Inertial Measurement Unit-Based Romberg Test for Assessing Adults With Vestibular Hypofunction.

This work aims to explore the utility of wearable inertial measurement units (IMUs) for quantifying movement in Romberg tests and investigate the extent of movement in adults with vestibular hypofunction (VH). A cross-sectional study was conducted at an academic tertiary medical center between March 2021 and April 2022. Adults diagnosed with unilateral vestibular hypofunction (UVH) or bilateral vestibular hypofunction (BVH) were enrolled in the VH group. Healthy controls (HCs) were recruited from community or outpatient clinics. The IMU-based instrumented Romberg and tandem Romberg tests on the floor were applied to both groups. The primary outcomes were kinematic body metrics (maximum acceleration [ACC], mean ACC, root mean square [RMS] of ACC, and mean sway velocity [MV]) along the medio-lateral (ML), cranio-caudal (CC), and antero-posterior (AP) axes. A total of 31 VH participants (mean age, 33.48 [SD 7.68] years; 19 [61%] female) and 31 HCs (mean age, 30.65 [SD 5.89] years; 18 [58%] female) were recruited. During the eyes-closed portion of the Romberg test, VH participants demonstrated significantly higher maximum ACC and increased RMS of ACC in head movement, as well as higher maximum ACC in pelvic movement along the ML axis. In the same test condition, individuals with BVH exhibited notably higher maximum ACC and RMS of ACC along the ML axis in head and pelvic movements compared with HCs. Additionally, BVH participants exhibited markedly increased maximum ACC along the ML axis in head movement during the eyes-open portion of the tandem Romberg test. Conversely, no significant differences were found between UVH participants and HCs in the assessed parameters. The instrumented Romberg and tandem Romberg tests characterized the kinematic differences in head, pelvis, and ankle movement between VH and healthy adults. The findings suggest that these kinematic body metrics can be useful for screening BVH and can provide goals for vestibular rehabilitation.

Multi-Task Learning U-Net for Functional Shoulder Sub-Task Segmentation.

The assessment of a frozen shoulder (FS) is critical for evaluating outcomes and medical treatment. Analysis of functional shoulder sub-tasks provides more crucial information, but current manual labeling methods are time-consuming and prone to errors. To address this challenge, we propose a deep multi-task learning (MTL) U-Net to provide an automatic and reliable functional shoulder sub-task segmentation (STS) tool for clinical evaluation in FS. The proposed approach contains the main task of STS and the auxiliary task of transition point detection (TPD). For the main STS task, a U-Net architecture including an encoder-decoder with skip connection is presented to perform shoulder sub-task classification for each time point. The auxiliary TPD task uses lightweight convolutional neural networks architecture to detect the boundary between shoulder sub-tasks. A shared structure is implemented between two tasks and their objective functions of them are optimized jointly. The fine-grained transition-related information from the auxiliary TPD task is expected to help the main STS task better detect boundaries between functional shoulder sub-tasks. We conduct the experiments using wearable inertial measurement units to record 815 shoulder task sequences collected from 20 healthy subjects and 43 patients with FS. The experimental results present that the deep MTL U-Net can achieve superior performance compared to using single-task models. It shows the effectiveness of the proposed method for functional shoulder STS. The code has been made publicly available at https://github.com/RobinChu9890/MTL-U-Net-for-Functional-Shoulder-STS.Clinical Relevance- This work provides an automatic and reliable functional shoulder sub-task segmentation tool for clinical evaluation in frozen shoulder.

Abnormal Respiratory Sound Identification Using Audio-Spectrogram Vision Transformer.

Respiratory disease, the third leading cause of deaths globally, is considered a high-priority ailment requiring significant research on identification and treatment. Stethoscope-recorded lung sounds and artificial intelligence-powered devices have been used to identify lung disorders and aid specialists in making accurate diagnoses. In this study, audio-spectrogram vision transformer (AS-ViT), a new approach for identifying abnormal respiration sounds, was developed. The sounds of the lungs are converted into visual representations called spectrograms using a technique called short-time Fourier transform (STFT). These images are then analyzed using a model called vision transformer to identify different types of respiratory sounds. The classification was carried out using the ICBHI 2017 database, which includes various types of lung sounds with different frequencies, noise levels, and backgrounds. The proposed AS-ViT method was evaluated using three metrics and achieved 79.1% and 59.8% for 60:40 split ratio and 86.4% and 69.3% for 80:20 split ratio in terms of unweighted average recall and overall scores respectively for respiratory sound detection, surpassing previous state-of-the-art results.

Boundary-Preserved Deep Denoising of Stochastic Resonance Enhanced Multiphoton Images.

