publications

2023

1. 

   ×

   PhD Thesis: Magnetic Resonance Imaging with Greater Fidelity and Efficiency

   Ke Wang

   University of California, Berkeley, 2023

   Abs URL

   Magnetic Resonance Imaging (MRI) is an effective medical imaging modality, offering excellent soft tissue contrast, versatile orientation capabilities, and no ionizing radiation exposure. However, its inherent physics constraints lead to time-consuming data acquisition and prolonged scan times. To reduce scan time, recently, deep learning (DL) has achieved notable success in reconstructing high-quality MR images from under-sampled data, surpassing conventional non-learned approaches. Despite this progress, challenges such as hand-crafted loss functions, high computational costs, and limited training data remain. In this dissertation, I will present a series of projects focused on enhancing fidelity and efficiency in MRI reconstruction. I will first introduce a supervised learning method that synthesizes multi-contrast MR images from a single MRF scan. Next, I will present a novel feature loss designed to preserve perceptual similarity, demonstrating its effectiveness in high-fidelity image reconstruction. Following that, I will touch upon memory-efficient learning for high-dimensional MRI reconstruction and present a novel framework for rigorous uncertainty estimation. Lastly, I will introduce a novel complex-valued representation tailored for tasks with limited training data.

2. 

   ×

   ResoNet: a Physics-Informed DL Framework for Off-Resonance Correction in MRI Trained with Noise

   Alfredo De Goyeneche, Shreya Ramachandran, Ke Wang, Ekin Karasan, and 3 more authors

   In Thirty-seventh Conference on Neural Information Processing Systems, 2023

   Abs URL

   Magnetic Resonance Imaging (MRI) is a powerful medical imaging modality that offers diagnostic information without harmful ionizing radiation. Unlike optical imaging, MRI sequentially samples the spatial Fourier domain k-space of the image. Measurements are collected in multiple shots, or readouts, and in each shot, data along a smooth trajectory is sampled. Conventional MRI data acquisition relies on sampling k-space row-by-row in short intervals, which is slow and inefficient. More efficient, non-Cartesian sampling trajectories (e.g., Spirals) use longer data readout intervals, but are more susceptible to magnetic field inhomogeneities, leading to off-resonance artifacts. Spiral trajectories cause off-resonance blurring in the image, and the mathematics of this blurring resembles that of optical blurring, where magnetic field variation corresponds to depth and readout duration to aperture size. Off-resonance blurring is a system issue with a physics-based, accurate forward model. We present a physics-informed deep learning framework for off-resonance correction in MRI, which is trained exclusively on synthetic, noise-like data with representative marginal statistics. Our approach allows for fat/water partial volume effects modeling and separation, and parallel imaging acceleration. Through end-to-end training using synthetic randomized data (i.e., images, coil sensitivities, field maps), we train the network to reverse off-resonance effects across diverse anatomies and contrasts without retraining. We demonstrate the effectiveness of our approach through results on phantom and \emphin-vivo data. This work has the potential to facilitate the clinical adoption of non-Cartesian sampling trajectories, enabling efficient, rapid, and motion-robust MRI scans. Code is publicly available at: https://github.com/mikgroup/ResoNet

3. 

   ×

   Semi-supervised Parametric Real-world Image Harmonization

   Ke Wang, Michaël Gharbi, He Zhang, Zhihao Xia, and 1 more author

   In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

   Abs Video Project Page PDF Code Poster

   Learning-based image harmonization techniques are usually trained to undo synthetic random global transformations applied to a masked foreground in a single ground truth photo. This simulated data does not model many of the important appearance mismatches (illumination, object boundaries, etc.) between foreground and background in real composites, leading to models that do not generalize well and cannot model complex local changes. We propose a new semi-supervised training strategy that addresses this problem and lets us learn complex local appearance harmonization from unpaired real composites, where foreground and background come from different images. Our model is fully parametric. It uses RGB curves to correct the global colors and tone and a shading map to model local variations. Our method outperforms previous work on established benchmarks and real composites, as shown in a user study, and processes high-resolution images interactively.

4. 

