Real-Time Ultrasound Segmentation, Analysis and Visualisation of Deep Cervical Muscle Structure

Semi-Automatic GUI Platform to Characterize Brain Development in Preterm Children Using Ultrasound Images

The third trimester of pregnancy is the most critical period for human brain development, during which significant changes occur in the morphology of the brain. The development of sulci and gyri allows for a considerable increase in the brain surface. In preterm newborns, these changes occur in an extrauterine environment that may cause a disruption of the normal brain maturation process. We hypothesize that a normalized atlas of brain maturation with cerebral ultrasound images from birth to term equivalent age will help clinicians assess these changes. This work proposes a semi-automatic Graphical User Interface (GUI) platform for segmenting the main cerebral sulci in the clinical setting from ultrasound images. This platform has been obtained from images of a cerebral ultrasound neonatal database images provided by two clinical researchers from the Hospital Sant Joan de Déu in Barcelona, Spain. The primary objective is to provide a user-friendly design platform for clinicians for running and visualizing an atlas of images validated by medical experts. This GUI offers different segmentation approaches and pre-processing tools and is user-friendly and designed for running, visualizing images, and segmenting the principal sulci. The presented results are discussed in detail in this paper, providing an exhaustive analysis of the proposed approach's effectiveness.

SCCNet: Self-correction boundary preservation with a dynamic class prior filter for high-variability ultrasound image segmentation

The highly ambiguous nature of boundaries and similar objects is difficult to address in some ultrasound image segmentation tasks, such as neck muscle segmentation, leading to unsatisfactory performance. Thus, this paper proposes a two-stage network called SCCNet (self-correction context network) using a self-correction boundary preservation module and class-context filter to alleviate these problems. The proposed self-correction boundary preservation module uses a dynamic key boundary point (KBP) map to increase the capability of iteratively discriminating ambiguous boundary points segments, and the predicted segmentation map from one stage is used to obtain a dynamic class prior filter to improve the segmentation performance at Stage 2. Finally, three datasets, Neck Muscle, CAMUS and Thyroid, are used to demonstrate that our proposed SCCNet outperforms other state-of-the art methods, such as BPBnet, DSNnet, and RAGCnet. Our proposed network shows at least a 1.2-3.7% improvement on the three datasets, Neck Muscle, Thyroid, and CAMUS. The source code is available at https://github.com/lijixing0425/SCCNet.

Integrated Application of Low-Intensity Pulsed Ultrasound in Diagnosis and Treatment of Atrophied Skeletal Muscle Induced in Tail-Suspended Rats

Long-term exposure to microgravity leads to muscle atrophy, which is primarily characterized by a loss of muscle mass and strength and reduces one′s functional capability. A weightlessness-induced muscle atrophy model was established using the tail suspension test to evaluate the intervention or therapeutic effect of low-intensity pulsed ultrasound (LIPUS) on muscle atrophy. The rats were divided into five groups at random: the model group (B), the normal control group (NC), the sham-ultrasound control group (SUC), the LIPUS of 50 mW/cm2 radiation group (50 UR), and the LIPUS of 150 mW/cm2 radiation group (150 UR). Body weight, gastrocnemius weight, muscle force, and B-ultrasound images were used to evaluate muscle atrophy status. Results showed that the body weight, gastrocnemius weight, and image entropy of the tail suspension group were significantly lower than those of the control group (p < 0.01), confirming the presence of muscle atrophy. Although the results show that the muscle force and two weights of the rats stimulated by LIPUS are still much smaller than those of the NC group, they are significantly different from those of the pure tail suspension B group (p < 0.01). On day 14, the gastrocnemius forces of the rats exposed to 50 mW/cm2 and 150 mW/cm2 LIPUS were 150% and 165% of those in the B group. The gastrocnemius weights were both 135% of those in the B group. This suggests that ultrasound can, to a certain extent, prevent muscular atrophy.