OBJECTIVE: With the rapid growth of high-speed deep-tissue imaging in biomedical research, there is an urgent need to develop a robust and effective denoising method to retain morphological features for further texture analysis and segmentation. Conventional denoising filters and models can easily suppress the perturbative noise in high-contrast images; however, for low photon budget multiphoton images, a high detector gain will not only boost the signals but also bring significant background noise. In such a stochastic resonance imaging regime, subthreshold signals may be detectable with the help of noise, meaning that a denoising filter capable of removing noise without sacrificing important cellular features, such as cell boundaries, is desirable. METHOD: We propose a convolutional neural network-based denoising autoencoder method - a fully convolutional deep denoising autoencoder (DDAE) - to improve the quality of three-photon fluorescence (3PF) and third-harmonic generation (THG) microscopy images. RESULTS: The average of 200 acquired images of a given location served as the low-noise answer for the DDAE training. Compared with other conventional denoising methods, our DDAE model shows a better signal-to-noise ratio (28.86 and 21.66 for 3PF and THG, respectively), structural similarity (0.89 and 0.70 for 3PF and THG, respectively), and preservation of the nuclear or cellular boundaries (F1-score of 0.662 and 0.736 for 3PF and THG, respectively). It shows that DDAE is a better trade-off approach between structural similarity and preserving signal regions. CONCLUSIONS: The results of this study validate the effectiveness of the DDAE system in boundary-preserved image denoising. CLINICAL IMPACT: The proposed deep denoising system can enhance the quality of microscopic images and effectively support clinical evaluation and assessment.

Domain-Adaptive Fall Detection Using Deep Adversarial Training.

Fall detection (FD) systems are important assistive technologies for healthcare that can detect emergency fall events and alert caregivers. However, it is not easy to obtain large-scale annotated fall events with various specifications of sensors or sensor positions during the implementation of accurate FD systems. Moreover, the knowledge obtained through machine learning has been restricted to tasks in the same domain. The mismatch between different domains might hinder the performance of FD systems. Cross-domain knowledge transfer is very beneficial for machine-learning based FD systems to train a reliable FD model with well-labeled data in new environments. In this study, we propose domain-adaptive fall detection (DAFD) using deep adversarial training (DAT) to tackle cross-domain problems, such as cross-position and cross-configuration. The proposed DAFD can transfer knowledge from the source domain to the target domain by minimizing the domain discrepancy to avoid mismatch problems. The experimental results show that the average F1-score improvement when using DAFD ranges from 1.5% to 7% in the cross-position scenario, and from 3.5% to 12% in the cross-configuration scenario, compared to using the conventional FD model without domain adaptation training. The results demonstrate that the proposed DAFD successfully helps to deal with cross-domain problems and to achieve better detection performance.

Multiphase Identification Algorithm for Fall Recording Systems Using a Single Wearable Inertial Sensor.

Fall-related information can help clinical professionals make diagnoses and plan fall prevention strategies. The information includes various characteristics of different fall phases, such as falling time and landing responses. To provide the information of different phases, this pilot study proposes an automatic multiphase identification algorithm for phase-aware fall recording systems. Seven young adults are recruited to perform the fall experiment. One inertial sensor is worn on the waist to collect the data of body movement, and a total of 525 trials are collected. The proposed multiphase identification algorithm combines machine learning techniques and fragment modification algorithm to identify pre-fall, free-fall, impact, resting and recovery phases in a fall process. Five machine learning techniques, including support vector machine, k-nearest neighbor (kNN), naïve Bayesian, decision tree and adaptive boosting, are applied to identify five phases. Fragment modification algorithm uses the rules to detect the fragment whose results are different from the neighbors. The proposed multiphase identification algorithm using the kNN technique achieves the best performance in 82.17% sensitivity, 85.74% precision, 73.51% Jaccard coefficient, and 90.28% accuracy. The results show that the proposed algorithm has the potential to provide automatic fine-grained fall information for clinical measurement and assessment.

Automatic Functional Shoulder Task Identification and Sub-task Segmentation Using Wearable Inertial Measurement Units for Frozen Shoulder Assessment.

Advanced sensor technologies have been applied to support frozen shoulder assessment. Sensor-based assessment tools provide objective, continuous and quantitative information for evaluation and diagnosis. However, the current tools for assessment of functional shoulder tasks mainly rely on manual operation. It may cause several technical issues to the reliability and usability of the assessment tool, including manual bias during the recording and additional efforts for data labeling. To tackle these issues, this pilot study aims to propose an automatic functional shoulder task identification and sub-task segmentation system using inertial measurement units to provide reliable shoulder task labeling and sub-task information for clinical professionals. The proposed method combines machine learning models and rule-based modification to identify shoulder tasks and segment sub-tasks accurately. A hierarchical design is applied to enhance the efficiency and performance of the proposed approach. Nine healthy subjects and nine frozen shoulder patients are invited to perform five common shoulder tasks in the lab-based and clinical environments, respectively. The experimental results show that the proposed method can achieve 87.11% F-score for shoulder task identification, and 83.23% F-score and 427 mean absolute time errors (milliseconds) for sub-task segmentation. The proposed approach demonstrates the feasibility of the proposed method to support reliable evaluation for clinical assessment.

