Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016

Computed tomography (CT) is widely used for dose planning in the radiotherapy of prostate cancer. However, CT has low tissue contrast, thus making manual contouring difficult. In contrast, magnetic resonance (MR) image provides high tissue contrast and is thus ideal for manual contouring. If MR image can be registered to CT image of the same patient, the contouring accuracy of CT could be substantially improved, which could eventually lead to high treatment efficacy. In this paper, we propose a learning-based approach for multimodal image registration. First, to fill the appearance gap between modalities, a structured random forest with auto-context model is learnt to synthesize MRI from CT and vice versa. Then, MRI-to-CT registration is steered in a dual manner of registering images with same appearances, i.e., (1) registering the synthesized CT with CT, and (2) also registering MRI with the synthesized MRI. Next, a dual-core deformation fusion framework is developed to iteratively and effectively combine these two registration results. Experiments on pelvic CT and MR images have shown the improved registration performance by our proposed method, compared with the existing non-learning based registration methods.

Multimodal registration is a challenging problem due the high variability of tissue appearance under different imaging modalities. The crucial component here is the choice of the right similarity measure. We make a step towards a general learning-based solution that can be adapted to specific situations and present a metric based on a convolutional neural network. Our network can be trained from scratch even from a few aligned image pairs. The metric is validated on intersubject deformable registration on a dataset different from the one used for training, demonstrating good generalization. In this task, we outperform mutual information by a significant margin.

We address the problem of multimodal image registration using a supervised learning approach. We pose the problem as a regression task, whose goal is to estimate the unknown geometric transformation from the joint appearance of the fixed and moving images. Our method is based on (i) context-aware features, which allow us to guide the registration using not only local, but also global structural information, and (ii) regression forests to map the very large contextual feature space to transformation parameters. Our approach improves the capture range, as we demonstrate on the publicly available IXI dataset. Furthermore, it can also handle difficult settings where other similarity metrics tend to fail; for instance, we show results on the deformable registration of Intravascular Ultrasound (IVUS) and Histology images.

In this paper a novel Large Deformation Diffeomorphic Metric Mapping (LDDMM) scheme is presented which has significantly lower computational and memory demands than standard LDDMM but achieves the same accuracy. We exploit the smoothness of velocities and transformations by using a coarser discretization compared to the image resolution. This reduces required memory and accelerates numerical optimization as well as solution of transport equations. Accuracy is essentially unchanged as the mismatch of transformed moving and fixed image is incorporated into the model at high resolution. Reductions in memory consumption and runtime are demonstrated for registration of lung CT images. State-of-the-art accuracy is shown for the challenging DIR-Lab chronic obstructive pulmonary disease (COPD) lung CT data sets obtaining a mean landmark distance after registration of 1.03 mm and the best average results so far.

Non-linear registration is an essential part of modern neuroimaging analysis, from morphometrics to functional studies. To be practical, non-linear registration methods must be precise and computational efficient. Current algorithms based on Thirion’s demons achieve high accuracies while having desirable properties such as diffeomorphic deformation fields. However, the increased complexity of these methods lead to a decrease in their efficiency. Here we propose a modification of the demons algorithm that both improves the accuracy and convergence speed, while maintaining the characteristics of a diffeomorphic registration. Our method outperforms all the analysed demons approaches in terms of speed and accuracy. Furthermore, this improvement is not limited to the demons algorithm, but applicable in most typical deformable registration algorithms.

Accurate motion estimation in thoracic computed tomography (CT) plays a crucial role in the diagnosis and treatment planning of lung cancer. This paper provides two key contributions to this motion estimation. First, we show we can effectively transform a CT image of effective linear attenuation coefficients to act as a density, i.e. exhibiting conservation of mass while undergoing a deformation. Second, we propose a method for diffeomorphic density registration for thoracic CT images. This algorithm uses the appropriate density action of the diffeomorphism group while offering a weighted penalty on local tissue compressibility. This algorithm appropriately models highly compressible areas of the body (such as the lungs) and incompressible areas (such as surrounding soft tissue and bones).

We present a robust method to correct for motion and deformations in in-utero volumetric MRI time series. Spatio-temporal analysis of dynamic MRI requires robust alignment across time in the presence of substantial and unpredictable motion. We make a Markov assumption on the nature of deformations to take advantage of the temporal structure in the image data. Forward message passing in the corresponding hidden Markov model (HMM) yields an estimation algorithm that only has to account for relatively small motion between consecutive frames. We demonstrate the utility of the temporal model by showing that its use improves the accuracy of the segmentation propagation through temporal registration. Our results suggest that the proposed model captures accurately the temporal dynamics of deformations in in-utero MRI time series.

The human hippocampus is a complex structure consisting of multiple anatomically and functionally distinct subfields. Obtaining subfield-specific measures from in vivo MRI is challenging, and can benefit from a detailed 3D anatomical reference. This paper builds a computational atlas of the hippocampus from high-resolution ex vivo MRI of 26 specimens using groupwise deformable registration. A surface-based approach based on the explicit segmentation and geometric modeling of hippocampal layers is used to initialize deformable registration of ex vivo MRI scans. This initialization improves of groupwise registration quality, as measured in terms of similarity metrics and qualitatively. The resulting atlas, which also includes annotations mapped from histology, is a unique resource for describing variability in hippocampal anatomy.

We present a novel method for image registration via a piecewise diffeomorphic deformation which accommodates sliding motion, such as that encountered at organ boundaries. Our method jointly computes the deformation as well as a coherent sliding boundary, represented by a segmentation of the domain into regions of smooth motion. Discontinuities are allowed only at the boundaries of these regions, while invertibility of the total deformation is enforced by disallowing separation or overlap between regions. Optimization alternates between discrete segmentation estimation and continuous deformation estimation. We demonstrate our method on chest 4DCT data showing sliding motion of the lungs against the thoracic cage during breathing.

Image-guided neurosurgery involves the display of MRI-based preoperative plans in an intraoperative reference frame. Interventional MRI (iMRI) can serve as a reference for non-rigid registration based propagation of preoperative MRI. Structural MRI images exhibit spatially varying intensity relationships, which can be captured by a local similarity measure such as the local normalized correlation coefficient (LNCC). However, LNCC weights local neighborhoods using a static spatial kernel and includes voxels from beyond a tissue or resection boundary in a neighborhood centered inside the boundary. We modify LNCC to use locally adaptive weighting inspired by bilateral filtering and evaluate it extensively in a numerical phantom study, a clinical iMRI study and a segmentation propagation study. The modified measure enables increased registration accuracy near tissue and resection boundaries.

Intra-interventional respiratory motion estimation has become vital for image-guided interventions, especially radiation therapy. While real-time tracking of highly discriminative landmarks like tumours and markers is possible with classic approaches (e.g. template matching), their robustness decreases when used with non-ionising imaging (4D MRI or US). Furthermore, they ignore the motion of neighbouring structures. We address these challenges by dividing the computation of dense deformable registration in two phases: First, a low-parametric full domain patient-specific motion model is learnt. Second, a sparse subset of feature locations is used to track motion locally, while the global motion patterns are constrained by the learnt model. In contrast to previous work, we optimise both objectives (local similarity and globally smooth motion) jointly using a coupled convex energy minimisation. This improves the tracking robustness and leads to a more accurate global motion estimation. The algorithm is computationally efficient and significantly outperforms classic template matching-based dense field estimation in 12 of 14 challenging 4D MRI and 4D ultrasound sequences.

