Search

Unsupervised domain adaptation (UDA) has been widely used to transfer knowledge from a labeled source domain to an unlabeled target domain to counter the difficulty of labeling in a new domain. The training of conventional solutions usually relies on the existence of both source and target domain data. However, privacy of the large-scale and well-labeled data in the source domain and trained model parameters can become the major concern of cross center/domain collaborations. In this work, to address this, we propose a practical solution to UDA for segmentation with a black-box segmentation model trained in the source domain only, rather than original source data or a white-box source model. Specifically, we resort to a knowledge distillation scheme with exponential mixup decay (EMD) to gradually learn target-specific representations. In addition, unsupervised entropy minimization is further applied to regularization of the target domain confidence. We evaluated our framework on the BraTS 2018 database, achieving performance on par with white-box source model adaptation approaches.

Cycle reconstruction regularized adversarial training-e.g., CycleGAN, DiscoGAN, and DualGAN-has been widely used for image style transfer with unpaired training data. Several recent works, however, have shown that local distortions are frequent, and structural consistency cannot be guaranteed. Targeting this issue, prior works usually relied on additional segmentation or consistent feature extraction steps that are task-specific. To counter this, this work aims to learn a general add-on structural feature extractor, by explicitly enforcing the structural alignment between an input and its synthesized image. Specifically, we propose a novel input-output image patches self-training scheme to achieve a disentanglement of underlying anatomical structures and imaging modalities. The translator and structure encoder are updated, following an alternating training protocol. In addition, the information w.r.t. imaging modality can be eliminated with an asymmetric adversarial game. We train, validate, and test our network on 1,768, 416, and 1,560 unpaired subject-independent slices of tagged and cine magnetic resonance imaging from a total of twenty healthy subjects, respectively, demonstrating superior performance over competing methods.

Accurate strain measurement in a deforming organ has been essential in motion analysis using medical images. In recent years, internal tissue's in vivo motion and strain computation has been mostly achieved through dynamic magnetic resonance (MR) imaging. However, such data lack information on tissue's intrinsic fiber directions, preventing computed strain tensors from being projected onto a direction of interest. Although diffusion-weighted MR imaging excels at providing fiber tractography, it yields static images unmatched with dynamic MR data. This work reports an algorithm workflow that estimates strain values in the diffusion MR space by matching corresponding tagged dynamic MR images. We focus on processing a dataset of various human tongue deformations in speech. The geometry of tongue muscle fibers is provided by diffusion tractography, while spatiotemporal motion fields are provided by tagged MR analysis. The tongue's deforming shapes are determined by segmenting a synthetic cine dynamic MR sequence generated from tagged data using a deep neural network. Estimated motion fields are transformed into the diffusion MR space using diffeomorphic registration, eventually leading to strain values computed in the direction of muscle fibers. The method was tested on 78 time volumes acquired during three sets of specific tongue deformations including both speech and protrusion motion. Strain in the line of action of seven internal tongue muscles was extracted and compared both intra- and inter-subject. Resulting compression and stretching patterns of individual muscles revealed the unique behavior of individual muscles and their potential activation pattern.

Assessment of cardiovascular disease (CVD) with cine magnetic resonance imaging (MRI) has been used to non-invasively evaluate detailed cardiac structure and function. Accurate segmentation of cardiac structures from cine MRI is a crucial step for early diagnosis and prognosis of CVD, and has been greatly improved with convolutional neural networks (CNN). There, however, are a number of limitations identified in CNN models, such as limited interpretability and high complexity, thus limiting their use in clinical practice. In this work, to address the limitations, we propose a lightweight and interpretable machine learning model, successive subspace learning with the subspace approximation with adjusted bias (Saab) transform, for accurate and efficient segmentation from cine MRI. Specifically, our segmentation framework is comprised of the following steps: (1) sequential expansion of near-to-far neighborhood at different resolutions; (2) channel-wise subspace approximation using the Saab transform for unsupervised dimension reduction; (3) class-wise entropy guided feature selection for supervised dimension reduction; (4) concatenation of features and pixel-wise classification with gradient boost; and (5) conditional random field for post-processing. Experimental results on the ACDC 2017 segmentation database, showed that our framework performed better than state-of-the-art U-Net models with 200× fewer parameters in delineating the left ventricle, right ventricle, and myocardium, thus showing its potential to be used in clinical practice.Clinical relevance- Delineation of the left ventricular cavity, myocardium, and right ventricle from cardiac MR images is a common clinical task to establish diagnosis and prognosis of CVD.

