Deep learning-assisted model-based off-resonance correction for non-Cartesian SWI.

PURPOSE: Patient-induced inhomogeneities in the static magnetic field cause distortions and blurring (off-resonance artifacts) during acquisitions with long readouts such as in SWI. Conventional versatile correction methods based on extended Fourier models are too slow for clinical practice in computationally demanding cases such as 3D high-resolution non-Cartesian multi-coil acquisitions. THEORY: Most reconstruction methods can be accelerated when performing off-resonance correction by reducing the number of iterations, compressed coils, and correction components. Recent state-of-the-art unrolled deep learning architectures could help but are generally not adapted to corrupted measurements as they rely on the standard Fourier operator in the data consistency term. The combination of correction models and neural networks is therefore necessary to reduce reconstruction times. METHODS: Hybrid pipelines using UNets were trained stack-by-stack over 99 SWI 3D SPARKLING 20-fold accelerated acquisitions at 0.6 mm isotropic resolution using different off-resonance correction methods. Target images were obtained using slow model-based corrections based on self-estimated Δ B 0 $$ \Delta {B}_0 $$ field maps. The proposed strategies, tested over 11 volumes, are compared to model-only and network-only pipelines. RESULTS: The proposed hybrid pipelines achieved scores competing with two to three times slower baseline methods, and neural networks were observed to contribute both as pre-conditioner and through inter-iteration memory by allowing more degrees of freedom over the model design. CONCLUSION: A combination of model-based and network-based off-resonance correction was proposed to significantly accelerate conventional methods. Different promising synergies were observed between acceleration factors (iterations, coils, correction) and model/network that could be expanded in the future.

Iterative static field map estimation for off-resonance correction in non-Cartesian susceptibility weighted imaging.

PURPOSE: Patient-induced inhomogeneities in the magnetic field cause distortions and blurring during acquisitions with long readouts such as in susceptibility-weighted imaging (SWI). Most correction methods require collecting an additional ΔB0$$ \Delta {\mathrm{B}}_0 $$ field map to remove these artifacts. THEORY: The static ΔB0$$ \Delta {\mathrm{B}}_0 $$ field map can be approximated with an acceptable error directly from a single echo acquisition in SWI. The main component of the observed phase is linearly related to ΔB0$$ \Delta {\mathrm{B}}_0 $$ and the echo time (TE), and the relative impact of non- ΔB0$$ \Delta {\mathrm{B}}_0 $$ terms becomes insignificant with TE$$ \mathrm{TE} $$ >20 ms at 3 T for a well-tuned system. METHODS: The main step is to combine and unfold the multi-channel phase maps wrapped many times, and several competing algorithms are compared for this purpose. Four in vivo brain data sets collected using the recently proposed 3D spreading projection algorithm for rapid k-space sampling (SPARKLING) readouts are used to assess the proposed method. RESULTS: The estimated 3D field maps generated with a 0.6 mm isotropic spatial resolution provide overall similar off-resonance corrections compared to reference corrections based on an external ΔB0$$ \Delta {\mathrm{B}}_0 $$ acquisitions, and even improved for 2 of 4 individuals. Although a small estimation error is expected, no aftermath was observed in the proposed corrections, whereas degradations were observed in the references. CONCLUSION: A static ΔB0$$ \Delta {\mathrm{B}}_0 $$ field map estimation method was proposed to take advantage of acquisitions with long echo times, and outperformed the reference technique based on an external field map. The difference can be attributed to an inherent robustness to mismatches between volumes and external ΔB0$$ \Delta {\mathrm{B}}_0 $$ maps, and diverse other sources investigated.

Value of quantitative airspace disease measured on chest CT and chest radiography at initial diagnosis compared to clinical variables for prediction of severe COVID-19.

