Estimating Full Regional Skeletal Muscle Fibre Orientation from B-Mode Ultrasound Images Using Convolutional, Residual, and Deconvolutional Neural Networks

Dual-input robust diagnostics for railway point machines via audio signals

Railway Point Machine (RPM) is a fundamental component of railway infrastructure and plays a crucial role in ensuring the safe operation of trains. Its primary function is to divert trains from one track to another, enabling connections between different lines and facilitating route selection. By judiciously deploying turnouts, railway systems can provide efficient transportation services while ensuring the safety of passengers and cargo. As signal processing technologies develop rapidly, taking the easy acquisition advantages of audio signals, a fault diagnosis method for RPMs is proposed by considering noise and multi-channel signals. The proposed method consists of several stages. Initially, the signal is subjected to pre-processing steps, including cropping and channel separation. Subsequently, the signal undergoes noise addition using the Random Length and Dynamic Position Noises Superposition (RDS) module, followed by conversion to a greyscale image. To enhance the data, Synthetic Minority Oversampling Technique (SMOTE) module is applied. Finally, the training data is fed into a Dual-input Attention Convolutional Neural Network (DIACNN). By employing various experimental techniques and designing diverse datasets, our proposed method demonstrates excellent robustness and achieves an outstanding classification accuracy of 99.73%.

Clinical Applications, Challenges, and Recommendations for Artificial Intelligence in Musculoskeletal and Soft-Tissue Ultrasound: AJR Expert Panel Narrative Review

Artificial intelligence (AI) is increasingly used in clinical practice for musculoskeletal imaging tasks, such as disease diagnosis and image reconstruction. AI applications in musculoskeletal imaging have focused primarily on radiography, CT, and MRI. Although musculoskeletal ultrasound stands to benefit from AI in similar ways, such applications have been relatively underdeveloped. In comparison with other modalities, ultrasound has unique advantages and disadvantages that must be considered in AI algorithm development and clinical translation. Challenges in developing AI for musculoskeletal ultrasound involve both clinical aspects of image acquisition and practical limitations in image processing and annotation. Solutions from other radiology subspecialties (e.g., crowdsourced annotations coordinated by professional societies), along with use cases (most commonly rotator cuff tendon tears and palpable soft-tissue masses), can be applied to musculoskeletal ultrasound to help develop AI. To facilitate creation of high-quality imaging datasets for AI model development, technologists and radiologists should focus on increasing uniformity in musculoskeletal ultrasound performance and increasing annotations of images for specific anatomic regions. This Expert Panel Narrative Review summarizes available evidence regarding AI's potential utility in musculoskeletal ultrasound and challenges facing its development. Recommendations for future AI advancement and clinical translation in musculoskeletal ultrasound are discussed.

Fully Automated Analysis of Muscle Architecture from B-Mode Ultrasound Images with DL_Track_US

OBJECTIVE

B-mode ultrasound can be used to image musculoskeletal tissues, but one major bottleneck is analyses of muscle architectural parameters (i.e., muscle thickness, pennation angle and fascicle length), which are most often performed manually.

METHODS

In this study we trained two different neural networks (classic U-Net and U-Net with VGG16 pre-trained encoder) to detect muscle fascicles and aponeuroses using a set of labeled musculoskeletal ultrasound images. We determined the best-performing model based on intersection over union and loss metrics. We then compared neural network predictions on an unseen test set with those obtained via manual analysis and two existing semi/automated analysis approaches (simple muscle architecture analysis [SMA] and UltraTrack). DL_Track_US detects the locations of the superficial and deep aponeuroses, as well as multiple fascicle fragments per image.

RESULTS

For single images, DL_Track_US yielded results similar to those produced by a non-trainable automated method (SMA; mean difference in fascicle length: 5.1 mm) and human manual analysis (mean difference: -2.4 mm). Between-method differences in pennation angle were within 1.5°, and mean differences in muscle thickness were less than 1 mm. Similarly, for videos, there was overlap between the results produced with UltraTrack and DL_Track_US, with intraclass correlations ranging between 0.19 and 0.88.

CONCLUSION

DL_Track_US is fully automated and open source and can estimate fascicle length, pennation angle and muscle thickness from single images or videos, as well as from multiple superficial muscles. We also provide a user interface and all necessary code and training data for custom model development.

