No file available
To read the file of this research,
you can request a copy directly from the authors.
ABN: Anti-Blur Neural Networks for Multi-Stage Deformable Image Registration
Preprints and early-stage research may not have been peer reviewed yet.
Abstract
Deformable image registration, i.e., the task of aligning multiple images into one coordinate system by non-linear transformation, serves as an essential preprocessing step for neuroimaging data. Recent research on deformable image registration is mainly focused on improving the registration accuracy using multi-stage alignment methods, where the source image is repeatedly deformed in stages by a same neural network until it is well-aligned with the target image. Conventional methods for multi-stage registration can often blur the source image as the pixel/voxel values are repeatedly interpolated from the image generated by the previous stage. However, maintaining image quality such as sharpness during image registration is crucial to medical data analysis. In this paper, we study the problem of anti-blur deformable image registration and propose a novel solution, called Anti-Blur Network (ABN), for multi-stage image registration. Specifically, we use a pair of short-term registration and long-term memory networks to learn the nonlinear deformations at each stage, where the short-term registration network learns how to improve the registration accuracy incrementally and the long-term memory network combines all the previous deformations to allow an interpolation to perform on the raw image directly and preserve image sharpness. Extensive experiments on both natural and medical image datasets demonstrated that ABN can accurately register images while preserving their sharpness. Our code and data can be found at https://github.com/anonymous3214/ABN
ResearchGate has not been able to resolve any citations for this publication.
We present recursive cascaded networks, a general architecture that enables learning deep cascades, for deformable image registration. The proposed architecture is simple in design and can be built on any base network. The moving image is warped successively by each cascade and finally aligned to the fixed image; this procedure is recursive in a way that every cascade learns to perform a progressive deformation for the current warped image. The entire system is end-to-end and jointly trained in an unsupervised manner. In addition, enabled by the recursive architecture, one cascade can be iteratively applied for multiple times during testing, which approaches a better fit between each of the image pairs. We evaluate our method on 3D medical images, where deformable registration is most commonly applied. We demonstrate that recursive cascaded networks achieve consistent, significant gains and outperform state-of-the-art methods. The performance reveals an increasing trend as long as more cascades are trained, while the limit is not observed. Code is available at https://github.com/microsoft/Recursive-Cascaded-Networks.
A novel non-rigid image registration algorithm is built upon fully convolutional networks (FCNs) to optimize and learn spatial transformations between pairs of images to be registered in a self-supervised learning framework. Different from most existing deep learning based image registration methods that learn spatial transformations from training data with known corresponding spatial transformations, our method directly estimates spatial transformations between pairs of images by maximizing an image-wise similarity metric between fixed and deformed moving images, similar to conventional image registration algorithms. The image registration is implemented in a multi-resolution image registration framework to jointly optimize and learn spatial transformations and FCNs at different spatial resolutions with deep self-supervision through typical feedforward and backpropagation computation. The proposed method has been evaluated for registering 3D structural brain magnetic resonance (MR) images and obtained better performance than state-of-the-art image registration algorithms.
Mining from neuroimaging data is becoming increasingly popular in the field of healthcare and bioinformatics, due to its potential to discover clinically meaningful structure patterns that could facilitate the understanding and diagnosis of neurological and neuropsychiatric disorders. Most recent research concentrates on applying subgraph mining techniques to discover connected subgraph patterns in the brain network. However, the underlying brain network structure is complicated. As a shallow linear model, subgraph mining cannot capture the highly non-linear structures, resulting in sub-optimal patterns. Therefore, how to learn representations that can capture the highly non-linearity of brain networks and preserve the underlying structures is a critical problem.
In this paper, we propose a Structural Deep Brain Network mining method, namely SDBN, to learn highly non-linear and structure-preserving representations of brain networks. Specifically, we first introduce a novel graph reordering approach based on module identification, which rearranges the order of the nodes to preserve the modular structure of the graph. Next, we perform structural augmentation to further enhance the spatial information of the reordered graph. Then we propose a deep feature learning framework for combining supervised learning and unsupervised learning in a small-scale setting, by augmenting Convolutional Neural Network (CNN) with decoding pathways for reconstruction. With the help of the multiple layers of non-linear mapping, the proposed SDBN approach can capture the highly non-linear structure of brain networks. Further, it has better generalization capability for high-dimensional brain networks and works well even for small sample learning. Benefit from CNN's task-oriented learning style, the learned hierarchical representation is meaningful for the clinical task. To evaluate the proposed SDBN method, we conduct extensive experiments on four real brain network datasets for disease diagnoses. The experiment results show that SDBN can capture discriminative and meaningful structural graph representations for brain disorder diagnosis.