Purpose: Rapid prognostication of COVID-19 patients is important for efficient resource allocation. We evaluated the relative prognostic value of baseline clinical variables (CVs), quantitative human-read chest CT (qCT), and AI-read chest radiograph (qCXR) airspace disease (AD) in predicting severe COVID-19. Approach: We retrospectively selected 131 COVID-19 patients (SARS-CoV-2 positive, March to October, 2020) at a tertiary hospital in the United States, who underwent chest CT and CXR within 48 hr of initial presentation. CVs included patient demographics and laboratory values; imaging variables included qCT volumetric percentage AD (POv) and qCXR area-based percentage AD (POa), assessed by a deep convolutional neural network. Our prognostic outcome was need for ICU admission. We compared the performance of three logistic regression models: using CVs known to be associated with prognosis (model I), using a dimension-reduced set of best predictor variables (model II), and using only age and AD (model III). Results: 60/131 patients required ICU admission, whereas 71/131 did not. Model I performed the poorest ( AUC = 0.67 [0.58 to 0.76]; accuracy = 77 % ). Model II performed the best ( AUC = 0.78 [0.71 to 0.86]; accuracy = 81 % ). Model III was equivalent ( AUC = 0.75 [0.67 to 0.84]; accuracy = 80 % ). Both models II and III outperformed model I ( AUC difference = 0.11 [0.02 to 0.19], p = 0.01 ; AUC difference = 0.08 [0.01 to 0.15], p = 0.04 , respectively). Model II and III results did not change significantly when POv was replaced by POa. Conclusions: Severe COVID-19 can be predicted using only age and quantitative AD imaging metrics at initial diagnosis, which outperform the set of CVs. Moreover, AI-read qCXR can replace qCT metrics without loss of prognostic performance, promising more resource-efficient prognostication.

A parallel spatial and Bloch manifold regularized iterative reconstruction method for MR Fingerprinting.

Magnetic Resonance Fingerprinting (MRF) reconstructs tissue maps based on a sequence of very highly undersampled images. In order to be able to perform MRF reconstruction, state-of-the-art MRF methods rely on priors such as the MR physics (Bloch equations) and might also use some additional low-rank or spatial regularization. However to our knowledge these three regularizations are not applied together in a joint reconstruction. The reason is that it is indeed challenging to incorporate effectively multiple regularizations in a single MRF optimization algorithm. As a result most of these methods are not robust to noise especially when the sequence length is short. In this paper, we propose a family of new methods where spatial and low-rank regularizations, in addition to the Bloch manifold regularization, are applied on the images. We show on digital phantom and NIST phantom scans, as well as volunteer scans that the proposed methods bring significant improvement in the quality of the estimated tissue maps.

Automated Detection and Quantification of COVID-19 Airspace Disease on Chest Radiographs: A Novel Approach Achieving Expert Radiologist-Level Performance Using a Deep Convolutional Neural Network Trained on Digital Reconstructed Radiographs From Computed Tomography-Derived Ground Truth.

OBJECTIVES: The aim of this study was to leverage volumetric quantification of airspace disease (AD) derived from a superior modality (computed tomography [CT]) serving as ground truth, projected onto digitally reconstructed radiographs (DRRs) to (1) train a convolutional neural network (CNN) to quantify AD on paired chest radiographs (CXRs) and CTs, and (2) compare the DRR-trained CNN to expert human readers in the CXR evaluation of patients with confirmed COVID-19. MATERIALS AND METHODS: We retrospectively selected a cohort of 86 COVID-19 patients (with positive reverse transcriptase-polymerase chain reaction test results) from March to May 2020 at a tertiary hospital in the northeastern United States, who underwent chest CT and CXR within 48 hours. The ground-truth volumetric percentage of COVID-19-related AD (POv) was established by manual AD segmentation on CT. The resulting 3-dimensional masks were projected into 2-dimensional anterior-posterior DRR to compute area-based AD percentage (POa). A CNN was trained with DRR images generated from a larger-scale CT dataset of COVID-19 and non-COVID-19 patients, automatically segmenting lungs, AD, and quantifying POa on CXR. The CNN POa results were compared with POa quantified on CXR by 2 expert readers and to the POv ground truth, by computing correlations and mean absolute errors. RESULTS: Bootstrap mean absolute error and correlations between POa and POv were 11.98% (11.05%-12.47%) and 0.77 (0.70-0.82) for average of expert readers and 9.56% to 9.78% (8.83%-10.22%) and 0.78 to 0.81 (0.73-0.85) for the CNN, respectively. CONCLUSIONS: Our CNN trained with DRR using CT-derived airspace quantification achieved expert radiologist level of accuracy in the quantification of AD on CXR in patients with positive reverse transcriptase-polymerase chain reaction test results for COVID-19.

Learning a Probabilistic Model for Diffeomorphic Registration.

