2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)最新文献

{"title":"Graphene-based Smart Insole for Gait Monitoring","authors":"Negin Faramarzi, Babar Ali, H. C. Bidsorkhi, A. D’Aloia, A. Tamburrano, M. S. Sarto","doi":"10.1109/MeMeA57477.2023.10171949","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171949","url":null,"abstract":"The importance of human motion and gait analysis in healthcare cannot be overstated, as it is intricately tied to chronic illnesses. The development of wearable electronics such as smart insole systems has enabled remote and long-term gait monitoring and provides more accurate data. Wearable electronics demand components that possess both flexibility and sensitivity, which are key to their performance. Utilizing low-cost and rapid prototyping techniques, the piezoresistive pressure sensor is developed with spray deposition of graphene nanoplatelets/polycaprolactone composite on the fiber-based commercial insole. The resulting sensor exhibits a pressure range up to 400 kPa and high linear sensitivity (~ 0.376 kPa-1), making it suitable for monitoring human motions. Furthermore, to investigate its practical application in real-time monitoring, the sensor is connected to a low-power programmable data logging and transmitting device for output signal acquisition. The sensor can distinguish different motion states such as walking, jumping, and running while proving its stability potential for long-term use.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"57 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125126527","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gait-based Biometric System Using Pressure Sensing Mats and Machine Learning Algorithms","authors":"J. Chiou, Ching Yen, Fei Wu","doi":"10.1109/MeMeA57477.2023.10171858","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171858","url":null,"abstract":"The COVID-19 pandemic has emphasized the awareness of avoiding contact with shared or public devices, such as those used in traditional biometric systems. Common biometric systems, including fingerprint, palmprint, and iris recognition, require physical contact with the device, which increases the risk of contracting infectious diseases. As a result, non-contact biometric systems, such as gait recognition, may be increasingly important in the future. In this paper, we present an accurate gait recognition system that uses pressure sensing mats. Our proposed system employs high-density pressure sensing mats that significantly reduce computational complexity when compared to traditional gait recognition methods that use cameras. We acquired pressure distribution data from 30 subjects, including 19 males and 11 females, and developed an algorithmic framework that involves data preprocessing and classification to identify different subjects. We implemented five supervised machine learning models as classifiers, and our results indicate that the Convolutional Neural Networks (CNN) model performed the best, with a classification accuracy of 92.08%. Our study shows that the proposed gait recognition system is an effective non-contact biometric system that can distinguish different individuals with high accuracy. The use of pressure sensing mats reduces the risks associated with physical contact, making it a promising solution for biometric recognition in public spaces during the ongoing COVID-19 pandemic. In conclusion, our research contributes to the development of non-contact biometric systems and presents a viable solution for future applications.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116748558","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A sensorized FES-cycling system to quantify training performance and optimize stimulation strategies","authors":"Nicole Sanna, Federica Ferrari, E. Ambrosini, A. Pedrocchi, M. Tarabini","doi":"10.1109/MeMeA57477.2023.10171920","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171920","url":null,"abstract":"For people with a spinal cord injury (SCI), cycling by means of Functional Electrical Stimulation (FES) represents an effective rehabilitation exercise. FES-cycling can have beneficial effects on paretic muscles reducing the secondary effects caused by paralysis. Moreover, it can be seen as a way to perform an inclusive sport activity for people with disability, making it an example of “Sport-Therapy”. In recent years, the Cybathlon competition has renewed the interest in this discipline. This paper presents the set-up of a mobile FES-cycling system. A commercial passive recumbent trike has been adapted for the use of cyclists with SCI. Two four-channel stimulators have been integrated in the system together with a measurement chain. This latter is composed by an encoder, a heart rate sensor and sensorized pedals to measure tangential and radial forces that the subject is producing with each leg independently. The system is developed with the aim to give real-time outcome information about cycling performance and to quantify differences between several stimulation strategies. One SCI pilot was involved in the study and exemplary results acquired during one of his training sessions are shown to demonstrate the feasibility of the system and its potentiality. In future, this set-up could be used to optimize stimulation strategies.