The high fall rate of the elderly brings enormous challenges to families and the medical system; therefore, early risk assessment and intervention are quite necessary. Compared to other sensor-based technologies, in-shoe plantar pressure sensors, effectiveness and low obtrusiveness are widely used for long-term fall risk assessments because of their portability. While frequently-used bipedal center-of-pressure (COP) features are derived from a pressure sensing platform, they are not suitable for the shoe system or pressure insole owing to the lack of relative position information. Therefore, in this study, a definition of “weak foot” was proposed to solve the sensitivity problem of single foot features and facilitate the extraction of temporal consistency related features. Forty-four multi-dimensional weak foot features based on single foot COP were correspondingly extracted; notably, the relationship between the fall risk and temporal inconsistency in the weak foot were discussed in this study, and probability distribution method was used to analyze the symmetry and temporal consistency of gait lines. Though experiments, foot pressure data were collected from 48 subjects with 24 high risk (HR) and 24 low risk (LR) ones obtained by the smart footwear system. The final models with 87.5% accuracy and 100% sensitivity on test data outperformed the base line models using bipedal COP. The results and feature space shown the novel features of wearable plantar pressure could comprehensively evaluate the difference between HR and LR groups. Our fall risk assessment models based on these features had good generalization performance, and showed practicability and reliability in real-life monitoring situations.
Background: Patients with knee osteoarthritis (KOA) often present lower extremity motor dysfunction. However, traditional radiography is a static assessment and cannot achieve long-term dynamic functional monitoring. Plantar pressure signals have demonstrated potential applications in the diagnosis and rehabilitation monitoring of KOA. Objective: Through wearable gait analysis technology, we aim to obtain abundant gait information based on machine learning techniques to develop a simple, rapid, effective, and patient-friendly functional assessment model for the KOA rehabilitation process to provide long-term remote monitoring, which is conducive to reducing the burden of social health care system. Methods: This cross-sectional study enrolled patients diagnosed with KOA who were able to walk independently for 2 minutes. Participants were given clinically recommended functional tests, including the 40-m fast-paced walk test (40mFPWT) and timed up-and-go test (TUGT). We used a smart shoe system to gather gait pressure data from patients with KOA. The multidimensional gait features extracted from the data and physical characteristics were used to establish the KOA functional feature database for the plantar pressure measurement system. 40mFPWT and TUGT regression prediction models were trained using a series of mature machine learning algorithms. Furthermore, model stacking and average ensemble learning methods were adopted to further improve the generalization performance of the model. Mean absolute error (MAE), mean absolute percentage error (MAPE), and root mean squared error (RMSE) were used as regression performance metrics to evaluate the results of different models. Results: A total of 92 patients with KOA were included, exhibiting varying degrees of severity as evaluated by the Kellgren and Lawrence classification. A total of 380 gait features and 4 physical characteristics were extracted to form the feature database. Effective stepwise feature selection determined optimal feature subsets of 11 variables for the 40mFPWT and 10 variables for the TUGT. Among all models, the weighted average ensemble model using 4 tree-based models had the best generalization performance in the test set, with an MAE of 2.686 seconds, MAPE of 9.602%, and RMSE of 3.316 seconds for the prediction of the 40mFPWT and an MAE of 1.280 seconds, MAPE of 12.389%, and RMSE of 1.905 seconds for the prediction of the TUGT. Conclusions: This wearable plantar pressure feature technique can objectively quantify indicators that reflect functional status and is promising as a new tool for long-term remote functional monitoring of patients with KOA. Future work is needed to further explore and investigate the relationship between gait characteristics and functional status with more functional tests and in larger sample cohorts.
26 August 2024 in IEEE Transactions on Ultrasonics, Ferroelectrics, and Frequency Control
Quantitative muscle function analysis based on the ultrasound imaging, has been used for various applications, particularly with recent development of deep learning methods. The nature of speckle noises in ultrasound images poses challenges to accurate and reliable data annotation for supervised learning algorithms. To obtain a large and reliable dataset without manual scanning and labelling, we proposed a synthesizing pipeline to provide synthetic ultrasound datasets of muscle movement with an accurate ground truth, allowing augmenting, training, and evaluating models for different tasks. Our pipeline contained biomechanical simulation using finite element method, an algorithm for reconstructing sparse fascicles, and a diffusion network for ultrasound image generation. With the adjustment of a few parameters, the proposed pipeline can generate a large dataset of real-time ultrasound images with diversity in morphology and pattern. With 3,030 ultrasound images generated, we qualitatively and quantitatively verified that the synthetic images closely matched with the in-vivo images. In addition, we applied the synthetic dataset into different tasks of muscle analysis. Compared to trained on an unaugmented dataset, model trained on synthetic one had better cross-dataset performance, which demonstrates the feasibility of synthesizing pipeline to augment model training and avoid over-fitting. The results of the regression task show potentials under the conditions that the number of datasets or the accurate label are limited. The proposed synthesizing pipeline can not only be used for muscle-related study, but for other similar study and model development, where sequential images are needed for training.
