Tongue contour tracking in dynamic ultrasound via higher-order MRFs and efficient fusion moves

Analyses of the human tongue motion as captured from 2D dynamic ultrasound data often requires segmentation of the mid-sagittal tongue contours. However, semi-automatic extraction of the tongue shape presents practical challenges. We approach this segmentation problem by proposing a novel higher-order Markov random field energy minimization framework. For efficient energy minimization, we propose two novel schemes to sample the solution space efficiently. To cope with the unpredictable tongue motion dynamics, we also propose to temporally adapt regularization based on contextual information. Unlike previous methods, we employ the latest optimization techniques to solve the tracking problem under one unified framework. Our method was validated on a set of 63 clinical data sequences, which allowed for comparative analyses with three other competing methods. Experimental results demonstrate that our method can segment sequences containing over 500 frames with mean accuracy of 3 mm, approaching the accuracy of manual segmentations created by trained clinical observers.     

A computational approach to calculate personalized pennation angle based on MRI: effect on motion analysis

Purpose

Muscles are the primary component responsible for the locomotion and change of posture of the human body. The physiologic basis of muscle force production and movement is determined by the muscle architecture (maximum muscle force, \(F_\mathrm{o}^\mathrm{m}\), optimal muscle fiber length, \(l_\mathrm{o}^\mathrm{m}\), tendon slack length, \(l_\mathrm{s}^\mathrm{t}\), and pennation angle at optimal muscle fiber length, \(\varphi _{0}\)). The pennation angle is related to the maximum force production and to the range of motion. The aim of this study was to investigate a computational approach to calculate subject-specific pennation angle from magnetic resonance images (MRI)-based 3D anatomical model and to determine the impact of this approach on the motion analysis with personalized musculoskeletal models.

Methods

A 3D method that calculates the pennation angle using MRI was developed. The fiber orientations were automatically computed, while the muscle line of action was determined using approaches based on anatomical landmarks and on centroids of image segmentation. Three healthy male volunteers were recruited for MRI scanning and motion capture acquisition. This work evaluates the effect of subject-specific pennation angle as musculoskeletal parameter in the lower limb, focusing on the quadriceps group. A comparison was made for assessing the contribution of personalized models on motion analysis. Gait and deep squat were analyzed using neuromuscular simulations (OpenSim).

Results

The results showed variation of the pennation angle between the generic and subject-specific models, demonstrating important interindividual differences, especially for the vastus intermedius and vastus medialis muscles. The pennation angle variation between personalized and generic musculoskeletal models generated significant variation in muscle moments and forces during dynamic motion analysis.

Conclusions

A MRI-based approach to define subject-specific pennation angle was proposed and evaluated in motion analysis models. The significant differences obtained for the moments and muscle forces in quadriceps muscles indicate that a personalized approach in modeling the pennation angle can provide more individual details when investigating motion behaviors in specific subjects.

     

Subject-specific functional localizers increase sensitivity and functional resolution of multi-subject analyses

One important goal of cognitive neuroscience is to discover and explain properties common to all human brains. The traditional solution for comparing functional activations across brains in fMRI is to align each individual brain to a template brain in a Cartesian coordinate system (e.g., the Montreal Neurological Institute template). However, inter-individual anatomical variability leads to decreases in sensitivity (ability to detect a significant activation when it is present) and functional resolution (ability to discriminate spatially adjacent but functionally different neural responses) in group analyses. Subject-specific functional localizers have been previously argued to increase the sensitivity and functional resolution of fMRI analyses in the presence of inter-subject variability in the locations of functional activations (e.g., Brett et al., 2002; Fedorenko and Kanwisher, 2009, 2011; Fedorenko et al., 2010; Kanwisher et al., 1997; Saxe et al., 2006). In the current paper we quantify this dependence of sensitivity and functional resolution on functional variability across subjects in order to illustrate the highly detrimental effects of this variability on traditional group analyses. We show that analyses that use subject-specific functional localizers usually outperform traditional group-based methods in both sensitivity and functional resolution, even when the same total amount of data is used for each analysis. We further discuss how the subject-specific functional localization approach, which has traditionally only been considered in the context of ROI-based analyses, can be extended to whole-brain voxel-based analyses. We conclude that subject-specific functional localizers are particularly well suited for investigating questions of functional specialization in the brain. An SPM toolbox that can perform all of the analyses described in this paper is publicly available, and the analyses can be applied retroactively to any dataset, provided that multiple runs were acquired per subject, even if no explicit "localizer" task was included.     