IFSS-Net: Interactive Few-Shot Siamese Network for Faster Muscle Segmentation and Propagation in Volumetric Ultrasound

We present an accurate, fast and efficient method for segmentation and muscle mask propagation in 3D freehand ultrasound data, towards accurate volume quantification. A deep Siamese 3D Encoder-Decoder network that captures the evolution of the muscle appearance and shape for contiguous slices is deployed. We use it to propagate a reference mask annotated by a clinical expert. To handle longer changes of the muscle shape over the entire volume and to provide an accurate propagation, we devise a Bidirectional Long Short Term Memory module. Also, to train our model with a minimal amount of training samples, we propose a strategy combining learning from few annotated 2D ultrasound slices with sequential pseudo-labeling of the unannotated slices. We introduce a decremental update of the objective function to guide the model convergence in the absence of large amounts of annotated data. After training with a few volumes, the decremental update strategy switches from a weak supervised training to a few-shot setting. Finally, to handle the class-imbalance between foreground and background muscle pixels, we propose a parametric Tversky loss function that learns to penalize adaptively the false positives and the false negatives. We validate our approach for the segmentation, label propagation, and volume computation of the three low-limb muscles on a dataset of 61600 images from 44 subjects. We achieve a Dice score coefficient of over 95% and a volumetric error of 1.6035 ± 0.587%.

Automated semi-real-time detection of muscle activity with ultrasound imaging

Ultrasound imaging (USI) biofeedback is a useful therapeutic tool; however, it relies on qualitative assessment by a trained therapist, while existing automatic analysis techniques are computationally demanding. This study aims to present a computationally inexpensive algorithm based on the difference in pixel intensity between USI frames. During an offline experiment, where data was analyzed after the study, participants performed isometric contractions of the gastrocnemius medialis (GM) muscle, as executed (30% of maximum contraction) or attempted (low force contraction up to a point when the participant is aware of exerting force or contracting the muscle) movements, while USI, EMG, and force data were recorded. The algorithm achieved 99% agreement with EMG and force measurements for executed movements and 93% for attempted movements, with USI detecting 1.9% more contractions than the other methods. In the online study, participants performed GM muscle contractions at 10% and 30% of maximum contraction, while the algorithm provided visual feedback proportional to the muscle activity (based on USI recordings during the maximum contraction) in less than 3 s following each contraction. We show that the participants reached the target consistently, learning to perform precise contractions. The algorithm is reliable and computationally very efficient, allowing real-time applications on standard computing hardware. It is a suitable method for automated detection, quantification of muscle contraction, and to provide biofeedback which can be used for training of targeted muscles, making it suitable for rehabilitation.

Three-dimensional quantitative muscle ultrasound in a healthy population

INTRODUCTION/AIMS

Quantitative muscle ultrasound offers biomarkers that aid in the diagnosis, detection, and follow-up of neuromuscular disorders. At present, quantitative muscle ultrasound methods are 2D and are often operator and device dependent. The aim of this study was to combine an existing device independent method with an automated ultrasound machine and perform 3D quantitative muscle ultrasound, providing new normative data of healthy controls.

METHODS

In total, 123 healthy volunteers were included. After physical examination, 3D ultrasound scans of the tibialis anterior muscle were acquired using an automated ultrasound scanner. Image postprocessing was performed to obtain calibrated echo intensity values based on a phantom reference.

RESULTS

Tibialis anterior muscle volumes of 61.2 ± 24.1 mL and 53.7 ± 22.7 mL were scanned in males and females, respectively. Echo intensity correlated with gender**, age**, fat fraction*, histogram kurtosis**, skewness* and standard deviation** (*P < .05, **P < .01). Outcome measures did not differ significantly for different acquisition presets. The 3D quantitative muscle ultrasound revealed the non-uniformity of echo intensity values over the length of the tibialis anterior muscle.

DISCUSSION

Our method extended 2D measurements and confirmed previous findings. Our method and reported normative data of (potential) biomarkers can be used to study neuromuscular disorders.

Glass-cutting medical images via a mechanical image segmentation method based on crack propagation

Medical image segmentation is crucial in diagnosing and treating diseases, but automatic segmentation of complex images is very challenging. Here we present a method, called the crack propagation method (CPM), based on the principles of fracture mechanics. This unique method converts the image segmentation problem into a mechanical one, extracting the boundary information of the target area by tracing the crack propagation on a thin plate with grooves corresponding to the area edge. The greatest advantage of CPM is in segmenting images involving blurred or even discontinuous boundaries, a task difficult to achieve by existing auto-segmentation methods. The segmentation results for synthesized images and real medical images show that CPM has high accuracy in segmenting complex boundaries. With increasing demand for medical imaging in clinical practice and research, this method will show its unique potential.