Automatic extraction and measurement of ultrasonic muscle morphological parameters based on multi-stage fusion and segmentation

BACKGROUND

Estimating skeletal muscle force output and structure requires measurement of morphological parameters including muscle thickness, pennation angle, and fascicle length. The identification of aponeurosis and muscle fascicles from medical images is required to measure these parameters accurately.

METHODS

This paper introduces a multi-stage fusion and segmentation model (named MSF-Net), to precisely extract muscle aponeurosis and fascicles from ultrasound images. The segmentation process is divided into three stages of feature fusion modules. A prior feature fusion module (PFFM) is designed in the first stage to fuse prior features, thus enabling the network to focus on the region of interest and eliminate image noise. The second stage involves the addition of multi-scale feature fusion module (MS-FFM) for effective fusion of elemental information gathered from different scales. This process enables the precise extraction of muscle fascicles of varied sizes. Finally, the high-low-level feature fusion attention module (H-LFFAM) is created in the third stage to selectively reinforce features containing useful information.

RESULTS

Our proposed MSF-Net outperforms other methods and achieves the highest evaluation metrics. In addition, MSF-Net can obtain similar results to manual measurements by clinical experts. The mean deviation of muscle thickness and fascicle length was 0.18 mm and 1.71 mm, and the mean deviation of pennation angle was 0.31°.

CONCLUSIONS

MSF-Net can accurately extract muscle morphological parameters, which enables medical experts to evaluate muscle morphology and function, and guide rehabilitation training. Therefore, MSF-Net provides a complementary imaging tool for clinical assessment of muscle structure and function.

Quantitative Muscle Fascicle Tractography Using Brightness-Mode Ultrasound

A muscle's architecture, defined as the geometric arrangement of its fibers with respect to its mechanical line of action, impacts its abilities to produce force and shorten or lengthen under load. Ultrasound and other noninvasive imaging methods have contributed significantly to our understanding of these structure-function relationships. The goal of this work was to develop a MATLAB toolbox for tracking and mathematically representing muscle architecture at the fascicle scale, based on brightness-mode ultrasound imaging data. The MuscleUS_Toolbox allows user-performed segmentation of a region of interest and automated modeling of local fascicle orientation; calculation of streamlines between aponeuroses of origin and insertion; and quantification of fascicle length, pennation angle, and curvature. A method is described for optimizing the fascicle orientation modeling process, and the capabilities of the toolbox for quantifying and visualizing fascicle architecture are illustrated in the human tibialis anterior muscle. The toolbox is freely available.

Full Spatial Muscle Fiber Orientation Estimation From Ultrasound Images Using a Multitask Deformable Residual Neural Network

This paper proposes a multitask deformable residual neural network, for full spatial muscle fiber orientation (MFO) estimation from ultrasound (US) images. It is developed based on the state-of-the-art model of residual UNet (ResUNet), which combines the residual block and UNet for more efficient deep learning. To better capture the characteristics of curved muscle fibers in US images, deformable convolution is used to improve the conventional convolutions in ResUNet. Moreover, along with the detection of MFO, an extra task concerning muscle segmentation is assigned to the model in order to improve the detection accuracy and robustness. Experimental results on an inhouse dataset built upon 10 healthy human subjects demonstrate the superiority of the proposed model for full spatial MFO estimation from US images.

Automated Method for Tracking Human Muscle Architecture on Ultrasound Scans during Dynamic Tasks

Existing approaches for automated tracking of fascicle length (FL) and pennation angle (PA) rely on the presence of a single, user-defined fascicle (feature tracking) or on the presence of a specific intensity pattern (feature detection) across all the recorded ultrasound images. These prerequisites are seldom met during large dynamic muscle movements or for deeper muscles that are difficult to image. Deep-learning approaches are not affected by these issues, but their applicability is restricted by their need for large, manually analyzed training data sets. To address these limitations, the present study proposes a novel approach that tracks changes in FL and PA based on the distortion pattern within the fascicle band. The results indicated a satisfactory level of agreement between manual and automated measurements made with the proposed method. When compared against feature tracking and feature detection methods, the proposed method achieved the lowest average root mean squared error for FL and the second lowest for PA. The strength of the proposed approach is that the quantification process does not require a training data set and it can take place even when it is not possible to track a single fascicle or observe a specific intensity pattern on the ultrasound recording.