This paper introduces Quicksilver, a fast deformable image registration method. Quicksilver registration for image-pairs works by patch-wise prediction of a deformation model based directly on image appearance. A deep encoder-decoder network is used as the prediction model. While the prediction strategy is general, we focus on predictions for the Large Deformation Diffeomorphic Metric Mapping (LDDMM) model. Specifically, we predict the momentum-parameterization of LDDMM, which facilitates a patch-wise prediction strategy while maintaining the theoretical properties of LDDMM, such as guaranteed diffeomorphic mappings for sufficiently strong regularization. We also provide a probabilistic version of our prediction network which can be sampled during test time to calculate uncertainties in the predicted deformations. Finally, we introduce a new correction network which greatly increases the prediction accuracy of an already existing prediction network. Experiments are conducted for both atlas-to-image and image-to-image registrations. These experiments show that our method accurately predicts registrations obtained by numerical optimization, is very fast, and achieves state-of-the-art registration results on four standard validation datasets. Quicksilver is freely available as open-source software.
We provide examples and highlights of Advanced Normalization Tools (ANTS) that address practical problems in real data.
We introduce the Mindboggle-101 dataset, the largest and most complete set of free, publicly accessible, manually labeled human brain images. To manually label the macroscopic anatomy in magnetic resonance images of 101 healthy participants, we created a new cortical labeling protocol that relies on robust anatomical landmarks and minimal manual edits after initialization with automated labels. The “Desikan–Killiany–Tourville” (DKT) protocol is intended to improve the ease, consistency, and accuracy of labeling human cortical areas. Given how difficult it is to label brains, the Mindboggle-101 dataset is intended to serve as brain atlases for use in labeling other brains, as a normative dataset to establish morphometric variation in a healthy population for comparison against clinical populations, and contribute to the development, training, testing, and evaluation of automated registration and labeling algorithms. To this end, we also introduce benchmarks for the evaluation of such algorithms by comparing our manual labels with labels automatically generated by probabilistic and multi-atlas registration-based approaches. All data and related software and updated information are available on the http://mindboggle.info/data website.
Effective diagnosis of Alzheimer's disease (AD), the most common type of dementia in elderly patients, is of primary importance in biomedical research. Recent studies have demonstrated that AD is closely related to the structure change of the brain network, i.e., the connectivity among different brain regions. The connectivity patterns will provide useful imaging-based biomarkers to distinguish Normal Controls (NC), patients with Mild Cognitive Impairment (MCI), and patients with AD. In this paper, we investigate the sparse inverse covariance estimation technique for identifying the connectivity among different brain regions. In particular, a novel algorithm based on the block coordinate descent approach is proposed for the direct estimation of the inverse covariance matrix. One appealing feature of the proposed algorithm is that it allows the user feedback (e.g., prior domain knowledge) to be incorporated into the estimation process, while the connectivity patterns can be discovered automatically. We apply the proposed algorithm to a collection of FDG-PET images from 232 NC, MCI, and AD subjects. Our experimental results demonstrate that the proposed algorithm is promising in revealing the brain region connectivity differences among these groups.
This work describes a systematic evaluation of several autofocus functions used for analytical fluorescent image cytometry studies of counterstained nuclei. Focusing is the first step in the automatic fluorescence in situ hybridization analysis of cells. Thirteen functions have been evaluated using qualitative and quantitative procedures. For the last of these procedures a figure-of-merit (FOM) is defined and proposed. This new FOM takes into account five important features of the focusing function. Our results show that functions based on correlation measures have the best performance for this type of image.