   ×

   High-fidelity direct contrast synthesis from magnetic resonance fingerprinting

   Ke Wang, Mariya Doneva, Jakob Meineke, Thomas Amthor, and 5 more authors

   Magnetic Resonance in Medicine, 2023

   Abs URL arXiv

   Magnetic Resonance Fingerprinting (MRF) is an efficient quantitative MRI technique that can extract important tissue and system parameters such as T1, T2, B0, and B1 from a single scan. This property also makes it attractive for retrospectively synthesizing contrast-weighted images. In general, contrast-weighted images like T1-weighted, T2-weighted, etc., can be synthesized directly from parameter maps through spin-dynamics simulation (i.e., Bloch or Extended Phase Graph models). However, these approaches often exhibit artifacts due to imperfections in the mapping, the sequence modeling, and the data acquisition. Here we propose a supervised learning-based method that directly synthesizes contrast-weighted images from the MRF data without going through the quantitative mapping and spin-dynamics simulation. To implement our direct contrast synthesis (DCS) method, we deploy a conditional Generative Adversarial Network (GAN) framework and propose a multi-branch U-Net as the generator. The input MRF data are used to directly synthesize T1-weighted, T2-weighted, and fluid-attenuated inversion recovery (FLAIR) images through supervised training on paired MRF and target spin echo-based contrast-weighted scans. In-vivo experiments demonstrate excellent image quality compared to simulation-based contrast synthesis and previous DCS methods, both visually as well as by quantitative metrics. We also demonstrate cases where our trained model is able to mitigate in-flow and spiral off-resonance artifacts that are typically seen in MRF reconstructions and thus more faithfully represent conventional spin echo-based contrast-weighted images.

5. ISMRM

   Iterative Motion-Compensated Reconstruction with Convolutional Neural Network (iMoCo-Net) for Ultrashort Echo Time (UTE) Proton Lung MRI

   Fei Tan, Ke Wang, Michael Lustig, and Peder Larson

   In Proc. Intl. Soc. Mag. Reson. Med, 2023

2022

1. 

   ×

   High fidelity deep learning-based MRI reconstruction with instance-wise discriminative feature matching loss

   Ke Wang, Jonathan I Tamir, Alfredo De Goyeneche, Uri Wollner, and 3 more authors

   Magnetic Resonance in Medicine, 2022

   Abs URL arXiv Code

   Purpose: To improve reconstruction fidelity of fine structures and textures in deep learning (DL) based reconstructions. Methods: A novel patch-based Unsupervised Feature Loss (UFLoss) is proposed and incorporated into the training of DL-based reconstruction frameworks in order to preserve perceptual similarity and high-order statistics. The UFLoss provides instance-level discrimination by mapping similar instances to similar low-dimensional feature vectors and is trained without any human annotation. By adding an additional loss function on the low-dimensional feature space during training, the reconstruction frameworks from under-sampled or corrupted data can reproduce more realistic images that are closer to the original with finer textures, sharper edges, and improved overall image quality. The performance of the proposed UFLoss is demonstrated on unrolled networks for accelerated 2D and 3D knee MRI reconstruction with retrospective under-sampling. Quantitative metrics including NRMSE, SSIM, and our proposed UFLoss were used to evaluate the performance of the proposed method and compare it with others. Results: In-vivo experiments indicate that adding the UFLoss encourages sharper edges and more faithful contrasts compared to traditional and learning-based methods with pure l2 loss. More detailed textures can be seen in both 2D and 3D knee MR images. Quantitative results indicate that reconstruction with UFLoss can provide comparable NRMSE and a higher SSIM while achieving a much lower UFLoss value. Conclusion: We present UFLoss, a patch-based unsupervised learned feature loss, which allows the training of DL-based reconstruction to obtain more detailed texture, finer features, and sharper edges with higher overall image quality under DL-based reconstruction frameworks.

2. 

   ×

   Rigorous Uncertainty Estimation for MRI Reconstruction

   Ke Wang, Anastasios Angelopoulos, Alfredo De Goyeneche, Amit Kohli, and 4 more authors

   In Proc. Intl. Soc. Mag. Reson. Med, 2022

   Abs URL

   Deep-learning (DL)-based MRI reconstructions have shown great potential to reduce scan time while maintaining diagnostic image quality. However, their adoption has been plagued with fears that the models will hallucinate or eliminate important anatomical features. To address this issue, we develop a framework to identify when and where a reconstruction model is producing potentially misleading results. Specifically, our framework produces confidence intervals at each pixel of a reconstruction image such that 95% of these intervals contain the true pixel value with high probability. In-vivo 2D knee and brain reconstruction results demonstrate the effectiveness of our proposed uncertainty estimation framework.

3. 