Fully Automatic Analysis of Muscle B-Mode Ultrasound Images Based on the Deep Residual Shrinkage U-Net

The parameters of muscle ultrasound images reflect the function and state of muscles. They are of great significance to the diagnosis of muscle diseases. Because manual labeling is time-consuming and laborious, the automatic labeling of muscle ultrasound image parameters has become a research topic. In recent years, there have been many methods that apply image processing and deep learning to automatically analyze muscle ultrasound images. However, these methods have limitations, such as being non-automatic, not applicable to images with complex noise, and only being able to measure a single parameter. This paper proposes a fully automatic muscle ultrasound image analysis method based on image segmentation to solve these problems. This method is based on the Deep Residual Shrinkage U-Net(RS-Unet) to accurately segment ultrasound images. Compared with the existing methods, the accuracy of our method shows a great improvement. The mean differences of pennation angle, fascicle length and muscle thickness are about 0.09°, 0.4 mm and 0.63 mm, respectively. Experimental results show that the proposed method realizes the accurate measurement of muscle parameters and exhibits stability and robustness.

Real-world analysis of artificial intelligence in musculoskeletal trauma

Musculoskeletal trauma accounts for a large percentage of emergency room visits and is amongst the top causes of unscheduled patient visits to the emergency room. Musculoskeletal trauma results in expenditure of billions of dollars and protracted losses of quality-adjusted life years. New and innovative methods are needed to minimise the impact by ensuring quick and accurate assessment. However, each of the currently utilised radiological procedures, such as radiography, ultrasonography, computed tomography, and magnetic resonance imaging, has resulted in implosion of medical imaging data. Deep learning, a recent advancement in artificial intelligence, has demonstrated the potential to analyse medical images with sensitivity and specificity at par with experts. In this review article, we intend to summarise and showcase the various developments which have occurred in the dynamic field of artificial intelligence and machine learning and how their applicability to different aspects of imaging in trauma can be explored to improvise our existing reporting systems and improvise on patient outcomes.

Machine learning to extract muscle fascicle length changes from dynamic ultrasound images in real-time

BACKGROUND AND OBJECTIVE

Dynamic muscle fascicle length measurements through B-mode ultrasound have become popular for the non-invasive physiological insights they provide regarding musculoskeletal structure-function. However, current practices typically require time consuming post-processing to track muscle length changes from B-mode images. A real-time measurement tool would not only save processing time but would also help pave the way toward closed-loop applications based on feedback signals driven by in vivo muscle length change patterns. In this paper, we benchmark an approach that combines traditional machine learning (ML) models with B-mode ultrasound recordings to obtain muscle fascicle length changes in real-time. To gauge the utility of this framework for 'in-the-loop' applications, we evaluate accuracy of the extracted muscle length change signals against time-series' derived from a standard, post-hoc automated tracking algorithm.

METHODS

We collected B-mode ultrasound data from the soleus muscle of six participants performing five defined ankle motion tasks: (a) seated, constrained ankle plantarflexion, (b) seated, free ankle dorsi/plantarflexion, (c) weight-bearing, calf raises (d) walking, and then a (e) mix. We trained machine learning (ML) models by pairing muscle fascicle lengths obtained from standardized automated tracking software (UltraTrack) with the respective B-mode ultrasound image input to the tracker, frame-by-frame. Then we conducted hyperparameter optimizations for five different ML models using a grid search to find the best performing parameters for a combination of high correlation and low RMSE between ML and UltraTrack processed muscle fascicle length trajectories. Finally, using the global best model/hyperparameter settings, we comprehensively evaluated training-testing outcomes within subject (i.e., train and test on same subject), cross subject (i.e., train on one subject, test on another) and within/direct cross task (i.e., train and test on same subject, but different task).

RESULTS

Support vector machine (SVM) was the best performing model with an average r = 0.70 ±0.34 and average RMSE = 2.86 ±2.55 mm across all direct training conditions and average r = 0.65 ±0.35 and average RMSE = 3.28 ±2.64 mm when optimized for all cross-participant conditions. Comparisons between ML vs. UltraTrack (i.e., ground truth) tracked muscle fascicle length versus time data indicated that ML tracked images reliably capture the salient qualitative features in ground truth length change data, even when correlation values are on the lower end. Furthermore, in the direct training, calf raises condition, which is most comparable to previous studies validating automated tracking performance during isolated contractions on a dynamometer, our ML approach yielded 0.90 average correlation, in line with other accepted tracking methods in the field.

CONCLUSIONS

By combining B-mode ultrasound and classical ML models, we demonstrate it is possible to achieve real-time tracking of human soleus muscle fascicles across a number of functionally relevant contractile conditions. This novel sensing modality paves the way for muscle physiology in-the-loop applications that could be used to modify gait via biofeedback or unlock novel wearable device control techniques that could enable restored or augmented locomotion performance.