We describe the construction of a digital brain atlas composed of data from manually delineated MRI data. A total of 56 structures were labeled in MRI of 40 healthy, normal volunteers. This labeling was performed according to a set of protocols developed for this project. Pairs of raters were assigned to each structure and trained on the protocol for that structure. Each rater pair was tested for concordance on 6 of the 40 brains; once they had achieved reliability standards, they divided the task of delineating the remaining 34 brains. The data were then spatially normalized to well-known templates using 3 popular algorithms: AIR5.2.5's nonlinear warp (Woods et al., 1998) paired with the ICBM452 Warp 5 atlas (Rex et al., 2003), FSL's FLIRT (Smith et al., 2004) was paired with its own template, a skull-stripped version of the ICBM152 T1 average; and SPM5's unified segmentation method (Ashburner and Friston, 2005) was paired with its canonical brain, the whole head ICBM152 T1 average. We thus produced 3 variants of our atlas, where each was constructed from 40 representative samples of a data processing stream that one might use for analysis. For each normalization algorithm, the individual structure delineations were then resampled according to the computed transformations. We next computed averages at each voxel location to estimate the probability of that voxel belonging to each of the 56 structures. Each version of the atlas contains, for every voxel, probability densities for each region, thus providing a resource for automated probabilistic labeling of external data types registered into standard spaces; we also computed average intensity images and tissue density maps based on the three methods and target spaces. These atlases will serve as a resource for diverse applications including meta-analysis of functional and structural imaging data and other bioinformatics applications where display of arbitrary labels in probabilistically defined anatomic space will facilitate both knowledge-based development and visualization of findings from multiple disciplines.
In this paper the authors present a new approach for the nonrigid registration of contrast-enhanced breast MRI. A hierarchical transformation model of the motion of the breast has been developed. The global motion of the breast is modeled by an affine transformation while the local breast motion is described by a free-form deformation (FFD) based on B-splines. Normalized mutual information is used as a voxel-based similarity measure which is insensitive to intensity changes as a result of the contrast enhancement. Registration is achieved by minimizing a cost function, which represents a combination of the cost associated with the smoothness of the transformation and the cost associated with the image similarity. The algorithm has been applied to the fully automated registration of three-dimensional (3-D) breast MRI in volunteers and patients. In particular, the authors have compared the results of the proposed nonrigid registration algorithm to those obtained using rigid and affine registration techniques. The results clearly indicate that the nonrigid registration algorithm is much better able to recover the motion and deformation of the breast than rigid or affine registration algorithms.
We present VoxelMorph, a fast learning-based framework for deformable, pairwise medical image registration. Traditional registration methods optimize an objective function for each pair of images, which can be time-consuming for large datasets or rich deformation models. In contrast to this approach and building on recent learning-based methods, we formulate registration as a function that maps an input image pair to a deformation field that aligns these images. We parameterize the function via a convolutional neural network and optimize the parameters of the neural network on a set of images. Given a new pair of scans, VoxelMorph rapidly computes a deformation field by directly evaluating the function. In this paper, we explore two different training strategies. In the first (unsupervised) setting, we train the model to maximize standard image matching objective functions that are based on the image intensities. In the second setting, we leverage auxiliary segmentations available in the training data. We demonstrate that the unsupervised model’s accuracy is comparable to the state-of-the-art methods while operating orders of magnitude faster. We also show that VoxelMorph trained with auxiliary data improves registration accuracy at test time and evaluate the effect of training set size on registration. Our method promises to speed up medical image analysis and processing pipelines while facilitating novel directions in learning-based registration and its applications. Our code is freely available at
https://github.com/voxelmorph/voxelmorph
.
Image registration, the process of aligning two or more images, is the core technique of many (semi-)automatic medical image analysis tasks. Recent studies have shown that deep learning methods, notably convolutional neural networks (ConvNets), can be used for image registration. Thus far training of ConvNets for registration was supervised using predefined example registrations. However, obtaining example registrations is not trivial. To circumvent the need for predefined examples, and thereby to increase convenience of training ConvNets for image registration, we propose the Deep Learning Image Registration (DLIR) framework for unsupervised affine and deformable image registration. In the DLIR framework ConvNets are trained for image registration by exploiting image similarity analogous to conventional intensity-based image registration. After a ConvNet has been trained with the DLIR framework, it can be used to register pairs of unseen images in one shot. We propose flexible ConvNets designs for affine image registration and for deformable image registration. By stacking multiple of these ConvNets into a larger architecture, we are able to perform coarse-to-fine image registration. We show for registration of cardiac cine MRI and registration of chest CT that performance of the DLIR framework is comparable to conventional image registration while being several orders of magnitude faster.
