arXiv subjects
Publications and source records attributed to Joseph V. Hajnal.
We present simple reconstruction networks for multi-coil data by extending deep cascade of CNN's and exploiting the data consistency layer. In particular, we propose two variants, where one is inspired by POCSENSE and the other is calibration-less. We show that the proposed approaches are competitive relative to the state of the art both quantitatively and qualitatively.
Accurately estimating and correcting the motion artifacts are crucial for 3D image reconstruction of the abdominal and in-utero magnetic resonance imaging (MRI). The state-of-art methods are based on slice-to-volume registration (SVR) where multiple 2D image stacks are acquired in three orthogonal orientations. In this work, we present a novel reconstruction pipeline that only needs one orientation of 2D MRI scans and can reconstruct the full high-resolution image without masking or registration steps. The framework consists of two main stages: the respiratory motion estimation using a self-supervised recurrent neural network, which learns the respiratory signals that are naturally embedded in the asymmetry relationship of the neighborhood slices and cluster them according to a respiratory state. Then, we train a 3D deconvolutional network for super-resolution (SR) reconstruction of the sparsely selected 2D images using integrated reconstruction and total variation loss. We evaluate the classification accuracy on 5 simulated images and compare our results with the SVR method in adult abdominal and in-utero MRI scans. The results show that the proposed pipeline can accurately estimate the respiratory state and reconstruct 4D SR volumes with better or similar performance to the 3D SVR pipeline with less than 20\% sparsely selected slices. The method has great potential to transform the 4D abdominal and in-utero MRI in clinical practice.
We propose a patch-based singular value shrinkage method for diffusion magnetic resonance image estimation targeted at low signal to noise ratio and accelerated acquisitions. It operates on the complex data resulting from a sensitivity encoding reconstruction, where asymptotically optimal signal recovery guarantees can be attained by modeling the noise propagation in the reconstruction and subsequently simulating or calculating the limit singular value spectrum. Simple strategies are presented to deal with phase inconsistencies and optimize patch construction. The pertinence of our contributions is quantitatively validated on synthetic data, an in vivo adult example, and challenging neonatal and fetal cohorts. Our methodology is compared with related approaches, which generally operate on magnitude-only data and use data-based noise level estimation and singular value truncation. Visual examples are provided to illustrate effectiveness in generating denoised and debiased diffusion estimates with well preserved spatial and diffusion detail.
In utero diffusion MRI provides unique opportunities to non-invasively study the microstructure of tissue during fetal development. A wide range of developmental processes, such as the growth of white matter tracts in the brain, the maturation of placental villous trees, or the fibres in the fetal heart remain to be studied and understood in detail. Advances in fetal interventions and surgery furthermore increase the need for ever more precise antenatal diagnosis from fetal MRI. However, the specific properties of the in utero environment, such as fetal and maternal motion, increased field-of-view, tissue interfaces and safety considerations, are significant challenges for most MRI techniques, and particularly for diffusion. Recent years have seen major improvements, driven by the development of bespoke techniques adapted to these specific challenges in both acquisition and processing. Fetal diffusion MRI, an emerging research tool, is now adding valuable novel information for both research and clinical questions. This paper will highlight specific challenges, outline strategies to target them, and discuss two main applications: fetal brain connectomics and placental maturation.
Purpose: A combined diffusion-relaxometry MR acquisition and analysis pipeline for in-vivo human placenta, which allows for exploration of coupling between T2* and apparent diffusion coefficient (ADC) measurements in a sub 10 minute scan time. Methods: We present a novel acquisition combining a diffusion prepared spin-echo with subsequent gradient echoes. The placentas of 17 pregnant women were scanned in-vivo, including both healthy controls and participants with various pregnancy complications. We estimate the joint T2*-ADC spectra using an inverse Laplace transform. Results: T2*-ADC spectra demonstrate clear quantitative separation between normal and dysfunctional placentas. Conclusions: Combined T2*-diffusivity MRI is promising for assessing fetal and maternal health during pregnancy. The T2*-ADC spectrum potentially provides additional information on tissue microstructure, compared to measuring these two contrasts separately. The presented method is immediately applicable to the study of other organs.