Automatic Measurement of Pennation Angle from Ultrasound Images using Resnets

In this study, an automatic pennation angle measuring approach based on deep learning is proposed. Firstly, the Local Radon Transform (LRT) is used to detect the superficial and deep aponeuroses on the ultrasound image. Secondly, a reference line are introduced between the deep and superficial aponeuroses to assist the detection of the orientation of muscle fibers. The Deep Residual Networks (Resnets) are used to judge the relative orientation of the reference line and muscle fibers. Then, reference line is revised until the line is parallel to the orientation of the muscle fibers. Finally, the pennation angle is obtained according to the direction of the detected aponeuroses and the muscle fibers. The angle detected by our proposed method differs by about 1° from the angle manually labeled. With a CPU, the average inference time for a single image of the muscle fibers with the proposed method is around 1.6 s, compared to 0.47 s for one of the image of a sequential image sequence. Experimental results show that the proposed method can achieve accurate and robust measurements of pennation angle.

The Feasibility of Dynamic Musculoskeletal Function Analysis of the Vastus Lateralis in Endurance Runners Using Continuous, Hands-Free Ultrasound

Dynamic imaging of the skeletal muscles used to be strenuous and often impossible to perform manually. Accordingly, long-term dynamic musculoskeletal imaging has not been performed. The feasibility of long-term dynamic musculoskeletal functional analysis using hands-free ultrasound will be demonstrated in ten healthy endurance runners. After every kilometer, the vastus lateralis muscle was imaged whilst running using a fixated probe connected to a smart phone. The image quality was quantified by estimation of the probe-skin contact preservation and the field-of-view stability. Moreover, the pennation angles and muscle thicknesses were computed automatically. Long-term dynamic acquisition was successful in nine out of ten runners. Probe-skin contact loss ranged between 0 and 57% of the gait cycle. The biggest change in field-of-view occurred during the first kilometer with an average decline in complex-wavelet structural similarity index of 0.21, followed by an onward total decrease of 0.09, on average. The mean pennation angle and thickness were approximately constant, with the average fluctuation being 0.94 degrees and 0.11 cm, respectively. The feasibility of long-term musculoskeletal function analysis has been demonstrated, with probe-skin contact loss the main limiting factor. Dynamic, hands-free ultrasound might enable research for a more profound insight in the prevention and rehabilitation of musculoskeletal injuries.

Artificial intelligence in musculoskeletal ultrasound imaging

Ultrasonography (US) is noninvasive and offers real-time, low-cost, and portable imaging that facilitates the rapid and dynamic assessment of musculoskeletal components. Significant technological improvements have contributed to the increasing adoption of US for musculoskeletal assessments, as artificial intelligence (AI)-based computer-aided detection and computer-aided diagnosis are being utilized to improve the quality, efficiency, and cost of US imaging. This review provides an overview of classical machine learning techniques and modern deep learning approaches for musculoskeletal US, with a focus on the key categories of detection and diagnosis of musculoskeletal disorders, predictive analysis with classification and regression, and automated image segmentation. Moreover, we outline challenges and a range of opportunities for AI in musculoskeletal US practice.

The Development of the Military Service Identification Tool: Identifying Military Veterans in a Clinical Research Database Using Natural Language Processing and Machine Learning

Background

Electronic health care records (EHRs) are a rich source of health-related information, with potential for secondary research use. In the United Kingdom, there is no national marker for identifying those who have previously served in the Armed Forces, making analysis of the health and well-being of veterans using EHRs difficult.

Objective

This study aimed to develop a tool to identify veterans from free-text clinical documents recorded in a psychiatric EHR database.

Methods

Veterans were manually identified using the South London and Maudsley (SLaM) Biomedical Research Centre Clinical Record Interactive Search—a database holding secondary mental health care electronic records for the SLaM National Health Service Foundation Trust. An iterative approach was taken; first, a structured query language (SQL) method was developed, which was then refined using natural language processing and machine learning to create the Military Service Identification Tool (MSIT) to identify if a patient was a civilian or veteran. Performance, defined as correct classification of veterans compared with incorrect classification, was measured using positive predictive value, negative predictive value, sensitivity, F1 score, and accuracy (otherwise termed Youden Index).