Multimodal MRI provides complementary and clinically relevant information to probe tissue condition and to characterize various diseases. However, it is often difficult to acquire sufficiently many modalities from the same subject due to limitations in study plans, while quantitative analysis is still demanded. In this work, we propose a unified conditional disentanglement framework to synthesize any arbitrary modality from an input modality. Our framework hinges on a cycle-constrained conditional adversarial training approach, where it can extract a modality-invariant anatomical feature with a modality-agnostic encoder and generate a target modality with a conditioned decoder. We validate our framework on four MRI modalities, including T1-weighted, T1 contrast enhanced, T2-weighted, and FLAIR MRI, from the BraTS'18 database, showing superior performance on synthesis quality over the comparison methods. In addition, we report results from experiments on a tumor segmentation task carried out with synthesized data.

Tagged magnetic resonance imaging (MRI) is a widely used imaging technique for measuring tissue deformation in moving organs. Due to tagged MRI's intrinsic low anatomical resolution, another matching set of cine MRI with higher resolution is sometimes acquired in the same scanning session to facilitate tissue segmentation, thus adding extra time and cost. To mitigate this, in this work, we propose a novel dual-cycle constrained bijective VAE-GAN approach to carry out tagged-to-cine MR image synthesis. Our method is based on a variational autoencoder backbone with cycle reconstruction constrained adversarial training to yield accurate and realistic cine MR images given tagged MR images. Our framework has been trained, validated, and tested using 1,768, 416, and 1,560 subject-independent paired slices of tagged and cine MRI from twenty healthy subjects, respectively, demonstrating superior performance over the comparison methods. Our method can potentially be used to reduce the extra acquisition time and cost, while maintaining the same workflow for further motion analyses.

To advance our understanding of speech motor control, it is essential to image and assess dynamic functional patterns of internal structures caused by the complex muscle anatomy inside the human tongue. Speech pathologists are investigating into new tools that help assessment of internal tongue muscle's cooperative mechanics on top of their anatomical differences. Previous studies using dynamic magnetic resonance imaging (MRI) of the tongue revealed that tongue muscles tend to function in different groups during speech, especially the floor-of-the-mouth (FOM) muscles. In this work, we developed a method that analyzed the unique functional pattern of the FOM muscles in speech. First, four-dimensional motion fields of the whole tongue were computed using tagged MRI. Meanwhile, a statistical atlas of the tongue was constructed to form a common space for subject comparison, while a manually delineated mask of internal tongue muscles was used to separate individual muscle's motion. Then we computed four-dimensional motion correlation between each muscle and the FOM muscle group. Finally, dynamic correlation of different muscle groups was compared and evaluated. We used data from a study group of nineteen subjects including both healthy controls and oral cancer patients. Results revealed that most internal tongue muscles coordinated in a similar pattern in speech while the FOM muscles followed a unique pattern that helped supporting the tongue body and pivoting its rotation. The proposed method can help provide further interpretation of clinical observations and speech motor control from an imaging point of view.

Self-training based unsupervised domain adaptation (UDA) has shown great potential to address the problem of domain shift, when applying a trained deep learning model in a source domain to unlabeled target domains. However, while the self-training UDA has demonstrated its effectiveness on discriminative tasks, such as classification and segmentation, via the reliable pseudo-label selection based on the softmax discrete histogram, the self-training UDA for generative tasks, such as image synthesis, is not fully investigated. In this work, we propose a novel generative self-training (GST) UDA framework with continuous value prediction and regression objective for cross-domain image synthesis. Specifically, we propose to filter the pseudo-label with an uncertainty mask, and quantify the predictive confidence of generated images with practical variational Bayes learning. The fast test-time adaptation is achieved by a round-based alternative optimization scheme. We validated our framework on the tagged-to-cine magnetic resonance imaging (MRI) synthesis problem, where datasets in the source and target domains were acquired from different scanners or centers. Extensive validations were carried out to verify our framework against popular adversarial training UDA methods. Results show that our GST, with tagged MRI of test subjects in new target domains, improved the synthesis quality by a large margin, compared with the adversarial training UDA methods.