It is very challenge to investigate the motion of the carotid artery wall in ultrasound images, because of the high nonlinear dynamics of this motion. In our study, the nonlinear dynamics of carotid artery wall motion is first approximated by our nonlinear state-space approach driven by a mathematical model of the mechanical deformation of carotid artery wall. Then, the two-dimensional motion of carotid artery wall is computed by solving the nonlinear state-space approach using the unscented Kalman filter. We have then evaluated the performance of our approach by comparing it with the manual tracing method (the correlation coefficient equals 0.9897 for the radial motion and 0.9703 for the longitudinal motion) and three other state-of-the-art methods for 73 subjects. The results indicate the reliable applicability of our approach in tracking the motion of the carotid artery wall and its potential usefulness in routine clinical diagnosis.

This paper reports a new automatic algorithm to estimate the misregistration in a quantitative manner. A random regression forest is constructed, predicting the local registration error. The forest is built using local and modality independent features related to the registration precision, the transformation model and intensity-based similarity after registration. The forest is trained and tested using manually annotated corresponding points between pairs of chest CT scans. The results show that the mean absolute error of regression is 0.72 ± 0.96 mm and the accuracy of classification in three classes (correct, poor and wrong registration) is 93.4 %, comparing favorably to a competing method. In conclusion, a method was proposed that for the first time shows the feasibility of automatic registration assessment by means of regression, and promising results were obtained.

The generation of a patient-specific finite element (FE) model of organs is important for preoperative surgical simulations. Although methods for generating a mesh from a 3D geometric model of organs are well established, the reproduction of complex structures, such as holes, branches, and jaggy boundaries, remains difficult. To approximate the deformation of complex structures, an approach for embedding a fine geometry in a coarse volumetric mesh can be used. In this paper, we introduce a volume embedding method that preserves the topology of a complicated structure on the basis of segmented medical images. Our evaluation shows that the generated FE model precisely reproduces the topology of a human brain according to a segmented medical image.

A 3D-2D image registration method is reported for guiding the placement of surgical devices (e.g., K-wires). The solution registers preoperative CT (and planning data therein) to intraoperative radiographs and computes the pose, shape, and deformation parameters of devices (termed “components”) known to be in the radiographic scene. The deformable known-component registration (dKC-Reg) method was applied in experiments emulating spine surgery to register devices (K-wires and spinal fixation rods) undergoing realistic deformation. A two-stage registration process (i) resolves patient pose from individual radiographs and (ii) registers components represented as polygonal meshes based on a B-spline model. The registration result can be visualized as overlay of the component in CT analogous to surgical navigation but without conventional trackers or fiducials. Target registration error in the tip and orientation of deformable K-wires was (1.5 ± 0.9) mm and (0.6° ± 0.2°), respectively. For spinal fixation rods, the registered components achieved Hausdorff distance of 3.4 mm. Future work includes testing in cadaver and clinical data and extension to more generalized deformation and component models.

Functional endoscopic sinus surgery (FESS) is a surgical procedure used to treat acute cases of sinusitis and other sinus diseases. FESS is fast becoming the preferred choice of treatment due to its minimally invasive nature. However, due to the limited field of view of the endoscope, surgeons rely on navigation systems to guide them within the nasal cavity. State of the art navigation systems report registration accuracy of over 1mm, which is large compared to the size of the nasal airways. We present an anatomically constrained video-CT registration algorithm that incorporates multiple video features. Our algorithm is robust in the presence of outliers. We also test our algorithm on simulated and in-vivo data, and test its accuracy against degrading initializations.

A novel probabilistic, group-wise rigid registration framework is proposed in this study, to robustly align and establish correspondence across anatomical shapes represented as unstructured point sets. Student’s t-mixture model (TMM) is employed to exploit their inherent robustness to outliers. The primary application for such a framework is the automatic construction of statistical shape models (SSMs) of anatomical structures, from medical images. Tools used for automatic segmentation and landmarking of medical images often result in segmentations with varying proportions of outliers. The proposed approach is able to robustly align shapes and establish valid correspondences in the presence of considerable outliers and large variations in shape. A multi-resolution registration (mrTMM) framework is also formulated, to further improve the performance of the proposed TMM-based registration method. Comparisons with a state-of-the art approach using clinical data show that the mrTMM method in particular, achieves higher alignment accuracy and yields SSMs that generalise better to unseen shapes.

This paper presents a registration-free method based on geometry spectrum for mapping two shapes. Our method can quantify and visualize the surface deformation by the variation of Laplace-Beltrami spectrum of the object. In order to examine our method, we employ synthetic data that has non-isometric deformation. We have also applied our method to quantifying the shape variation between the left and right hippocampus in epileptic human brains. The results on both synthetic and real patient data demonstrate the effectiveness and accuracy of our method.

Myocardial Contrast Echocardiography (MCE) with micro-bubble contrast agent enables myocardial perfusion quantification which is invaluable for the early detection of coronary artery diseases. In this paper, we proposed a new segmentation method called Shape Model guided Random Forests (SMRF) for the analysis of MCE data. The proposed method utilizes a statistical shape model of the myocardium to guide the Random Forest (RF) segmentation in two ways. First, we introduce a novel Shape Model (SM) feature which captures the global structure and shape of the myocardium to produce a more accurate RF probability map. Second, the shape model is fitted to the RF probability map to further refine and constrain the final segmentation to plausible myocardial shapes. Evaluated on clinical MCE images from 15 patients, our method obtained promising results (Dice = 0.81, Jaccard = 0.70, MAD = 1.68 mm, HD = 6.53 mm) and showed a notable improvement in segmentation accuracy over the classic RF and its variants.

Using image-based descriptors to investigate clinical hypotheses and therapeutic implications is challenging due to the notorious “curse of dimensionality” coupled with a small sample size. In this paper, we present a low-dimensional analysis of anatomical shape variability in the space of diffeomorphisms and demonstrate its benefits for clinical studies. To combat the high dimensionality of the deformation descriptors, we develop a probabilistic model of principal geodesic analysis in a bandlimited low-dimensional space that still captures the underlying variability of image data. We demonstrate the performance of our model on a set of 3D brain MRI scans from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database. Our model yields a more compact representation of group variation at substantially lower computational cost than models based on the high-dimensional state-of-the-art approaches such as tangent space PCA (TPCA) and probabilistic principal geodesic analysis (PPGA).

Computer models of the heart are of increasing interest for clinical applications due to their discriminative and predictive abilities. However a single 3D simulation can be computationally expensive and long, which can make some practical applications such as the personalisation phase, or a sensitivity analysis of mechanical parameters over the simulated behaviour quite slow. In this manuscript we present a multiscale 0D/3D model which allows us to have a reliable (and extremely fast) approximation of the behaviour of the 3D model under a few simplifying assumptions. We first detail the two different models, then explain the coupling of the two models to get fast 0D approximation of 3D simulations. Finally we demonstrated how the multiscale model can speed-up an efficient optimization algorithm, which enables a fast personalisation of the 3D simulations by leveraging on the advantages of each scale.