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116430832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Performance Change with the Ratio of Training Data A Case Study on the Binary Classification of COVID-19 Chest X-Ray by using Convolutional Neural Networks","authors":"Kuniki Imagawa, Kohei Shiomoto","doi":"10.1109/MeMeA57477.2023.10171929","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171929","url":null,"abstract":"One of the features of artificial intelligence/machine learning-based medical devices resides in their ability to learn from real-world data. The performance may change after the market introduction. There are many aspects that contribute to the performance change relative to the real-world training data, such as the number and disease ratio. In actual clinical practice, the ratio of obtained training data varies from country to country, from region to region within each country, and from one hospital to another. Therefore, establishing a pre-change control plan at a premarket stage is essential to achieve safety and effectiveness through total product life cycles. In our previous work, we evaluated the performance change on the binary classification of coronavirus disease 2019 (COVID-19) and normal with the number of training data using two publicly large available chest X-ray (CXR) images. However, these results were obtained with the same ratio in the training data. Thus, this study aims to evaluate the performance change with a non-uniform ratio of COVID-19 CXR images based on the results of previous studies. We used the AlexNet and ResNet34 with and without the fine-tuning method as convolutional neural network (CNN) models. A total of 500, 1000, and 2000 CXR images were selected as training and validation datasets. These datasets represent states in which the performance change improves rapidly and those in which an equilibrium state is reached. Each dataset was divided into seven datasets, and the area under the curve was employed to evaluate the performance change for each dataset through independent 1000 test datasets with the same ratio. Our result shows that all performances indicate that there is an upward convex relationship to the ratio of COVID-19 CXR images, and the vertex is where the ratio is the same. This trend was remarkable for the rapidly improving state and the CNNs without a fine-tuning method. Moreover, the visual explanations technique called Grad-CAM for interpreting classification results of CNN models support these results.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"110 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114820500","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EMG Based Clinical Evaluation of an Unpowered Exoskeleton Device","authors":"R. Halder, Bijit Basumatary, A. Pandya, Ganesh Ram Jangir, Anil K. Jain, A. Sahani","doi":"10.1109/MeMeA57477.2023.10171864","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171864","url":null,"abstract":"This paper reports a clinical study to characterize reduction in load on the major muscles of the back by use of an unpowered, lightweight, protective and therapeutic exoskeleton device named JaipurBelt that supports the spine and waist. Seventy nine subjects underwent Institutional Ethical Committee approved clinical trial at Santokba Durlabhji Memorial Hospital (SDMH), Jaipur, India. The protocols used for this study incorporate without device without load (WOJBWOL), without device with load (WOJBWL), with device without load at a medium level of support (WJBMidWOL), with device with load at a medium level of support (WJBMidWL), with device with load at a maximum level of support (WJBMaxWL). The EMG was recorded from six major back muscles. The result showed that, average reduction of muscle activity in all six muscles for Stoop Bending Up (SBU) is about 7.62%, and for Stoop Bending Down (SBD) is about 12.19% in without load condition. In with load condition and maximum level of support (WJBMaxWL), the overall maximum reduction of muscle activity was 80.97% for Ninth Thoracic Vertebra of Erector Spine (EST9), 44.39%. for Fourth Lumbar Vertebra of Erector Spine (ESL4), 24.62% for Multifidus (MF), 10.18% for Quadratus Lumborum (QL), 37.54% for Gluteus maximus (GM), 40.23% for Rectus Femoris (RF). In this clinical study, with the use of this unpowered exoskeleton device, it was found that there is a substantial reduction in muscle force requirements for load lifting, frequent bending ups, bending down and stooping activities by reducing the load from back and abdominal muscles. Thus, use of this device can potentially helps in reducing the risk of lower back disorders, fatigue, musculoskeletal problems, spinal disorders like slip disc and associated pain. This study was conducted after registration with Central trial register of India (CTRI registration number CTRI/2017/01/007649dtd 16/01/2017).","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129495178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Characterization of Implantable Capacitive Intrabody Communication Channel between In-body and On-body Devices on a Liquid Phantom","authors":"Matija Roglić, Yueming