sensors-logo

Journal Browser

Journal Browser

Advances in Biomedical Sensing, Instrumentation and Systems

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Wearables".

Deadline for manuscript submissions: closed (15 December 2023) | Viewed by 38251

Special Issue Editor


E-Mail Website
Guest Editor
Department of Information Engineering, Università Politecnica delle Marche, 60131 Ancona (AN), Italy
Interests: analog, digital and mixed signal circuit design and simulation; embedded systems design; wireless sensors and networks; signal processing
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Advances in electronics and computational capabilities are constantly increasing the possibilities to make portable, wearable, miniaturized, more power-efficient and/or more accurate sensing devices and instruments, which can also incorporate enough intelligence to autonomously analyze the captured signals and possibly react to them.

The aim of this Special Issue is to collect relevant papers that deal with all aspects regarding the challenges and solutions in the development of sensing devices, their hardware, their communication requirements, and how the data thus acquired is processed to provide useful information to the user of the system, be it the subject itself or a qualified physician or technician.

We thus seek papers that describe innovative developments in the acquisition of biomedical-related signals, their enabling technologies, and the interpretation of the data through automated techniques like machine learning and artificial intelligence.

Review articles that provide readers with scholarly educational material about the current research trends on the matter are also welcome.

Submissions are encouraged which address topics including, but are not limited to, the following:

  • Biosignal acquisition.
  • Wearable devices.
  • Portable sensors.
  • Wireless sensors.
  • Health tracking.
  • Health monitoring.
  • Sensor networks for biomedical signal acquisition.
  • Machine learning for biomedical signal analysis.
  • Automatic diagnosis and classification.

Prof. Dr. Giorgio Biagetti
Guest Editor

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Related Special Issue

Published Papers (18 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

13 pages, 2050 KiB  
Article
Improving Automatic Smartwatch Electrocardiogram Diagnosis of Atrial Fibrillation by Identifying Regularity within Irregularity
by Anouk Velraeds, Marc Strik, Joske van der Zande, Leslie Fontagne, Michel Haissaguerre, Sylvain Ploux, Ying Wang and Pierre Bordachar
Sensors 2023, 23(22), 9283; https://doi.org/10.3390/s23229283 - 20 Nov 2023
Viewed by 943
Abstract
Smartwatches equipped with automatic atrial fibrillation (AF) detection through electrocardiogram (ECG) recording are increasingly prevalent. We have recently reported the limitations of the Apple Watch (AW) in correctly diagnosing AF. In this study, we aim to apply a data science approach to a [...] Read more.
Smartwatches equipped with automatic atrial fibrillation (AF) detection through electrocardiogram (ECG) recording are increasingly prevalent. We have recently reported the limitations of the Apple Watch (AW) in correctly diagnosing AF. In this study, we aim to apply a data science approach to a large dataset of smartwatch ECGs in order to deliver an improved algorithm. We included 723 patients (579 patients for algorithm development and 144 patients for validation) who underwent ECG recording with an AW and a 12-lead ECG (21% had AF and 24% had no ECG abnormalities). Similar to the existing algorithm, we first screened for AF by detecting irregularities in ventricular intervals. However, as opposed to the existing algorithm, we included all ECGs (not applying quality or heart rate exclusion criteria) but we excluded ECGs in which we identified regular patterns within the irregular rhythms by screening for interval clusters. This “irregularly irregular” approach resulted in a significant improvement in accuracy compared to the existing AW algorithm (sensitivity of 90% versus 83%, specificity of 92% versus 79%, p < 0.01). Identifying regularity within irregular rhythms is an accurate yet inclusive method to detect AF using a smartwatch ECG. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

27 pages, 26520 KiB  
Article
Rehabilitation of Patients with Arthrogenic Muscular Inhibition in Pathologies of Knee Using Virtual Reality
by Juan Pablo Flórez Fonnegra, Andrea Carolina Pino Prestan, Lucelly López López, Juan C. Yepes and Vera Z. Pérez
Sensors 2023, 23(22), 9114; https://doi.org/10.3390/s23229114 - 11 Nov 2023
Viewed by 1118
Abstract
Arthrogenic muscle inhibition (AMI) refers to muscular alterations that are generated, producing biomechanical motor control and movement problems, leading to deficiencies in strength and atrophy. Currently, there exist methods that involve virtual reality (VR) and have been well perceived by physiotherapists. The present [...] Read more.
Arthrogenic muscle inhibition (AMI) refers to muscular alterations that are generated, producing biomechanical motor control and movement problems, leading to deficiencies in strength and atrophy. Currently, there exist methods that involve virtual reality (VR) and have been well perceived by physiotherapists. The present research measured the potential benefits in terms of therapeutic adherence and speed of recovery, through a comparative analysis in a healthcare provider institution, in Medellín, Colombia, with and without the aid of VR. For this purpose, dynamometry, and surface electromyography (sEMG) signal acquisition tools were used. The treatment involved neuromodulation, ranges of motion and mobility work, strengthening and reintegration into movement, complemented with TENS, NMENS and therapeutic exercise, where the patient was expected to receive a satisfactory and faster adherence and recovery. A group of 15 people with AMI who include at least 15 min of VR per session in their treatment were compared with another group who received only the base treatment, i.e., the control group. Analyzing the variables individually, it is possible to affirm that VR, as a complement, statistically significantly improved the therapeutic adherence in 33.3% for CG and 37.5% for IG. Additionally, it increased strength with both legs, the symmetry between them, and decreased the level of pain and stiffness that is related to mobility. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