Automatic segmentation of complex medical images is challenging. Here, the authors present a crack propagation method based on the principles of fracture mechanics: extracting the boundary information of the target area by tracing the crack propagation on a thin plate with grooves corresponding to the area edge.

LUMINOUS database: lumbar multifidus muscle segmentation from ultrasound images

BACKGROUND

Among the paraspinal muscles, the structure and function of the lumbar multifidus (LM) has become of great interest to researchers and clinicians involved in lower back pain and muscle rehabilitation. Ultrasound (US) imaging of the LM muscle is a useful clinical tool which can be used in the assessment of muscle morphology and function. US is widely used due to its portability, cost-effectiveness, and ease-of-use. In order to assess muscle function, quantitative information of the LM must be extracted from the US image by means of manual segmentation. However, manual segmentation requires a higher level of training and experience and is characterized by a level of difficulty and subjectivity associated with image interpretation. Thus, the development of automated segmentation methods is warranted and would strongly benefit clinicians and researchers. The aim of this study is to provide a database which will contribute to the development of automated segmentation algorithms of the LM.

CONSTRUCTION AND CONTENT

This database provides the US ground truth of the left and right LM muscles at the L5 level (in prone and standing positions) of 109 young athletic adults involved in Concordia University's varsity teams. The LUMINOUS database contains the US images with their corresponding manually segmented binary masks, serving as the ground truth. The purpose of the database is to enable development and validation of deep learning algorithms used for automatic segmentation tasks related to the assessment of the LM cross-sectional area (CSA) and echo intensity (EI). The LUMINOUS database is publicly available at http://data.sonography.ai .

CONCLUSION

The development of automated segmentation algorithms based on this database will promote the standardization of LM measurements and facilitate comparison among studies. Moreover, it can accelerate the clinical implementation of quantitative muscle assessment in clinical and research settings.

Targeted Achilles Tendon Training and Rehabilitation Using Personalized and Real-Time Multiscale Models of the Neuromusculoskeletal System

Musculoskeletal tissues, including tendons, are sensitive to their mechanical environment, with both excessive and insufficient loading resulting in reduced tissue strength. Tendons appear to be particularly sensitive to mechanical strain magnitude, and there appears to be an optimal range of tendon strain that results in the greatest positive tendon adaptation. At present, there are no tools that allow localized tendon strain to be measured or estimated in training or a clinical environment. In this paper, we first review the current literature regarding Achilles tendon adaptation, providing an overview of the individual technologies that so far have been used in isolation to understand in vivo Achilles tendon mechanics, including 3D tendon imaging, motion capture, personalized neuromusculoskeletal rigid body models, and finite element models. We then describe how these technologies can be integrated in a novel framework to provide real-time feedback of localized Achilles tendon strain during dynamic motor tasks. In a proof of concept application, Achilles tendon localized strains were calculated in real-time for a single subject during walking, single leg hopping, and eccentric heel drop. Data was processed at 250 Hz and streamed on a smartphone for visualization. Achilles tendon peak localized strains ranged from ∼3 to ∼11% for walking, ∼5 to ∼15% during single leg hop, and ∼2 to ∼9% during single eccentric leg heel drop, overall showing large strain variation within the tendon. Our integrated framework connects, across size scales, knowledge from isolated tendons and whole-body biomechanics, and offers a new approach to Achilles tendon rehabilitation and training. A key feature is personalization of model components, such as tendon geometry, material properties, muscle geometry, muscle-tendon paths, moment arms, muscle activation, and movement patterns, all of which have the potential to affect tendon strain estimates. Model personalization is important because tendon strain can differ substantially between individuals performing the same exercise due to inter-individual differences in these model components.