In order to deal with ambiguous image appearances in cell segmentation, high-level shape modeling has been introduced to delineate cell boundaries. However, shape modeling usually requires sufficient annotated training shapes, which are often labor intensive or unavailable. Meanwhile, when applying the model to different datasets, it is necessary to repeat the tedious annotation process to generate enough training data, and this will significantly limit the applicability of the model. In this paper, we propose to transfer shape modeling learned from an existing but different dataset (e.g. lung cancer) to assist cell segmentation in a new target dataset (e.g. skeletal muscle) without expensive manual annotations. Considering the intrinsic geometry structure of cell shapes, we incorporate the shape transfer model into a sparse representation framework with a manifold embedding constraint, and provide an efficient algorithm to solve the optimization problem. The proposed algorithm is tested on multiple microscopy image datasets with different tissue and staining preparations, and the experiments demonstrate its effectiveness.

Statistical shape analysis has relied on various models, each with its strengths and limitations. For multigroup analyses, while typical methods pool data to fit a single statistical model, partial pooling through hierarchical modeling can be superior. For pointset shape representations, we propose a novel hierarchical model in Riemannian shape space. The inference treats individual shapes and group-mean shapes as latent variables, and uses expectation maximization that relies on sampling shapes. Our generative model, including shape-smoothness priors, can be robust to segmentation errors, producing more compact per-group models and realistic shape samples. We propose a method for efficient sampling in Riemannian shape space. The results show the benefits of our hierarchical Riemannian generative model for hypothesis testing, over the state of the art.

Computational fluid dynamics (CFD) is a valuable tool for studying vascular diseases, but requires long computational time. To alleviate this issue, we propose a statistical framework to predict the aneurysmal wall shear stress patterns directly from the aneurysm shape. A database of 38 complex intracranial aneurysm shapes is used to generate aneurysm morphologies and CFD simulations. The shapes and wall shear stresses are then converted to clouds of hybrid points containing both types of information. These are subsequently used to train a joint statistical model implementing a mixture of principal component analyzers. Given a new aneurysmal shape, the trained joint model is firstly collapsed to a shape only model and used to initialize the missing shear stress values. The estimated hybrid point set is further refined by projection to the joint model space. We demonstrate that our predicted patterns can achieve significant similarities to the CFD-based results.

In this paper, we propose a general segmentation framework of Multi-Task Shape Regression (MTSR) which formulates segmentation as multi-task learning to leverage its strength of jointly solving multiple tasks enhanced by capturing task correlations. The MTSR entirely estimates coordinates of all points on shape contours by multi-task regression, where estimation of each coordinate corresponds to a regression task; the MTSR can jointly handle nonlinear relationships between image appearance and shapes while capturing holistic shape information by encoding coordinate correlations, which enables estimation of highly variable shapes, even with vague edge or region inhomogeneity. The MTSR achieves a long-desired general framework without relying on any specific assumptions or initialization, which enables flexible and fully automatic segmentation of multiple objects simultaneously, for different applications irrespective of modalities. The MTSR is validated on six representative applications of diverse images, achieves consistently high performance with dice similarity coefficient (DSC) up to 0.93 and largely outperforms state of the arts in each application, which demonstrates its effectiveness and generality for medical image segmentation.

This paper addresses the efficient statistical modeling of multi-organ structures, one of the most challenging scenarios in the medical imaging field due to the frequently limited availability of data. Unlike typical approaches where organs are considered either as single objects or as part of predefined groups, we introduce a more general and natural approach in which all the organs are inter-related inspired by the rhizome theory. Combining canonical correlation analysis with a generalized version of principal component analysis, we propose a new general and flexible framework for multi-organ shape modeling to efficiently characterize the individual organ variability and the relationships between different organs. This new framework called SOMOS can be easily parameterized to mimic a wide variety of alternative statistical shape modeling approaches, including the classic point distribution model, and its more recent multi-resolution variants. The significant superiority of SOMOS over alternative approaches was successfully verified for two different multi-organ databases: six subcortical structures of the brain, and seven abdominal organs. Finally, the organ-prediction capability of the model also significantly outperformed a partial least squared regression-based approach.

Fast and robust detection of anatomical structures or pathologies represents a fundamental task in medical image analysis. Most of the current solutions are however suboptimal and unconstrained by learning an appearance model and exhaustively scanning the space of parameters to detect a specific anatomical structure. In addition, typical feature computation or estimation of meta-parameters related to the appearance model or the search strategy, is based on local criteria or predefined approximation schemes. We propose a new learning method following a fundamentally different paradigm by simultaneously modeling both the object appearance and the parameter search strategy as a unified behavioral task for an artificial agent. The method combines the advantages of behavior learning achieved through reinforcement learning with effective hierarchical feature extraction achieved through deep learning. We show that given only a sequence of annotated images, the agent can automatically and strategically learn optimal paths that converge to the sought anatomical landmark location as opposed to exhaustively scanning the entire solution space. The method significantly outperforms state-of-the-art machine learning and deep learning approaches both in terms of accuracy and speed on 2D magnetic resonance images, 2D ultrasound and 3D CT images, achieving average detection errors of 1-2 pixels, while also recognizing the absence of an object from the image.

In this paper we present a new method of uncovering patients with aortic valve diseases in large electronic health record systems through learning with multimodal data. The method automatically extracts clinically-relevant valvular disease features from five multimodal sources of information including structured diagnosis, echocardiogram reports, and echocardiogram imaging studies. It combines these partial evidence features in a random forests learning framework to predict patients likely to have the disease. Results of a retrospective clinical study from a 1000 patient dataset are presented that indicate that over 25 % new patients with moderate to severe aortic stenosis can be automatically discovered by our method that were previously missed from the records.

3D cardiac MR imaging enables accurate analysis of cardiac morphology and physiology. However, due to the requirements for long acquisition and breath-hold, the clinical routine is still dominated by multi-slice 2D imaging, which hamper the visualization of anatomy and quantitative measurements as relatively thick slices are acquired. As a solution, we propose a novel image super-resolution (SR) approach that is based on a residual convolutional neural network (CNN) model. It reconstructs high resolution 3D volumes from 2D image stacks for more accurate image analysis. The proposed model allows the use of multiple input data acquired from different viewing planes for improved performance. Experimental results on 1233 cardiac short and long-axis MR image stacks show that the CNN model outperforms state-of-the-art SR methods in terms of image quality while being computationally efficient. Also, we show that image segmentation and motion tracking benefits more from SR-CNN when it is used as an initial upscaling method than conventional interpolation methods for the subsequent analysis.

Since the introduction of wide cone detector systems, CT myocardial perfusion has been an area of increased interest, for which non-rigid registration [NRR] is a key step to further analysis. We propose a novel motion management pipeline for perfusion data, GPNLPerf (Group-wise, non-local, NRR for perfusion analysis) centering on group-wise NRR using non-local spatio-temporal constraints. The proposed pipeline deals with the NRR challenges for 4D perfusion data and results in generating clinically relevant perfusion parameters. We demonstrate results on 9 dynamic perfusion exams comparing results quantitatively with ANTs NRR and also show qualitative results on perfusion maps.