30 November 2023 in IEEE Transactions on Neural Systems and Rehabilitation Engineering
In cross-subject fall risk classification based on plantar pressure, a challenge is that data from different subjects have significant individual information. Thus, the models with insufficient generalization ability can’t perform well on new subjects, which limits their application in daily life. To solve this problem, domain adaptation methods are applied to reduce the gap between source and target domain. However, these methods focus on the distribution of the source and the target domain, but ignore the potential correlation among multiple source subjects, which deteriorates domain adaptation performance. In this paper, we proposed a novel method named domain adaptation with subject fusion (SFDA) for fall risk assessment, greatly improving the cross-subject assessment ability. Specifically, SFDA synchronously carries out source target adaptation and multiple source subject fusion by domain adversarial module to reduce source-target gap and distribution distance within source subjects of same class. Consequently, target samples can learn more task-specific features from source subjects to improve the generalization ability. Experiment results show that SFDA achieved mean accuracy of 79.17 % and 73.66 % based on two backbones in a cross-subject classification manner, outperforming the state-of-the-art methods on continuous plantar pressure dataset. This study proves the effectiveness of SFDA and provides a novel tool for implementing cross-subject and few-gait fall risk assessment.
This study investigated the effect of wearable ultrasound-imaging-based visual feedback (UVF) on assisting paretic ankle dorsiflexion training of chronic stroke survivors. Thirty-three participants with unilateral hemiplegia performed maximal isometric contractions on an isokinetic dynamometer in randomized conditions with and without UVF that provided by a wearable ultrasound imaging system. Torque parameters (mean, peak, percentage of maximal voluntary contraction) and tibialis anterior muscle thickness were analyzed across different contraction phases. Statistical comparisons were conducted using paired t-tests or Wilcoxon tests. Correlation analyses were performed using Pearson’s or Spearman’s tests. Results demonstrated that UVF significantly improved torque output, as evidence by the increased percentage of maximal voluntary contraction (%MVC) during entire contractions (p = 0.007), increased mean (p ≤ 0.022) and peak (p ≤ 0.044) torque and the %MVC (p ≤ 0.004) during mid and end phases, and larger muscle thickness during mid contraction (p = 0.045). Moderate correlations were found between torque and muscle thickness (r ≥ 0.30, p ≤ 0.049). These findings preliminarily supported the positive outcomes of real-time wearable UVFs in enhancing paretic ankle dorsiflexion strength and force control during isometric contractions in chronic stroke survivors. While the developed and validated new training protocol may potentially serve as a practical adjunct to existing rehabilitation approaches, further investigations emphasizing the functional outcomes and clinical translations are still needed to verify the clinical utility.
Sarcopenia is characterized by a degeneration of muscle mass and strength that incurs impaired mobility, posing grievous impacts on the quality of life and well-being of older adults worldwide. In 2018, a new international consensus was formulated to incorporate ultrasound imaging of the rectus femoris (RF) muscle for early sarcopenia assessment. Nonetheless, current clinical RF muscle identification and delineation procedures are manual, subjective, inaccurate, and challenging. Thus, developing an effective AI-empowered RF segmentation model to streamline downstream sarcopenia assessment is highly desirable. Yet, this area of research readily goes unnoticed compared to other disciplines, and relevant research is desperately wanted, especially in comparison among traditional, classic, and cutting-edge segmentation networks. This study evaluated an emerging Automatic Segment Anything Model (AutoSAM) compared to the U-Net and nnU-Net models for RF segmentation on ultrasound images. We prospectively analyzed ultrasound images of 257 older adults (aged > 65) in a community setting from Hong Kong’s District Elderly Community Centers. Three models were developed on a training set (n = 219) and independently evaluated on a testing set (n = 38) in aspects of DICE, Intersection-over-Union, Hausdorff Distance (HD), accuracy, precision, recall, as well as stability. The results indicated that the AutoSAM achieved the best segmentation agreement in all the evaluating metrics, consistently outperforming the U-Net and nnU-Net models. The results offered an effective state-of-the-art RF muscle segmentation tool for sarcopenia assessment in the future.