Data Consistent Deep Rigid MRI Motion Correction.

Motion artifacts are a pervasive problem in MRI, leading to misdiagnosis or mischaracterization in population-level imaging studies. Current retrospective rigid intra-slice motion correction techniques jointly optimize estimates of the image and the motion parameters. In this paper, we use a deep network to reduce the joint image-motion parameter search to a search over rigid motion parameters alone.

Local SAR management strategies to use two-channel RF shimming for fetal MRI at 3 T.

Purpose: This study evaluates the imaging performance of two-channel RF-shimming for fetal MRI at 3 T using four different local specific absorption rate (SAR) management strategies.

Methods: Due to the ambiguity of safe local SAR levels for fetal MRI, local SAR limits for RF shimming were determined based on either each individual's own SAR levels in standard imaging mode (CP mode) or the maximum SAR level observed across seven pregnant body models in CP mode. Local SAR was constrained either indirectly by further constraining the whole-body SAR (wbSAR) or directly by using subject-specific local SAR models.

Stochastic-offset-enhanced restricted slice excitation and 180° refocusing designs with spatially non-linear ΔB shim array fields.

Purpose: Developing a general framework with a novel stochastic offset strategy for the design of optimized RF pulses and time-varying spatially non-linear ΔB shim array fields for restricted slice excitation and refocusing with refined magnetization profiles within the intervals of the fixed voxels.

Methods: Our framework uses the decomposition property of the Bloch equations to enable joint design of RF-pulses and shim array fields for restricted slice excitation and refocusing with auto-differentiation optimization. Bloch simulations are performed independently on orthogonal basis vectors, Mx, My, and Mz, which enables designs for arbitrary initial magnetizations.

SVoRT: Iterative Transformer for Slice-to-Volume Registration in Fetal Brain MRI.

Volumetric reconstruction of fetal brains from multiple stacks of MR slices, acquired in the presence of almost unpredictable and often severe subject motion, is a challenging task that is highly sensitive to the initialization of slice-to-volume transformations. We propose a novel slice-to-volume registration method using Transformers trained on synthetically transformed data, which model multiple stacks of MR slices as a sequence. With the attention mechanism, our model automatically detects the relevance between slices and predicts the transformation of one slice using information from other slices.

Latent signal models: Learning compact representations of signal evolution for improved time-resolved, multi-contrast MRI.

Purpose: To improve time-resolved reconstructions by training auto-encoders to learn compact representations of Bloch-simulated signal evolution and inserting the decoder into the forward model.

Methods: Building on model-based nonlinear and linear subspace techniques, we train auto-encoders on dictionaries of simulated signal evolution to learn compact, nonlinear, latent representations. The proposed latent signal model framework inserts the decoder portion of the auto-encoder into the forward model and directly reconstructs the latent representation.

NeSVoR: Implicit Neural Representation for Slice-to-Volume Reconstruction in MRI.

Reconstructing 3D MR volumes from multiple motion-corrupted stacks of 2D slices has shown promise in imaging of moving subjects, e. g., fetal MRI.

Cross-Sectional Observational Study of Typical in utero Fetal Movements Using Machine Learning.

Early variations of fetal movements are the hallmark of a healthy developing central nervous system. However, there are no automatic methods to quantify the complex 3D motion of the developing fetus in utero. The aim of this prospective study was to use machine learning (ML) on in utero MRI to perform quantitative kinematic analysis of fetal limb movement, assessing the impact of maternal, placental, and fetal factors.

Joint Frequency and Image Space Learning for MRI Reconstruction and Analysis.

We propose neural network layers that explicitly combine frequency and image feature representations and show that they can be used as a versatile building block for reconstruction from frequency space data. Our work is motivated by the challenges arising in MRI acquisition where the signal is a corrupted Fourier transform of the desired image. The proposed joint learning schemes enable both correction of artifacts native to the frequency space and manipulation of image space representations to reconstruct coherent image structures at every layer of the network.