Accurate measurement of left ventricular volumes and Ejection Fraction from cine MRI is of paramount importance to the evaluation of cardiovascular functions, yet it usually requires laborious and tedious work of trained experts to interpret them. To facilitate this procedure, numerous computer aided diagnosis (CAD) methods and tools have been proposed, most of which focus on the left or right ventricle segmentation. However, the identification of ES and ED frames from cardiac sequences is largely ignored, which is a key procedure in the automated workflow. This seemingly easy task is quite challenging, due to the requirement of high accuracy (i.e., precisely identifying specific frames from a sequence) and subtle differences among consecutive frames. Recently, with the rapid growth of annotated data and the increasing computational power, deep learning methods have been widely exploited in medical image analysis. In this paper, we propose a novel deep learning architecture, named as temporal regression network (TempReg-Net), to accurately identify specific frames from MRI sequences, by integrating the Convolutional Neural Network (CNN) with the Recurrent Neural Network (RNN). Specifically, a CNN encodes the spatial information of a cardiac sequence, and a RNN decodes the temporal information. In addition, we design a new loss function in our network to constrain the structure of predicted labels, which further improves the performance. Our approach is extensively validated on thousands of cardiac sequences and the average difference is merely 0.4 frames, comparing favorably with previous systems.

Estimating blood volume of the left ventricle (LV) in the end-diastolic and end-systolic phases is important in diagnosing cardiovascular diseases. Proper estimation of the volume requires knowledge of which MRI slice contains the topmost basal region of the LV. Automatic basal slice detection has proved challenging; as a result, basal slice detection remains a manual task which is prone to inter-observer variability. This paper presents a novel method that is able to track the basal slice over the whole cardiac cycle. The method was tested on 56 healthy and pathological cases and was able to identify the basal slices similar to experts’ selection for 80 % and 85 % of the cases for end-diastole and end-systole, respectively. This provides a significant improvement over the leading state-of-the-art approach that obtained 59 % and 44 % agreement with experts on the same input.

The estimation of local parameter values for a 3D cardiac model is important for revealing abnormal tissues with altered material properties and for building patient-specific models. Existing works in local parameter estimation typically represent the heart with a small number of pre-defined segments to reduce the dimension of unknowns. Such low-resolution approaches have limited ability to estimate tissues with varying sizes, locations, and distributions. We present a novel optimization framework to achieve a higher-resolution parameter estimation without using a high number of unknowns. It has two central elements: (1) a multi-scale coarse-to-fine optimization that uses low-resolution solutions to facilitate the higher-resolution optimization; and (2) a spatially-adaptive scheme that dedicates higher resolution to regions of heterogeneous tissue properties whereas retaining low resolution in homogeneous regions. Synthetic and real-data experiments demonstrate the ability of the presented framework to improve the accuracy of local parameter estimation in comparison to optimization based on fixed-segment models.

Three-dimensional reconstructions of coronary arteries can overcome some of the limitations of 2D X-ray angiography, namely artery overlap/foreshortening and lack of depth information. Model-based arterial reconstruction algorithms usually rely on 2D coronary artery segmentations and require good robustness to outliers. In this paper, we propose a novel probabilistic method to reconstruct coronary artery centrelines from retrospectively gated X-ray images based on a probabilistic mixture model. Specifically, 3D coronary artery centrelines are described by a mixture of Student’s t-distributions, and the reconstruction is formulated as maximum-likelihood estimation of the mixture model parameters, given the 2D segmentations of arteries from 2D X-ray images. Our method provides robustness against the erroneously segmented parts in the 2D segmentations by taking advantage of the inherent robustness of t-distributions. We validate our reconstruction results using synthetic phantom and clinical X-ray angiography data. The results show that the proposed method can cope with imperfect and noisy segmentation data.

In this paper, we propose a novel approach to study cardiac motion in 4D image sequences. Whereas traditional approaches rely on the registration of the whole sequence with respect to the first frame usually corresponding to the end-diastole (ED) image, we define a more generic basis using the barycentric subspace spanned by a number of references images of the sequence. These subspaces are implicitly defined as the locus of points which are weighted Karcher means of $$k+1$$ references images. We build such subspace on the cardiac motion images, to get a Barycentric Template that is no longer defined by a single image but parametrized by coefficients: the barycentric coordinates. We first show that the barycentric coordinates - the coefficients of the projection of the motion during a cardiac sequence - define a meaningful signature for group-wise analysis of dynamics and can efficiently separate two populations. Then, we use the barycentric template as a prior for regularization in cardiac motion tracking, efficiently reducing the error of tracking between end-systole and end-diastole by almost 40 % as well as the error of the evaluation of the ejection fraction. Finally, to best exploit the fact that multiple reference images allow to reduce the registration displacement, we derived a symmetric and transitive registration that can be used both for frame-to-frame and frame-to-reference registration and further improves the accuracy of the registration.

We present a method to extract coronary vessels from fluoroscopic x-ray sequences. Given the vessel structure for the source frame, vessel correspondence candidates in the subsequent frame are generated by a novel hierarchical search scheme to overcome the aperture problem. Optimal correspondences are determined within a Markov random field optimization framework. Post-processing is performed to extract vessel branches newly visible due to the inflow of contrast agent. Quantitative and qualitative evaluation conducted on a dataset of 18 sequences demonstrate the effectiveness of the proposed method.

We present a novel method for the automated extraction of blood vessel centerlines. There are two major contributions. First, in order to avoid the shortcuts to which minimal path methods are prone, we find optimal paths in a computed flow field. We solve for a steady state porous media flow inside a region of interest and trace centerlines as maximum flow paths. We explain how to estimate anisotropic orientation tensors which are used as permeability tensors in our flow field computation. Second, we introduce a convolutional neural network (CNN) classifier for removing extraneous paths in the detected centerlines. We apply our method to the extraction of coronary artery centerlines found in Computed Tomography Angiography (CTA). The robustness and stability of our method are enhanced by using a model-based detection of coronary specific territories and main branches to constrain the search space [15]. Validation against 20 comprehensively annotated datasets had a sensitivity and specificity at or above 90 %. Validation against 106 clinically annotated coronary arteries showed a sensitivity above 97 %.

Photoacoustic (PA) imaging has been gaining attention as a new imaging modality that can non-invasively visualize blood vessels inside biological tissues. In the process of imaging large body parts through multi-scan fusion, alignment turns out to be an important issue, since body motion degrades image quality. In this paper, we carefully examine the characteristics of PA images and propose a novel registration method that achieves better alignment while effectively decomposing the shot volumes into low-rank foreground (blood vessels), dense background (noise), and sparse complement (corruption) components on the basis of the PA characteristics. The results of experiments using a challenging real data-set demonstrate the efficacy of the proposed method, which significantly improved image quality, and had the best alignment accuracy among the state-of-the-art methods tested.