18 pages, 2283 KiB  
Article
Ensemble Wavelet Decomposition-Based Detection of Mental States Using Electroencephalography Signals
by Smith K. Khare, Varun Bajaj, Nikhil B. Gaikwad and G. R. Sinha
Sensors 2023, 23(18), 7860; https://doi.org/10.3390/s23187860 - 13 Sep 2023
Cited by 2 | Viewed by 1415
Abstract
Technological advancements in healthcare, production, automobile, and aviation industries have shifted working styles from manual to automatic. This automation requires smart, intellectual, and safe machinery to develop an accurate and efficient brain–computer interface (BCI) system. However, developing such BCI systems requires effective processing [...] Read more.
Technological advancements in healthcare, production, automobile, and aviation industries have shifted working styles from manual to automatic. This automation requires smart, intellectual, and safe machinery to develop an accurate and efficient brain–computer interface (BCI) system. However, developing such BCI systems requires effective processing and analysis of human physiology. Electroencephalography (EEG) is one such technique that provides a low-cost, portable, non-invasive, and safe solution for BCI systems. However, the non-stationary and nonlinear nature of EEG signals makes it difficult for experts to perform accurate subjective analyses. Hence, there is an urgent need for the development of automatic mental state detection. This paper presents the classification of three mental states using an ensemble of the tunable Q wavelet transform, the multilevel discrete wavelet transform, and the flexible analytic wavelet transform. Various features are extracted from the subbands of EEG signals during focused, unfocused, and drowsy states. Separate and fused features from ensemble decomposition are classified using an optimized ensemble classifier. Our analysis shows that the fusion of features results in a dimensionality reduction. The proposed model obtained the highest accuracies of 92.45% and 97.8% with ten-fold cross-validation and the iterative majority voting technique. The proposed method is suitable for real-time mental state detection to improve BCI systems. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

30 pages, 5063 KiB  
Article
Robust Arm Impedocardiography Signal Quality Enhancement Using Recursive Signal Averaging and Multi-Stage Wavelet Denoising Methods for Long-Term Cardiac Contractility Monitoring Armbands
by Omar Escalona, Nicole Cullen, Idongesit Weli, Niamh McCallan, Kok Yew Ng and Dewar Finlay
Sensors 2023, 23(13), 5892; https://doi.org/10.3390/s23135892 - 25 Jun 2023
Cited by 3 | Viewed by 1210
Abstract
Impedance cardiography (ICG) is a low-cost, non-invasive technique that enables the clinical assessment of haemodynamic parameters, such as cardiac output and stroke volume (SV). Conventional ICG recordings are taken from the patient’s thorax. However, access to ICG vital signs from the upper-arm brachial [...] Read more.
Impedance cardiography (ICG) is a low-cost, non-invasive technique that enables the clinical assessment of haemodynamic parameters, such as cardiac output and stroke volume (SV). Conventional ICG recordings are taken from the patient’s thorax. However, access to ICG vital signs from the upper-arm brachial artery (as an associated surrogate) can enable user-convenient wearable armband sensor devices to provide an attractive option for gathering ICG trend-based indicators of general health, which offers particular advantages in ambulatory long-term monitoring settings. This study considered the upper arm ICG and control Thorax-ICG recordings data from 15 healthy subject cases. A prefiltering stage included a third-order Savitzky–Golay finite impulse response (FIR) filter, which was applied to the raw ICG signals. Then, a multi-stage wavelet-based denoising strategy on a beat-by-beat (BbyB) basis, which was supported by a recursive signal-averaging optimal thresholding adaptation algorithm for Arm-ICG signals, was investigated for robust signal quality enhancement. The performance of the BbyB ICG denoising was evaluated for each case using a 700 ms frame centred on the heartbeat ICG pulse. This frame was extracted from a 600-beat ensemble signal-averaged ICG and was used as the noiseless signal reference vector (gold standard frame). Furthermore, in each subject case, enhanced Arm-ICG and Thorax-ICG above a threshold of correlation of 0.95 with the noiseless vector enabled the analysis of beat inclusion rate (BIR%), yielding an average of 80.9% for Arm-ICG and 100% for Thorax-ICG, and BbyB values of the ICG waveform feature metrics A, B, C and VET accuracy and precision, yielding respective error rates (ER%) of 0.83%, 11.1%, 3.99% and 5.2% for Arm-IG, and 0.41%, 3.82%, 1.66% and 1.25% for Thorax-ICG, respectively. Hence, the functional relationship between ICG metrics within and between the arm and thorax recording modes could be characterised and the linear regression (Arm-ICG vs. Thorax-ICG) trends could be analysed. Overall, it was found in this study that recursive averaging, set with a 36 ICG beats buffer size, was the best Arm-ICG BbyB denoising process, with an average of less than 3.3% in the Arm-ICG time metrics error rate. It was also found that the arm SV versus thorax SV had a linear regression coefficient of determination (R2) of 0.84. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