Gao, Ivana Artić, Z. Lucev","doi":"10.1109/MeMeA57477.2023.10171879","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171879","url":null,"abstract":"Implantable capacitive coupling (CC) intrabody communication (IBC) provides a method of communication for in-body devices to communicate not only between each other, but also with an on-body device and vice versa, using a low power, highly secure way of communication. However, to be able to realize such systems, it is important to understand the characteristics of a communication channel in an implantable CC. Therefore, in this paper, measurements of the received power in an implantable CC IBC system were performed on a liquid phantom with the same conductivity as a muscle tissue, using proprietary developed battery-powered devices (transmitter and receiver) for different measurement scenarios. The transmitter was placed inside the phantom while the receiver was placed outside of the phantom and vice versa, and the type of electrode used was changed. The results showcase the importance of minimizing the bandpass profile effect caused by the long cables. It is also shown that insulating the ground electrode affects the measured attenuation by about 6 dBm.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129514475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Flexible Microfluidics for Raman Measurements on Skin","authors":"A. Golparvar, Assim Boukhayma, S. Carrara","doi":"10.1109/MeMeA57477.2023.10171904","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171904","url":null,"abstract":"The present modalities of body chemistry monitoring via invasive skin penetration sampling have potential safety hazards in long-term continuous biomarker analysis due to utilizing biorecognition elements. Non-invasive optical sensing modalities show promise in biosensing by providing accurate biomolecule measurements. For instance, Raman spectroscopy provides quantifiable information about specific vibrational energy levels of the molecule’s chemical bonds that can be selectively linked to the molecule’s concentration even in a complex medium. However, these emerging modalities for medical measurements require precision measures on human tissues. This can be enabled by microfluidics. Therefore, merging Raman spectroscopy and microfluidics can provide inherently selective, extremely sensitive, repeatable, and highly accurate in situ optical biosensing from small sample volumes without acquiring biorecognition elements. To that aim, microfluidics devices are required to operate on the skin to provide precise Raman scattering measurements of sweat. However, the material choice for Raman-microfluidics is not trivial because, other than system usability and material/skin interface biocompatibility, the material selection also depends on Raman instrumentation parameters as well as on the target molecule and sensing medium. Therefore, this paper aims to show optimizations of such design for soft epidermal microfluidics for Raman scattering-based biosensing on skin. First, we investigate the Raman activity of three soft polymeric materials in experiments mimicking real testing scenarios. Then, we select the best materials to develop a flexible “lab-on-skin” platform compatible with Raman spectroscopy. Next, we develop multilayer microfluidic devices with simple, cleanroom-free, and soft lithography-free processes using laser patterning, controlled casting, and layer bonding with acrylic adhesives or O2 plasma activation. Finally, we characterize the developed soft microfluidic devices in ex vivo sweat lactate monitoring with syntactic sweat, including +30 sweat analytes which correctly mimic actual human sweat on porcine skin and show sensitive and repeatable medical measurement.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128891754","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Duo-Stage driven Deep Neural Network Approach for Mitigating Electrode Shift Impact on Myoelectric Pattern Recognition Systems","authors":"Frank Kulwa, O. W. Samuel, M. G. Asogbon, Tolulope Tofunmi Oyemakinde, O. Obe, Guanglin Li","doi":"10.1109/MeMeA57477.2023.10171910","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171910","url":null,"abstract":"A major barrier to the commercialization of pattern recognition (PR)-based myoelectric prostheses is the lack of robustness to confounding factors such as electrode shift which has been lingering for years. To overcome this challenge, a novel Duo-Stage Convolutional Neural Network (DS-CNN) is proposed. The DS-CNN is comprised of two cascaded stages in which the first stage deciphers the occurrence of a particular kind of shift upon which a requisite CNN model is triggered in the second stage for accurate decoding of individual motion intent, which is necessary for initiating robust control of the prostheses. The proposed scheme works on raw EMG signals as input which reduces the preprocessing time that would be required in conventional machine learning-based PR schemes, to effectively mitigate both transverse and longitudinal shifts using the same network architecture. This approach was validated for four distinct electrode shift conditions (with shifts in the range of 7.50mm-10.05mm) in a dataset obtained from 18 able-bodied subjects that performed 8 classes of targeted hand gestures. The experimental results show that the proposed dual-stage driven deep neural network model can adequately resolve the effects of electrode shift with classification accuracy near the No-shift scenario (< 1.70% difference between shift mitigation and No shift scenarios). These outcomes suggest that our method can provide a practical solution for adaptation to electrode shift, thus improving the robustness of the EMG pattern recognition systems in both clinical and commercial settings.