Angiographic imaging is a crucial domain of medical imaging. In particular, Magnetic Resonance Angiography (MRA) is used for both clinical and research purposes. This article presents the first framework geared toward the design of virtual MRA images from real MRA images. It relies on a pipeline that involves image processing, vascular modeling, computational fluid dynamics and MR image simulation, with several purposes. It aims to provide to the whole scientific community (1) software tools for MRA analysis and blood flow simulation; and (2) data (computational meshes, virtual MRAs with associated ground truth), in an open-source/open-data paradigm. Beyond these purposes, it constitutes a versatile tool for progressing in the understanding of vascular networks, especially in the brain, and the associated imaging technologies.

Nailfold capillaroscopy (NC) allows non-invasive imaging of systemic sclerosis (SSc) related microvascular disease. We have developed a state-of-the-art NC system that enables fast, panoramic imaging of the whole nailfold at high-magnification, and incorporates novel software to make fully automated estimates of capillary structure and blood flow velocity. We present the first results of a study in which 50 patients with SSc, 12 with primary Raynauds phenomenon (PRP) and 50 healthy controls (HC) were imaged using the new system, and show that a combined model of capillary measurements strongly separates SSc from HC/PRP (ROC $$A_z$$=0.93). Including capillary flow improves model performance, suggesting flow provides complementary information to capillary structure for diagnosing SSc.

Renal artery segmentation remained a big challenging due to its low contrast. In this paper, we present a novel graph-cut method using tensor-based distance metric for blood vessel segmentation in scale-valued images. Conventional graph-cut methods only use intensity information, which may result in failing in segmentation of small blood vessels. To overcome this drawback, this paper introduces local geometric structure information represented as tensors to find a better solution than conventional graph-cut. A Riemannian metric is utilized to calculate tensors statistics. These statistics are used in a Gaussian Mixture Model to estimate the probability distribution of the foreground and background regions. The experimental results showed that the proposed graph-cut method can segment about $$80\,\%$$ of renal arteries with 1mm precision in diameter.

We present an automatic three-dimensional segmentation approach based on continuous max flow that targets tubular structures in medical images. Our method uses second-order derivative information provided by Frangi et al.’s vesselness feature and exploits it twofold: First, the vesselness response itself is used for localizing the tubular structure of interest. Second, the eigenvectors of the Hessian eigendecomposition guide our anisotropic total variation–regularized segmentation. In a simulation experiment, we demonstrate the superiority of anisotropic as compared to isotropic total variation–regularized segmentation in the presence of noise. In an experiment with magnetic resonance images of the human cervical spinal cord, we compare our automated segmentations to those of two human observers. Finally, a comparison with a dedicated state-of-the-art spinal cord segmentation framework shows that we achieve comparable to superior segmentation quality.

In this work, we tackle the important problem of dense 3D volume labeling in medical imaging. We start by introducing HED-3D, a 3D extension of the state-of-the-art 2D edge detector (HED). Next, we develop a novel 3D-Convolutional Neural Network (CNN) architecture, I2I-3D, that predicts boundary location in volumetric data. Our fine-to-fine, deeply supervised framework addresses three critical issues to 3D boundary detection: (1) efficient, holistic, end-to-end volumetric label training and prediction (2) precise voxel-level prediction to capture fine scale structures prevalent in medical data and (3) directed multi-scale, multi-level feature learning. We evaluate our approaches on a dataset consisting of 93 medical image volumes with a wide variety of anatomical regions and vascular structures. We show that our deep learning approaches out-perform the current state-of-the-art in 3D vascular boundary detection (structured forests 3D), by a large margin, as well as HED applied to slices. Prediction takes about one minute on a typical $$512\,\times \,512\,\times \,512$$ volume, when using GPU.

One of the most widely used non-invasive clinical metric for diagnosing patients with symptoms of coronary artery disease is %stenosis derived from cCTA. Estimation of %stenosis involves two steps - the measurement of local diameter and the measurement of a reference healthy diameter. The estimation of a reference healthy diameter is challenging, especially in diffuse, ostial and bifurcation lesions. We develop a machine learning algorithm using random forest regressors for the estimation of healthy diameter using downstream and upstream properties of coronary tree vasculature as features. We use a population-based estimation, in contrast to single patient estimation that is used in the majority of the literature. We demonstrate that this method is able to predict the diameter of healthy sections with a correlation coefficient of 0.95. We then estimate %stenosis based on the ratio of the local vessel diameter to the estimated healthy diameter. Compared to a reference anisotropic kernel regression method, the proposed method, HALE (Healthy Area of Lumen Estimation), has a superior area under curve (0.90 vs 0.83) and operating point sensitivity/specificity (90 %/85 % vs 82 %/76 %) for the detection of stenoses. We also demonstrate superior performance of HALE against invasive quantitative coronary angiography (QCA), compared to the reference method (mean absolute error: 14 % vs 31 %, p$$\,<\,$$0.001).

This paper presents a portable imaging device designed to detect peripheral blood vessels for cannula insertion that are otherwise difficult to visualize beneath the skin. The device combines near infrared stereo vision, ultrasound, and real-time image analysis to map the 3D structure of subcutaneous vessels. We show that the device can identify adult forearm vessels and be used to guide manual insertions in tissue phantoms with increased first-stick accuracy compared to unassisted cannulation. We also demonstrate that the system may be coupled with a robotic manipulator to perform automated, image-guided venipuncture.

Several important tasks in medical image analysis can be stated in the form of an optimization problem whose feasible solutions are connected subgraphs. Examples include the reconstruction of neural or vascular structures under connectedness constraints.We discuss the minimum cost connected subgraph (MCCS) problem and its approximations from the perspective of medical applications. We propose (a) objective-dependent constraints and (b) novel constraint generation schemes to solve this optimization problem exactly by means of a branch-and-cut algorithm. These are shown to improve scalability and allow us to solve instances of two medical benchmark datasets to optimality for the first time. This enables us to perform a quantitative comparison between exact and approximative algorithms, where we identify the geodesic tree algorithm as an excellent alternative to exact inference on the examined datasets.

Pharmacokinetic analysis of Positron Emission Tomography (PET) data typically requires at least one hour of image acquisition, which poses a great disadvantage in clinical practice. In this work, we propose a novel approach for pharmacokinetic modelling with significantly reduced PET acquisition time, by incorporating the blood flow information from simultaneously acquired arterial spin labelling (ASL) magnetic resonance imaging (MRI). A relationship is established between blood flow, measured by ASL, and the transfer rate constant from plasma to tissue of the PET tracer, leading to modified PET kinetic models with ASL-derived flow information. Evaluation on clinical amyloid imaging data from an Alzheimer’s disease (AD) study shows that the proposed approach with the simplified reference tissue model can achieve amyloid burden estimation from 30 min [$$^{18}$$F]florbetapir PET data and 5 min simultaneous ASL MR data, which is comparable with the estimation from 60 min PET data (mean error$$\,=-0.03$$). Conversely, standardised uptake value ratio (SUVR), the alternative measure from the data showed a positive bias in areas of higher amyloid burden (mean error$$\,=0.07$$).