20 pages, 657 KiB  
Article
Context Recognition Algorithms for Energy-Efficient Freezing-of-Gait Detection in Parkinson’s Disease
by Luigi Borzì, Luis Sigcha and Gabriella Olmo
Sensors 2023, 23(9), 4426; https://doi.org/10.3390/s23094426 - 30 Apr 2023
Cited by 3 | Viewed by 1902
Abstract
Freezing of gait (FoG) is a disabling clinical phenomenon of Parkinson’s disease (PD) characterized by the inability to move the feet forward despite the intention to walk. It is one of the most troublesome symptoms of PD, leading to an increased risk of [...] Read more.
Freezing of gait (FoG) is a disabling clinical phenomenon of Parkinson’s disease (PD) characterized by the inability to move the feet forward despite the intention to walk. It is one of the most troublesome symptoms of PD, leading to an increased risk of falls and reduced quality of life. The combination of wearable inertial sensors and machine learning (ML) algorithms represents a feasible solution to monitor FoG in real-world scenarios. However, traditional FoG detection algorithms process all data indiscriminately without considering the context of the activity during which FoG occurs. This study aimed to develop a lightweight, context-aware algorithm that can activate FoG detection systems only under certain circumstances, thus reducing the computational burden. Several approaches were implemented, including ML and deep learning (DL) gait recognition methods, as well as a single-threshold method based on acceleration magnitude. To train and evaluate the context algorithms, data from a single inertial sensor were extracted using three different datasets encompassing a total of eighty-one PD patients. Sensitivity and specificity for gait recognition ranged from 0.95 to 0.96 and 0.80 to 0.93, respectively, with the one-dimensional convolutional neural network providing the best results. The threshold approach performed better than ML- and DL-based methods when evaluating the effect of context awareness on FoG detection performance. Overall, context algorithms allow for discarding more than 55% of non-FoG data and less than 4% of FoG episodes. The results indicate that a context classifier can reduce the computational burden of FoG detection algorithms without significantly affecting the FoG detection rate. Thus, implementation of context awareness can present an energy-efficient solution for long-term FoG monitoring in ambulatory and free-living settings. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

16 pages, 1246 KiB  
Article
Characterization of Inclination Analysis for Predicting Onset of Heart Failure from Primary Care Electronic Medical Records
by Federica Guida, Marta Lenatti, Karim Keshavjee, Alireza Khatami, Aziz Guergachi and Alessia Paglialonga
Sensors 2023, 23(9), 4228; https://doi.org/10.3390/s23094228 - 24 Apr 2023
Viewed by 1288
Abstract
The aim of this study is to characterize the performance of an inclination analysis for predicting the onset of heart failure (HF) from routinely collected clinical biomarkers extracted from primary care electronic medical records. A balanced dataset of 698 patients (with/without HF), including [...] Read more.
The aim of this study is to characterize the performance of an inclination analysis for predicting the onset of heart failure (HF) from routinely collected clinical biomarkers extracted from primary care electronic medical records. A balanced dataset of 698 patients (with/without HF), including a minimum of five longitudinal measures of nine biomarkers (body mass index, diastolic and systolic blood pressure, fasting glucose, glycated hemoglobin, low-density and high-density lipoproteins, total cholesterol, and triglycerides) is used. The proposed algorithm achieves an accuracy of 0.89 (sensitivity of 0.89, specificity of 0.90) to predict the inclination of biomarkers (i.e., their trend towards a ‘survival’ or ‘collapse’ as defined by an inclination analysis) on a labeled, balanced dataset of 40 patients. Decision trees trained on the predicted inclination of biomarkers have significantly higher recall (0.69 vs. 0.53) and significantly higher negative predictive value (0.60 vs. 0.55) than those trained on the average values computed from the measures of biomarkers available before the onset of the disease, suggesting that an inclination analysis can help identify the onset of HF in the primary care patient population from routinely available clinical data. This exploratory study provides the basis for further investigations of inclination analyses to identify at-risk patients and generate preventive measures (i.e., personalized recommendations to reverse the trend of biomarkers towards collapse). Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