Segmentation of finger tendon and synovial sheath in ultrasound image using deep convolutional neural network

BACKGROUND

Trigger finger is a common hand disease, which is caused by a mismatch in diameter between the tendon and the pulley. Ultrasound images are typically used to diagnose this disease, which are also used to guide surgical treatment. However, background noise and unclear tissue boundaries in the images increase the difficulty of the process. To overcome these problems, a computer-aided tool for the identification of finger tissue is needed.

RESULTS

Two datasets were used for evaluation: one comprised different cases of individual images and another consisting of eight groups of continuous images. Regarding result similarity and contour smoothness, our proposed deeply supervised dilated fully convolutional DenseNet (D2FC-DN) is better than ATASM (the state-of-art segmentation method) and representative CNN methods. As a practical application, our proposed method can be used to build a tendon and synovial sheath model that can be used in a training system for ultrasound-guided trigger finger surgery.

CONCLUSION

We proposed a D2FC-DN for finger tendon and synovial sheath segmentation in ultrasound images. The segmentation results were remarkably accurate for two datasets. It can be applied to assist the diagnosis of trigger finger by highlighting the tissues and generate models for surgical training systems in the future.

METHODS

We propose a novel finger tendon segmentation method for use with ultrasound images that can also be used for synovial sheath segmentation that yields a more complete description for analysis. In this study, a hybrid of effective convolutional neural network techniques are applied, resulting in a deeply supervised dilated fully convolutional DenseNet (D2FC-DN), which displayed excellent segmentation performance on the tendon and synovial sheath.

Ultrasound imaging to assess skeletal muscle architecture during movements: a systematic review of methods, reliability, and challenges

B-mode ultrasound is often used to quantify muscle architecture during movements. Our objectives were to 1) systematically review the reliability of fascicle length (FL) and pennation angles (PA) measured using ultrasound during movements involving voluntary contractions; 2) systematically review the methods used in studies reporting reliability, discuss associated challenges, and provide recommendations to improve the reliability and validity of dynamic ultrasound measurements; and 3) provide an overview of computational approaches for quantifying fascicle architecture, their validity, agreement with manual quantification of fascicle architecture, and advantages and drawbacks. Three databases were searched until June 2019. Studies among healthy human individuals aged 17-85 yr that investigated the reliability of FL or PA in lower-extremity muscles during isoinertial movements and that were written in English were included. Thirty studies (n = 340 participants) were included for reliability analyses. Between-session reliability as measured by coefficient of multiple correlations (CMC), and coefficient of variation (CV) was FL CMC: 0.89-0.96; CV: 8.3% and PA CMC: 0.87-0.90; CV: 4.5-9.6%. Within-session reliability was FL CMC: 0.82-0.99; CV: 0.0-6.7% and PA CMC: 0.91; CV: 0.0-15.0%. Manual analysis reliability was FL CMC: 0.89-0.96; CV: 0.0-15.9%; PA CMC: 0.84-0.90; and CV: 2.0-9.8%. Computational analysis FL CMC was 0.82-0.99, and PA CV was 14.0-15.0%. Eighteen computational approaches were identified, and these generally showed high agreement with manual analysis and high validity compared with phantoms or synthetic images. B-mode ultrasound is a reliable method to quantify fascicle architecture during movement. Additionally, computational approaches can provide a reliable and valid estimation of fascicle architecture.

Estimation of absolute states of human skeletal muscle via standard B-mode ultrasound imaging and deep convolutional neural networks

The objective is to test automated in vivo estimation of active and passive skeletal muscle states using ultrasonic imaging. Current technology (electromyography, dynamometry, shear wave imaging) provides no general, non-invasive method for online estimation of skeletal muscle states. Ultrasound (US) allows non-invasive imaging of muscle, yet current computational approaches have never achieved simultaneous extraction or generalization of independently varying active and passive states. We use deep learning to investigate the generalizable content of two-dimensional (2D) US muscle images. US data synchronized with electromyography of the calf muscles, with measures of joint moment/angle, were recorded from 32 healthy participants (seven female; ages: 27.5, 19–65). We extracted a region of interest of medial gastrocnemius and soleus using our prior developed accurate segmentation algorithm. From the segmented images, a deep convolutional neural network was trained to predict three absolute, drift-free components of the neurobiomechanical state (activity, joint angle, joint moment) during experimentally designed, simultaneous independent variation of passive (joint angle) and active (electromyography) inputs. For all 32 held-out participants (16-fold cross-validation) the ankle joint angle, electromyography and joint moment were estimated to accuracy 55 ± 8%, 57 ± 11% and 46 ± 9%, respectively. With 2D US imaging, deep neural networks can encode, in generalizable form, the activity–length–tension state relationship of these muscles. Observation-only, low-power 2D US imaging can provide a new category of technology for non-invasive estimation of neural output, length and tension in skeletal muscle. This proof of principle has value for personalized muscle assessment in pain, injury, neurological conditions, neuropathies, myopathies and ageing.