Fluid Intake Monitoring System Using a Wearable Inertial Sensor for Fluid Intake Management.

Fluid intake is important for people to maintain body fluid homeostasis. Inadequate fluid intake leads to negative health consequences, such as headache, dizziness and urolithiasis. However, people in busy lifestyles usually forget to drink sufficient water and neglect the importance of fluid intake. Fluid intake management is important to assist people in adopting individual drinking behaviors. This work aims to propose a fluid intake monitoring system with a wearable inertial sensor using a hierarchical approach to detect drinking activities, recognize sip gestures and estimate fluid intake amount. Additionally, container-dependent amount estimation models are developed due to the influence of containers on fluid intake amount. The proposed fluid intake monitoring system could achieve 94.42% accuracy, 90.17% sensitivity, and 40.11% mean absolute percentage error (MAPE) for drinking detection, gesture spotting and amount estimation, respectively. Particularly, MAPE of amount estimation is improved approximately 10% compared to the typical approaches. The results have demonstrated the feasibility and the effectiveness of the proposed fluid intake monitoring system.

Subtask Segmentation of Timed Up and Go Test for Mobility Assessment of Perioperative Total Knee Arthroplasty.

Total knee arthroplasty (TKA) is one of the most common treatments for people with severe knee osteoarthritis (OA). The accuracy of outcome measurements and quantitative assessments for perioperative TKA is an important issue in clinical practice. Timed up and go (TUG) tests have been validated to measure basic mobility and balance capabilities. A TUG test contains a series of subtasks, including sit-to-stand, walking-out, turning, walking-in, turning around, and stand-to-sit tasks. Detailed information about subtasks is essential to aid clinical professionals and physiotherapists in making assessment decisions. The main objective of this study is to design and develop a subtask segmentation approach using machine-learning models and knowledge-based postprocessing during the TUG test for perioperative TKA. The experiment recruited 26 patients with severe knee OA (11 patients with bilateral TKA planned and 15 patients with unilateral TKA planned). A series of signal-processing mechanisms and pattern recognition approaches involving machine learning-based multi-classifiers, fragmentation modification and subtask inference are designed and developed to tackle technical challenges in typical classification algorithms, including motion variability, fragmentation and ambiguity. The experimental results reveal that the accuracy of the proposed subtask segmentation approach using the AdaBoost technique with a window size of 128 samples is 92%, which is an improvement of at least 15% compared to that of the typical subtask segmentation approach using machine-learning models only.

Multi-Sensor Fusion Approach for Improving Map-Based Indoor Pedestrian Localization.

The interior space of large-scale buildings, such as hospitals, with a variety of departments, is so complicated that people may easily lose their way while visiting. Difficulties in wayfinding can cause stress, anxiety, frustration and safety issues to patients and families. An indoor navigation system including route planning and localization is utilized to guide people from one place to another. The localization of moving subjects is a critical-function component in an indoor navigation system. Pedestrian dead reckoning (PDR) is a technology that is widely employed for localization due to the advantage of being independent of infrastructure. To improve the accuracy of the localization system, combining different technologies is one of the solutions. In this study, a multi-sensor fusion approach is proposed to improve the accuracy of the PDR system by utilizing a light sensor, Bluetooth and map information. These simple mechanisms are applied to deal with the issue of accumulative error by identifying edge and sub-edge information from both Bluetooth and the light sensor. Overall, the accumulative error of the proposed multi-sensor fusion approach is below 65 cm in different cases of light arrangement. Compared to inertial sensor-based PDR system, the proposed multi-sensor fusion approach can improve 90% of the localization accuracy in an environment with an appropriate density of ceiling-mounted lamps. The results demonstrate that the proposed approach can improve the localization accuracy by utilizing multi-sensor data and fulfill the feasibility requirements of localization in an indoor navigation system.

Data Collection and Analysis Using Wearable Sensors for Monitoring Knee Range of Motion after Total Knee Arthroplasty.