17 pages, 686 KiB  
Article
The Virtual Sleep Lab—A Novel Method for Accurate Four-Class Sleep Staging Using Heart-Rate Variability from Low-Cost Wearables
by Pavlos Topalidis, Dominik P. J. Heib, Sebastian Baron, Esther-Sevil Eigl, Alexandra Hinterberger and Manuel Schabus
Sensors 2023, 23(5), 2390; https://doi.org/10.3390/s23052390 - 21 Feb 2023
Cited by 4 | Viewed by 3634
Abstract
Sleep staging based on polysomnography (PSG) performed by human experts is the de facto “gold standard” for the objective measurement of sleep. PSG and manual sleep staging is, however, personnel-intensive and time-consuming and it is thus impractical to monitor a person’s sleep architecture [...] Read more.
Sleep staging based on polysomnography (PSG) performed by human experts is the de facto “gold standard” for the objective measurement of sleep. PSG and manual sleep staging is, however, personnel-intensive and time-consuming and it is thus impractical to monitor a person’s sleep architecture over extended periods. Here, we present a novel, low-cost, automatized, deep learning alternative to PSG sleep staging that provides a reliable epoch-by-epoch four-class sleep staging approach (Wake, Light [N1 + N2], Deep, REM) based solely on inter-beat-interval (IBI) data. Having trained a multi-resolution convolutional neural network (MCNN) on the IBIs of 8898 full-night manually sleep-staged recordings, we tested the MCNN on sleep classification using the IBIs of two low-cost (<EUR 100) consumer wearables: an optical heart rate sensor (VS) and a breast belt (H10), both produced by POLAR®. The overall classification accuracy reached levels comparable to expert inter-rater reliability for both devices (VS: 81%, κ = 0.69; H10: 80.3%, κ = 0.69). In addition, we used the H10 and recorded daily ECG data from 49 participants with sleep complaints over the course of a digital CBT-I-based sleep training program implemented in the App NUKKUAA™. As proof of principle, we classified the IBIs extracted from H10 using the MCNN over the course of the training program and captured sleep-related changes. At the end of the program, participants reported significant improvements in subjective sleep quality and sleep onset latency. Similarly, objective sleep onset latency showed a trend toward improvement. Weekly sleep onset latency, wake time during sleep, and total sleep time also correlated significantly with the subjective reports. The combination of state-of-the-art machine learning with suitable wearables allows continuous and accurate monitoring of sleep in naturalistic settings with profound implications for answering basic and clinical research questions. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

13 pages, 1456 KiB  
Article
Validity and Reliability of Kinvent Plates for Assessing Single Leg Static and Dynamic Balance in the Field
by Hugo Meras Serrano, Denis Mottet and Kevin Caillaud
Sensors 2023, 23(4), 2354; https://doi.org/10.3390/s23042354 - 20 Feb 2023
Cited by 2 | Viewed by 2136
Abstract
The objective of this study was to validate PLATES for assessing unipodal balance in the field, for example, to monitor ankle instabilities in athletes or patients. PLATES is a pair of lightweight, connected force platforms that measure only vertical forces. In 14 healthy [...] Read more.
The objective of this study was to validate PLATES for assessing unipodal balance in the field, for example, to monitor ankle instabilities in athletes or patients. PLATES is a pair of lightweight, connected force platforms that measure only vertical forces. In 14 healthy women, we measured ground reaction forces during Single Leg Balance and Single Leg Landing tests, first under laboratory conditions (with PLATES and with a 6-DOF reference force platform), then during a second test session in the field (with PLATES). We found that for these simple unipodal balance tests, PLATES was reliable in the laboratory and in the field: PLATES gives results comparable with those of a reference force platform with 6-DOF for the key variables in the tests (i.e., Mean Velocity of the Center of Pressure and Time to Stabilization). We conclude that health professionals, physical trainers, and researchers can use PLATES to conduct Single Leg Balance and Single Leg Landing tests in the laboratory and in the field. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