Deformable registration of magnetic resonance images between patients with brain tumors and healthy subjects has been an important tool to specify tumor geometry through location alignment and facilitate pathological analysis. Since tumor region does not match with any ordinary brain tissue, it has been difficult to deformably register a patient's brain to a normal one. Many patient images are associated with irregularly distributed lesions, resulting in further distortion of normal tissue structures and complicating registration's similarity measure. In this work, we follow a multi-step context-aware image inpainting framework to generate synthetic tissue intensities in the tumor region. The coarse image-to-image translation is applied to make a rough inference of the missing parts. Then, a feature-level patch-match refinement module is applied to refine the details by modeling the semantic relevance between patch-wise features. A symmetry constraint reflecting a large degree of anatomical symmetry in the brain is further proposed to achieve better structure understanding. Deformable registration is applied between inpainted patient images and normal brains, and the resulting deformation field is eventually used to deform original patient data for the final alignment. The method was applied to the Multimodal Brain Tumor Segmentation (BraTS) 2018 challenge database and compared against three existing inpainting methods. The proposed method yielded results with increased peak signal-to-noise ratio, structural similarity index, inception score, and reduced L1 error, leading to successful patient-to-normal brain image registration.

Unsupervised domain adaptation (UDA) aims to transfer knowledge learned from a labeled source domain to an unlabeled and unseen target domain, which is usually trained on data from both domains. Access to the source domain data at the adaptation stage, however, is often limited, due to data storage or privacy issues. To alleviate this, in this work, we target source free UDA for segmentation, and propose to adapt an "off-the-shelf" segmentation model pre-trained in the source domain to the target domain, with an adaptive batch-wise normalization statistics adaptation framework. Specifically, the domain-specific low-order batch statistics, i.e., mean and variance, are gradually adapted with an exponential momentum decay scheme, while the consistency of domain shareable high-order batch statistics, i.e., scaling and shifting parameters, is explicitly enforced by our optimization objective. The transferability of each channel is adaptively measured first from which to balance the contribution of each channel. Moreover, the proposed source free UDA framework is orthogonal to unsupervised learning methods, e.g., self-entropy minimization, which can thus be simply added on top of our framework. Extensive experiments on the BraTS 2018 database show that our source free UDA framework outperformed existing source-relaxed UDA methods for the cross-subtype UDA segmentation task and yielded comparable results for the cross-modality UDA segmentation task, compared with a supervised UDA methods with the source data.

The tongue is capable of producing intelligible speech because of successful orchestration of muscle groupings-i.e., functional units-of the highly complex muscles over time. Due to the different motions that tongues produce, functional units are transitional structures which transform muscle activity to surface tongue geometry and they vary significantly from one subject to another. In order to compare and contrast the location and size of functional units in the presence of such substantial inter-person variability, it is essential to study both common and subject-specific functional units in a group of people carrying out the same speech task. In this work, a new normalization technique is presented to simultaneously identify the common and subject-specific functional units defined in the tongue when tracked by tagged magnetic resonance imaging. To achieve our goal, a joint sparse non-negative matrix factorization framework is used, which learns a set of building blocks and subject-specific as well as common weighting matrices from motion quantities extracted from displacements. A spectral clustering technique is then applied to the subject-specific and common weighting matrices to determine the subject-specific functional units for each subject and the common functional units across subjects. Our experimental results using in vivo tongue motion data show that our approach is able to identify the common and subject-specific functional units with reduced size variability of tongue motion during speech.