Multi-modality data are widely used in clinical applications, such as tumor detection and brain disease diagnosis. Different modalities can usually provide complementary information, which commonly leads to improved performance. However, some modalities are commonly missing for some subjects due to various technical and practical reasons. As a result, multi-modality data are usually incomplete, raising the multi-modality missing data completion problem. In this work, we formulate the problem as a conditional image generation task and propose an encoder-decoder deep neural network to tackle this problem. Specifically, the model takes the existing modality as input and generates the missing modality. By employing an auxiliary adversarial loss, our model is able to generate high-quality missing modality images. At the same time, we propose to incorporate the available category information of subjects in training to enable the model to generate more informative images. We evaluate our method on the Alzheimer's Disease Neuroimaging Initiative~(ADNI) database, where positron emission tomography~(PET) modalities are missing. Experimental results show that the trained network can generate high-quality PET modalities based on existing magnetic resonance imaging~(MRI) modalities, and provide complementary information to improve the detection and tracking of the Alzheimer's disease. Our results also show that the proposed methods generate higher quality images than baseline methods as measured by various image quality statistics.
In this paper we propose a method to solve nonrigid image registration through a learning approach, instead of via iterative optimization of a predefined dissimilarity metric. We design a Convolutional Neural Network (CNN) architecture that, in contrast to all other work, directly estimates the displacement vector field (DVF) from a pair of input images. The proposed RegNet is trained using a large set of artificially generated DVFs, does not explicitly define a dissimilarity metric, and integrates image content at multiple scales to equip the network with contextual information. At testing time nonrigid registration is performed in a single shot, in contrast to current iterative methods. We tested RegNet on 3D chest CT follow-up data. The results show that the accuracy of RegNet is on par with a conventional B-spline registration, for anatomy within the capture range. Training RegNet with artificially generated DVFs is therefore a promising approach for obtaining good results on real clinical data, thereby greatly simplifying the training problem. Deformable image registration can therefore be successfully casted as a learning problem.
Robust image registration in medical imaging is essential for comparison or fusion of images, acquired from various perspectives, modalities or at different times. Typically, an objective function needs to be minimized assuming specific a priori deformation models and predefined or learned similarity measures. However, these approaches have difficulties to cope with large deformations or a large variability in appearance. Using modern deep learning (DL) methods with automated feature design, these limitations could be resolved by learning the intrinsic mapping solely from experience. We investigate in this paper how DL could help organ-specific (ROI-specific) deformable registration, to solve motion compensation or atlas-based segmentation problems for instance in prostate diagnosis. An artificial agent is trained to solve the task of non-rigid registration by exploring the parametric space of a statistical deformation model built from training data. Since it is difficult to extract trustworthy ground-truth deformation fields, we present a training scheme with a large number of synthetically deformed image pairs requiring only a small number of real inter-subject pairs. Our approach was tested on inter-subject registration of prostate MR data and reached a median DICE score of .88 in 2-D and .76 in 3-D, therefore showing improved results compared to state-of-the-art registration algorithms.
Existing deformable registration methods require exhaustively iterative optimization, along with careful parameter tuning, to estimate the deformation field between images. Although some learning-based methods have been proposed for initiating deformation estimation, they are often template-specific and not flexible in practical use. In this paper, we propose a convolutional neural network (CNN) based regression model to directly learn the complex mapping from the input image pair (i.e., a pair of template and subject) to their corresponding deformation field. Specifically, our CNN architecture is designed in a patch-based manner to learn the complex mapping from the input patch pairs to their respective deformation field. First, the equalized active-points guided sampling strategy is introduced to facilitate accurate CNN model learning upon a limited image dataset. Then, the similarity-steered CNN architecture is designed, where we propose to add the auxiliary contextual cue, i.e., the similarity between input patches, to more directly guide the learning process. Experiments on different brain image datasets demonstrate promising registration performance based on our CNN model. Furthermore, it is found that the trained CNN model from one dataset can be successfully transferred to another dataset, although brain appearances across datasets are quite variable.