16 pages, 7397 KiB  
Article
Selective Deeply Supervised Multi-Scale Attention Network for Brain Tumor Segmentation
by Azka Rehman, Muhammad Usman, Abdullah Shahid, Siddique Latif and Junaid Qadir
Sensors 2023, 23(4), 2346; https://doi.org/10.3390/s23042346 - 20 Feb 2023
Cited by 4 | Viewed by 1798
Abstract
Brain tumors are among the deadliest forms of cancer, characterized by abnormal proliferation of brain cells. While early identification of brain tumors can greatly aid in their therapy, the process of manual segmentation performed by expert doctors, which is often time-consuming, tedious, and [...] Read more.
Brain tumors are among the deadliest forms of cancer, characterized by abnormal proliferation of brain cells. While early identification of brain tumors can greatly aid in their therapy, the process of manual segmentation performed by expert doctors, which is often time-consuming, tedious, and prone to human error, can act as a bottleneck in the diagnostic process. This motivates the development of automated algorithms for brain tumor segmentation. However, accurately segmenting the enhanced and core tumor regions is complicated due to high levels of inter- and intra-tumor heterogeneity in terms of texture, morphology, and shape. This study proposes a fully automatic method called the selective deeply supervised multi-scale attention network (SDS-MSA-Net) for segmenting brain tumor regions using a multi-scale attention network with novel selective deep supervision (SDS) mechanisms for training. The method utilizes a 3D input composed of five consecutive slices, in addition to a 2D slice, to maintain sequential information. The proposed multi-scale architecture includes two encoding units to extract meaningful global and local features from the 3D and 2D inputs, respectively. These coarse features are then passed through attention units to filter out redundant information by assigning lower weights. The refined features are fed into a decoder block, which upscales the features at various levels while learning patterns relevant to all tumor regions. The SDS block is introduced to immediately upscale features from intermediate layers of the decoder, with the aim of producing segmentations of the whole, enhanced, and core tumor regions. The proposed framework was evaluated on the BraTS2020 dataset and showed improved performance in brain tumor region segmentation, particularly in the segmentation of the core and enhancing tumor regions, demonstrating the effectiveness of the proposed approach. Our code is publicly available. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

18 pages, 4075 KiB  
Article
Brain–Computer Interface Based on Steady-State Visual Evoked Potential Using Quick-Response Code Pattern for Wheelchair Control
by Nannaphat Siribunyaphat and Yunyong Punsawad
Sensors 2023, 23(4), 2069; https://doi.org/10.3390/s23042069 - 12 Feb 2023
Cited by 5 | Viewed by 2418
Abstract
Brain–computer interfaces (BCIs) are widely utilized in control applications for people with severe physical disabilities. Several researchers have aimed to develop practical brain-controlled wheelchairs. An existing electroencephalogram (EEG)-based BCI based on steady-state visually evoked potential (SSVEP) was developed for device control. This study [...] Read more.
Brain–computer interfaces (BCIs) are widely utilized in control applications for people with severe physical disabilities. Several researchers have aimed to develop practical brain-controlled wheelchairs. An existing electroencephalogram (EEG)-based BCI based on steady-state visually evoked potential (SSVEP) was developed for device control. This study utilized a quick-response (QR) code visual stimulus pattern for a robust existing system. Four commands were generated using the proposed visual stimulation pattern with four flickering frequencies. Moreover, we employed a relative power spectrum density (PSD) method for the SSVEP feature extraction and compared it with an absolute PSD method. We designed experiments to verify the efficiency of the proposed system. The results revealed that the proposed SSVEP method and algorithm yielded an average classification accuracy of approximately 92% in real-time processing. For the wheelchair simulated via independent-based control, the proposed BCI control required approximately five-fold more time than the keyboard control for real-time control. The proposed SSVEP method using a QR code pattern can be used for BCI-based wheelchair control. However, it suffers from visual fatigue owing to long-time continuous control. We will verify and enhance the proposed system for wheelchair control in people with severe physical disabilities. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

14 pages, 1767 KiB  
Article
Intraclass Clustering-Based CNN Approach for Detection of Malignant Melanoma
by Adrian D. Bandy, Yannis Spyridis, Barbara Villarini and Vasileios Argyriou
Sensors 2023, 23(2), 926; https://doi.org/10.3390/s23020926 - 13 Jan 2023
Cited by 4 | Viewed by 1960
Abstract
This paper describes the process of developing a classification model for the effective detection of malignant melanoma, an aggressive type of cancer in skin lesions. Primary focus is given on fine-tuning and improving a state-of-the-art convolutional neural network (CNN) to obtain the optimal [...] Read more.
This paper describes the process of developing a classification model for the effective detection of malignant melanoma, an aggressive type of cancer in skin lesions. Primary focus is given on fine-tuning and improving a state-of-the-art convolutional neural network (CNN) to obtain the optimal ROC-AUC score. The study investigates a variety of artificial intelligence (AI) clustering techniques to train the developed models on a combined dataset of images across data from the 2019 and 2020 IIM-ISIC Melanoma Classification Challenges. The models were evaluated using varying cross-fold validations, with the highest ROC-AUC reaching a score of 99.48%. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