Purpose Intrinsic and extrinsic tongue muscles in healthy and diseased populations vary both in their intra- and intersubject behaviors during speech. Identifying coordination patterns among various tongue muscles can provide insights into speech motor control and help in developing new therapeutic and rehabilitative strategies. Method We present a method to analyze multisubject tongue muscle correlation using motion patterns in speech sound production. Motion of muscles is captured using tagged magnetic resonance imaging and computed using a phase-based deformation extraction algorithm. After being assembled in a common atlas space, motions from multiple subjects are extracted at each individual muscle location based on a manually labeled mask using high-resolution magnetic resonance imaging and a vocal tract atlas. Motion correlation between each muscle pair is computed within each labeled region. The analysis is performed on a population of 16 control subjects and 3 post-partial glossectomy patients. Results The floor-of-mouth (FOM) muscles show reduced correlation comparing to the internal tongue muscles. Patients present a higher amount of overall correlation between all muscles and exercise en bloc movements. Conclusions Correlation matrices in the atlas space show the coordination of tongue muscles in speech sound production. The FOM muscles are weakly correlated with the internal tongue muscles. Patients tend to use FOM muscles more than controls to compensate for their postsurgery function loss.

High resolution magnetic resonance (MR) images are desired in many clinical applications, yet acquiring such data with an adequate signal-to-noise ratio requires a long time, making them costly and susceptible to motion artifacts. A common way to partly achieve this goal is to acquire MR images with good in-plane resolution and poor through-plane resolution (i.e., large slice thickness). For such 2D imaging protocols, aliasing is also introduced in the through-plane direction, and these high-frequency artifacts cannot be removed by conventional interpolation. Super-resolution (SR) algorithms which can reduce aliasing artifacts and improve spatial resolution have previously been reported. State-of-the-art SR methods are mostly learning-based and require external training data consisting of paired low resolution (LR) and high resolution (HR) MR images. However, due to scanner limitations, such training data are often unavailable. This paper presents an anti-aliasing (AA) and self super-resolution (SSR) algorithm that needs no external training data. It takes advantage of the fact that the in-plane slices of those MR images contain high frequency information. Our algorithm consists of three steps: 1) We build a self AA (SAA) deep network followed by 2) an SSR deep network, both of which can be applied along different orientations within the original images, and 3) recombine the multiple orientations output from Steps 1 and 2 using Fourier burst accumulation. We perform our SAA+SSR algorithm on a diverse collection of MR data without modification or preprocessing other than N4 inhomogeneity correction, and demonstrate significant improvement compared to competing SSR methods.

An accurate prediction of brain tumor progression is crucial for optimized treatment of the tumors. Gliomas are primarily treated by combining surgery, external beam radiotherapy, and chemotherapy. Among them, radiotherapy is a non-invasive and effective therapy, and an understanding of tumor growth will allow better therapy planning. In particular, estimating parameters associated with tumor growth, such as the diffusion coefficient and proliferation rate, is crucial to accurately characterize physiology of tumor growth and to develop predictive models of tumor infiltration and recurrence. Accurate parameter estimation, however, is a challenging task due to inaccurate tumor boundaries and the approximation of the tumor growth model. Here, we introduce a Bayesian framework for a subject-specific tumor growth model that estimates the tumor parameters effectively. This is achieved by using an improved elliptical slice sampling method based on an adaptive sample region. Experimental results on clinical data demonstrate that the proposed method provides a higher acceptance rate, while preserving the parameter estimation accuracy, compared with other state-of-the-art methods such as Metropolis-Hastings and elliptical slice sampling without any modification. Our approach has the potential to provide a method to individualize therapy, thereby offering an optimized treatment.

Amyotrophic Lateral Sclerosis (ALS) is a neurological disease that causes death of neurons controlling muscle movements. Loss of speech and swallowing functions is a major impact due to degeneration of the tongue muscles. In speech studies using magnetic resonance (MR) techniques, diffusion tensor imaging (DTI) is used to capture internal tongue muscle fiber structures in three-dimensions (3D) in a non-invasive manner. Tagged magnetic resonance images (tMRI) are used to record tongue motion during speech. In this work, we aim to combine information obtained with both MR imaging techniques to compare the functionality characteristics of the tongue between normal and ALS subjects. We first extracted 3D motion of the tongue using tMRI from fourteen normal subjects in speech. The estimated motion sequences were then warped using diffeomorphic registration into the b0 spaces of the DTI data of two normal subjects and an ALS patient. We then constructed motion atlases by averaging all warped motion fields in each b0 space, and computed strain in the line of action along the muscle fiber directions provided by tractography. Strain in line with the fiber directions provides a quantitative map of the potential active region of the tongue during speech. Comparison between normal and ALS subjects explores the changing volume of compressing tongue tissues in speech facing the situation of muscle degradation. The proposed framework provides for the first time a dynamic map of contracting fibers in ALS speech patterns, and has the potential to provide more insight into the detrimental effects of ALS on speech.