A common problem with spatiotemporal data is how to simplify the data to discover an underlying network that consists of cohesive spatial regions (nodes) and relationships between those regions (edges). This network discovery problem naturally exists in a multitude of domains including climate data (dipoles), astronomical data (gravitational lensing) and the focus of this paper, fMRI scans of human subjects. Whereas previous work requires strong supervision, we propose an unsupervised matrix tri-factorization formulation with complex constraints and spatial regularization. We show that this formulation works well in controlled experiments with synthetic networks and is able to recover the underlying ground-truth network. We then show that for real fMRI data our approach can reproduce well known results in neurology regarding the default mode network in resting-state healthy and Alzheimer affected individuals.
Objective methods for assessing perceptual image quality have traditionally attempted to quantify the visibility of errors between a distorted image and a reference image using a variety of known properties of the human visual system. Under the assumption that human visual perception is highly adapted for extracting structural information from a scene, we introduce an alternative framework for quality assessment based on the degradation of structural information. As a specific example of this concept, we develop a Structural Similarity Index and demonstrate its promise through a set of intuitive examples, as well as comparison to both subjective ratings and state-of-the-art objective methods on a database of images compressed with JPEG and JPEG2000. A MatLab implementation of the proposed algorithm is available online at http://www.cns.nyu.edu/~lcv/ssim/.
There is large consent that successful training of deep networks requires many thousand annotated training samples. In this paper, we present a network and training strategy that relies on the strong use of data augmentation to use the available annotated samples more efficiently. The architecture consists of a contracting path to capture context and a symmetric expanding path that enables precise localization. We show that such a network can be trained end-to-end from very few images and outperforms the prior best method (a sliding-window convolutional network) on the ISBI challenge for segmentation of neuronal structures in electron microscopic stacks. Using the same network trained on transmitted light microscopy images (phase contrast and DIC) we won the ISBI cell tracking challenge 2015 in these categories by a large margin. Moreover, the network is fast. Segmentation of a 512x512 image takes less than a second on a recent GPU. The full implementation (based on Caffe) and the trained networks are available at
http://lmb.informatik.uni-freiburg.de/people/ronneber/u-net
.
In this paper, we present the concept of diffusing models to perform image-to-image matching. Having two images to match, the main idea is to consider the objects boundaries in one image as semi-permeable membranes and to let the other image, considered as a deformable grid model, diffuse through these interfaces, by the action of effectors situated within the membranes. We illustrate this concept by an analogy with Maxwell's demons. We show that this concept relates to more traditional ones, based on attraction, with an intermediate step being optical flow techniques. We use the concept of diffusing models to derive three different non-rigid matching algorithms, one using all the intensity levels in the static image, one using only contour points, and a last one operating on already segmented images. Finally, we present results with synthesized deformations and real medical images, with applications to heart motion tracking and three-dimensional inter-patients matching.
Convolutional Neural Networks define an exceptionally powerful class of
models, but are still limited by the lack of ability to be spatially invariant
to the input data in a computationally and parameter efficient manner. In this
work we introduce a new learnable module, the Spatial Transformer, which
explicitly allows the spatial manipulation of data within the network. This
differentiable module can be inserted into existing convolutional
architectures, giving neural networks the ability to actively spatially
transform feature maps, conditional on the feature map itself, without any
extra training supervision or modification to the optimisation process. We show
that the use of spatial transformers results in models which learn invariance
to translation, scale, rotation and more generic warping, resulting in
state-of-the-art performance on several benchmarks, and for a number of classes
of transformations.
Several biomedical applications require accurate image registration that can cope effectively with complex organ deformations. This paper addresses this problem by introducing a generic deformable registration algorithm with a new regularization scheme, which is performed through bilateral filtering of the deformation field. The proposed approach is primarily designed to handle smooth deformations both between and within body structures, and also more challenging deformation discontinuities exhibited by sliding organs. The conventional Gaussian smoothing of deformation fields is replaced by a bilateral filtering procedure, which compromises between the spatial smoothness and local intensity similarity kernels, and is further supported by a deformation field similarity kernel. Moreover, the presented framework does not require any explicit prior knowledge about the organ motion properties (e.g. segmentation) and therefore forms a fully automated registration technique. Validation was performed using synthetic phantom data and publicly available clinical 4D CT lung data sets. In both cases, the quantitative analysis shows improved accuracy when compared to conventional Gaussian smoothing. In addition, we provide experimental evidence that masking the lungs in order to avoid the problem of sliding motion during registration performs similarly in terms of the target registration error when compared to the proposed approach, however it requires accurate lung segmentation. Finally, quantification of the level and location of detected sliding motion yields visually plausible results by demonstrating noticeable sliding at the pleural cavity boundaries.