17 pages, 2407 KiB  
Article
Can Data-Driven Supervised Machine Learning Approaches Applied to Infrared Thermal Imaging Data Estimate Muscular Activity and Fatigue?
by David Perpetuini, Damiano Formenti, Daniela Cardone, Athos Trecroci, Alessio Rossi, Andrea Di Credico, Giampiero Merati, Giampietro Alberti, Angela Di Baldassarre and Arcangelo Merla
Sensors 2023, 23(2), 832; https://doi.org/10.3390/s23020832 - 11 Jan 2023
Cited by 3 | Viewed by 2646
Abstract
Surface electromyography (sEMG) is the acquisition, from the skin, of the electrical signal produced by muscle activation. Usually, sEMG is measured through electrodes with electrolytic gel, which often causes skin irritation. Capacitive contactless electrodes have been developed to overcome this limitation. However, contactless [...] Read more.
Surface electromyography (sEMG) is the acquisition, from the skin, of the electrical signal produced by muscle activation. Usually, sEMG is measured through electrodes with electrolytic gel, which often causes skin irritation. Capacitive contactless electrodes have been developed to overcome this limitation. However, contactless EMG devices are still sensitive to motion artifacts and often not comfortable for long monitoring. In this study, a non-invasive contactless method to estimate parameters indicative of muscular activity and fatigue, as they are assessed by EMG, through infrared thermal imaging (IRI) and cross-validated machine learning (ML) approaches is described. Particularly, 10 healthy participants underwent five series of bodyweight squats until exhaustion interspersed by 1 min of rest. During exercising, the vastus medialis activity and its temperature were measured through sEMG and IRI, respectively. The EMG average rectified value (ARV) and the median frequency of the power spectral density (MDF) of each series were estimated through several ML approaches applied to IRI features, obtaining good estimation performances (r = 0.886, p < 0.001 for ARV, and r = 0.661, p < 0.001 for MDF). Although EMG and IRI measure physiological processes of a different nature and are not interchangeable, these results suggest a potential link between skin temperature and muscle activity and fatigue, fostering the employment of contactless methods to deliver metrics of muscular activity in a non-invasive and comfortable manner in sports and clinical applications. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

22 pages, 5874 KiB  
Article
A Comparative Study on a Novel Quality Assessment Protocol Based on Image Analysis Methods for Color Doppler Ultrasound Diagnostic Systems
by Giorgia Fiori, Andrada Pica, Salvatore Andrea Sciuto, Franco Marinozzi, Fabiano Bini and Andrea Scorza
Sensors 2022, 22(24), 9868; https://doi.org/10.3390/s22249868 - 15 Dec 2022
Cited by 3 | Viewed by 1565
Abstract
Color Doppler (CD) imaging is widely used in diagnostics since it allows real-time detection and display of blood flow superimposed on the B-mode image. Nevertheless, to date, a shared worldwide standard on Doppler equipment testing is still lacking. In this context, the study [...] Read more.
Color Doppler (CD) imaging is widely used in diagnostics since it allows real-time detection and display of blood flow superimposed on the B-mode image. Nevertheless, to date, a shared worldwide standard on Doppler equipment testing is still lacking. In this context, the study herein proposed would give a contribution focusing on the combination of five test parameters to be included in a novel Quality Assessment (QA) protocol for CD systems testing. A first approach involving the use of the Kiviat diagram was investigated, assuming the diagram area, normalized with respect to one of the gold standards, as an index of the overall Doppler system performance. The QA parameters were obtained from the post-processing of CD data through the implementation of custom-written image analysis methods and procedures, here applied to three brand-new high-technology-level ultrasound systems. Experimental data were collected through phased and convex array probes, in two configuration settings, by means of a Doppler flow phantom set at different flow rate regimes. The outcomes confirmed that the Kiviat diagram might be a promising tool applied to quality controls of Doppler equipment, although further investigations should be performed to assess the sensitivity and specificity of the proposed approach. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