Tissue surface shape and reflectance spectra provide rich intra-operative information useful in surgical guidance. We propose a hybrid system which displays an endoscopic image with a fast joint inspection of tissue surface shape using structured light (SL) and hyperspectral imaging (HSI). For SL a miniature fibre probe is used to project a coloured spot pattern onto the tissue surface. In HSI mode standard endoscopic illumination is used, with the fibre probe collecting reflected light and encoding the spatial information into a linear format that can be imaged onto the slit of a spectrograph. Correspondence between the arrangement of fibres at the distal and proximal ends of the bundle was found using spectral encoding. Then during pattern decoding, a fully convolutional network (FCN) was used for spot detection, followed by a matching propagation algorithm for spot identification. This method enabled fast reconstruction (12 frames per second) using a GPU. The hyperspectral image was combined with the white light image and the reconstructed surface, showing the spectral information of different areas. Validation of this system using phantom and ex vivo experiments has been demonstrated.

The never-ending quest for lower radiation exposure is a major challenge to the image quality of advanced CT scans. Post-processing algorithms have been recently proposed to improve low-dose CT denoising after image reconstruction. In this work, a novel algorithm, termed the locally-consistent non-local means (LC-NLM), is proposed for this challenging task. By using a database of high-SNR CT patches to filter noisy pixels while locally enforcing spatial consistency, the proposed algorithm achieves both powerful denoising and preservation of fine image details. The LC-NLM is compared both quantitatively and qualitatively, for synthetic and real noise, to state-of-the-art published algorithms. The highest structural similarity index (SSIM) were achieved by LC-NLM in 8 out of 10 denoised chest CT volumes. Also, the visual appearance of the denoised images was clearly better for the proposed algorithm. The favorable comparison results, together with the computational efficiency of LC-NLM makes it a promising tool for low-dose CT denoising.

In this paper, we demonstrate that image reconstruction can be expressed in terms of neural networks. We show that filtered back-projection can be mapped identically onto a deep neural network architecture. As for the case of iterative reconstruction, the straight forward realization as matrix multiplication is not feasible. Thus, we propose to compute the back-projection layer efficiently as fixed function and its gradient as projection operation. This allows a data-driven approach for joint optimization of correction steps in projection domain and image domain. As a proof of concept, we demonstrate that we are able to learn weightings and additional filter layers that consistently reduce the reconstruction error of a limited angle reconstruction by a factor of two while keeping the same computational complexity as filtered back-projection. We believe that this kind of learning approach can be extended to any common CT artifact compensation heuristic and will outperform hand-crafted artifact correction methods in the future.

We present a one-step approach based on low-rank tensor recovery for axial alignment in 360-degree anterior chamber optical coherence tomography. Achieving translational alignment and rotation correction of cross-sections simultaneously, this technique obtains a better anterior segment topographical representation and improves quantitative measurement accuracy and reproducibility of disease related parameters. Through its use of global information, the proposed method is more robust compared to using only individual or paired slices, and less sensitive to noise and motion artifacts. In angle closure analysis on 30 patient eyes, the preliminary results indicate that the proposed axial alignment method can not only facilitate manual qualitative analysis with more distinct landmark representation and much less human labor, but also can improve the accuracy of automatic quantitative assessment by 2.9 %, which demonstrates that the proposed approach is promising for a wide range of clinical applications.

In this paper we consider dense volumetric modeling of moving samples such as body parts. Most dense modeling methods consider samples observed with a moving X-ray device and cannot easily handle moving samples. We propose a novel method that uses a surface motion capture system associated to a single low-cost/low-dose planar X-ray imaging device for dense in-depth attenuation information. Our key contribution is to rely on Bayesian inference to solve for a dense attenuation volume given planar radioscopic images of a moving sample. The approach enables multiple sources of noise to be considered and takes advantage of limited prior information to solve an otherwise ill-posed problem. Results show that the proposed strategy is able to reconstruct dense volumetric attenuation models from a very limited number of radiographic views over time on simulated and in-vivo data.

Cataracts are the leading cause of visual impairment and blindness worldwide. Cataract grading, i.e. assessing the presence and severity of cataracts, is essential for diagnosis and progression monitoring. We present in this work an automatic method for predicting cataract grades from slit-lamp lens images. Different from existing techniques which normally formulate cataract grading as a regression problem, we solve it through reconstruction-based classification, which has been shown to yield higher performance when the available training data is densely distributed within the feature space. To heighten the effectiveness of this reconstruction-based approach, we introduce a new semantic feature representation that facilitates alignment of test and reference images, and include locality constraints on the linear reconstruction to reduce the influence of less relevant reference samples. In experiments on the large ACHIKO-NC database comprised of 5378 images, our system outperforms the state-of-the-art regression methods over a range of evaluation metrics.

QSM is used to estimate the underlying tissue magnetic susceptibility and oxygen saturation in veins. This paper presents vessel orientation as a new regularization term to improve the accuracy of $$l_1$$ regularized QSM reconstruction in cerebral veins. For that purpose, the vessel tree is first extracted from an initial QSM reconstruction. In a second step, the vascular geometric prior is incorporated through an orthogonality constraint into the QSM reconstruction. Using a multi-orientation QSM acquisition as gold standard, we show that the QSM reconstruction obtained with the vessel anatomy prior provides up to 40 % RMSE reduction relative to the baseline $$l_1$$ regularizer approach. We also demonstrate in vivo OEF maps along venous veins based on segmentations from QSM. The utility of the proposed method is further supported by inclusion of a separate MRI venography scan to introduce more detailed vessel orientation information into the reconstruction, which provides significant improvement in vessel conspicuity.

High angular resolution diffusion imaging (HARDI) can produce better estimates of fiber orientation and richer sets of features for disease classification than diffusion tensor imaging. However, existing HARDI reconstruction algorithms require a large number of gradient directions, making the acquisition time too long to be clinically viable. State-of-the-art compressed sensing methods can reduce the number of measurements needed for accurate reconstruction by exploiting angular sparsity at each voxel, but the global sparsity level is therefore bounded below by the number of voxels. In this work, we aim to find a significantly sparser representation of HARDI by exploiting redundancies in both the spatial and angular domains jointly with a global HARDI basis. However, this leads to a massive global optimization problem over the whole brain which cannot be solved using existing sparse coding methods. We present a novel Kronecker extension to ADMM that exploits the separable spatial-angular structure of HARDI data to efficiently find a globally sparse reconstruction. We validate our method on phantom and real HARDI brain data by showing that we can achieve accurate reconstructions with a global sparsity level corresponding to less then one atom per voxel, surpassing the absolute limit of the state-of-the-art.

In this paper, we introduce a fast alternating method for reconstructing highly undersampled dynamic MRI data using 3D convolutional sparse coding. The proposed solution leverages Fourier Convolution Theorem to accelerate the process of learning a set of 3D filters and iteratively refine the MRI reconstruction based on the sparse codes found subsequently. In contrast to conventional CS methods which exploit the sparsity by applying universal transforms such as wavelet and total variation, our approach extracts and adapts the temporal information directly from the MRI data using compact shift-invariant 3D filters. We provide a highly parallel algorithm with GPU support for efficient computation, and therefore, the reconstruction outperforms CPU implementation of the state-of-the art dictionary learning-based approaches by up to two orders of magnitude.