CMC-Net: 3D calf muscle compartment segmentation with sparse annotation

Accurate 3D segmentation of calf muscle compartments in volumetric MR images is essential to diagnose as well as assess progression of muscular diseases. Recently, good segmentation performance was achieved using state-of-the-art deep learning approaches, which, however, require large amounts of annotated data for training. Considering that obtaining sufficiently large medical image annotation datasets is often difficult, time-consuming, and requires expert knowledge, minimizing the necessary sizes of expert-annotated training datasets is of great importance. This paper reports CMC-Net, a new deep learning framework for calf muscle compartment segmentation in 3D MR images that selects an effective small subset of 2D slices from the 3D images to be labelled, while also utilizing unannotated slices to facilitate proper generalization of the subsequent training steps. Our model consists of three parts: (1) an unsupervised method to select the most representative 2D slices on which expert annotation is performed; (2) ensemble model training employing these annotated as well as additional unannotated 2D slices; (3) a model-tuning method using pseudo-labels generated by the ensemble model that results in a trained deep network capable of accurate 3D segmentations. Experiments on segmentation of calf muscle compartments in 3D MR images show that our new approach achieves good performance with very small annotation ratios, and when utilizing full annotation, it outperforms state-of-the-art full annotation segmentation methods. Additional experiments on a 3D MR thigh dataset further verify the ability of our method in segmenting leg muscle groups with sparse annotation.     

Constrained nonnegative matrix factorization and hyperspectral image dimensionality reduction

This letter presents a constrained nonnegative matrix factorization (NMF)-based method for hyperspectral image dimensionality reduction. The proposed method combines the NMF and Laplacian Eigenmaps (LE). It overcomes the drawback that NMF does not consider the intrinsic geometric structure of the data space. In LE framework, an affinity graph is constructed to encode the geometrical information. The proposed technique seeks a matrix factorization which considers the graph structure. We also use the smoothness constraint and the sparsity constraint on the lower dimensional matrices. The gradient descent approach is used to find solution of the proposed model. In order to evaluate the developed method, we use the support vector machine and the k-nearest neighbourhood (KNN) approach for hyperspectral image classification. Experiments are done on a hyperspectral image. The results are compared with those obtained using other hyperspectal image dimensionality reduction methods. The classification accuracy using the proposed method is higher than that of the alternative approaches.     

90例功能性语音障碍患者发音特点分析

目的了解功能性语音障碍的发音错误特点，为此类患者的治疗提供指导。方法对90例功能性语音障碍患者按发音语音学规则进行分类，找出各类发音错误发生的规律。结果90例功能性语音障碍分类如下：非送气化、腭化、侧化、舌前音化、舌后音化、声门停顿音、辅音省略、塞音化、塞擦音化及舌后音化鼻腔构音。其中舌后音化鼻腔构音仅发生在舌尖边音l，非送气化错误主要发生在送气性塞音、塞擦音(p、t、k、q、c、ch等)。结论功能性语音障碍发生错误主要累及音节中的辅音，不同类型的发音错误，其辅音受累情况有一定的规律。     

Independent component analysis of fMRI group studies by self-organizing clustering

Independent component analysis (ICA) is a valuable technique for the multivariate data-driven analysis of functional magnetic resonance imaging (fMRI) data sets. Applications of ICA have been developed mainly for single subject studies, although different solutions for group studies have been proposed. These approaches combine data sets from multiple subjects into a single aggregate data set before ICA estimation and, thus, require some additional assumptions about the separability across subjects of group independent components. Here, we exploit the application of similarity measures and a related visual tool to study the natural self-organizing clustering of many independent components from multiple individual data sets in the subject space. Our proposed framework flexibly enables multiple criteria for the generation of group independent components and their random-effects evaluation. We present real visual activation fMRI data from two experiments, with different spatiotemporal structures, and demonstrate the validity of this framework for a blind extraction and selection of meaningful activity and functional connectivity group patterns. Our approach is either alternative or complementary to the group ICA of aggregated data sets in that it exploits commonalities across multiple subject-specific patterns, while addressing as much as possible of the intersubject variability of the measured responses. This property is particularly of interest for a blind group and subgroup pattern extraction and selection.     