12 pages, 2277 KiB  
Article
Efficient Low-Frequency SSVEP Detection with Wearable EEG Using Normalized Canonical Correlation Analysis
by Victor Javier Kartsch, Velu Prabhakar Kumaravel, Simone Benatti, Giorgio Vallortigara, Luca Benini, Elisabetta Farella and Marco Buiatti
Sensors 2022, 22(24), 9803; https://doi.org/10.3390/s22249803 - 14 Dec 2022
Cited by 1 | Viewed by 3696
Abstract
Recent studies show that the integrity of core perceptual and cognitive functions may be tested in a short time with Steady-State Visual Evoked Potentials (SSVEP) with low stimulation frequencies, between 1 and 10 Hz. Wearable EEG systems provide unique opportunities to test these [...] Read more.
Recent studies show that the integrity of core perceptual and cognitive functions may be tested in a short time with Steady-State Visual Evoked Potentials (SSVEP) with low stimulation frequencies, between 1 and 10 Hz. Wearable EEG systems provide unique opportunities to test these brain functions on diverse populations in out-of-the-lab conditions. However, they also pose significant challenges as the number of EEG channels is typically limited, and the recording conditions might induce high noise levels, particularly for low frequencies. Here we tested the performance of Normalized Canonical Correlation Analysis (NCCA), a frequency-normalized version of CCA, to quantify SSVEP from wearable EEG data with stimulation frequencies ranging from 1 to 10 Hz. We validated NCCA on data collected with an 8-channel wearable wireless EEG system based on BioWolf, a compact, ultra-light, ultra-low-power recording platform. The results show that NCCA correctly and rapidly detects SSVEP at the stimulation frequency within a few cycles of stimulation, even at the lowest frequency (4 s recordings are sufficient for a stimulation frequency of 1 Hz), outperforming a state-of-the-art normalized power spectral measure. Importantly, no preliminary artifact correction or channel selection was required. Potential applications of these results to research and clinical studies are discussed. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

17 pages, 6065 KiB  
Article
The Number and Structure of Muscle Synergies Depend on the Number of Recorded Muscles: A Pilot Simulation Study with OpenSim
by Cristina Brambilla and Alessandro Scano
Sensors 2022, 22(22), 8584; https://doi.org/10.3390/s22228584 - 08 Nov 2022
Cited by 5 | Viewed by 1919
Abstract
The muscle synergy approach is used to evaluate motor control and to quantitatively determine the number and structure of the modules underlying movement. In experimental studies regarding the upper limb, typically 8 to 16 EMG probes are used depending on the application, although [...] Read more.
The muscle synergy approach is used to evaluate motor control and to quantitatively determine the number and structure of the modules underlying movement. In experimental studies regarding the upper limb, typically 8 to 16 EMG probes are used depending on the application, although the number of muscles involved in motor generation is higher. Therefore, the number of motor modules may be underestimated and the structure altered with the standard spatial synergy model based on the non-negative matrix factorization (NMF). In this study, we compared the number and structure of muscle synergies when considering 12 muscles (an “average” condition that represents previous studies) and 32 muscles of the upper limb, also including multiple muscle heads and deep muscles. First, we estimated the muscle activations with an upper-limb model in OpenSim using data from multi-directional reaching movements acquired in experimental sessions; then, spatial synergies were extracted from EMG activations from 12 muscles and from 32 muscles and their structures were compared. Finally, we compared muscle synergies obtained from OpenSim and from real experimental EMG signals to assess the reliability of the results. Interestingly, we found that on average, an additional synergy is needed to reconstruct the same R2 level with 32 muscles with respect to 12 muscles; synergies have a very similar structure, although muscles with comparable physiological functions were added to the synergies extracted with 12 muscles. The additional synergies, instead, captured patterns that could not be identified with only 12 muscles. We concluded that current studies may slightly underestimate the number of controlled synergies, even though the main structure of synergies is not modified when adding more muscles. We also show that EMG activations estimated with OpenSim are in partial (but not complete) agreement with experimental recordings. These findings may have significative implications for motor control and clinical studies. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

14 pages, 2989 KiB  
Article
An “Instantaneous” Response of a Human Visual System to Hue: An EEG-Based Study
by Gleb V. Tcheslavski and Maryam Vasefi
Sensors 2022, 22(21), 8484; https://doi.org/10.3390/s22218484 - 04 Nov 2022
Viewed by 1089
Abstract
(1) The article presents a new technique to interpret biomedical data (EEG) to assess cortical responses to continuous color/hue variations. We propose an alternative approach to analyze EEG activity evoked by visual stimulation. This approach may augment the traditional VEP analysis. (2) Considering [...] Read more.
(1) The article presents a new technique to interpret biomedical data (EEG) to assess cortical responses to continuous color/hue variations. We propose an alternative approach to analyze EEG activity evoked by visual stimulation. This approach may augment the traditional VEP analysis. (2) Considering ensembles of EEG epochs as multidimensional spatial vectors evolving over time (rather than collections of time-domain signals) and evaluating the similarity between such vectors across different EEG epochs may result in a more accurate detection of colors that evoke greater responses of the visual system. To demonstrate its suitability, the developed analysis technique was applied to the EEG data that we previously collected from 19 participants with normal color vision, while exposing them to stimuli of continuously varying hue. (3) Orange/yellow and dark blue/violet colors generally aroused better-pronounced cortical responses. The selection of EEG channels allowed for assessing the activity that predominantly originates from specific cortical regions. With such channel selection, the strongest response to the hue was observed from Parieto-Temporal region of the right hemisphere. The statistical test—Kruskal–Wallis one-way analysis of variance—indicates that the distance evaluated for spatial EEG vectors at different post-stimulus latencies generally originate from different statistical distributions with a probability exceeding 99.9% (α = 0.001). Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

