Learning Data Consistency and its Application to Dynamic MR Imaging

Cheng, Jing; Cui, Zhuo‐Xu; Huang, Wenqi; Ke, Ziwen; Ying, Leslie; Wang, Haifeng; Zhu, Yanjie; Liang, Dong

doi:10.1109/tmi.2021.3096232

Cited by 32 publications

(28 citation statements)

References 54 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In turn, they cannot guarantee that the recovered HR image is consistent with the input LR image in the measurement domain, i.e., the network output can deviate significantly from actual measurements. For improving the reliability of HR SM estimates, we introduce a novel data-consistency module in TranSMS to enforce consistency between recovered and acquired data, inspired by similar approaches devised for image reconstruction in accelerated MRI tasks [46,47]. Note that the signal model in Eq.…”

Section: Network Modelmentioning

confidence: 99%

TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

Güngör¹,

Askin²,

Soydan³

et al. 2021

Preprint

View full text Add to dashboard Cite

Magnetic particle imaging (MPI) is a recent modality that offers exceptional contrast for magnetic nanoparticles (MNP) at high spatio-temporal resolution. A common procedure in MPI starts with a calibration scan to measure the system matrix (SM), which is then used to setup an inverse problem to reconstruct images of the particle distribution during subsequent scans. This calibration enables the reconstruction to sensitively account for various system imperfections. Yet time-consuming SM measurements have to be repeated under notable drifts or changes in system properties. Here, we introduce a novel deep learning approach for accelerated MPI calibration based on transformers for SM super-resolution (TranSMS). Low-resolution SM measurements are performed using large MNP samples for improved signal-to-noise ratio efficiency, and the high-resolution SM is super-resolved via a model-based deep network. TranSMS leverages a vision transformer module to capture contextual relationships in low-resolution input images, a dense convolutional module for localizing highresolution image features, and a data-consistency module to ensure consistency to measurements. Demonstrations on simulated and experimental data indicate that TranSMS achieves significantly improved SM recovery and image reconstruction in MPI, while enabling acceleration up to 64-fold during two-dimensional calibration.

show abstract

Section: Network Modelmentioning

confidence: 99%

TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

Güngör¹,

Askin²,

Soydan³

et al. 2021

Preprint

View full text Add to dashboard Cite

show abstract

“…A convolutional neural network (CNN) is the main neural network most commonly used in computer vision and medical imaging and is mainly composed of a convolution layer, pool layer, and full connection layer. Because CNNs can gradually detect more and more abstract and complex feature levels, they play a key role in the research of medical images for the differential diagnosis of tumors, tumor segmentation, lesion detection, and accelerated imaging 12,13 …”

Section: Introductionmentioning

confidence: 99%

“…Because CNNs can gradually detect more and more abstract and complex feature levels, they play a key role in the research of medical images for the differential diagnosis of tumors, tumor segmentation, lesion detection, and accelerated imaging. 12,13 With the successful application of AI in RC, our review will provide a summary of several important topics on the current clinical applications of AI for RC, including staging, prediction of high-risk factors, genotyping, response to therapy, recurrence, metastasis, prognosis, and segmentation based on MRI (Fig. 1).…”

Section: Introductionmentioning

confidence: 99%

MRI‐Based Artificial Intelligence in Rectal Cancer

Wong

et al. 2022

Magnetic Resonance Imaging

View full text Add to dashboard Cite

Rectal cancer (RC) accounts for approximately one-third of colorectal cancer (CRC), with death rates increasing in patients younger than 50 years old. Magnetic resonance imaging (MRI) is routinely performed for tumor evaluation. However, the semantic features from images alone remain insufficient to guide treatment decisions. Functional MRIs are useful for revealing microstructural and functional abnormalities and nevertheless have low or modest repeatability and reproducibility. Therefore, during the preoperative evaluation and follow-up treatment of patients with RC, novel noninvasive imaging markers are needed to describe tumor characteristics to guide treatment strategies and achieve individualized diagnosis and treatment. In recent years, the development of artificial intelligence (AI) has created new tools for RC evaluation based on MRI. In this review, we summarize the research progress of AI in the evaluation of staging, prediction of high-risk factors, genotyping, response to therapy, recurrence, metastasis, prognosis, and segmentation with RC. We further discuss the challenges of clinical application, including improvement in imaging, model performance, and the biological meaning of features, which may also be major development directions in the future.

show abstract

“…With its superior reconstruction quality and processing speed, convolutional neural networks (CNNs) based fast MRI methods [23,26,27] enabled enhanced latent feature extraction by the deep hierarchical structure, and were successfully developed for a wide range of MRI sequences and clinical applications [19,4,14].…”

Section: Introductionmentioning

confidence: 99%

Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI

Huang¹,

Xing²,

Gao³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fast MRI aims to reconstruct a high fidelity image from partially observed measurements. Exuberant development in fast MRI using deep learning has been witnessed recently. Meanwhile, novel deep learning paradigms, e.g., Transformer based models, are fast-growing in natural language processing and promptly developed for computer vision and medical image analysis due to their prominent performance. Nevertheless, due to the complexity of the Transformer, the application of fast MRI may not be straightforward. The main obstacle is the computational cost of the self-attention layer, which is the core part of the Transformer, can be expensive for high resolution MRI inputs. In this study, we propose a new Transformer architecture for solving fast MRI that coupled Shifted Windows Transformer with U-Net to reduce the network complexity. We incorporate deformable attention to construe the explainability of our reconstruction model. We empirically demonstrate that our method achieves consistently superior performance on the fast MRI task. Besides, compared to state-of-the-art Transformer models, our method has fewer network parameters while revealing explainability. The code is publicly available at https://github.com/ayanglab/SDAUT.

show abstract

Learning Data Consistency and its Application to Dynamic MR Imaging

Cited by 32 publications

References 54 publications

TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

TranSMS: Transformers for Super-Resolution Calibration in Magnetic Particle Imaging

MRI‐Based Artificial Intelligence in Rectal Cancer

Swin Deformable Attention U-Net Transformer (SDAUT) for Explainable Fast MRI

Contact Info

Product

Resources

About