Measurement of infant tongue thickness using ultrasound: a technical note

Novel uses of ultrasound include obtaining images of intra-oral structures to further research in speech production and feeding. In this technical note we describe a noninvasive, cost-effective, and reliable method for measuring infant tongue muscle thickness. The current pilot study demonstrates high reliability of a trained ultrasonographer to obtain adequate images of the infant tongue and the ability to measure reliably between two anatomic landmarks to determine tongue thickness and investigate a potential relationship between tongue size and tongue force.     

Refining the benefit-risk framework for the assessment of medicines: valuing and weighting benefit and risk parameters

A common framework is necessary for the transparent articulation of the benefits and risks of a therapeutic product across disparate stakeholders. The assignment of value and weighting to each component parameter presents challenges deriving from different stakeholder objectives, methods, and perspectives. Building on prior experiences with a validated framework approach, this forum focused on identifying challenges and approaches to the assignment of values and weightings using a case study applied to a hypothetical medicinal product.     

Strategies for block-design fMRI experiments during task-related motion of structures of the oral cavity

Functional MRI (fMRI) studies of jaw motion, speech, and swallowing disorders have been hampered by motion artifacts. Tissue motion perturbs the static magnetic field, creating geometric distortions in echo-planar images that lead to many false positives in activation maps. These problems have restricted blood oxygenation level-dependent (BOLD) fMRI studies involving orofacial muscles to event-related designs, which offer weak contrast-to-noise ratios when compared to block designs. Two new approaches are described that greatly reduce false positives in the activation maps created by the distortions in block-design fMRI studies involving jaw and tongue motion during chewing. First, an appropriate task duration of 10-14 s was found to maximize functional contrast while minimizing motion artifacts. Second, three motion-sensitive postprocessing methods were applied successively to examine the temporal and spatial characteristics of responses and identify and remove false positives caused by motion artifacts. These techniques are shown to allow the use of block design in an fMRI study of a jaw motion task. Extension to speech and swallowing tasks is discussed.     

Grayscale self-adjusting network with weak feature enhancement for 3D lumbar anatomy segmentation

The automatic segmentation of lumbar anatomy is a fundamental problem for the diagnosis and treatment of lumbar disease. The recent development of deep learning techniques has led to remarkable progress in this task, including the possible segmentation of nerve roots, intervertebral discs, and dural sac in a single step. Despite these advances, lumbar anatomy segmentation remains a challenging problem due to the weak contrast and noise of input images, as well as the variability of intensities and size in lumbar structures across different subjects. To overcome these challenges, we propose a coarse-to-fine deep neural network framework for lumbar anatomy segmentation, which obtains a more accurate segmentation using two strategies. First, a progressive refinement process is employed to correct low-confidence regions by enhancing the feature representation in these regions. Second, a grayscale self-adjusting network (GSA-Net) is proposed to optimize the distribution of intensities dynamically. Experiments on datasets comprised of 3D computed tomography (CT) and magnetic resonance (MR) images show the advantage of our method over current segmentation approaches and its potential for diagnosing and lumbar disease treatment.     

Kraniomandibuläre Dysfunktion bei Kindern mit Funktionsstörungen im zervikookzipitalen Übergang

The presence of a cross or overbite, teeth grinding and pressing, myofunctional disorders, a deviation in the resting tongue position, sucking habits, jaw pain or headaches, postural disorders, and migraine in children may be first predictors of juvenile craniomandibular disorders (CMD). The cause is usually found in a deviation of postural control development in early childhood. Particularly functional disorders in the upper cervical region can influence jaw position. Already in the first few months of life, the course is set for further development—with effects on the entire body, e.?g., altered statics or non-physiological coordination. The most common postural deficits associated with muscular CMD in children are a forward head posture, hyperlordosis, and genu valgum, as well as scoliosis with uneven shoulders in patients with midline deviations. Children benefit from manual medical therapies, neurofunctional training, speech therapy, and a lot of exercise.     

