117 publications found
Sort by
Pressure sensor calibration using a water-filled latex finger to account for the mechanical interaction between the hard palate and the deformable human tongue.

We present a calibration system called Dried Water Column (DWC). It applies pressure on a sensor with a latex finger filled with water, which pressure is controlled with a water column. This is intended to mimic the way the deformable tongue mechanically interacts with the hard palate. We show that, once some specificities of the elastic/plastic behavior of the latex finger are taken into account, namely the softening due to Mullins Effect and the non-elastic deformation occurring above a certain pressure level, the DWC provides a reliable measure of the linear relation between the pressure and the output voltage of the sensor within the limited pressure range [0, 2.5kPa]. Such a precise calibration would not be possible with a rigid actuator, which position on the sensor can dramatically influence the measures. Extrapolating the linear relationship thus determined to a larger pressure range compatible with speech production and swallowing ([0, 35kPa]), is possible once it has been verified that the behavior of the sensor is linear over this pressure range. This can be done with any rigid or semi rigid actuator. This reliable calibration procedure can be easily reproduced in any laboratory, and can be applied to any pressure sensor.

In-vivo characterization of the lumbar annulus fibrosus in adults with ultrasonography and shear wave elastography.

In vivo characterization of intervertebral disc (IVD) mechanical properties and microstructure could give an insight into the onset and progression of disc pathologies. Ultrasound shearwave elastography provided promising results in children, but feasibility in adult lumbar discs, which are deep in the abdomen, was never proved. The aim of this work was to determine the feasibility and reliability of ultrasound assessment of lumbar IVD in adults. Thirty asymptomatic adults were included (22 to 67 years old). Subjects were lying supine, and the annulus fibrosus of the L3-L4 IVD was imaged by conventional ultrasonography and shearwave elastography. Shear wave speed (SWS) and lamellar thickness were measured. Reliability was determined through repeated measurements acquired by three operators. Average SWS in AF at the L3L4 level was 4.0±0.9m/s, with an inter-operator uncertainty of 8.7%, while lamellar thickness was 255±27µm with an uncertainty of 9.6%. Measurement was not feasible in one out of four subjects with BMI > 24kg/m² (overweight). Ultrasound assessment of annulus fibrosus revealed feasible, within certain limitations, and reproducible. This method gives an insight into disc microstructure and mechanical properties, and it could be applied for the early detection or follow-up of disc pathologies.

3D reconstruction of the scapula from biplanar X-rays for pose estimation and morphological analysis.

Patient-specific scapular shape in functional posture can be highly relevant to clinical research. Biplanar radiography is a relevant modality for that purpose with already two existing assessment methods. However, they are either time-consuming or lack accuracy. The aim of this study was to propose a new, more user-friendly and accurate method to determine scapular shape. The proposed method relied on simplified manual inputs and an upgraded version of the first 3D estimate based on statistical inferences and Moving-Least Square (MLS) deformation of a template. Then, manual adjustments, with real-time MLS algorithm and contour matching adjustments with an adapted minimal path method, were added to improve the match between the projected 3D model and the radiographic contours. The accuracy and reproducibility of the method were assessed (with 6 and 12 subjects, respectively). The shape accuracy was in average under 2mm (1.3mm in the glenoid region). The reproducibility study on the clinical parameters found intra-observer 95% confidence intervals under 3mm or 3° for all parameters, except for glenoid inclination and Critical Shoulder Angle, ranging between 3° and 6°. This method is a first step towards an accurate reconstruction of the scapula to assess clinical parameters in a functional posture. This can already be used in clinical research on non-pathologic bones to investigate the scapulothoracic joint in functional position.

Characterization of the ankle dynamic joint stiffness as a function of gait speed for overground and treadmill walking.

The ankle dynamic joint stiffness (DJS), defined as the slope of the joint angle-moment plot, measures the resistance of the ankle joint to movement when the foot is in contact with the ground. DJS helps to stabilize the ankle joint, and its characterization helps to identify gait pathology and assist foot prosthesis design. This study analyzes the available gait dynamics data to obtain ankle DJS parameters for population groups according to age, gender, and gait speed for overground and treadmill walking. This study classified the groups into five walking speeds normalized using the Froude number. Herein, 12 ankle DJS parameters were determined. These include four linear segments: controlled plantar flexion (CP), early response phase (ERP), large response phase (LRP), and descending phase (DP), their corresponding turning points, the net mechanical work, the absorbed work, and the loop direction. Ankle dynamics data for 92 individuals was collected from two gait data repositories. The analysis reveals a notable disparity in stiffness values between overground and treadmill gait. Specifically, the CP stiffness is significantly higher for overground gait. In contrast, the DP stiffness displays an opposing pattern, with higher values observed during treadmill walking. A negative stiffness for LRP was found at fast speeds for all groups. The sorted data, analysis tools, and findings of this study are meant to help practitioners design prosthetic and rehabilitation devices based on age, gender, and walking environment at different gait speeds.

Open Access
H-Deep-Net: A deep hybrid network with stationary wavelet packet transforms for Retinal detachment classification through fundus images.

Nowadays, automated disease diagnosis has become a vital role in the medical field due to the significant population expansion. An automated disease diagnostic approach assists clinicians in the diagnosis of disease by giving exact, consistent, and prompt results, along with minimizing the mortality rate. Retinal detachment has recently emerged as one of the most severe and acute ocular illnesses, spreading worldwide. Therefore, an automated and quickest diagnostic model should be implemented to diagnose retinal detachment at an early stage. This paper introduces a new hybrid approach of best basis stationary wavelet packet transform and modified VGG19-Bidirectional long short-term memory to detect retinal detachment using retinal fundus images automatically. In this paper, the best basis stationary wavelet packet transform is utilized for image analysis, modified VGG19-Bidirectional long short-term memory is employed as the deep feature extractors, and then obtained features are classified through the Adaptive boosting technique. The experimental outcomes demonstrate that our proposed method obtained 99.67% sensitivity, 95.95% specificity, 98.21% accuracy, 97.43% precision, 98.54% F1-score, and 0.9985 AUC. The model obtained the intended results on the presently accessible database, which may be enhanced further when additional RD images become accessible. The proposed approach aids ophthalmologists in identifying and easily treating RD patients.

Application of cluster repeated mini-batch training method to classify electroencephalography for grab and lift tasks.

Modern deep neural network training is based on mini-batch stochastic gradient optimization. While using extensive mini-batches improves the computational parallelism, the small batch training proved that it delivers improved generalization performance and allows a significantly smaller memory, which might also improve machine throughput. However, mini-batch size and characteristics, a key factor for training deep neural networks, has not been sufficiently investigated in training correlated group features and looping with highly complex ones. In addition, the unsupervised learning method clusters the data into different groups with similar properties to make the training process more stable and faster. Then, the supervised learning algorithm was applied with the cluster repeated mini-batch training (CRMT) methods. The CRMT algorithm changed the random minibatch characteristics in the training step into training in order of clusters. Specifically, the self-organizing maps (SOM) were used to cluster the information into n groups based on the dataset's labels Then, neural network models (ANN) were trained with each cluster using the cluster repeated mini-batch training method. Experiments conducted on EEG datasets demonstrate the survey of the proposed method and optimize it. In addition, the results in our research outperform other state-of-the-art methods.