18 pages, 3695 KiB  
Article
A Parallel Cross Convolutional Recurrent Neural Network for Automatic Imbalanced ECG Arrhythmia Detection with Continuous Wavelet Transform
by Tabassum Islam Toma and Sunwoong Choi
Sensors 2022, 22(19), 7396; https://doi.org/10.3390/s22197396 - 28 Sep 2022
Cited by 4 | Viewed by 1927
Abstract
Automatic detection of arrhythmia using electrocardiogram (ECG) and deep learning (DL) is very important to reduce the global death rate from cardiovascular diseases (CVD). Previous studies on automatic arrhythmia detection relied largely on various ECG features and have achieved considerable classification accuracy using [...] Read more.
Automatic detection of arrhythmia using electrocardiogram (ECG) and deep learning (DL) is very important to reduce the global death rate from cardiovascular diseases (CVD). Previous studies on automatic arrhythmia detection relied largely on various ECG features and have achieved considerable classification accuracy using DL-based models. However, most previous research has ignored multi-class imbalanced problems in ECG arrhythmia detection. Therefore, it remains a challenge to improve the classification performance of the DL-based models. This paper proposes a novel parallel cross convolutional recurrent neural network in order to improve the arrhythmia detection performance of imbalanced ECG signals. The proposed model incorporates a recurrent neural network and a two-dimensional (2D) convolutional neural network (CNN) and can effectively learn temporal characteristics and rich spatial information of raw ECG signals. Continuous wavelet transform (CWT) is used to transform the ECG signals into a 2D scalogram composed of time–frequency components, and subsequently, the 2D-CNN can learn spatial information from the 2D scalogram. The proposed model is not only efficient in learning features with imbalanced samples but can also significantly improve model convergence with higher accuracy. The overall performance of our proposed model is evaluated based on the MIT-BIH arrhythmia dataset. Detailed analysis of evaluation metrics reveals that the proposed model is very effective in arrhythmia detection and significantly better than the existing hierarchical network models. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

18 pages, 416 KiB  
Article
EEG-Based Alzheimer’s Disease Recognition Using Robust-PCA and LSTM Recurrent Neural Network
by Michele Alessandrini, Giorgio Biagetti, Paolo Crippa, Laura Falaschetti, Simona Luzzi and Claudio Turchetti
Sensors 2022, 22(10), 3696; https://doi.org/10.3390/s22103696 - 12 May 2022
Cited by 23 | Viewed by 3313
Abstract
The use of electroencephalography (EEG) has recently grown as a means to diagnose neurodegenerative pathologies such as Alzheimer’s disease (AD). AD recognition can benefit from machine learning methods that, compared with traditional manual diagnosis methods, have higher reliability and improved recognition accuracy, being [...] Read more.
The use of electroencephalography (EEG) has recently grown as a means to diagnose neurodegenerative pathologies such as Alzheimer’s disease (AD). AD recognition can benefit from machine learning methods that, compared with traditional manual diagnosis methods, have higher reliability and improved recognition accuracy, being able to manage large amounts of data. Nevertheless, machine learning methods may exhibit lower accuracies when faced with incomplete, corrupted, or otherwise missing data, so it is important do develop robust pre-processing techniques do deal with incomplete data. The aim of this paper is to develop an automatic classification method that can still work well with EEG data affected by artifacts, as can arise during the collection with, e.g., a wireless system that can lose packets. We show that a recurrent neural network (RNN) can operate successfully even in the case of significantly corrupted data, when it is pre-filtered by the robust principal component analysis (RPCA) algorithm. RPCA was selected because of its stated ability to remove outliers from the signal. To demonstrate this idea, we first develop an RNN which operates on EEG data, properly processed through traditional PCA; then, we use corrupted data as input and process them with RPCA to filter outlier components, showing that even with data corruption causing up to 20% erasures, the RPCA was able to increase the detection accuracy by about 5% with respect to the baseline PCA. Full article
(This article belongs to the Special Issue Advances in Biomedical Sensing, Instrumentation and Systems)
Show Figures

Figure 1

Back to TopTop