Patch-based super-resolution of arterial spin labeling magnetic resonance images

Meurée, Cédric; Maurel, Pierre; Ferré, Jean-Christophe; Barillot, Christian

doi:10.1016/j.neuroimage.2019.01.004

Cited by 14 publications

(10 citation statements)

References 26 publications

(56 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Методика основана на получении специальных карт с использованием быстрых импульсных последовательностей. При выполнении перфузионной МРТ оценивают основные параметры церебрального кровотока: CBV, CBF, MTT, TTP [15,16].…”

Section: магнитно-резонансная томография (мрт) при остром инсультеunclassified

Neuroimaging of Acute Ischemic Stroke: Current State

Алдатов

Труфанов

Фокин

2019

Transl. med. (Print)

View full text Add to dashboard Cite

РезюмеЗа последнее десятилетие отмечается значительное усовершенствование методов нейровизуализации для улучшения ранней диагностики острого инсульта. Компьютерная и магнитно-резонансная томография часто используются при внутримозговом кровоизлиянии или для оценки противопоказаний к тромболизису, чтобы обнаружить локализацию зоны ишемии и оценить время начала инсульта. С наличием быстрых и передовых методов визуализации отмечается растущий интерес к их применению для прогнозирования успеха и исключения рисков специфической терапии.В данном обзоре рассматриваются существующие методы нейровизуализации при острых инсультах. Чтобы интерпретировать результаты нейровизуализации, важно знать клиническую картину. Кроме того, фактор времени, от момента начала инсульта до коллатерального кровоснабжения, должен быть включен в существующие терапевтические стратегии на основе визуализации.Ключевые слова: ишемический инсульт, компьютерная томография, магнитно-резонансная томография, артерии головного мозга, реканализация, тромболизис.

show abstract

Section: магнитно-резонансная томография (мрт) при остром инсультеunclassified

Neuroimaging of Acute Ischemic Stroke: Current State

Алдатов

Труфанов

Фокин

2019

Transl. med. (Print)

View full text Add to dashboard Cite

show abstract

“…However, the repeated acquisition can lead to longer scanning time and may introduce movement artifacts. 12 Another limitation of ASL imaging is its low spatial resolution. Typically, the in-plane resolution of ASL images is 3-4 mm and the through-plane resolution is 4-8 mm, 13 while the average cortical thickness is around 2.589 mm.…”

Section: Introductionmentioning

confidence: 99%

“…To ensure adequate SNR, multiple paired images are acquired and averaged. However, the repeated acquisition can lead to longer scanning time and may introduce movement artifacts 12 . Another limitation of ASL imaging is its low spatial resolution.…”

Section: Introductionmentioning

confidence: 99%

Unsupervised arterial spin labeling image superresolution via multiscale generative adversarial network

et al. 2022

View full text Add to dashboard Cite

Purpose Arterial spin labeling (ASL) magnetic resonance imaging (MRI) is an advanced noninvasive imaging technology that can measure cerebral blood flow (CBF) quantitatively without a contrast agent injection or radiation exposure. However, because of the weak labeling, conventional ASL images usually suffer from low signal‐to‐noise ratio (SNR), poor spatial resolution, and long acquisition time. Therefore, a method that can simultaneously improve the spatial resolution and SNR is needed. Methods In this work, we proposed an unsupervised superresolution (SR) method to improve ASL image resolution based on a pyramid of generative adversarial networks (GAN). Through layer‐by‐layer training, the generators can learn features from the coarsest to the finest. The last layer's generator that contains fine details and textures was used to generate the final SR ASL images. In our proposed framework, the corresponding T1‐weighted MR image was supplied as a second‐channel input of the generators to provide high‐resolution prior information. In addition, a low‐pass‐filter loss term was included to suppress the noise of the original ASL images. To evaluate the performance of the proposed framework, a simulation study and two real‐patient experiments based on the in vivo datasets obtained from three healthy subjects on a 3T MR scanner were conducted, regarding the low‐resolution (LR) to normal‐resolution (NR) and the NR‐to‐SR tasks. The proposed method was compared to the nearest neighbor interpolation, trilinear interpolation, third‐order B‐splines interpolation methods, and deep image prior (DIP) with the peak signal‐to‐noise ratio (PSNR) and structural similarity index (SSIM) as the quantification metrics. The averaged ASL images acquired with 44 min acquisition time were used as the ground truth for real‐patient LR‐to‐NR study. The ablation studies of low‐pass‐filter loss term and T1‐weighted MR image were performed based on simulation data. Results For the simulation study, results show that the proposed method achieved significantly higher PSNR (p$p$‐value <$<$ 0.05) and SSIM (p$p$‐value <$<$ 0.05) than the nearest neighbor interpolation, trilinear interpolation, third‐order B‐splines interpolation, and DIP methods. For the real‐patient LR‐to‐NR experiment, results show that the proposed method can generate high‐quality SR ASL images with clearer structure boundaries and low noise levels and has the highest mean PSNR and SSIM. For real‐patient NR‐to‐SR tasks, the structure of the results using the proposed method is sharper and clearer, which are the most similar to the structure of the reference 44 min acquisition image than other methods. The proposed method also shows the ability to remove artifacts in the NR image while superresolution. The ablation study verified that the low‐pass‐filter loss term and T1‐weighted MR image are necessary for the proposed method. Conclusions The proposed unsupervised multiscale GAN framework can simultaneously improve spatial resolution and reduce image noise. Experimen...

show abstract

“…Jun et al [5] proposed wide residual networks with fixed skip connections for MR images super-resolution. Meure et al [6] presented a patch-based SR algorithm of ASL magnetic resonance images, where the nonlinear weights were determined from non-local image patches. Tanno et al [7] proposed a new CNN-based model to perform a diffusion tensor imaging SR task.…”

Section: Introductionmentioning

confidence: 99%

Feedback Graph Attention Convolutional Network for Medical Image Enhancement

Hu¹,

Yan²,

Ren³

et al. 2020

Preprint

View full text Add to dashboard Cite

Artifacts, blur and noise are the common distortions degrading MRI images during the acquisition process, and deep neural networks have been demonstrated to help in improving image quality. To well exploit global structural information and texture details, we propose a novel biomedical image enhancement network, named Feedback Graph Attention Convolutional Network (FB-GACN). As a key innovation, we consider the global structure of an image by building a graph network from image sub-regions that we consider to be node features, linking them non-locally according to their similarity. The proposed model consists of three main parts: 1) The parallel graph similarity branch and content branch, where the graph similarity branch aims at exploiting the similarity and symmetry across different image sub-regions in lowresolution feature space and provides additional priors for the content branch to enhance texture details. 2) A feedback mechanism with a recurrent structure to refine low-level representations with high-level information and generate powerful high-level texture details by handling the feedback connections. 3) A reconstruction to remove the artifacts and recover super-resolution images by using the estimated sub-region correlation priors obtained from the graph similarity branch. We evaluate our method on two image enhancement tasks: i) cross-protocol super resolution of diffusion MRI; ii) artifact removal of FLAIR MR images. Experimental results demonstrate that the proposed algorithm outperforms the state-of-the-art methods.

show abstract

Patch-based super-resolution of arterial spin labeling magnetic resonance images

Cited by 14 publications

References 26 publications

Neuroimaging of Acute Ischemic Stroke: Current State

Neuroimaging of Acute Ischemic Stroke: Current State

Unsupervised arterial spin labeling image superresolution via multiscale generative adversarial network

Feedback Graph Attention Convolutional Network for Medical Image Enhancement

Contact Info

Product

Resources

About