We present a novel framework for retrospective dynamic 3D volume reconstruction from a multi-slice MRI acquisition using manifold alignment. K-space data are continuously acquired under free breathing using a radial golden-angle trajectory in a slice-by-slice manner. Non-overlapping consecutive profiles that were acquired within a short time window are grouped together. All grouped profiles from all slices are then simultaneously embedded using manifold alignment into a common manifold space (MS), in which profiles that were acquired at similar respiratory states are close together. Subsequently, a 3D volume can be reconstructed at each of the grouped profile MS positions by combining profiles that are close in the MS. This enables the original multi-slice dataset to be used to reconstruct a dynamic 3D sequence based on the respiratory state correspondences established in the MS. Our method was evaluated on both synthetic and in vivo datasets. For the synthetic datasets, the reconstructed dynamic sequence achieved a normalised cross correlation of 0.98 and peak signal to noise ratio of 26.64 dB compared with the ground truth. For the in vivo datasets, based on sharpness measurements and visual comparison, our method performed better than reconstruction using an adapted central k-space gating method.

We propose a new regularization for spherical deconvolution in diffusion MRI. It is based on observing that higher-order tensor representations of fiber ODFs should be H-psd, i.e., they should have a positive semidefinite (psd) matrix $$H_T$$. We show that this constraint is stricter than the currently more widely used non-negativity, and that it can be enforced easily using quadratic cone programming. We demonstrate its use in a multi-tissue deconvolution framework that models the different tissue types in the continuous SHORE basis and can therefore be applied to data with multiple b values that are not organized on shells, such as in Diffusion Spectrum Imaging. Experiments on simulated fiber crossings, data from the Human Connectome Project, and clinical data, demonstrate the improved speed and accuracy of this new method.

Large-scale neuroimaging studies often use multiple individual imaging contrasts. Due to the finite time available for imaging, there is intense competition for the time allocated to the individual modalities; thus it is crucial to maximise the utility of each method given the resources available. Arterial Spin Labelled (ASL) MRI often forms part of such studies. Measuring perfusion of oxygenated blood in the brain is valuable for several diseases, but quantification using multiple inversion time ASL is time-consuming due to poor SNR and consequently slow acquisitions. Here, we apply Bayesian principles of experimental design to clinical-length ASL acquisitions, resulting in significant improvements to perfusion estimation. Using simulations and experimental data, we validate this approach for a five-minute ASL scan. Our design procedure can be constrained to any chosen scan duration, making it well-suited to improve a variety of ASL implementations. The potential for adaptation to other modalities makes this an attractive method for optimising acquisition in the time-pressured environment of neuroimaging studies.

MR angiography (MRA) and phase-contrast MRA (PC-MRA) generation methods that facilitate blood flow assessment in the heart and thoracic vessels typically lead to the compression of data from all the timeframes of a cardiac cycle into one 2D or 3D image. This process, however, results in information loss from individual timeframes. We propose a new method for PC-MRA data generation from 4D flow MRI, which uses registration between the timeframes of the 4D acquisition to create a “four-dimensional PC-MR CardioAngiography (4D PC-MRCA)” that retains vascular and cardiac blood flow information over the entire cardiac cycle.When evaluated on 10 4D flow MRI datasets, 4D PC-MRCA outperformed 3D PC-MRA, especially when cardiac or vessel motion was present. Consequently, the proposed method improves the existing PC-MRA generation techniques by effectively utilizing spatial as well as temporal blood flow information on both the heart and thoracic vasculature from 4D flow MR images.

In the diagnosis of myocardial infarction, magnetic resonance imaging can provide information about myocardial contractility and tissue characterization, including viability. In current clinical practice, separate scans are required for each aspect. A recently proposed method showed how the same information can be extracted from a single, short scan of $$4\,\text {s}$$, but made strong assumptions about the underlying cardiac motion. We propose a fixed-point iteration scheme that retains the benefits of their approach while lifting its limitations, making it robust to cardiac arrhythmia. We compare our method to the state of the art using phantom data as well as data from 11 patients and show a consistent improvement of all evaluation criteria, e. g. the end-diastolic Dice coefficient of an arrythmic case improves from $$86\,\%$$ (state-of-the-art method) to $$94\,\%$$ (proposed method).

The Dixon method is a popular and widely used technique for fat-water separation in magnetic resonance imaging, and today, nearly all scanner manufacturers are offering a Dixon-type pulse sequence that produces scans with four types of images: in-phase, out-of-phase, fat-only, and water-only. A natural ambiguity due to phase wrapping and local minima in the optimization problem cause a frequent artifact of fat-water inversion where fat- and water-only voxel values are swapped. This artifact affects up to 10 % of routinely acquired Dixon images, and thus, has severe impact on subsequent analysis. We propose a simple yet very effective method, Dixon-Fix, for correcting fat-water swaps. Our method is based on regressing fat- and water-only images from in- and out-of-phase images by learning the conditional distribution of image appearance. The predicted images define the unary potentials in a globally optimal maximum-a-posteriori estimation of the swap labeling with spatial consistency. We demonstrate the effectiveness of our approach on whole-body MRI with various types of fat-water swaps.

Simultaneous multi-slice (SMS) echo-planar imaging has had a huge impact on the acceleration and routine use of diffusion-weighted MRI (DWI) in neuroimaging studies in particular the human connectome project; but also holds the potential to facilitate DWI of moving subjects, as proposed by the new technique developed in this paper. We present a novel registration-based motion tracking technique that takes advantage of the multi-plane coverage of the anatomy by simultaneously acquired slices to enable robust reconstruction of neural microstructure from SMS DWI of moving subjects. Our technique constitutes three main components: (1) motion tracking and estimation using SMS registration, (2) detection and rejection of intra-slice motion, and (3) robust reconstruction. Quantitative results from 14 volunteer subject experiments and the analysis of motion-corrupted SMS DWI of 6 children indicate robust reconstruction in the presence of continuous motion and the potential to extend the use of SMS DWI in very challenging populations.

It is faster and therefore cheaper to acquire magnetic resonance images (MRI) with higher in-plane resolution than through-plane resolution. The low resolution of such acquisitions can be increased using post-processing techniques referred to as super-resolution (SR) algorithms. SR is known to be an ill-posed problem. Most state-of-the-art SR algorithms rely on the presence of external/training data to learn a transform that converts low resolution input to a higher resolution output. In this paper an SR approach is presented that is not dependent on any external training data and is only reliant on the acquired image. Patches extracted from the acquired image are used to estimate a set of new images, where each image has increased resolution along a particular direction. The final SR image is estimated by combining images in this set via the technique of Fourier Burst Accumulation. Our approach was validated on simulated low resolution MRI images, and showed significant improvement in image quality and segmentation accuracy when compared to competing SR methods. SR of FLuid Attenuated Inversion Recovery (FLAIR) images with lesions is also demonstrated.