We present an optical flow algorithm for large displacement motions. Most existing optical flow methods use the standard coarse-to-fine framework to deal with large displacement motions which has intrinsic limitations. Instead, we formulate the motion estimation problem as a motion segmentation problem. We use approximate nearest neighbor fields to compute an initial motion field and use a robust algorithm to compute a set of similarity transformations as the motion candidates for segmentation. To account for deviations from similarity transformations, we add local deformations in the segmentation process. We also observe that small objects can be better recovered using translations as the motion candidates. We fuse the motion results obtained under similarity transformations and under translations together before a final refinement. Experimental validation shows that our method can successfully handle large displacement motions. Although we particularly focus on large displacement motions in this work, we make no sacrifice in terms of overall performance. In particular, our method ranks at the top of the Middlebury benchmark.
This paper describes the implementation of autofocusing for tissue microscopy. We first investigate the suitability of several criterion functions for the evaluation of image sharpness. Since tissue sections are invariably stained, we also discuss the selection of the colour component on which autofocusing will be performed. In tissue microscopy, where a section generally comprises multiple layers, it is often not possible to obtain an image that is well focused over the field of view because of the limited depth of field of the objective. We describe focus enhancement algorithms, closely related to the autofocus system, which may be employed to obtain an entirely sharp image.
Thesis (Ph. D.)--Dept. of Electrical Engineering, Stanford University, 1971. Bibliography: leaves 443-452.
All fields of neuroscience that employ brain imaging need to communicate their results with reference to anatomical regions. In particular, comparative morphometry and group analysis of functional and physiological data require coregistration of brains to establish correspondences across brain structures. It is well established that linear registration of one brain to another is inadequate for aligning brain structures, so numerous algorithms have emerged to nonlinearly register brains to one another. This study is the largest evaluation of nonlinear deformation algorithms applied to brain image registration ever conducted. Fourteen algorithms from laboratories around the world are evaluated using 8 different error measures. More than 45,000 registrations between 80 manually labeled brains were performed by algorithms including: AIR, ANIMAL, ART, Diffeomorphic Demons, FNIRT, IRTK, JRD-fluid, ROMEO, SICLE, SyN, and four different SPM5 algorithms ("SPM2-type" and regular Normalization, Unified Segmentation, and the DARTEL Toolbox). All of these registrations were preceded by linear registration between the same image pairs using FLIRT. One of the most significant findings of this study is that the relative performances of the registration methods under comparison appear to be little affected by the choice of subject population, labeling protocol, and type of overlap measure. This is important because it suggests that the findings are generalizable to new subject populations that are labeled or evaluated using different labeling protocols. Furthermore, we ranked the 14 methods according to three completely independent analyses (permutation tests, one-way ANOVA tests, and indifference-zone ranking) and derived three almost identical top rankings of the methods. ART, SyN, IRTK, and SPM's DARTEL Toolbox gave the best results according to overlap and distance measures, with ART and SyN delivering the most consistently high accuracy across subjects and label sets. Updates will be published on the http://www.mindboggle.info/papers/ website.
Registration is an important component of medical image analysis and for analysing large amounts of data it is desirable to have fully automatic registration methods. Many different automatic registration methods have been proposed to date, and almost all share a common mathematical framework - one of optimising a cost function. To date little attention has been focused on the optimisation method itself, even though the success of most registration methods hinges on the quality of this optimisation. This paper examines the assumptions underlying the problem of registration for brain images using inter-modal voxel similarity measures. It is demonstrated that the use of local optimisation methods together with the standard multi-resolution approach is not sufficient to reliably find the global minimum. To address this problem, a global optimisation method is proposed that is specifically tailored to this form of registration. A full discussion of all the necessary implementation details is included as this is an important part of any practical method. Furthermore, results are presented for inter-modal, inter-subject registration experiments that show that the proposed method is more reliable at finding the global minimum than several of the currently available registration packages in common usage.