Region of interest based analysis of functional imaging data

fMRI analysis techniques are presented that test functional hypotheses at the region of interest (ROI) level. An SPM-compatible Matlab toolbox has been developed that allows the creation of subject-specific ROI masks based on anatomical markers and the testing of functional hypotheses on the regional response using multivariate time-series analysis techniques. The combined application of subject-specific ROI definition and region-level functional analysis is shown to appropriately compensate for intersubject anatomical variability, offering finer localization and increased sensitivity to task-related effects than standard techniques based on whole-brain normalization and voxel or cluster-level functional analysis, while providing a more direct link between discrete brain region hypotheses and the statistical analyses used to test them.     

Rethinking medical image reconstruction via shape prior,going deeper and faster: Deep joint indirect registration and reconstruction

Indirect image registration is a promising technique to improve image reconstruction quality by providing a shape prior for the reconstruction task. In this paper, we propose a novel hybrid method that seeks to reconstruct high quality images from few measurements whilst requiring low computational cost. With this purpose, our framework intertwines indirect registration and reconstruction tasks is a single functional. It is based on two major novelties. Firstly, we introduce a model based on deep nets to solve the indirect registration problem, in which the inversion and registration mappings are recurrently connected through a fixed-point interaction based sparse optimisation. Secondly, we introduce specific inversion blocks, that use the explicit physical forward operator, to map the acquired measurements to the image reconstruction. We also introduce registration blocks based deep nets to predict the registration parameters and warp transformation accurately and efficiently. We demonstrate, through extensive numerical and visual experiments, that our framework outperforms significantly classic reconstruction schemes and other bi-task method; this in terms of both image quality and computational time. Finally, we show generalisation capabilities of our approach by demonstrating their performance on fast Magnetic Resonance Imaging (MRI), sparse view computed tomography (CT) and low dose CT with measurements much below the Nyquist limit.     

Slic-Seg: A minimally interactive segmentation of the placenta from sparse and motion-corrupted fetal MRI in multiple views

Segmentation of the placenta from fetal MRI is challenging due to sparse acquisition, inter-slice motion, and the widely varying position and shape of the placenta between pregnant women. We propose a minimally interactive framework that combines multiple volumes acquired in different views to obtain accurate segmentation of the placenta. In the first phase, a minimally interactive slice-by-slice propagation method called Slic-Seg is used to obtain an initial segmentation from a single motion-corrupted sparse volume image. It combines high-level features, online Random Forests and Conditional Random Fields, and only needs user interactions in a single slice. In the second phase, to take advantage of the complementary resolution in multiple volumes acquired in different views, we further propose a probability-based 4D Graph Cuts method to refine the initial segmentations using inter-slice and inter-image consistency. We used our minimally interactive framework to examine the placentas of 16 mid-gestation patients from MRI acquired in axial and sagittal views respectively. The results show the proposed method has 1) a good performance even in cases where sparse scribbles provided by the user lead to poor results with the competitive propagation approaches; 2) a good interactivity with low intra- and inter-operator variability; 3) higher accuracy than state-of-the-art interactive segmentation methods; and 4) an improved accuracy due to the co-segmentation based refinement, which outperforms single volume or intensity-based Graph Cuts.     

DeepStroke: An efficient stroke screening framework for emergency rooms with multimodal adversarial deep learning

In an emergency room (ER) setting, stroke triage or screening is a common challenge. A quick CT is usually done instead of MRI due to MRI’s slow throughput and high cost. Clinical tests are commonly referred to during the process, but the misdiagnosis rate remains high. We propose a novel multimodal deep learning framework, DeepStroke, to achieve computer-aided stroke presence assessment by recognizing patterns of minor facial muscles incoordination and speech inability for patients with suspicion of stroke in an acute setting. Our proposed DeepStroke takes one-minute facial video data and audio data readily available during stroke triage for local facial paralysis detection and global speech disorder analysis. Transfer learning was adopted to reduce face-attribute biases and improve generalizability. We leverage a multi-modal lateral fusion to combine the low- and high-level features and provide mutual regularization for joint training. Novel adversarial training is introduced to obtain identity-free and stroke-discriminative features. Experiments on our video-audio dataset with actual ER patients show that DeepStroke outperforms state-of-the-art models and achieves better performance than both a triage team and ER doctors, attaining a 10.94% higher sensitivity and maintaining 7.37% higher accuracy than traditional stroke triage when specificity is aligned. Meanwhile, each assessment can be completed in less than six minutes, demonstrating the framework’s great potential for clinical translation.     