Purpose: The aims of this article were to determine the effects of hard palate morphology and glossectomy surgery on tongue position and shape during /s/ for patients with small tumors. The first expectation was that laminal /s/ would be more prevalent in patients, than apical, due to reduced tongue tip control after surgery. The second was that patients would hold the tongue more anteriorly than controls to compensate for reduced tongue mass., Method: Three-dimensional tongue volumes were calculated from magnetic resonance imaging for the whole tongue and the portion anterior to the first molar during the /s/ in /əsuk/ for 21 controls and 14 patients. These volumes were used to calculate tongue anteriority and cross-sectional shape. Dental casts were used to measure palate perimeter, height, and width of the hard palate., Results: Palate height correlated with tongue height in controls (p < .05), but not patients. In patients, tongue anteriority correlated negatively with canine width and cross-sectional tongue shape (p < .05). Controls with a high palate favored laminal /s/. Patients preferred laminal /s/ regardless of palate height (p < .01)., Conclusions: For controls, hard palate height affected tongue height; a higher palate yielded a higher tongue. For patients, hard palate width affected tongue width; a narrower palate yielded a more anterior tongue. Tongue shape was unaffected by any palate features. Preference for /s/ showed an interaction effect between subject and palate height. Controls with high palates preferred a laminal /s/. All patients preferred a laminal /s/; glossectomy surgery may reduce tongue tip control.

Representation of human tongue motion using three-dimensional vector fields over time can be used to better understand tongue function during speech, swallowing, and other lingual behaviors. To characterize the inter-subject variability of the tongue's shape and motion of a population carrying out one of these functions it is desirable to build a statistical model of the four-dimensional (4D) tongue. In this paper, we propose a method to construct a spatio-temporal atlas of tongue motion using magnetic resonance (MR) images acquired from fourteen healthy human subjects. First, cine MR images revealing the anatomical features of the tongue are used to construct a 4D intensity image atlas. Second, tagged MR images acquired to capture internal motion are used to compute a dense motion field at each time frame using a phase-based motion tracking method. Third, motion fields from each subject are pulled back to the cine atlas space using the deformation fields computed during the cine atlas construction. Finally, a spatio-temporal motion field atlas is created to show a sequence of mean motion fields and their inter-subject variation. The quality of the atlas was evaluated by deforming cine images in the atlas space. Comparison between deformed and original cine images showed high correspondence. The proposed method provides a quantitative representation to observe the commonality and variability of the tongue motion field for the first time, and shows potential in evaluation of common properties such as strains and other tensors based on motion fields.

Purpose: Measuring tongue deformation and internal muscle motion during speech has been a challenging task because the tongue deforms in 3 dimensions, contains interdigitated muscles, and is largely hidden within the vocal tract. In this article, a new method is proposed to analyze tagged and cine magnetic resonance images of the tongue during speech in order to estimate 3-dimensional tissue displacement and deformation over time., Method: The method involves computing 2-dimensional motion components using a standard tag-processing method called harmonic phase, constructing superresolution tongue volumes using cine magnetic resonance images, segmenting the tongue region using a random-walker algorithm, and estimating 3-dimensional tongue motion using an incompressible deformation estimation algorithm., Results: Evaluation of the method is presented with a control group and a group of people who had received a glossectomy carrying out a speech task. A 2-step principal-components analysis is then used to reveal the unique motion patterns of the subjects. Azimuth motion angles and motion on the mirrored hemi-tongues are analyzed., Conclusion: Tests of the method with a various collection of subjects show its capability of capturing patient motion patterns and indicate its potential value in future speech studies.