Total knee arthroplasty (TKA) is the most common treatment for degenerative osteoarthritis of that articulation. However, either in rehabilitation clinics or in hospital wards, the knee range of motion (ROM) can currently only be assessed using a goniometer. In order to provide continuous and objective measurements of knee ROM, we propose the use of wearable inertial sensors to record the knee ROM during the recovery progress. Digitalized and objective data can assist the surgeons to control the recovery status and flexibly adjust rehabilitation programs during the early acute inpatient stage. The more knee flexion ROM regained during the early inpatient period, the better the long-term knee recovery will be and the sooner early discharge can be achieved. The results of this work show that the proposed wearable sensor approach can provide an alternative for continuous monitoring and objective assessment of knee ROM recovery progress for TKA patients compared to the traditional goniometer measurements.

Novel Hierarchical Fall Detection Algorithm Using a Multiphase Fall Model.

Falls are the primary cause of accidents for the elderly in the living environment. Reducing hazards in the living environment and performing exercises for training balance and muscles are the common strategies for fall prevention. However, falls cannot be avoided completely; fall detection provides an alarm that can decrease injuries or death caused by the lack of rescue. The automatic fall detection system has opportunities to provide real-time emergency alarms for improving the safety and quality of home healthcare services. Two common technical challenges are also tackled in order to provide a reliable fall detection algorithm, including variability and ambiguity. We propose a novel hierarchical fall detection algorithm involving threshold-based and knowledge-based approaches to detect a fall event. The threshold-based approach efficiently supports the detection and identification of fall events from continuous sensor data. A multiphase fall model is utilized, including free fall, impact, and rest phases for the knowledge-based approach, which identifies fall events and has the potential to deal with the aforementioned technical challenges of a fall detection system. Seven kinds of falls and seven types of daily activities arranged in an experiment are used to explore the performance of the proposed fall detection algorithm. The overall performances of the sensitivity, specificity, precision, and accuracy using a knowledge-based algorithm are 99.79%, 98.74%, 99.05% and 99.33%, respectively. The results show that the proposed novel hierarchical fall detection algorithm can cope with the variability and ambiguity of the technical challenges and fulfill the reliability, adaptability, and flexibility requirements of an automatic fall detection system with respect to the individual differences.

Significant Change Spotting for Periodic Human Motion Segmentation of Cleaning Tasks Using Wearable Sensors.

The proportion of the aging population is rapidly increasing around the world, which will cause stress on society and healthcare systems. In recent years, advances in technology have created new opportunities for automatic activities of daily living (ADL) monitoring to improve the quality of life and provide adequate medical service for the elderly. Such automatic ADL monitoring requires reliable ADL information on a fine-grained level, especially for the status of interaction between body gestures and the environment in the real-world. In this work, we propose a significant change spotting mechanism for periodic human motion segmentation during cleaning task performance. A novel approach is proposed based on the search for a significant change of gestures, which can manage critical technical issues in activity recognition, such as continuous data segmentation, individual variance, and category ambiguity. Three typical machine learning classification algorithms are utilized for the identification of the significant change candidate, including a Support Vector Machine (SVM), k-Nearest Neighbors (kNN), and Naive Bayesian (NB) algorithm. Overall, the proposed approach achieves 96.41% in the F1-score by using the SVM classifier. The results show that the proposed approach can fulfill the requirement of fine-grained human motion segmentation for automatic ADL monitoring.

Wearable sensor-based rehabilitation exercise assessment for knee osteoarthritis.

Since the knee joint bears the full weight load of the human body and the highest pressure loads while providing flexible movement, it is the body part most vulnerable and susceptible to osteoarthritis. In exercise therapy, the early rehabilitation stages last for approximately six weeks, during which the patient works with the physical therapist several times each week. The patient is afterwards given instructions for continuing rehabilitation exercise by him/herself at home. This study develops a rehabilitation exercise assessment mechanism using three wearable sensors mounted on the chest, thigh and shank of the working leg in order to enable the patients with knee osteoarthritis to manage their own rehabilitation progress. In this work, time-domain, frequency-domain features and angle information of the motion sensor signals are used to classify the exercise type and identify whether their postures are proper or not. Three types of rehabilitation exercise commonly prescribed to knee osteoarthritis patients are: Short-Arc Exercise, Straight Leg Raise, and Quadriceps Strengthening Mini-squats. After ten subjects performed the three kinds of rehabilitation activities, three validation techniques including 10-fold cross-validation, within subject cross validation, and leave-one-subject cross validation are utilized to confirm the proposed mechanism. The overall recognition accuracy for exercise type classification is 97.29% and for exercise posture identification it is 88.26%. The experimental results demonstrate the feasibility of the proposed mechanism which can help patients perform rehabilitation movements and progress effectively. Moreover, the proposed mechanism is able to detect multiple errors at once, fulfilling the requirements for rehabilitation assessment.