In diffusion MRI, the outcome of estimation problems can often be improved by taking into account the correlation of diffusion-weighted images scanned with neighboring wavevectors in q-space. For this purpose, we propose in this paper to employ tight wavelet frames constructed on non-flat domains for multi-scale sparse representation of diffusion signals. This representation is well suited for signals sampled regularly or irregularly, such as on a grid or on multiple shells, in q-space. Using spectral graph theory, the frames are constructed based on quasi-affine systems (i.e., generalized dilations and shifts of a finite collection of wavelet functions) defined on graphs, which can be seen as a discrete representation of manifolds. The associated wavelet analysis and synthesis transforms can be computed efficiently and accurately without the need for explicit eigen-decomposition of the graph Laplacian, allowing scalability to very large problems. We demonstrate the effectiveness of this representation, generated using what we call tight graph framelets, in two specific applications: denoising and super-resolution in q-space using $$\ell _{0}$$ regularization. The associated optimization problem involves only thresholding and solving a trivial inverse problem in an iterative manner. The effectiveness of graph framelets is confirmed via evaluation using synthetic data with noncentral chi noise and real data with repeated scans.

Quantifying $$T_2$$ and $$T_2^*$$ relaxation times from MRI becomes a standard tool to assess modifications of biological tissues over time or differences between populations. However, due to the relationship between the relaxation time and the associated MR signals such an analysis is subject to error. In this work, we provide a Bayesian analysis of this relationship. More specifically, we build posterior distributions relating the raw (spin or gradient echo) acquisitions and the relaxation time and its modifications over acquisitions. Such an analysis has three main merits. First, it allows to build hierarchical models including prior information and regularisations over voxels. Second, it provides many estimators of the parameters distribution including the mean and the $$\alpha $$-credible intervals. Finally, as credible intervals are available, testing properly whether the relaxation time (or its modification) lies within a certain range with a given credible level is simple. We show the interest of this approach on synthetic datasets and on two real applications in multiple sclerosis.

Magnetic resonance fingerprinting (MRF) quantifies various properties simultaneously by matching measurements to a dictionary of precomputed signals. We propose to extend the MRF framework by using a database to introduce additional parameters and spatial characteristics to the dictionary. We show that, with an adequate matching technique which includes an update of selected fingerprints in parameter space, it is possible to reconstruct parametric maps, synthesize modalities, and label tissue types at the same time directly from an MRF acquisition. We compare (1) relaxation maps from a spatiotemporal dictionary against a temporal MRF dictionary, (2) synthetic diffusion metrics versus those obtained with a standard diffusion acquisition, and (3) anatomical labels generated from MRF signals to an established segmentation method, demonstrating the potential of using MRF for multiparametric brain mapping.

Noise is a major issue influencing quantitative analysis in diffusion MRI. The effects of noise can be reduced by repeated acquisitions, but this leads to long acquisition times that can be unrealistic in clinical settings. For this reason, post-acquisition denoising methods have been widely used to improve SNR. Among existing methods, non-local means (NLM) has been shown to produce good image quality with edge preservation. However, currently the application of NLM to diffusion MRI has been mostly focused on the spatial space (i.e., the x-space), despite the fact that diffusion data live in a combined space consisting of the x-space and the q-space (i.e., the space of wavevectors). In this paper, we propose to extend NLM to both x-space and q-space. We show how patch-matching, as required in NLM, can be performed concurrently in x-q space with the help of azimuthal equidistant projection and rotation invariant features. Extensive experiments on both synthetic and real data confirm that the proposed x-q space NLM (XQ-NLM) outperforms the classic NLM.

Magnetic resonance spectroscopic imaging (MRSI) is an imaging modality used for generating metabolic maps of the tissue in-vivo. These maps show the concentration of metabolites in the sample being investigated and their accurate quantification is important to diagnose diseases. However, the major roadblocks in accurate metabolite quantification are: low spatial resolution, long scanning times, poor signal-to-noise ratio (SNR) and the subsequent noise-sensitive non-linear model fitting. In this work, we propose a frequency-phase spectral denoising method based on the concept of non-local means (NLM) that improves the robustness of data analysis and scanning times while potentially increasing spatial resolution. We evaluate our method on simulated data sets as well as on human in-vivo MRSI data. Our denoising method improves the SNR while maintaining the spatial resolution of the spectra.

Diffusion MRI is a frequently-used imaging modality that can infer microstructural properties of tissue, down to the scale of microns. For single-compartment models, such as the diffusion tensor (DT), the model interpretation depends on voxels having homogeneous composition. This limitation makes it difficult to measure diffusion parameters for small structures such as the fornix in the brain, because of partial volume. In this work, we use a segmentation from a structural scan to calculate the tissue composition for each diffusion voxel. We model the measured diffusion signal as a linear combination of signals from each of the tissues present in the voxel, and fit parameters on a per-region basis by optimising over all diffusion data simultaneously. We test the proposed method by using diffusion data from the Human Connectome Project (HCP). We downsample the HCP data, and show that our method returns parameter estimates that are closer to the high-resolution ground truths than for classical methods. We show that our method allows accurate estimation of diffusion parameters for regions with partial volume. Finally, we apply the method to compare diffusion in the fornix for adults born extremely preterm and matched controls.

This paper introduces a novel computer-aided diagnostic (CAD) system for the assessment of renal transplant status that integrates image-based biomarkers derived from 4D (3D + b-value) diffusion-weighted (DW) MRI, and clinical biomarkers. To analyze DW-MRI, our framework starts with kidney tissue segmentation using a level set approach after DW-MRI data alignment to handle the motion effects. Secondly, the cumulative empirical distributions (i.e., CDFs) of apparent diffusion coefficients (ADCs) of the segmented DW-MRIs are estimated at low and high gradient strengths and duration (b-values) accounting for both blood perfusion and diffusion, respectively. Finally, these CDFs are fused with laboratory-based biomarkers (creatinine clearance and serum plasma creatinine) for the classification of transplant status using a deep learning-based classification approach utilizing a stacked non-negativity constrained auto-encoder. Using “leave-one-subject-out” experiments on a cohort of 58 subjects, the proposed CAD system distinguished non-rejection transplants from kidneys with abnormalities with a 95 % accuracy (sensitivity = 95 %, specificity = 94 %) and achieved a 95 % correct classification between early rejection and other kidney diseases. Our preliminary results demonstrate the promise of the proposed CAD system as a reliable non-invasive diagnostic tool for renal transplants assessment.

Diffusion MRI is a key in-vivo non invasive imaging capability that can probe the microstructure of the brain. However, its limited resolution requires complex voxelwise generative models of the diffusion. Diffusion Compartment (DC) models divide the voxel into smaller compartments in which diffusion is homogeneous. We present a comprehensive framework for maximum likelihood estimation (MLE) of such models that jointly features ML estimators of (i) the baseline MR signal, (ii) the noise variance, (iii) compartment proportions, and (iv) diffusion-related parameters. ML estimators are key to providing reliable mapping of brain microstructure as they are asymptotically unbiased and of minimal variance. We compare our algorithm (which efficiently exploits analytical properties of MLE) to alternative implementations and a state-of-the-art strategy. Simulation results show that our approach offers the best reduction in computational burden while guaranteeing convergence of numerical estimators to the MLE. In-vivo results also reveal remarkably reliable microstructure mapping in areas as complex as the centrum semi-ovale. Our ML framework accommodates any DC model and is available freely for multi-tensor models as part of the ANIMA software (https://github.com/Inria-Visages/Anima-Public/wiki).