An extended aperture has the potential to greatly improve ultrasound imaging performance. This work extends the effective aperture size by coherently compounding the received radio frequency data from multiple transducers. A framework is developed in which an ultrasound imaging system consisting of $N$ synchronized matrix arrays, each with partly shared field of view, take turns to transmit plane waves. Only one individual transducer transmits at each time while all $N$ transducers simultaneously receive. The subwavelength localization accuracy required to combine information from multiple transducers is achieved without the use of any external tracking device. The method developed in this study is based on the study of the backscattered echoes received by the same transducer and resulting from a targeted scatterer point in the medium insonated by the multiple ultrasound probes of the system. The current transducer locations along with the speed of sound in the medium are deduced by optimizing the cross-correlation between these echoes. The method is demonstrated experimentally in 2-D using ultrasound point and anechoic lesion phantoms and a first demonstration of a free-hand experiment is also shown. Results demonstrate that the coherent multi-transducer imaging has the potential to improve ultrasound image quality, improving resolution and target detectability. Lateral resolution, contrast and contrast-to-noise ratio improved from 0.67 mm, -6.708 dB and 0.702, respectively, when using a single probe, to 0.18 mm, -7.251 dB and 0.721 in the coherent multi-transducer imaging case.
Accelerating the data acquisition of dynamic magnetic resonance imaging (MRI) leads to a challenging ill-posed inverse problem, which has received great interest from both the signal processing and machine learning community over the last decades. The key ingredient to the problem is how to exploit the temporal correlation of the MR sequence to resolve the aliasing artefact. Traditionally, such observation led to a formulation of a non-convex optimisation problem, which were solved using iterative algorithms. Recently, however, deep learning based-approaches have gained significant popularity due to its ability to solve general inversion problems. In this work, we propose a unique, novel convolutional recurrent neural network (CRNN) architecture which reconstructs high quality cardiac MR images from highly undersampled k-space data by jointly exploiting the dependencies of the temporal sequences as well as the iterative nature of the traditional optimisation algorithms. In particular, the proposed architecture embeds the structure of the traditional iterative algorithms, efficiently modelling the recurrence of the iterative reconstruction stages by using recurrent hidden connections over such iterations. In addition, spatiotemporal dependencies are simultaneously learnt by exploiting bidirectional recurrent hidden connections across time sequences. The proposed algorithm is able to learn both the temporal dependency and the iterative reconstruction process effectively with only a very small number of parameters, while outperforming current MR reconstruction methods in terms of computational complexity, reconstruction accuracy and speed.
Diffusion-weighted MRI measures the direction and scale of the local diffusion process in every voxel through its spectrum in q-space, typically acquired in one or more shells. Recent developments in microstructure imaging and multi-tissue decomposition have sparked renewed attention in the radial b-value dependence of the signal. Applications in motion correction and outlier rejection therefore require a compact linear signal representation that extends over the radial as well as angular domain. Here, we introduce SHARD, a data-driven representation of the q-space signal based on spherical harmonics and a radial decomposition into orthonormal components. This representation provides a complete, orthogonal signal basis, tailored to the spherical geometry of q-space and calibrated to the data at hand. We demonstrate that the rank-reduced decomposition outperforms model-based alternatives in human brain data, whilst faithfully capturing the micro- and meso-structural information in the signal. Furthermore, we validate the potential of joint radial-spherical as compared to single-shell representations. As such, SHARD is optimally suited for applications that require low-rank signal predictions, such as motion correction and outlier rejection. Finally, we illustrate its application for the latter using outlier robust regression.
Inspired by recent advances in deep learning, we propose a framework for reconstructing dynamic sequences of 2D cardiac magnetic resonance (MR) images from undersampled data using a deep cascade of convolutional neural networks (CNNs) to accelerate the data acquisition process. In particular, we address the case where data is acquired using aggressive Cartesian undersampling. Firstly, we show that when each 2D image frame is reconstructed independently, the proposed method outperforms state-of-the-art 2D compressed sensing approaches such as dictionary learning-based MR image reconstruction, in terms of reconstruction error and reconstruction speed. Secondly, when reconstructing the frames of the sequences jointly, we demonstrate that CNNs can learn spatio-temporal correlations efficiently by combining convolution and data sharing approaches. We show that the proposed method consistently outperforms state-of-the-art methods and is capable of preserving anatomical structure more faithfully up to 11-fold undersampling. Moreover, reconstruction is very fast: each complete dynamic sequence can be reconstructed in less than 10s and, for the 2D case, each image frame can be reconstructed in 23ms, enabling real-time applications.