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123448457","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Computational Modelling of Probe Configurations for Electrical Impedance Spectroscopy-based Differentiation of Thyroid and Parathyroid Tissues","authors":"Malwina Matella, D. Walker, Keith D. Hunter","doi":"10.1109/MeMeA57477.2023.10171880","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171880","url":null,"abstract":"Background: The ZedScan™ probe is an electrical impedance spectroscopy (EIS) device originally developed as a tool to diagnose Cervical Intraepithelial Neoplasia (CIN), recently explored as a potential tool to distinguish parathyroid glands from the surrounding tissues during surgery [1]. As reported, the relatively large size of the tip of the probe (5.5 mm) can be problematic to accurately cover and measure the impedance of small structures, such as parathyroid glands (3-7 mm). In this study, we will utilise a computational model to quantity the uncertainty associated with the probe misalignment and evaluate the benefits of reducing the size of the probe on thyroid and parathyroid differentiation. Materials and Methods: Multiscale finite element models of thyroid and parathyroid were developed to investigate the impact of the EIS measurement accuracy of various probe-parathyroid misalignment scenarios. Subsequently, the macroscale impedivity of thyroid and parathyroid tissues was simulated with smaller probe configurations to explore the benefits of probe optimisation. Results: The probe misalignment study reported up to 40%, 21% and 26% decrease in low-and high-frequency impedance and impedance frequency, respectively, compared to results with a desirable parathyroid-probe coverage. The decrease in parathyroid impedance brings the results closer to thyroid baseline EIS spectrum, reducing the feasibility of tissues separation. The probe optimisation study reported about 4% increase in parathyroid’s low-frequency impedance, showing a slight improvement in the thyroid and parathyroid differentiation. Conclusions: This study revealed the importance of the accuracy of the EIS measurement with the ZedScan™ device by demonstrating that imprecise parathyroid coverage could result in ‘contaminated’ measurements constraining their differentiation. Moreover, a smaller probe-tip design has the potential to further increase the ease of acquiring accurate parathyroid results, slightly improving the separation between the tissues on the basis of EIS measurements.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126575693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Exploratory study on Evolutionary Random Forests for Classification in Medical Datasets","authors":"Susanne Blotwijk, Camille Raets, Kurt Barbé","doi":"10.1109/MeMeA57477.2023.10171908","DOIUrl":"https://doi.org/10.1109/MeMeA57477.2023.10171908","url":null,"abstract":"This paper presents an exploratory study on the efficacy of different machine learning algorithms for classification in medical datasets, with a particular focus on a recently published evolutionary random forest algorithm. The study is motivated by the increasing availability of medical measurements obtained from various new sources such as wearables, and continued improvements in existing measurement techniques, which have resulted in an increase in the number of variables that can be measured per patient. Meanwhile, recruiting patients and collecting data often remain a costly and time-consuming endeavor, resulting in datasets with high dimensionality and low instance to feature ratios. The study aims to evaluate the performance of these machine learning algorithms and to investigate their sensitivity to varying sample sizes. Additionally, the study examines whether the use of an evolutionary random forest algorithm can improve performance and robustness in these datasets. The study was conducted on nine different datasets to assess the extent to which the findings can be generalized. The results indicate that the evolutionary random forest generally outperforms other classification algorithms. Furthermore, the performance gap often widens at lower instance to feature ratios. Future work may build on these findings to develop more sophisticated machine learning algorithms that are tailored to specific medical classification applications.","PeriodicalId":191927,"journal":{"name":"2023 IEEE International Symposium on Medical Measurements and Applications (MeMeA)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-06-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116928070","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}