Objective Analysis of Neck Muscle Boundaries for Cervical Dystonia Using Ultrasound Imaging and Deep Learning

OBJECTIVE

To provide objective visualization and pattern analysis of neck muscle boundaries to inform and monitor treatment of cervical dystonia.

METHODS

We recorded transverse cervical ultrasound (US) images and whole-body motion analysis of sixty-one standing participants (35 cervical dystonia, 26 age matched controls). We manually annotated 3,272 US images sampling posture and the functional range of pitch, yaw, and roll head movements. Using previously validated methods, we used 60-fold cross validation to train, validate and test a deep neural network (U-net) to classify pixels to 13 categories (five paired neck muscles, skin, ligamentum nuchae, vertebra). For all participants for their normal standing posture, we segmented US images and classified condition (Dystonia/Control), sex and age (higher/lower) from segment boundaries. We performed an explanatory, visualization analysis of dystonia muscle-boundaries.

RESULTS

For all segments, agreement with manual labels was Dice Coefficient (64 ± 21%) and Hausdorff Distance (5.7 ± 4 mm). For deep muscle layers, boundaries predicted central injection sites with average precision 94 ± 3%. Using leave-one-out cross-validation, a support-vector-machine classified condition, sex, and age from predicted muscle boundaries at accuracy 70.5%, 67.2%, 52.4% respectively, exceeding classification by manual labels. From muscle boundaries, Dystonia clustered optimally into three sub-groups. These sub-groups are visualized and explained by three eigen-patterns which correlate significantly with truncal and head posture.

CONCLUSION

Using US, neck muscle shape alone discriminates dystonia from healthy controls.

SIGNIFICANCE

Using deep learning, US imaging allows online, automated visualization, and diagnostic analysis of cervical dystonia and segmentation of individual muscles for targeted injection.

Paraspinal Muscle Segmentation Based on Deep Neural Network

The accurate segmentation of the paraspinal muscle in Magnetic Resonance (MR) images is a critical step in the automated analysis of lumbar diseases such as chronic low back pain, disc herniation and lumbar spinal stenosis. However, the automatic segmentation of multifidus and erector spinae has not yet been achieved due to three unusual challenges: (1) the muscle boundary is unclear; (2) the gray histogram distribution of the target overlaps with the background; (3) the intra- and inter-patient shape is variable. We propose to tackle the problem of the automatic segmentation of paravertebral muscles using a deformed U-net consisting of two main modules: the residual module and the feature pyramid attention (FPA) module. The residual module can directly return the gradient while preserving the details of the image to make the model easier to train. The FPA module fuses different scales of context information and provides useful salient features for high-level feature maps. In this paper, 120 cases were used for experiments, which were provided and labeled by the spine surgery department of Shengjing Hospital of China Medical University. The experimental results show that the model can achieve higher predictive capability. The dice coefficient of the multifidus is as high as 0.949, and the Hausdorff distance is 4.62 mm. The dice coefficient of the erector spinae is 0.913 and the Hausdorff distance is 7.89 mm. The work of this paper will contribute to the development of an automatic measurement system for paraspinal muscles, which is of great significance for the treatment of spinal diseases.