An Extended Phase Graph framework for modelling systems with exchange or magnetization transfer (MT) is proposed. The framework, referred to as EPG-X, models coupled two-compartment systems by describing each compartment with separate phase graphs that exchange during evolution periods. There are two variants: EPG-X(BM) for systems governed by the Bloch-McConnell equations; and EPG-X(MT) for the pulsed MT formalism. For the MT case the "bound" protons have no transverse components so their phase graph consists only longitudinal states. EPG-X was used to model steady-state gradient echo imaging, MT effects in multislice Turbo Spin Echo imaging, multiecho CPMG for multicomponent T2 relaxometry and transient variable flip angle gradient echo imaging of the type used for MR Fingerprinting. Experimental data were also collected for the final case. Steady-state predictions from EPG-X closely match directly derived steady-state solutions which differ substantially from classic "single pool" EPG predictions. EPG-X(MT) predicts similar MT related levels of signal attenuation in white matter as have been reported elsewhere in the literature. Modelling of CPMG echo trains with EPG-X(BM) suggests that exchange processes can lead to an underestimate of the fraction of short T2 species. Modelling of transient gradient echo sequences with EPG-X(MT) suggests that measurable MT effects result from variable saturation of bound protons, particularly after inversion pulses. In conclusion, EPG-X can be used for modelling of the transient signal response of systems exhibiting chemical exchange or MT. This may be particularly beneficial for relaxometry approaches that rely on characterising transient rather than steady-state sequences.
The acquisition of Magnetic Resonance Imaging (MRI) is inherently slow. Inspired by recent advances in deep learning, we propose a framework for reconstructing MR images from undersampled data using a deep cascade of convolutional neural networks to accelerate the data acquisition process. We show that for Cartesian undersampling of 2D cardiac MR images, the proposed method outperforms the state-of-the-art compressed sensing approaches, such as dictionary learning-based MRI (DLMRI) reconstruction, in terms of reconstruction error, perceptual quality and reconstruction speed for both 3-fold and 6-fold undersampling. Compared to DLMRI, the error produced by the method proposed is approximately twice as small, allowing to preserve anatomical structures more faithfully. Using our method, each image can be reconstructed in 23 ms, which is fast enough to enable real-time applications.
In this paper we present a novel method for the correction of motion artifacts that are present in fetal Magnetic Resonance Imaging (MRI) scans of the whole uterus. Contrary to current slice-to-volume registration (SVR) methods, requiring an inflexible anatomical enclosure of a single investigated organ, the proposed patch-to-volume reconstruction (PVR) approach is able to reconstruct a large field of view of non-rigidly deforming structures. It relaxes rigid motion assumptions by introducing a specific amount of redundant information that is exploited with parallelized patch-wise optimization, super-resolution, and automatic outlier rejection. We further describe and provide an efficient parallel implementation of PVR allowing its execution within reasonable time on commercially available graphics processing units (GPU), enabling its use in the clinical practice. We evaluate PVR's computational overhead compared to standard methods and observe improved reconstruction accuracy in presence of affine motion artifacts of approximately 30% compared to conventional SVR in synthetic experiments. Furthermore, we have evaluated our method qualitatively and quantitatively on real fetal MRI data subject to maternal breathing and sudden fetal movements. We evaluate peak-signal-to-noise ratio (PSNR), structural similarity index (SSIM), and cross correlation (CC) with respect to the originally acquired data and provide a method for visual inspection of reconstruction uncertainty. With these experiments we demonstrate successful application of PVR motion compensation to the whole uterus, the human fetus, and the human placenta.
In this paper, we propose DeepCut, a method to obtain pixelwise object segmentations given an image dataset labelled with bounding box annotations. It extends the approach of the well-known GrabCut method to include machine learning by training a neural network classifier from bounding box annotations. We formulate the problem as an energy minimisation problem over a densely-connected conditional random field and iteratively update the training targets to obtain pixelwise object segmentations. Additionally, we propose variants of the DeepCut method and compare those to a naive approach to CNN training under weak supervision. We test its applicability to solve brain and lung segmentation problems on a challenging fetal magnetic resonance dataset and obtain encouraging results in terms of accuracy.