We propose to learn a low-dimensional probabilistic deformation model from data which can be used for the registration and the analysis of deformations. The latent variable model maps similar deformations close to each other in an encoding space. It enables to compare deformations, to generate normal or pathological deformations for any new image, or to transport deformations from one image pair to any other image. Our unsupervised method is based on the variational inference. In particular, we use a conditional variational autoencoder network and constrain transformations to be symmetric and diffeomorphic by applying a differentiable exponentiation layer with a symmetric loss function. We also present a formulation that includes spatial regularization such as the diffusion-based filters. In addition, our framework provides multi-scale velocity field estimations. We evaluated our method on 3-D intra-subject registration using 334 cardiac cine-MRIs. On this dataset, our method showed the state-of-the-art performance with a mean DICE score of 81.2% and a mean Hausdorff distance of 7.3 mm using 32 latent dimensions compared to three state-of-the-art methods while also demonstrating more regular deformation fields. The average time per registration was 0.32 s. Besides, we visualized the learned latent space and showed that the encoded deformations can be used to transport deformations and to cluster diseases with a classification accuracy of 83% after applying a linear projection.

AIR-MRF: Accelerated iterative reconstruction for magnetic resonance fingerprinting.

Existing approaches for reconstruction of multiparametric maps with magnetic resonance fingerprinting (MRF) are currently limited by their estimation accuracy and reconstruction time. We aimed to address these issues with a novel combination of iterative reconstruction, fingerprint compression, additional regularization, and accelerated dictionary search methods. The pipeline described here, accelerated iterative reconstruction for magnetic resonance fingerprinting (AIR-MRF), was evaluated with simulations as well as phantom and in vivo scans. We found that the AIR-MRF pipeline provided reduced parameter estimation errors compared to non-iterative and other iterative methods, particularly at shorter sequence lengths. Accelerated dictionary search methods incorporated into the iterative pipeline reduced the reconstruction time at little cost of quality.

High-resolution dynamic CE-MRA of the thorax enabled by iterative TWIST reconstruction.

PURPOSE: To evaluate the clinical benefit of using a new iterative reconstruction technique fully integrated on a standard clinical scanner and reconstruction system using a TWIST acquisition for high-resolution dynamic three-dimensional contrast-enhanced MR angiography (CE-MRA). METHODS: Low-dose, high-resolution TWIST datasets of 11 patients were reconstructed using both standard GRAPPA-based reconstruction for reference and iterative reconstruction, which reduces the temporal footprint of reconstructed images. Image quality of both techniques was assessed by two experienced readers, as well as quantitatively evaluated using a time-signal curve analysis. RESULTS: Image quality scores consistently and significantly improved by using iterative reconstruction compared with the standard approach. Most notably, the delineation of small to mid-size vasculature improved from a mean Likert score between "nondiagnostic" and "poor" for standard to between "good" and "excellent" for iterative reconstruction. The full width at half maximum of the contrast agent bolus computed from the time-signal curve was also reduced by iterative reconstruction, allowing for more precise bolus timing. CONCLUSION: Iterative reconstruction can substantially improve high-resolution dynamic CE-MRA image quality, most notably in small to mid-size vasculature. Dynamic CE-MRA with iterative reconstruction could become an alternative to conventional static 3D CE-MRA, thus simplifying the clinical workflow. Magn Reson Med 77:833-840, 2017. © 2016 International Society for Magnetic Resonance in Medicine.

Learning multimodal dictionaries.

Real-world phenomena involve complex interactions between multiple signal modalities. As a consequence, humans are used to integrate at each instant perceptions from all their senses in order to enrich their understanding of the surrounding world. This paradigm can be also extremely useful in many signal processing and computer vision problems involving mutually related signals. The simultaneous processing of multimodal data can, in fact, reveal information that is otherwise hidden when considering the signals independently. However, in natural multimodal signals, the statistical dependencies between modalities are in general not obvious. Learning fundamental multimodal patterns could offer deep insight into the structure of such signals. In this paper, we present a novel model of multimodal signals based on their sparse decomposition over a dictionary of multimodal structures. An algorithm for iteratively learning multimodal generating functions that can be shifted at all positions in the signal is proposed, as well. The learning is defined in such a way that it can be accomplished by iteratively solving a generalized eigenvector problem, which makes the algorithm fast, flexible, and free of user-defined parameters. The proposed algorithm is applied to audiovisual sequences and it is able to discover underlying structures in the data. The detection of such audio-video patterns in audiovisual clips allows to effectively localize the sound source on the video in presence of substantial acoustic and visual distractors, outperforming state-of-the-art audiovisual localization algorithms.