   ×

   Implicit data crimes: Machine learning bias arising from misuse of public data

   Efrat Shimron, Jonathan I Tamir, Ke Wang, and Michael Lustig

   Proceedings of the National Academy of Sciences, 2022

   Abs Video URL arXiv Code

   Although open databases are an important resource in the current deep learning (DL) era, they are sometimes used “off label”: Data published for one task are used to train algorithms for a different one. This work aims to highlight that this common practice may lead to biased, overly optimistic results. We demonstrate this phenomenon for inverse problem solvers and show how their biased performance stems from hidden data-processing pipelines. We describe two processing pipelines typical of open-access databases and study their effects on three well-established algorithms developed for MRI reconstruction: compressed sensing, dictionary learning, and DL. Our results demonstrate that all these algorithms yield systematically biased results when they are naively trained on seemingly appropriate data: The normalized rms error improves consistently with the extent of data processing, showing an artificial improvement of 25 to 48% in some cases. Because this phenomenon is not widely known, biased results sometimes are published as state of the art; we refer to that as implicit “data crimes.” This work hence aims to raise awareness regarding naive off-label usage of big data and reveal the vulnerability of modern inverse problem solvers to the resulting bias.

4. ISMRM

   ResoNet: Physics Informed Deep Learning based Off-Resonance Correction Trained on Synthetic Data

   Alfredo De Goyeneche1, Shreya Ramachandran, Ke Wang, Ekin Karasan, and 2 more authors

   In Proc. Intl. Soc. Mag. Reson. Med, 2022
5. ISMRM

   BladeNet: Rapid PROPELLER Acquisition and Reconstruction for High spatio-temporal Resolution Abdominal MRI

   Efrat Shimron, Alfredo De Goyeneche, Ke Wang, Ali B. Syed, and 2 more authors

   In Proc. Intl. Soc. Mag. Reson. Med, 2022

2021

1. 

   ×

   Memory-efficient learning for high-dimensional mri reconstruction

   Ke Wang, Michael Kellman, Christopher M Sandino, Kevin Zhang, and 4 more authors

   In Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part VI 24

   Abs Video URL arXiv Code Poster

   Deep learning (DL) based unrolled reconstructions have shown state-of-the-art performance for under-sampled magnetic resonance imaging (MRI). Similar to compressed sensing, DL can leverage high-dimensional data (e.g. 3D, 2D+time, 3D+time) to further improve performance. However, network size and depth are currently limited by the GPU memory required for backpropagation. Here we use a memory-efficient learning (MEL) framework which favorably trades off storage with a manageable increase in computation during training. Using MEL with multi-dimensional data, we demonstrate improved image reconstruction performance for in-vivo 3D MRI and 2D+time cardiac cine MRI. MEL uses far less GPU memory while marginally increasing the training time, which enables new applications of DL to high-dimensional MRI.

2. 

   ×

   CG-SENSE revisited: Results from the first ISMRM reproducibility challenge

   Oliver Maier, Steven Hubert Baete, Alexander Fyrdahl, Kerstin Hammernik, and 7 more authors

   Magnetic resonance in medicine, 2021

   Abs URL

   The aim of this work is to shed light on the issue of reproducibility in MR image reconstruction in the context of a challenge. Participants had to recreate the results of Advances in sensitivity encoding with arbitrary k-space trajectories by Pruessmann et al. The task of the challenge was to reconstruct radially acquired multicoil k-space data brain/heart following the method in the original paper, reproducing its key figures. Results were compared to consolidated reference implementations created after the challenge, accounting for the two most common programming languages used in the submissions Matlab/Python. Visually, differences between submissions were small. Pixel-wise differences originated from image orientation, assumed field-of-view, or resolution. The reference implementations were in good agreement, both visually and in terms of image similarity metrics. While the description level of the published algorithm enabled participants to reproduce CG-SENSE in general, details of the implementation varied, for example, density compensation or Tikhonov regularization. Implicit assumptions about the data lead to further differences, emphasizing the importance of sufficient metadata accompanying open datasets. Defining reproducibility quantitatively turned out to be nontrivial for this image reconstruction challenge, in the absence of ground-truth results. Typical similarity measures like NMSE of SSIM were misled by image intensity scaling and outlier pixels. Thus, to facilitate reproducibility, researchers are encouraged to publish code and data alongside the original paper. Future methodological papers on MR image reconstruction might benefit from the consolidated reference implementations of CG-SENSE presented here, as a benchmark for methods comparison.