The human tongue is composed of multiple internal muscles that work collaboratively during the production of speech. Assessment of muscle mechanics can help understand the creation of tongue motion, interpret clinical observations, and predict surgical outcomes. Although various methods have been proposed for computing the tongue's motion, associating motion with muscle activity in an interdigitated fiber framework has not been studied. In this work, we aim to develop a method that reveals different tongue muscles' activities in different time phases during speech. We use four-dimensional tagged magnetic resonance (MR) images and static high-resolution MR images to obtain tongue motion and muscle anatomy, respectively. Then we compute strain tensors and local tissue compression along the muscle fiber directions in order to reveal their shortening pattern. This process relies on the support from multiple image analysis methods, including super-resolution volume reconstruction from MR image slices, segmentation of internal muscles, tracking the incompressible motion of tissue points using tagged images, propagation of muscle fiber directions over time, and calculation of strain in the line of action, etc. We evaluated the method on a control subject and two post-glossectomy patients in a controlled speech task. The normal subject's tongue muscle activity shows high correspondence with the production of speech in different time instants, while both patients' muscle activities show different patterns from the control due to their resected tongues. This method shows potential for relating overall tongue motion to particular muscle activity, which may provide novel information for future clinical and scientific studies.

Quantitative characterization and comparison of tongue motion during speech and swallowing present fundamental challenges because of striking variations in tongue structure and motion across subjects. A reliable and objective description of the dynamics tongue motion requires the consistent integration of inter-subject variability to detect the subtle changes in populations. To this end, in this work, we present an approach to constructing an unbiased spatio-temporal atlas of the tongue during speech for the first time, based on cine-MRI from twenty two normal subjects. First, we create a common spatial space using images from the reference time frame, a neutral position, in which the unbiased spatio-temporal atlas can be created. Second, we transport images from all time frames of all subjects into this common space via the single transformation. Third, we construct atlases for each time frame via groupwise diffeomorphic registration, which serves as the initial spatio-temporal atlas. Fourth, we update the spatio-temporal atlas by realigning each time sequence based on the Lipschitz norm on diffeomorphisms between each subject and the initial atlas. We evaluate and compare different configurations such as similarity measures to build the atlas. Our proposed method permits to accurately and objectively explain the main pattern of tongue surface motion.

Dynamic MRI has been widely used to track the motion of the tongue and measure its internal deformation during speech and swallowing. Accurate segmentation of the tongue is a prerequisite step to define the target boundary and constrain the tracking to tissue points within the tongue. Segmentation of 2D slices or 3D volumes is challenging because of the large number of slices and time frames involved in the segmentation, as well as the incorporation of numerous local deformations that occur throughout the tongue during motion. In this paper, we propose a semi-automatic approach to segment 3D dynamic MRI of the tongue. The algorithm steps include seeding a few slices at one time frame, propagating seeds to the same slices at different time frames using deformable registration, and random walker segmentation based on these seed positions. This method was validated on the tongue of five normal subjects carrying out the same speech task with multi-slice 2D dynamic cine-MR images obtained at three orthogonal orientations and 26 time frames. The resulting semi-automatic segmentations of a total of 130 volumes showed an average dice similarity coefficient (DSC) score of 0.92 with less segmented volume variability between time frames than in manual segmentations., (Copyright © 2014 Elsevier Ltd. All rights reserved.)

Tongue motion during speech and swallowing involves synergies of locally deforming regions, or functional units. Motion clustering during tongue motion can be used to reveal the tongue's intrinsic functional organization. A novel matrix factorization and clustering method for tissues tracked using tagged magnetic resonance imaging (tMRI) is presented. Functional units are estimated using a graph-regularized sparse non-negative matrix factorization framework, learning latent building blocks and the corresponding weighting map from motion features derived from tissue displacements. Spectral clustering using the weighting map is then performed to determine the coherent regions--i.e., functional units--efined by the tongue motion. Two-dimensional image data is used to ver-fy that the proposed algorithm clusters the different types of images ac-urately. Three-dimensional tMRI data from five subjects carrying out simple non-speech/speech tasks are analyzed to show how the proposed approach defines a subject/task-specific functional parcellation of the tongue in localized regions.