Change in T2* measurements of placenta and fetal organs during Braxton Hicks contractions.

Maternal-placental perfusion can be temporarily compromised by Braxton Hicks (BH) uterine contractions. Although prior studies have employed T2* changes to investigate the effect of BH contractions on placental oxygen, the effect of these contractions on the fetus has not been fully characterized. We investigated the effect of BH contractions on quantitative fetal organ T2* across gestation together with the birth information.

Parallel transmission 2D RARE imaging at 7T with transmit field inhomogeneity mitigation and local SAR control.

Purpose: We develop and test a parallel transmit (pTx) pulse design framework to mitigate transmit field inhomogeneity with control of local specific absorption rate (SAR) in 2D rapid acquisition with relaxation enhancement (RARE) imaging at 7T.

Methods: We design large flip angle RF pulses with explicit local SAR constraints by numerical simulation of the Bloch equations. Parallel computation and analytical expressions for the Jacobian and the Hessian matrices are employed to reduce pulse design time.

Selective RF excitation designs enabled by time-varying spatially non-linear ΔB fields with applications in fetal MRI.

Purpose: To demonstrate, through numerical simulations, novel designs of spatially selective radiofrequency (RF) excitations of the fetal brain by both a restricted 2D slice and 3D inner-volume selection. These designs exploit a single-channel RF pulse, conventional gradient fields, and the spatially non-linear ΔB fields of a multi-coil shim array, using an auto-differentiation optimization algorithm.

Methods: The design algorithm jointly optimizes the RF pulse and the time-varying ΔB fields, which is produced by a 64-channel multi-coil ΔB body array to augment the RF and the linear gradient fields, using an auto-differentiation approach.

Automated detection and reacquisition of motion-degraded images in fetal HASTE imaging at 3 T.

Purpose: Fetal brain Magnetic Resonance Imaging suffers from unpredictable and unconstrained fetal motion that causes severe image artifacts even with half-Fourier single-shot fast spin echo (HASTE) readouts. This work presents the implementation of a closed-loop pipeline that automatically detects and reacquires HASTE images that were degraded by fetal motion without any human interaction.

Methods: A convolutional neural network that performs automatic image quality assessment (IQA) was run on an external GPU-equipped computer that was connected to the internal network of the MRI scanner.

A 31-channel integrated "AC/DC" B shim and radiofrequency receive array coil for improved 7T MRI.

Purpose: To test an integrated "AC/DC" array approach at 7T, where B inhomogeneity poses an obstacle for functional imaging, diffusion-weighted MRI, MR spectroscopy, and other applications.

Methods: A close-fitting 7T 31-channel (31-ch) brain array was constructed and tested using combined Rx and ΔB shim channels driven by a set of rapidly switchable current amplifiers. The coil was compared to a shape-matched 31-ch reference receive-only array for RF safety, signal-to-noise ratio (SNR), and inter-element noise correlation.

Improving D-2-hydroxyglutarate MR spectroscopic imaging in mutant isocitrate dehydrogenase glioma patients with multiplexed RF-receive/B -shim array coils at 3 T.

MR spectroscopic imaging (MRSI) noninvasively maps the metabolism of human brains. In particular, the imaging of D-2-hydroxyglutarate (2HG) produced by glioma isocitrate dehydrogenase (IDH) mutations has become a key application in neuro-oncology. However, the performance of full field-of-view MRSI is limited by B spatial nonuniformity and lipid artifacts from tissues surrounding the brain.

Quantitative T and T mapping by magnetic resonance fingerprinting (MRF) of the placenta before and after maternal hyperoxia.

Introduction: MR relaxometry has been used to assess placental exchange function, but methods to date are not sufficiently fast to be robust to placental motion. Magnetic resonance fingerprinting (MRF) permits rapid, voxel-wise, intrinsically co-registered T and T mapping. After characterizing measurement error, we scanned pregnant women during air and oxygen breathing to demonstrate MRF's ability to detect placental oxygenation changes.