3. ISMRM

   DSLR+: Enhancing deep subspace learning reconstruction for high-dimensional MRI

   Christopher Sandino, Frank Ong, Ke Wang, Michael Lustig, and 1 more author

   In Proc. Intl. Soc. Mag. Reson. Med, 2021
4. ISMRM

   A GPU-accelerated Extended Phase Graph Algorithm for differentiable optimization and learning

   Somnath Rakshit, Ke Wang, and Jonathan I. Tamir

   In Proc. Intl. Soc. Mag. Reson. Med, 2021
5. 

   ×

   OUTCOMES: Rapid Under-sampling Optimization achieves up to 50% improvements in reconstruction accuracy for multi-contrast MRI sequences

   Ke Wang, Enhao Gong, Yuxin Zhang, Suchadrima Banerjee, and 2 more authors

   arXiv preprint arXiv:2103.04566, 2021

   arXiv

2020

1. 

   ×

   Computational MRI with physics-based constraints: Application to multicontrast and quantitative imaging

   Jonathan I Tamir, Frank Ong, Suma Anand, Ekin Karasan, and 2 more authors

   IEEE signal processing magazine, 2020

   Abs URL

   Compressed sensing takes advantage of low-dimensional signal structure to reduce sampling requirements far below the Nyquist rate. In magnetic resonance imaging (MRI), this often takes the form of sparsity through wavelet transform, finite differences, and low rank extensions. Though powerful, these image priors are phenomenological in nature and do not account for the mechanism behind the image formation. On the other hand, MRI signal dynamics are governed by physical laws, which can be explicitly modeled and used as priors for reconstruction. 1These explicit and implicit signal priors can be synergistically combined in an inverse problem framework to recover sharp, multi-contrast images from highly accelerated scans. Furthermore, the physics-based constraints provide a recipe for recovering quantitative, bio-physical parameters from the data. This article introduces physics-based modeling constraints in MRI and shows how they can be used in conjunction with compressed sensing for image reconstruction and quantitative imaging. We describe model-based quantitative MRI, as well as its linear subspace approximation. We also discuss approaches to selecting user-controllable scan parameters given knowledge of the physical model. We present several MRI applications that take advantage of this framework for the purpose of multi-contrast imaging and quantitative mapping.

2019

1. 

   ×

   Non-Invasive Remote Temperature Monitoring Using Microwave-Induced Thermoacoustic Imaging

   Hao Nan, Aidan Fitzpatrick, Ke Wang, and Amin Arbabian

   In 2019 41st Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

   Abs URL

   Non-invasive temperature monitoring of tissue at depth in real-time is critical to hyperthermia therapies such as high-intensity focused ultrasound. Knowledge of temperature allows for monitoring treatment as well as providing real-time feedback to adjust deposited power in order to maintain safe and effective temperatures. Microwave-induced thermoacoustic (TA) imaging, which combines the conductivity/dielectric contrast of microwave imaging with the resolution of ultrasound, shows potential for estimating temperature non-invasively in real-time by indirectly measuring the temperature dependent parameters from reconstructed images. In this work, we study the temperature dependent behavior of the generated pressure in the TA effect and experimentally demonstrate simultaneous imaging and temperature monitoring using TA imaging. The proof-of-concept experiments demonstrate millimeter spatial resolution while achieving degree-level accuracy.

2. ISMRM

   Unsupervised Learning for Improved Fidelity Multi-contrast MRI

   Ke Wang, Frank Ong, Jonathan I. Tamir, and Michael Lustig

   In Proc. Intl. Soc. Mag. Reson. Med, 2019

2018

1. ACCAS

   Reconstruction and Registration of Large-Scale Medical Scene Using Point Clouds Data from Different Modalities

   Ke Wang, Han Song, Jiahui Zhang, Xinran Zhang, and 1 more author

   arXiv preprint arXiv:1809.01318, 2018

   arXiv
2. ISMRM

   Ultrafast Temperature Estimation from Undersampled K-space for MR Guided Microwave Ablation

   Ke Wang, Zijing Dong, Bingyao Chen, Jiafei Yang, and 2 more authors

   In Proc. Intl. Soc. Mag. Reson. Med, 2018

2017

1. ISMRM

   Fast Temperature Estimation Using Golden Angle Radial from Undersampled K-space for MR Guided Microwave Ablation

   Ke Wang, Fuyixue Wang, Zijing Dong, Bingyao Chen, and 3 more authors

   In Proc. Intl. Soc. Mag. Reson. Med, 2017