成年功能性构音障碍患者的语音训练及临床特点分析

目的探讨成年功能性构音障碍（FAD）患者的临床特点与语音训练方法。 方法对37例成年FAD患者进行语音评估,分析其临床特点并进行针对性的语音训练。 结果37例成年FAD患者主要的构音错误类型为置换、歪曲,其次为脱落。构音错误方式有舌前音化（19例）、非送气化（11例）、侧化构音（10例）、舌后音化（7例）、辅音脱落（7例）、混合型（4例）、唇齿音化（3例）、舌面音化（2例）。经过1～5个疗程的语音训练,28例治愈,8例好转,1例无效,训练后的语音清晰度测定值［（91.22±10.10）%］较训练前［（56.03±14.71）%］提高,差异有统计学意义（P<0.05）。 结论成年FAD患者主要的构音错误类型是置换和歪曲,基于构音错误方式开展针对性语音训练是治疗成年FAD的有效措施。     

Rigid motion invariant statistical shape modeling based on discrete fundamental forms: Data from the osteoarthritis initiative and the Alzheimer’s disease neuroimaging initiative

We present a novel approach for nonlinear statistical shape modeling that is invariant under Euclidean motion and thus alignment-free. By analyzing metric distortion and curvature of shapes as elements of Lie groups in a consistent Riemannian setting, we construct a framework that reliably handles large deformations. Due to the explicit character of Lie group operations, our non-Euclidean method is very efficient allowing for fast and numerically robust processing. This facilitates Riemannian analysis of large shape populations accessible through longitudinal and multi-site imaging studies providing increased statistical power. Additionally, as planar configurations form a submanifold in shape space, our representation allows for effective estimation of quasi-isometric surfaces flattenings. We evaluate the performance of our model w.r.t. shape-based classification of hippocampus and femur malformations due to Alzheimer’s disease and osteoarthritis, respectively. In particular, we outperform state-of-the-art classifiers based on geometric deep learning as well as statistical shape modeling especially in presence of sparse training data. To provide insight into the model’s ability of capturing biological shape variability, we carry out an analysis of specificity and generalization ability.     

Statistically-driven 3D fiber reconstruction and denoising from multi-slice cardiac DTI using a Markov random field model

The construction of subject-specific dense and realistic 3D meshes of the myocardial fibers is an important pre-requisite for the simulation of cardiac electrophysiology and mechanics. Current diffusion tensor imaging (DTI) techniques, however, provide only a sparse sampling of the 3D cardiac anatomy based on a limited number of 2D image slices. Moreover, heart motion affects the diffusion measurements, thus resulting in a significant amount of noisy fibers. This paper presents a Markov random field (MRF) approach for dense reconstruction of 3D cardiac fiber orientations from sparse DTI 2D slices. In the proposed MRF model, statistical constraints are used to relate the missing and the known fibers, while a consistency term is encoded to ensure that the obtained 3D meshes are locally continuous. The validation of the method using both synthetic and real DTI datasets demonstrates robust fiber reconstruction and denoising, as well as physiologically meaningful estimations of cardiac electrical activation.     

Deep low-Rank plus sparse network for dynamic MR imaging

In dynamic magnetic resonance (MR) imaging, low-rank plus sparse (L+S) decomposition, or robust principal component analysis (PCA), has achieved stunning performance. However, the selection of the parameters of L+S is empirical, and the acceleration rate is limited, which are common failings of iterative compressed sensing MR imaging (CS-MRI) reconstruction methods. Many deep learning approaches have been proposed to address these issues, but few of them use a low-rank prior. In this paper, a model-based low-rank plus sparse network, dubbed L+S-Net, is proposed for dynamic MR reconstruction. In particular, we use an alternating linearized minimization method to solve the optimization problem with low-rank and sparse regularization. Learned soft singular value thresholding is introduced to ensure the clear separation of the L component and S component. Then, the iterative steps are unrolled into a network in which the regularization parameters are learnable. We prove that the proposed L+S-Net achieves global convergence under two standard assumptions. Experiments on retrospective and prospective cardiac cine datasets show that the proposed model outperforms state-of-the-art CS and existing deep learning methods and has great potential for extremely high acceleration factors (up to $24\times$).