Application of MR-derived cross-sectional guideline of cervical spine muscles to validate neck surface electromyography placement

The importance of surface-EMG placement for development and interpretation of EMG-assisted biomechanical models is well established. Since MR has become a reliable noninvasive cervical spine musculoskeletal diagnostic tool, this investigation attempted to illustrate the anatomical relationships of individual cervical spine muscles with their paired surface-EMG electrodes. The secondary purpose of this investigation was to provide an MR cross-sectional pictorial and descriptive guideline of the cervical spine musculature. MR scans were performed on a healthy adult male subject from skull to manubrium of the sternum. Prior to scanning, MR safe markers were placed over neck muscles following surface EMG placement recommendations. Twenty-three neck muscles were traced manually in each of 267 scan slices. 3-D models of the neck musculoskeletal structure were constructed to aid with understanding the complex anatomy of the region as well as to identify correct EMG electrode locations and to identify muscles' curved lines-of-action. 3D models of the MR-safe markers were constructed relative to the target muscles. Based on the findings of this study, muscle palpation and bony landmarks can be used to effectively identify appropriate surface EMG electrode locations to record upper trapezius, middle trapezius, semispinalis capitis, splenius capitis, levator scapulae, scalenus, sternocleidomastoid and hyoid muscles activities.

Working towards an objective segmental assessment of trunk control in children with cerebral palsy

BACKGROUND

Physical therapy evaluations of motor control are currently based on subjective clinical assessments. Despite validation, these can still be inconsistent between therapists and between clinics, compromising the process of validating a therapeutic intervention and the subsequent generation of evidence-based practice (EBP) guidelines. EBP benefits from well-defined objective measurements that complement existing subjective assessments.

RESEARCH QUESTION

The aim of this study was to develop an objective measure of head/trunk control in children with Cerebral Palsy (CP) using previously developed video-based methods of head/trunk alignment and absence of external support and compare these with the existing subjective Segmental Assessment of Trunk Control (SATCo).

METHODS

Twelve children with CP were recruited and an average of 3 (±1.1) SATCo tests performed per child. The full SATCo was concurrently video-recorded from a sagittal view; markers were placed on specific landmarks of the head, trunk and pelvis to track and estimate head/trunk segment position. A simplified objective rule was created for control and used on videos showing no external support. This replicated the clinical parameters and enabled identification of the segmental-loss-of-control. The subjectively and objectively identified segmental-loss-of-control were compared using a Pearson Correlation Coefficient.

RESULTS

An angular-threshold of 17° from alignment showed the minimum bias between the subjectively and the objectively measured segmental-loss-of-control (mean error =-0.11 and RMSE = 1.5) and a significant correlation (r = 0.78, r² = 0.61, p < .01).

SIGNIFICANCE

This study showed that simple objective video-based measurements can be used to reconstruct the subjective assessment of segmental head/trunk control. This suggests that a clinically-friendly video-based objective measure has future potential to complement subjective assessments and to assist in the generation of EBP guidelines. Further development will increase the information that can be extracted from video images and enable generation of a fully automated objective measure.

Proactive Selective Inhibition Targeted at the Neck Muscles: This Proximal Constraint Facilitates Learning and Regulates Global Control

While individual muscle function is known, the sensory and motor value of muscles within the whole-body sensorimotor network is complicated. Specifically, the relationship between neck muscle action and distal muscle synergies is unknown. This work demonstrates a causal relationship between regulation of the neck muscles and global motor control. Studying violinists performing unskilled and skilled manual tasks, we provided ultrasound feedback of the neck muscles with instruction to minimize neck muscle change during task performance and observed the indirect effect on whole-body movement. Analysis of ultrasound, kinematic, electromyographic and electrodermal recordings showed that proactive inhibition targeted at neck muscles had an indirect global effect reducing the cost of movement, reducing complex involuntary, task-irrelevant movement patterns and improving balance. This effect was distinct from the effect of gaze alignment which increased physiological cost and reduced laboratory-referenced movement. Neck muscle inhibition imposes a proximal constraint on the global motor plan, forcing a change in highly automated sensorimotor control. The proximal location ensures global influence. The criterion, inhibition of unnecessary action, ensures reduced cost while facilitating task-relevant variation. This mechanism regulates global motor function and facilitates reinforcement learning to change engrained, maladapted sensorimotor control associated with chronic pain, injury and performance limitation.