BIODEVICES 2022 Abstracts

Full Papers Short Papers
Full Papers
Paper Nr: 2
Title:

Automatic Detection of Timed-up and Go Tests with IMU Sensor Data
Authors:

Franz Kroll, Sven Löffler, Ilja Becker and Petra Hofstedt
Abstract: The evaluation of the current state and examination of geriatric patients is a time consuming process for the medical staff and the patients. The independence of the geriatric patients is further reduced through the interruptions in their daily life caused by these examinations. One of these evaluation techniques is the so called Timed-Up and Go test (TUG). The test uses a simple sequence of motions to assess the fall risk of a person. Advances in the technology of wearable sensors and machine learning make it possible to automate these evaluation methods with a compact system. This paper continues the research that was already done in the fields of human activity recognition and automatic TUG detection and proposes a novel method for the automatic detection of the Timed-Up and Go without interrupting the daily life of the patients.
Download
Paper Nr: 7
Title:

Incorporation of VOC-Selective Peptides in Gas Sensing Materials
Authors:

Ana R. Oliveira, Efthymia Ramou, Gonçalo G. Teixeira, Susana J. Palma and Ana A. Roque
Abstract: Enhancing the selectivity of gas sensing materials towards specific volatile organic compounds (VOCs) is challenging due to the chemical simplicity of VOCs as well as the difficulty in interfacing VOC selective biological elements with electronic components used in the transduction process. We aimed to tune the selectivity of gas sensing materials through the incorporation of VOC-selective peptides into gel-like gas sensing materials. Specifically, a peptide (P1) known to discriminate single carbon deviations among benzene and derivatives, along with two modified versions (P2 and P3), were integrated with gel compositions containing gelatin, ionic liquid and without or with a liquid crystal component (ionogels and hybrid gels respectively). These formulations change their electrical or optical properties upon VOC exposure, and were tested as sensors in an in-house developed e-nose. Their ability to distinct and identify VOCs was evaluated via a supervised machine learning classifier. Enhanced discrimination of benzene and hexane was detected for the P1-based hybrid gel. Additionally, complementarity of the electrical and optical sensors was observed considering that a combination of both their accuracy predictions yielded the best classification results for the tested VOCs. This indicates that a combinatorial array in a dual-mode e-nose could provide optimal performance and enhanced selectivity.
Download
Paper Nr: 10
Title:

Experimental Security Analysis of Connected Pacemakers
Authors:

Guillaume Bour, Marie G. Moe and Ravishankar Borgaonkar
Abstract: Medical devices and their connectivity capabilities are providing a variety of benefits to the healthcare domain, including remote monitoring, automated alerts, and improved patient outcomes. However, these medical devices introduce a range of new potential cyber security risks when connected to the Internet, affecting the patient or the healthcare infrastructure. In this paper, we systematically analyze the security issues of connected pacemakers. In particular, we use a black box testing methodology against a commercial pacemaker device and the network infrastructure. Our main objective is to understand how the data is sent from a bedside monitor in the patient’s home to the backend server hosted by the pacemaker manufacturer, and whether or not this data is protected from a cyber security perspective. To do so, we leveraged several hardware related vulnerabilities found in the bedside monitor to obtain the firmware of the device and then reverse engineered the proprietary communication protocol. We demonstrate how vulnerabilities in this protocol can be leveraged to allow an attacker to perform a man-in-the-middle attack on the pacemaker.
Download
Paper Nr: 11
Title:

Personalized Hip Replacement: State of the Art and New Tools Proposals
Authors:

Isabel Moscol, William Solórzano-Requejo, Carlos Ojeda and Ciro Rodríguez
Abstract: Hip replacement is one of the most successful surgical events that progressively more patients require because of the better life expectancy and increase in the average age of several countries. It further promoted the improvement of hip prosthesis lifespan in sciences such as materials, mechanics and, recently, computer science with artificial intelligence (AI). The present investigation aims to make a systematic review of the progress with recent developments and criteria to get optimal outcomes in the design and selection of hip implants, emphasizing femoral stem parameters for their relevance to the entire prosthesis performance. New software tools such as clustering, and a different finite element analysis (FEA) approach are introduced to speed up customized design processes without sacrificing accuracy. Clustering algorithms delimited the proximal femur properly according to its anatomical locations. Moreover, Altair SimSolid® software proved satisfactory accuracy compared to NX® simulation values despite the complex morphology of the proximal femur with a maximum deviation of 12.94% and a simulation time of less than 30%.
Download
Paper Nr: 12
Title:

The Method and Apparatus for Peripheral Arterial Disease Treatment
Authors:

Alexey Sudarev and Evgeny Korotich
Abstract: The paper is devoted to a new method of peripheral arterial disease (PAD) treatment - cardiosynchronized antegrade pneumocompression. The method is based on sequential compression of the lower extremities to create an enhanced antegrade pressure wave in the arteries in order to increase blood flow in the distal parts of the lower extremities. The main provisions of the method, the physiological model of exposure are considered. It is shown how to optimally synchronize the impulses with the cardiac cycle for the simultaneous achievement of a beneficial hemodynamic effect in the limbs and coronary vessels. The structure of the device for the implementation of the method based on the system for external counterpulsation CARDIOPULSAR is presented. The physiological effects of exposure (increased blood flow, ABPI, temperature of the extremities) were investigated. The results of treatment on volunteers were presented.
Download
Paper Nr: 14
Title:

Automatic Segmentation of the Cervical Region in Colposcopic Images
Authors:

Paloma C. Andrade and Sesh Commuri
Abstract: Cervical cancer is one of the most common cancers affecting women, especially in developing countries and in resource constrained areas in the western world. While easily treatable if detected early, the lack of adequate resources and skilled physicians make this disease difficult to detect and treat. In this paper, we propose a vision-based approach anchored in machine-learning principles to detect and quantify lesions on the surface of the cervix. Preliminary results indicate that the proposed method can segment images of the cervix and successfully detect lesions other artifacts. The image normalization approach can also determine the locations of lesions and their spread. Validation of this approach during clinical trials is being pursued as the first step towards developing low-cost bioinformatics-based screening tools for early detection of cervical cancer.
Download
Paper Nr: 15
Title:

A Mechatronics-twin Framework based on Stewart Platform for Effective Exploration of Operational Behaviors of Prosthetic Sockets with Amputees
Authors:

Dejiu Chen, Suranjan R. Ottikkutti and Kaveh N. Tahmasebi
Abstract: A Stewart platform is a six-degree-of-freedom parallel manipulator widely used as the motion base for flight simulators, antenna positioning systems, machine tool technology, etc. This work presents a novel mechatronics-twin framework that integrates such a manipulator with advanced biomechanical models and simulations for effective exploration of operational behaviors of prosthetic sockets with amputees. By means of the biomechanical models and simulations, the framework allows the users to first analyze the fundamental operational characteristics of individual amputees according to their specific body geometries, pelvis-femur structures, sizes of transfemoral sockets, etc. Such operational characteristics are then fed to one Stewart platform as the reference control signals for the generation of dynamic loads and behaviors of prosthetic sockets that are otherwise difficult to observe or realize with the real amputees. Experiments in form of integration testing show that the proposed control strategy is capable of generating expected dynamic operational conditions. Currently, the mechatronics-twin framework supports a wide range of biomechanical configurations and the quantification of the respective intra-socket load conditions for socket design optimization and anomaly detection.
Download
Paper Nr: 18
Title:

Tele-tDCS: A Novel Tele-neuromodulation Framework using Internet of Medical Things
Authors:

Samuel D. Herring, M. A. Hannan Bin Azhar and Mohamed Sakel
Abstract: As part of the Internet of Medical Things (IoMT) within Biomedical Engineering, telehealth is an emerging field. Due to the recent events surrounding COVID-19, it has become obvious that Telehealth treatments must be developed as a means of protecting vulnerable patients in hospitals by reducing the need to visit and therefore reducing risk to physicians. This paper investigates the feasibility of developing a non-invasive remote neuro-stimulation system using internet-based transcranial Direct Current Stimulation (tDCS). A hardware-based prototype tDCS device has been developed to be controlled using a remote command-line interface over the internet. As a result, a physician can remotely set the parameters for the tDCS treatment and monitor the treatment in real-time to ensure patient safety. In this study, the feasibility of a Tele-tDCS system was investigated, as well as the capabilities a Tele-tDCS system should offer to patients.
Download
Paper Nr: 30
Title:

Ortho-Monitorizer: A Portable Device to Monitor the Use of Upper Limb Orthoses - A Concept Proof
Authors:

Raquel Gonçalves, Carla Quintão, Ricardo Vigário and Cláudia Quaresma
Abstract: This article presents the development of a wearable and portable system, the Ortho-Monitorizer, which allows an objective, continuous and simultaneous monitoration of the temperature and pressure exerted on the skin on the 3 main pressure points derived from the use of a hand and wrist orthosis. It also allows the monitorization of the patient’s compliance to the orthosis, providing its time of use. This way, adjustments to the orthosis can be optimized, reducing the discomfort felt by the patient, increasing compliance, reducing the risk of pressure sores’ formation derived from inadequate levels of pressure applied, and consequently, increasing the effectiveness of orthosis’ use. Therefore, an Arduino Uno, powered by a powerbank, is used as microcontroller. Three force sensors and three temperature sensors are controlled by the microcontroller to detect the pressure and temperature. A Bluetooth Low Energy module is used to send data from the Arduino to an android application under development, which will allow healthcare professionals to consult all the information and clinical history relating to each patient, as well as allowing the patient to develop a greater awareness and sense of responsibility regarding their performance in relation to the guidelines provided by the health professional.
Download
Paper Nr: 31
Title:

paMELA - Photoacoustic Melanoma Detector Design for Real-Time Imaging of Melanin with 18 db SNR and 10 μm Precision
Authors:

Elia A. Vallicelli, Giberto Chirico, Oliver Cosmi, Lorenzo Stevenazzi and Mattia Tambaro
Abstract: This article presents the complete photon-to-bit cross-domain model of a photoacoustic melanoma detector (paMELA), consisting of a pulsed laser, a multichannel acoustic sensor, an analog front-end and a DSP stage for the implementation of an acoustic imaging algorithm. The photoacoustic effect can be exploited to obtain complementary information on a suspected melanoma with respect to classical dermatoscopic techniques. By modelling the physical phenomena (generation and propagation of the acoustic signal), electromechanical process (pressure-voltage transduction by the acoustic sensor), the analog and digital signal processing, it is possible to evaluate the impact of each stage on the quality of the final image. Finally, the simulation results of paMELA allow to evaluate the performance of the detector in terms of localization precision and signal-to-noise ratio, using both a single point-like source and a complete biological tissue phantom with different sources sizes and features, obtaining 18 dB of SNR and 10 μm of precision in 1s acquisition.
Download
Short Papers
Paper Nr: 3
Title:

Development of Myoelectric Control Module for Prosthetic Hand with Artifact Removal during Sensory Electrical Stimulation
Authors:

Yashuo Yu, Chih-Hong Chou, Jie Zhang, Manzhao Hao and Ning Lan
Abstract: Evoked Tactile Sensation (ETS) with transcutaneous electrical nerve stimulation (TENS) can provide amputees with a non-invasive neural interface for sensory feedback. However, sensory stimulation at the projected finger map (PFM) on the stump skin causes interference in surface electromyographic (sEMG) signals used for prosthesis control. This study developed a practical solution that combined hardware blanking and software filtering to eliminate stimulus artifacts in real-time. A synchronized blanking circuit was inserted after the differential amplifiers to partially remove artifact spikes. EMG signal was then sampled and further processed by a digital signal processor (DSP). A digital comb filter removed the remaining artifacts at all harmonic frequencies of stimulation. The filtered EMG was rectified, and its envelope was extracted to control prosthetic hand. This technique was tested for its effectiveness in removing stimulus artifacts in three able-bodied subjects and in one transradial amputee operating a Bebionic hand. Results in able-bodied subjects indicated that the technique was effective in removing stimulus artifacts in EMG under different conditions. In the amputee subject, grasp control using the Bebionic hand was obtained with simultaneous sensory stimulation in the ipsilateral stump. The amputee subject achieved an average success rate of 90% for identifying the length of grasped objects. Tests confirmed that the technique is adequate to remove stimulus artifacts from EMG signals and allows control of the Bebionic hand with simultaneous sensory stimulation.
Download
Paper Nr: 4
Title:

Comparing Closed-loop Control of Drug Infusion using MPC and PID
Authors:

Tiro Setati, Willem J. Perold, Pieter R. Fourie and Daniel Withey
Abstract: Continuous intravenous drug delivery can require careful dosage and the maintenance of consistent blood plasma concentration levels. Here, the closed-loop control of drug concentration in simulated patients’ bloodstreams was investigated. During the investigation, the closed-loop controller performance of a Proportional-Integral-Derivative (PID) and a Model Predictive Controller (MPC) were compared. From the simulation results, the MPC has shown to be a better controller because of its shorter settling time and smaller stepresponse overshoot, which are desirable in a clinical setting. However, the MPC has shown to be more resource-intensive on the controller system. Through the simulations conducted, it can therefore be concluded that a closed-loop controller containing an MPC control block adequately controls the drug infusion to a simulated patient.
Download
Paper Nr: 6
Title:

Brainy Home: A Virtual Smart Home and Wheelchair Control Application Powered by Brain Computer Interface
Authors:

Cihan Uyanik, Muhammad A. Khan, Rig Das, John P. Hansen and Sadasivan Puthusserypady
Abstract: In recent years, smart home applications have become imperative to improve the life quality of people, especially for those with motor disabilities. While the smart home applications are controlled with interaction tools such as mobile phones, voice commands, and hand gestures, these may not be appropriate for people with severe disabilities that impacts their motor functions, for instance locked-in-syndrome (LIS), amyotrophic lateral sclerosis (ALS), cerebral palsy, stroke, etc. In this research, we have developed a smart home and wheelchair control application in a virtual environment, which is controlled solely by the steady-state visual evoked potential (SSVEP) based brain computer interface (BCI) system. It is a relatively low cost, easy to setup wireless communication protocol, which offers high accuracy. The system has been tested on 15 healthy subjects and the preliminary results comprehensively show that all the subjects completed the device interaction tasks with approximately 100% accuracy, and wheelchair navigation tasks with over 90% accuracy. These results clearly indicate that in future, the developed system could be used for real-time interfacing with assistive devices and smart home appliances. The proposed system, thus may play a vital role in empowering the disabled people to perform daily-life activities independently.
Download
Paper Nr: 9
Title:

Study of Polymers for the Implementation of an Axial Impeller with a Central Shaft in a Ventricular Assist Device
Authors:

Johanna Muñoz-Pérez, Carlos Jiménez-Carballo, Gabriela Ortiz-León and Marta Vílchez-Monge
Abstract: The main goal of the present research was to determine the value of the mechanical parameters with which a material to be used in a blood pump impeller must comply. To obtain these values, multiphysical numerical simulation and modeling of the Fluid-Structure Interaction (FSI) of the impeller with defined conditions and geometry was carried out, by means of Computational Fluid Dynamics (CFD) based on the Finite Element Method (FEM), specifically the partitioned procedure was used. As a result of the simulations, the deformed geometries, the maximum values of the Von Mises stress and the volumetric deformations for an axial impeller with a central shaft were obtained. From this research it was determined that from the structural point of view the selected biocompatible polymers are candidates for the manufacture of the impeller.
Download
Paper Nr: 13
Title:

Improved Method for Measuring the Pulse Wave Propagation Velocity for Palpable Arteries
Authors:

V. E. Antsiperov, M. V. Danilychev, G. K. Mansurov and E. R. Pavlyukova
Abstract: The results, regarding the development and testing of a quantitative method for diagnosing the condition of the arterial walls, based on the application of a three-channel pneumatic sensor of an original design, are presented. The possibility of using the data obtained by this device in combination with synchronous ECG measurement to determine the velocity of pulse wave propagation between two cross sections of the selected artery has been demonstrated. One of the key points of this technology is the selection of a specific pulse wave element as a reference mark for tracking the signal transit time relative to the R-peak of the synchronous ECG. After collecting measurement statistics, the average values of the wave propagation time between the selected points of the artery, considering the variability of the front delay values, are used to directly calculate the propagation velocity of the pulse wave in the investigated area of the artery. The value of the pulse wave propagation velocity in return is an objective parameter that characterizes the degree of elasticity (or stiffness) of the artery walls and their behaviour in different physiological situations.
Download
Paper Nr: 16
Title:

pH and SpO2 Miniaturized Sensors for Fetal Health Monitoring

Authors:

T. Nguyen, A. Bessiere, Q. Rousset, B. Journet, S. L’Horset, H. Takhedmit and G. Lissorgues
Abstract: In this paper we present a prototype which is a first attempt to get continuous fetal health monitoring during labor. This system is capable of simultaneously measuring pH, SpO2 and provides a clear photoplethysmogram in real time. A Titanium nitride pH sensing electrode of 600 μm diameter in size performed a linear Nernstian sensitivity of 62.8 mV/pH within the pH range of interest from 6 to 8 and a precision of 0.14 in pH. The reflectance SpO2 sensor employed two LEDs at 630 nm and 940 nm wavelengths and is monitored by a MSP432 microcontroller; the result recorded shows close behavior to a commercial device. This work is under optimization process for a better accuracy and aiming for integration into a specific miniaturized device with a touch screen as user interface.
Download
Paper Nr: 19
Title:

Novel Concept for a Mechanical Intraurethral Artificial Urinary Sphincter
Authors:

Alexander Preis, Johannes Treviranus, Elisabeth Benke, Sebastian Reitelshöfer and Jörg Franke
Abstract: Stress urinary incontinence is a common pathologic condition in society and an increasing socio-economic challenge. Current artificial urinary sphincters for severe cases have high failure rates, cannot be applied sex-independent and their handling is not intuitive. To address these issues, a novel intraurethral closure system was developed. It works without an external energy supply and consists of an inflatable balloon that presses against the inner contour of a surrounding cylindrical structure implanted in the urethra. Regulation of the closure system is achieved by the interaction of the three main components: the closure balloon, the throttle and the compensating reservoir. The developed closing mechanism seals the bladder at rest and during short peak loads and opens only when the bladder pressure is increased by pressing with the abdominals for a longer period of time for micturition.
Download
Paper Nr: 20
Title:

Android-based ECG Monitoring System for Atrial Fibrillation Detection using a BITalino® ECG Sensor
Authors:

Gabriel S. Lazaretti, João P. Teixeira, Eduardo V. Kuhn and Pedro H. Borghi
Abstract: Cardiac arrhythmias are disorders that affect the rate and/or rhythm of the heartbeats. The diagnosis of most arrhythmias is made through the analysis of the electrocardiogram (ECG), which consists of a graphical representation of the electrical activity of the heart. Atrial fibrillation (AF) is the most present type of arrhythmia in the world population. In this context, this work deals with the implementation of a system for automatic analysis of ECG signals aiming to identify AF episodes. The system consists of a signal acquisition step performed by an ECG sensor connected to an acquisition platform. The acquired signal is transmitted via bluetooth to a smartphone with AndroidTM operating system. The signal processing is carried out through an application developed using the IDE AndroidTM Studio. When assessed over signals from the MIT-BIH Atrial Fibrillation database, the R-wave peak detection algorithm showed mean values of sensitivity and positive predictivity of 98.99% and 95.95%, respectively. The classification model used is based on a long short-term memory (LSTM) neural network and had an average accuracy of 94.94% for identifying AF episodes.
Download
Paper Nr: 21
Title:

Separation Microfluidic Devices Fabricated by Different Milling Processes
Authors:

Inês M. Gonçalves, Miguel Madureira, Inês Miranda, Helmut Schütte, Ana S. Moita, Graça Minas, Stefan Gassmann and Rui Lima
Abstract: The diagnostic of several diseases can be performed by analysing the blood plasma of the patient. Despite of the extensive research work, there is still the need to improve the current low-cost fabrication techniques and devices for the separation of the plasma from the blood cells. Microfluidic biomedical devices have great potential for that process. Hence, two microfluidic devices made by micromilling and sealed with or without the solvent bonding technique were tested by means of a blood analogue fluid. A high-speed video microscopy system was used for the visualization and acquisition of the analogue fluid flow. Then, the separation of particles and plasma was evaluated using the software ImageJ. The device manufactured by the micromilling process without bonding showed a significant reduction of the amount of cells between the entrance and the exit of the microchannels. However, further analysis and optimizations of the microfluidic devices will be conducted in future work.
Download
Paper Nr: 22
Title:

Fourier Ptychography Microscopy Resolution Improvement Employing Refocusing
Authors:

Arban Uka, Gent Imeraj, Bjorna Qesaraku and Besmir Shehu
Abstract: Fourier ptychography is a computational imaging technique that is used to overcome the physical limitations in determining the spatial resolution of an optical system by combining a large number of low resolution images. The low resolution images are acquired using programmed illumination from an array of light sources, thus enabling the scanning of the k-space, which is the reciprocal space of the real domain. The use of this approach would improve the resolution when biological samples from patients are analyzed in multiparametric chambers. When an off-center light source is used at an oblique incidence angle, the optical path length changes thus defocusing the expected image. The common depth of focus of microscopes is a few micrometers and when a chamber of thickness from 0.5-1.0 cm is used, an adjustment of the focusing is needed. Here in this work, we report Fourier ptychography using LED illumination and an improved image quality is acquired when refocusing is implemented.
Download
Paper Nr: 26
Title:

Method for Assessing Blood Flow in Segments of the Eye using Multichannel Rheoophthalmography
Authors:

Elena N. Iomdina, Nina Y. Kushnarevich, Tatiana Y. Larina, Petr V. Luzhnov, Anna A. Kiseleva and Elena P. Tarutta
Abstract: The paper presents the issue of studying changes and redistribution of the blood flow level in different segments of the eye using the electrical impedance method - rheoophthalmography. There are described and considered the quantitative values using this method for the posterior segment of the eye and the retrobulbar segment of the eye. Based on the obtained data, an algorithm for differentiation of disease stage for research groups with myopia is proposed. The principle of its operation is described. The prospects for increasing the efficiency of the developed algorithm are considered.
Download
Paper Nr: 27
Title:

Clinical Efficacy and Pathogenetic Substantiation of Adjuvant Extracorporeal Photochemotherapy in Pemphigus Vulgaris
Authors:

A. V. Molochkov, Yu. V. Molochkova, A. V. Kildyushevsky, O. V. Karzanov and M. G. Kartashova
Abstract: This article reportson our clinical experience of application of extracorporeal photochemotherapy conducted with the ultraviolet extracorporeal blood irradiator or "KIT-A" (SJJ NPP "Cyclone-Test", Russia) as an adjuvant method in treatment of pemphigus vulgaris. We assess pathogenetic substantiation and clinical results of the proposed method as well as discussion on dynamics of immunological parameters in patients receiving actual treatment. Also current article analyze the possibility of applyingextracorporeal photochemotherapy method as an adjuvant treatment of pemphigus vulgaris with typicaldisease course.
Download
Paper Nr: 28
Title:

Data Acquisition, Conditioning and Processing System for a Wearable-based Biostimulation
Authors:

Leonardo Sestrem, Raul Kaizer, João Gonçalves, Paulo Leitão, João P. Teixeira, José Lima, Tiago Franco and José A. Carvalho
Abstract: Data acquisition by electromyography, as well as the muscle stimulation, has become more accessible with the new developments in the wearable technology and medicine. In fact, for treatments, games or sports, it is possible to find examples of the use of muscle signals to analyse specific aspects related, e.g., to disease, injuries or movement impulses. However, these systems are usually expensive, does not integrate data acquisition with the muscle stimulation and does not exhibit an adaptive control behaviour that consider the pathology and the patient response. This paper presents a wearable system that integrates the signal acquisition and the electrostimulation using dry thin-film titanium-based electrodes. The acquired data is transmitted to a mobile application running on a smartphone by using Bluetooth Low Energy (BLE) technology, where it is analysed by employing artificial intelligence algorithms to provide customised treatments for each patient profile and type of pathology, and taking into consideration the feedback of the acquired electromyography signal. The acquired patient’s data is also stored in a secure cloud database to support the physician to analyse and follow-up the clinical results from the rehabilitation process.
Download
Paper Nr: 29
Title:

A BCI-controlled Robot Assistant for Navigation and Object Manipulation in a VR Smart Home Environment
Authors:

Ethel Pruss, Jos Prinsen, Anita Vrins, Caterina Ceccato and Maryam Alimardani
Abstract: BCI-controlled smart homes enable people with severe motor disabilities to perform household activities, which would otherwise be inaccessible to them. In this paper, we present a proof of concept of an assistive robot with telepresence functionality inside a Virtual Reality (VR) smart home. Using live EEG data and a P300 Brain-Computer Interface (BCI), the user is able to control a virtual agent and interact with the smart home environment. We further discuss the potential use cases of our proposed system for patients with motor impairment and recommend directions for future research.
Download
Paper Nr: 1
Title:

Machine Learning-based Approach for Stroke Classification using Electroencephalogram (EEG) Signals
Authors:

Aktham Sawan, Mohammed Awad and Radwan Qasrawi
Abstract: In recent years, the health care field has heavily relied on the field of computation. The medical decision support system DSS, for instance, helps health professionals obtain accurate and reliable readings and diagnosis of patients’ vital signs. Nowadays, several medical devices allow capturing brain signals, some of these devices are wearable, which enhances signal quality and facilitates access to the signals than the traditional EEG devices. EEG signals are critical for assessing mental health and analyzing brain characteristics as they are able to detect a wide range of nerve-related diseases, such as stroke. This research seeks to study the use of machine learning techniques for the medical diagnosis of stroke through EEG signals obtained from the wearable device ‘MUSE 2.’ Eight ML techniques were used for analysis, the XGboost classifiers outperformed other classifiers in identifying strokes with an accuracy rate of 83.89%. The findings proved a 7.89% improvement on accuracy from the previous study “Predicting stroke severity with a 3-minute recording from the Muse portable EEG study.
Download
Paper Nr: 17
Title:

Innovative Methodology for the 3D Reconstruction of Body Geometries using Open-source Software
Authors:

Javier Tuesta-Guzmán, William Solórzano-Requejo, Gustavo Grosso-Salazar, Carlos Ojeda and Andrés Díaz Lantada
Abstract: Bioengineering teaching has limitations in developing countries due to the inaccessibility of expensive technology like scanners and commercial software, which holds back progress in the biomedical area because of a lack of resources. In this work, a new methodology is presented with the aim of obtaining a 3D model of body part by open-source software: Meshroom®, Meshmixer®, Ultimaker Cura®; and a cell phone camera. The procedure is based on three methods which were tested: images taken for a short time, burst mode and video-to-frames. Through the process of reverse engineering photogrammetry, an arm and a foot were obtained from images and for comparing the model with the real body part, 3D printing was used. The outstanding method is video-to-frames thanks to the high quality of the generated models and the shortest reconstruction time it presents. The technique developed can promote the education of engineers in the biomedical area, also providing an advance for developers with low economic resources, allowing them to have a new possibility of research.
Download
Paper Nr: 23
Title:

Development of a Piezoelectric Micromachined Ultrasound Transducer using Microfabrication Technology for in Vitro Neuromodulation
Authors:

Ryo Furukawa and Takashi Tateno
Abstract: Ultrasound neuromodulation, in which local and deep areas of the brain are stimulated, is promising for clinical applications. However, the mechanisms of action underlying the stimulation are still unknown. To elucidate the induction mechanisms, in vitro experiments are useful because they allow the extracellular conditions to be easily controlled. In this study, we developed a piezoelectric micromachined ultrasound transducer (PMUT) to modulate the activity of brain slices at the micrometer scale. To examine the relationship between the transducer size and the resonant frequency of the voltage-driven oscillations, we modeled the multi-layered structure and performed numerical calculations. A simple mathematical expression to estimate the size of the PMUT was obtained. We also designed and fabricated a PMUT with identical circular diaphragms with 580-μm radius. In addition, recording microelectrodes were fabricated into the PMUTs to monitor the transducer-driven neural activity. To characterize the PMUT properties, including the intensity and resonant frequency, we measured the pressure oscillations of the transducer driven by the applied sinusoidal voltage. Finally, we discuss the possibility of using our PMUT to stimulate brain slices in future applications.
Download
Paper Nr: 24
Title:

Prototyping and Early Validation of an Integrated, Electrochemical and Mass Three-sensor Array for Dengue Detection
Authors:

Ahmad A. Zainuddin, Mohd M. Asri, Cyril Guines, Muhammad Z. Zabedi, Khin M. Htay, Abdul A. Rahim, Matthieu Chatras, Arnaud Pothier, Wing C. Mak and Anis N. Nordin
Abstract: This paper presents the current progress towards a lab-on-chip biosensor for early dengue detection, consisting of an integrated sensor with dual-function working electrode that enables in-situ measurements of both electrochemical impedance spectroscopy (EIS) and quartz crystal microbalance (QCM) enclosed in a miniaturized 3D-printed package equipped with electrical contacts and sample fluid delivery to the quartz biosensor array. The sensors consist of an array of three 10 MHz IEQCM biosensors on a single quartz substrate. Early validation is performed for future dengue sensing application. We report the design, optimisation, and fabrication of the sensors, as well as early optimisation and validation of surface bioconjugation of antibodies. This lab-on-chip has the potential to provide accurate dengue detection due to its high sensitivity and dynamic range, as well as providing rapid and early dengue detection in point-of-care settings.
Download