abstract

“…Our model is trained using the Adam optimizer for 50 epochs, and a learning rate is set to 1e-5. For the FastMRI dataset, the evaluation index values of all comparison methods are obtained from MSDT (Zou et al 2023). For AXA dataset, the indicators of MSDT are obtained by direct testing it, and the other comparison methods are retrained and tested to obtain the corresponding indicators.…”

Section: Methodsmentioning

confidence: 99%

“…The higher the PSNR and SSIM values, the better the performance of the method. In order to demonstrate the validity of the proposed method, we objectively compare it with some state-of-the-art methods, including EDSR (Lim et al 2017), MCSR (Zeng et al 2018), NEU (Neubert et al 2020), MINet (Feng et al 2021a) and MSDT (Zou et al 2023), and the results obtained by the comparison method are all from the official specifications. Table 1 and Table 2 show the average measure results of 2× and 4× SR reconstruction on the FastMRI and AXA datasets for all comparison methods.…”

Section: Objective and Subjective Comparisonmentioning

confidence: 99%

MFTN: Multi-Level Feature Transfer Network Based on MRI-Transformer for MR Image Super-resolution

Huang,

Chen,

Yang

et al. 2024

AAAI

View full text Add to dashboard Cite

Due to the unique environment and inherent properties of magnetic resonance imaging (MRI) instruments, MR images typically have lower resolution. Therefore, improving the resolution of MR images is beneficial for assisting doctors in diagnosing the condition. Currently, the existing MR image super-resolution (SR) methods still have the problem of insufficient detail reconstruction. To overcome this issue, this paper proposes a multi-level feature transfer network (MFTN) based on MRI-Transformer to realize SR of low-resolution MRI data. MFTN consists of a multi-scale feature reconstruction network (MFRN) and a multi-level feature extraction branch (MFEB). MFRN is constructed as a pyramid structure to gradually reconstruct image features at different scales by integrating the features obtained from MFEB, and MFEB is constructed to provide detail information at different scales for low resolution MR image SR reconstruction by constructing multiple MRI-Transformer modules. Each MRI-Transformer module is designed to learn the transfer features from the reference image by establishing feature correlations between the reference image and low-resolution MR image. In addition, a contrast learning constraint item is added to the loss function to enhance the texture details of the SR image. A large number of experiments show that our network can effectively reconstruct high-quality MR Images and achieves better performance compared to some state-of-the-art methods. The source code of this work will be released on GitHub.

show abstract

“…MRI predominates in radiogenomics for breast imaging [ 91 ] and has been found to be the most accurate test for finding BC [ 92 , 93 , 94 ]. Yamamoto et al looked at 10 patients who had preoperative dynamic contrast-enhanced (DCE)-MRI and global gene expression data [ 95 , 96 , 97 , 98 , 99 , 100 , 101 , 102 , 103 , 104 , 105 , 106 , 107 , 108 , 109 , 110 , 111 , 112 , 113 , 114 , 115 , 116 , 117 , 118 ]. The relationship between MRI phenotypes and underlying global BC gene expression patterns was presented using a preliminary radiogenomic association map.…”

Section: Current Application Of Radiogenomics In Oncologymentioning

confidence: 99%

“…This approach, known as co-learning, links a modality with abundant resources to one with limited resources, enhancing inference capabilities in the latter through the relevant modality [ 96 ]. Multi-modal analysis has found application across diverse domains including geographical and biomedical image analysis [ 97 , 98 ], video analysis [ 99 , 100 ], and sentiment analysis [ 101 ]. Various methods facilitate co-learning in multi-modal analysis, such as tensor learning [ 102 ], generative models [ 103 ], graphical models [ 104 , 105 ], prior knowledge regularization [ 106 ], multiple kernel learning [ 107 ], and neural networks [ 108 , 109 , 110 ].…”

Section: Current Application Of Radiogenomics In Oncologymentioning

confidence: 99%

The Convergence of Radiology and Genomics: Advancing Breast Cancer Diagnosis with Radiogenomics

Demetriou,

Lockhat,

Brzozowski

et al. 2024

Cancers

View full text Add to dashboard Cite

Despite significant progress in the prevention, screening, diagnosis, prognosis, and therapy of breast cancer (BC), it remains a highly prevalent and life-threatening disease affecting millions worldwide. Molecular subtyping of BC is crucial for predictive and prognostic purposes due to the diverse clinical behaviors observed across various types. The molecular heterogeneity of BC poses uncertainties in its impact on diagnosis, prognosis, and treatment. Numerous studies have highlighted genetic and environmental differences between patients from different geographic regions, emphasizing the need for localized research. International studies have revealed that patients with African heritage are often diagnosed at a more advanced stage and exhibit poorer responses to treatment and lower survival rates. Despite these global findings, there is a dearth of in-depth studies focusing on communities in the African region. Early diagnosis and timely treatment are paramount to improving survival rates. In this context, radiogenomics emerges as a promising field within precision medicine. By associating genetic patterns with image attributes or features, radiogenomics has the potential to significantly improve early detection, prognosis, and diagnosis. It can provide valuable insights into potential treatment options and predict the likelihood of survival, progression, and relapse. Radiogenomics allows for visual features and genetic marker linkage that promises to eliminate the need for biopsy and sequencing. The application of radiogenomics not only contributes to advancing precision oncology and individualized patient treatment but also streamlines clinical workflows. This review aims to delve into the theoretical underpinnings of radiogenomics and explore its practical applications in the diagnosis, management, and treatment of BC and to put radiogenomics on a path towards fully integrated diagnostics.

show abstract

Multi-scale deformable transformer for multi-contrast knee MRI super-resolution

Cited by 17 publications

References 27 publications

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction

Speeding Up and Improving Image Quality in Glioblastoma MRI Protocol by Deep Learning Image Reconstruction

MFTN: Multi-Level Feature Transfer Network Based on MRI-Transformer for MR Image Super-resolution

The Convergence of Radiology and Genomics: Advancing Breast Cancer Diagnosis with Radiogenomics

Contact Info

Product

Resources

About