Accurate segmentation is an important preprocessing step for measuring the internal deformation of the tongue during speech and swallowing using 3D dynamic MRI. In an MRI stack, manual segmentation of every 2D slice and time frame is time-consuming due to the large number of volumes captured over the entire task cycle. In this paper, we propose a semi-automatic segmentation workflow for processing 3D dynamic MRI of the tongue. The steps comprise seeding a few slices, seed propagation by deformable registration, random walker segmentation of the temporal stack of images and 3D super-resolution volumes. This method was validated on the tongue of two subjects carrying out the same speech task with multi-slice 2D dynamic cine-MR images obtained at three orthogonal orientations and 26 time frames. The resulting semi-automatic segmentations of 52 volumes showed an average dice similarity coefficient (DSC) score of 0.9 with reduced segmented volume variability compared to manual segmentations.

Measuring the internal muscular motion and deformation of the tongue during natural human speech is of high interest to head and neck surgeons and speech language pathologists. A pipeline for calculating 3D tongue motion from dynamic cine and tagged Magnetic Resonance (MR) images during speech has been developed. This paper presents the result of a complete analysis of eleven subjects' (seven normal controls and four glossectomy patients) global tongue motion during speech obtained through MR imaging and processed through the tongue motion analysis pipeline. The data is regularized into the same framework for comparison. A generalized two-step principal component analysis is used to show the major difference between patients' and controls' tongue motions. A test is performed to demonstrate the ability of this process to distinguish patient data from control data and to show the potential power of quantitative analysis that the tongue motion pipeline can achieve.

Understanding the deformation of the tongue during human speech is important for head and neck surgeons and speech and language scientists. Tagged magnetic resonance (MR) imaging can be used to image 2D motion, and data from multiple image planes can be combined via post-processing to yield estimates of 3D motion. However, lacking boundary information, this approach suffers from inaccurate estimates near the tongue surface. This paper describes a method that combines two sources of information to yield improved estimation of 3D tongue motion. The method uses the harmonic phase (HARP) algorithm to extract motion from tags and diffeomorphic demons to provide surface deformation. It then uses an incompressible deformation estimation algorithm to incorporate both sources of displacement information to form an estimate of the 3D whole tongue motion. Experimental results show that use of combined information improves motion estimation near the tongue surface, a problem that has previously been reported as problematic in HARP analysis, while preserving accurate internal motion estimates. Results on both normal and abnormal tongue motions are shown.

American English can be produced with two types of /s/: apical or laminal. These productions differ in that the apical gesture requires independent tongue tip elevation, and the laminal does not. Postglossectomy speakers, who have lost a unilateral portion of the tongue body along the outer edge, lose innervation to the tongue tip. We hypothesize that postglossectomy patients, even those with a preserved tongue tip, will be more likely to use laminal tongue shapes because of reduced control of the tongue tip. This study examines /s/ type, palate height, and related parameters in 24 control participants and 13 patients with lateral resections using cine-MRI and dental casts. Results of this dataset show that palate height affects choice of /s/ in control participants, but not in patients. Patients tend to use laminal /s/.

This work investigates a novel 3D multimodal deformable registration method to align high-resolution magnetic resonance imaging (MRI) with cine MRI of the tongue for better visual and motion analysis. Both modalities have different strengths to characterize and analyze the tongue structure or motion. Visual and motion analysis of combined anatomical and temporal information can synergistically improve the utility of each modality. An automated multimodal registration method is presented utilizing structural information computed from the 3D Harris operator to encode spatial and geometric cues into the computation of mutual information. The robustness and accuracy of the proposed method have been demonstrated using experiments on clinical datasets and yielded better performance compared to the conventional method and an average error comparable to the inter-observer variability.

A multi-modality image registration algorithm for the alignment of myocardial perfusion SPECT (MPS) and coronary computed tomography angiography (CTA) scans is presented in this work. Coronary CTA and MPS provides clinically complementary information in the diagnosis of coronary artery disease. An automated registration algorithm is proposed utilizing segmentation results of MPS volumes, where regions of myocardium and blood pools are extracted and used as an anatomical mask. Using a variational framework, we adopt an energy functional with a piecewise constant image model and optimize it numerically with a gradient descent algorithm. The computational efficiency and robustness of the proposed automatic registration of CTA with MPS have been demonstrated by the experiments that yielded an average error smaller than an MPS voxel size.