Results

A gold standard dataset of 6672 free-text clinical documents was manually annotated by human coders. Of these documents, 66.00% (4470/6672) were then used to train the SQL and MSIT approaches and 34.00% (2202/6672) were used for testing the approaches. To develop the MSIT, an iterative 2-stage approach was undertaken. In the first stage, an SQL method was developed to identify veterans using a keyword rule–based approach. This approach obtained an accuracy of 0.93 in correctly predicting civilians and veterans, a positive predictive value of 0.81, a sensitivity of 0.75, and a negative predictive value of 0.95. This method informed the second stage, which was the development of the MSIT using machine learning, which, when tested, obtained an accuracy of 0.97, a positive predictive value of 0.90, a sensitivity of 0.91, and a negative predictive value of 0.98.

Conclusions

The MSIT has the potential to be used in identifying veterans in the United Kingdom from free-text clinical documents, providing new and unique insights into the health and well-being of this population and their use of mental health care services.

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.

SVM-Enabled Intelligent Genetic Algorithmic Model for Realizing Efficient Universal Feature Selection in Breast Cyst Image Acquired via Ultrasound Sensing Systems

In recent years, there are several cost-effective intelligent sensing systems such as ultrasound imaging systems for visualizing the internal body structures of the body. Further, such intelligent sensing systems such as ultrasound systems have been deployed by medical doctors around the globe for efficient detection of several diseases and disorders in the human body. Even though the ultrasound sensing system is a useful tool for obtaining the imagery of various body parts, there is always a possibility of inconsistencies in these images due to the variation in the settings of the system parameters. Therefore, in order to overcome such issues, this research devises an SVM-enabled intelligent genetic algorithmic model for choosing the universal features with four distinct settings of the parameters. Subsequently, the distinguishing characteristics of these features are assessed utilizing the Sorensen-Dice coefficient, t-test, and Pearson’s R measure. It is apparent from the results of the SVM-enabled intelligent genetic algorithmic model that this approach aids in the effectual selection of universal features for the breast cyst images. In addition, this approach also accomplishes superior accuracy in the classification of the ultrasound image for four distinct settings of the parameters.

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.

Fully automated image-based estimation of postural point-features in children with cerebral palsy using deep learning

The aim of this study was to provide automated identification of postural point-features required to estimate the location and orientation of the head, multi-segmented trunk and arms from videos of the clinical test 'Segmental Assessment of Trunk Control' (SATCo). Three expert operators manually annotated 13 point-features in every fourth image of 177 short (5-10 s) videos (25 Hz) of 12 children with cerebral palsy (aged: 4.52 ± 2.4 years), participating in SATCo testing. Linear interpolation for the remaining images resulted in 30 825 annotated images. Convolutional neural networks were trained with cross-validation, giving held-out test results for all children. The point-features were estimated with error 4.4 ± 3.8 pixels at approximately 100 images per second. Truncal segment angles (head, neck and six thoraco-lumbar-pelvic segments) were estimated with error 6.4 ± 2.8°, allowing accurate classification (F 1 > 80%) of deviation from a reference posture at thresholds up to 3°, 3° and 2°, respectively. Contact between arm point-features (elbow and wrist) and supporting surface was classified at F 1 = 80.5%. This study demonstrates, for the first time, technical feasibility to automate the identification of (i) a sitting segmental posture including individual trunk segments, (ii) changes away from that posture, and (iii) support from the upper limb, required for the clinical SATCo.

Noise-Robust Sound-Event Classification System with Texture Analysis

Sound-event classification has emerged as an important field of research in recent years. In particular, investigations using sound data are being conducted in various industrial fields. However, sound-event classification tasks have become more difficult and challenging with the increase in noise levels. In this study, we propose a noise-robust system for the classification of sound data. In this method, we first convert one-dimensional sound signals into two-dimensional gray-level images using normalization, and then extract the texture images by means of the dominant neighborhood structure (DNS) technique. Finally, we experimentally validate the noise-robust approach by using four classifiers (convolutional neural network (CNN), support vector machine (SVM), k-nearest neighbors(k-NN), and C4.5). The experimental results showed superior classification performance in noisy conditions compared with other methods. The F1 score exceeds 98.80% in railway data, and 96.57% in livestock data. Besides, the proposed method can be implemented in a cost-efficient manner (for instance, use of a low-cost microphone) while maintaining high level of accuracy in noisy environments. This approach can be used either as a standalone solution or as a supplement to the known methods to obtain a more accurate solution.

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.