STRESS: Super-Resolution for Dynamic Fetal MRI using Self-Supervised Learning.

Fetal motion is unpredictable and rapid on the scale of conventional MR scan times. Therefore, dynamic fetal MRI, which aims at capturing fetal motion and dynamics of fetal function, is limited to fast imaging techniques with compromises in image quality and resolution. Super-resolution for dynamic fetal MRI is still a challenge, especially when multi-oriented stacks of image slices for oversampling are not available and high temporal resolution for recording the dynamics of the fetus or placenta is desired.

Rapid head-pose detection for automated slice prescription of fetal-brain MRI.

In fetal-brain MRI, head-pose changes between prescription and acquisition present a challenge to obtaining the standard sagittal, coronal and axial views essential to clinical assessment. As motion limits acquisitions to thick slices that preclude retrospective resampling, technologists repeat ~55-second stack-of-slices scans (HASTE) with incrementally reoriented field of view numerous times, deducing the head pose from previous stacks. To address this inefficient workflow, we propose a robust head-pose detection algorithm using full-uterus scout scans (EPI) which take ~5 seconds to acquire.

Safety and imaging performance of two-channel RF shimming for fetal MRI at 3T.

Purpose: This study investigates whether two-channel radiofrequency (RF) shimming can improve imaging without increasing specific absorption rate (SAR) for fetal MRI at 3T.

Methods: Transmit field ( ) average and variation in the fetus was simulated in seven numerical pregnant body models. Safety was quantified by maternal and fetal peak local SAR and fetal average SAR.

Enhanced detection of fetal pose in 3D MRI by Deep Reinforcement Learning with physical structure priors on anatomy.

Fetal MRI is heavily constrained by unpredictable and substantial fetal motion that causes image artifacts and limits the set of viable diagnostic image contrasts. Current mitigation of motion artifacts is predominantly performed by fast, single-shot MRI and retrospective motion correction. Estimation of fetal pose in real time during MRI stands to benefit prospective methods to detect and mitigate fetal motion artifacts where inferred fetal motion is combined with online slice prescription with low-latency decision making.

Semi-Supervised Learning for Fetal Brain MRI Quality Assessment with ROI consistency.

Fetal brain MRI is useful for diagnosing brain abnormalities but is challenged by fetal motion. The current protocol for T2-weighted fetal brain MRI is not robust to motion so image volumes are degraded by inter- and intra-slice motion artifacts. Besides, manual annotation for fetal MR image quality assessment are usually time-consuming.

An integrated RF-receive/B-shim array coil boosts performance of whole-brain MR spectroscopic imaging at 7 T.

Metabolic imaging of the human brain by in-vivo magnetic resonance spectroscopic imaging (MRSI) can non-invasively probe neurochemistry in healthy and disease conditions. MRSI at ultra-high field (≥ 7 T) provides increased sensitivity for fast high-resolution metabolic imaging, but comes with technical challenges due to non-uniform B field. Here, we show that an integrated RF-receive/B-shim (AC/DC) array coil can be used to mitigate 7 T B inhomogeneity, which improves spectral quality and metabolite quantification over a whole-brain slab.

Placental MRI: Development of an MRI compatible ex vivo system for whole placenta dual perfusion.

Purpose: Placental dysfunction plays a key role in diseases that affect the fetus in utero and after birth. Aiming to develop a platform for validating in vivo placental MRI and investigations into placental physiology, we designed and built a prototype MRI-compatible perfusion chamber with an integrated MRI receive coil for high SNR ex vivo placental imaging.

Principal Results: After optimizing placenta vascular clearing and perfusion protocols, we performed contrast enhanced MR angiography and MR relaxometry on eight carefully selected placentas while they were perfused via the umbilical arteries (UAs).