In this paper, we extend a previously reported intensity-based nonrigid registration algorithm by using a novel regularization term to constrain the deformation. Global motion is modeled by a rigid transformation while local motion is described by a free-form deformation based on B-splines. An information theoretic measure, normalized mutual information, is used as an intensity-based image similarity measure. Registration is performed by searching for the deformation that minimizes a cost function consisting of a weighted combination of the image similarity measure and a regularization term. The novel regularization term is a local volume-preservation (incompressibility) constraint, which is motivated by the assumption that soft tissue is incompressible for small deformations and short time periods. The incompressibility constraint is implemented by penalizing deviations of the Jacobian determinant of the deformation from unity. We apply the nonrigid registration algorithm with and without the incompressibility constraint to precontrast and postcontrast magnetic resonance (MR) breast images from 17 patients. Without using a constraint, the volume of contrast-enhancing lesions decreases by 1%--78% (mean 26%). Image improvement (motion artifact reduction) obtained using the new constraint is compared with that obtained using a smoothness constraint based on the bending energy of the coordinate grid by blinded visual assessment of maximum intensity projections of subtraction images. For both constraints, volume preservation improves, and motion artifact correction worsens, as the weight of the constraint penalty term increases. For a given volume change of the contrast-enhancing lesions (2% of the original volume), the incompressibility constraint reduces motion artifacts ...
One of the most challenging problems in modern neuroimaging is detailed characterization of neurodegeneration. Quantifying spatial and longitudinal atrophy patterns is an important component of this process. These spatiotemporal signals will aid in discriminating between related diseases, such as frontotemporal dementia (FTD) and Alzheimer's disease (AD), which manifest themselves in the same at-risk population. Here, we develop a novel symmetric image normalization method (SyN) for maximizing the cross-correlation within the space of diffeomorphic maps and provide the Euler-Lagrange equations necessary for this optimization. We then turn to a careful evaluation of our method. Our evaluation uses gold standard, human cortical segmentation to contrast SyN's performance with a related elastic method and with the standard ITK implementation of Thirion's Demons algorithm. The new method compares favorably with both approaches, in particular when the distance between the template brain and the target brain is large. We then report the correlation of volumes gained by algorithmic cortical labelings of FTD and control subjects with those gained by the manual rater. This comparison shows that, of the three methods tested, SyN's volume measurements are the most strongly correlated with volume measurements gained by expert labeling. This study indicates that SyN, with cross-correlation, is a reliable method for normalizing and making anatomical measurements in volumetric MRI of patients and at-risk elderly individuals.
Computer vision, graphics, and image processing
- R Bajcsy
- S Kovačič
R. Bajcsy and S. Kovačič, "Multiresolution elastic matching," Computer
vision, graphics, and image processing, vol. 46, no. 1, pp. 1-21, 1989.
End-to-end unsupervised deformable image registration with a convolutional neural network," in Deep learning in medical image analysis and multimodal learning for clinical decision support
- B D De Vos
- F F Berendsen
- M A Viergever
- M Staring
- I Išgum
B. D. de Vos, F. F. Berendsen, M. A. Viergever, M. Staring, and I. Išgum,
"End-to-end unsupervised deformable image registration with a convolutional neural network," in Deep learning in medical image analysis
and multimodal learning for clinical decision support. Springer, 2017,
pp. 204-212.
Dual-attention recurrent networks for affine registration of neuroimaging data
- X Dai
- X Kong
- X Liu
- J B Lee
- C Moore
X. Dai, X. Kong, X. Liu, J. B. Lee, and C. Moore, "Dual-attention
recurrent networks for affine registration of neuroimaging data," in Proceedings of the 2020 SIAM International Conference on Data Mining.
SIAM, 2020, pp. 379-387.
Probabilistic multilayer regularization network for unsupervised 3d brain image registration
- L Liu
- X Hu
- L Zhu
- P.-A Heng
L. Liu, X. Hu, L. Zhu, and P.-A. Heng, "Probabilistic multilayer
regularization network for unsupervised 3d brain image registration," in
International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, 2019, pp. 346-354.
Adam: A method for stochastic optimization
- D P Kingma
- J Ba
D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization,"
arXiv preprint arXiv:1412.6980, 2014.