Submit to Bioengineering Review for Bioengineering Propose a Special Issue

Journal Browser

► Journal Browser

Advances of Biomedical Signal Processing

Special Issue Editors
Special Issue Information
Keywords
Published Papers

A special issue of Bioengineering (ISSN 2306-5354). This special issue belongs to the section "Biosignal Processing".

Deadline for manuscript submissions: closed (30 April 2023) | Viewed by 31609

Share This Special Issue

Special Issue Editors

Dr. Faezeh Marzbanrad

E-Mail Website
Guest Editor

Department of Electrical and Computer Systems Engineering, Monash University, 14 Alliance Lane, Clayton, VIC 3800, Australia
Interests: biomedical signal processing; machine learning; artificial intelligence in healthcare; multi-modal data fusion; medical devices; mobile-health; tele-health

Dr. Chiranjibi Sitaula

E-Mail Website
Guest Editor

Department of Electrical and Computer Systems Engineering, Monash University, Clayton, VIC, Australia
Interests: biomedical image processing; machine learning; computer vision; natural language processing; health informatics; signal processing

Special Issue Information

Dear Colleagues,

With the technological advancements in biosensors, wearables devices, and the Internet of Things (IoT) in healthcare, there have been rapidly growing demands for the processing of biomedical big data, to enable efficient health monitoring and provide reliable clinical decision support. Biomedical signal processing and Artificial Intelligence (AI) play a crucial role in healthcare innovation through efficient and real-time data acquisition, representation and visualization, storage, de-nosing, and refinement. Smart medical devices often rely on novel biomedical signal processing and machine learning for data mining, modeling and analysis, vital sign estimation, clustering, regression, classification, and beyond for automated screening and diagnosis.

This Special Issue will focus on advanced signal and image processing and machine learning in biomedical and healthcare applications including but not limited to screening and diagnostics, patient monitoring, telehealth, health risk assessment, medical prognosis, and survival analysis.

Original research contributions will be prioritized, but critical reviews about the state of the art, current limitations, and future directions are welcome.

Dr. Faezeh Marzbanrad
Dr. Chiranjibi Sitaula
Guest Editors

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. Bioengineering is an international peer-reviewed open access monthly 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 2700 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.

Keywords

biomedical signal processing
biomedical data analysis
machine learning including deep learning for biomedical applications
physiological signals
medical image analysis
biomedical big data analysis
IoT in healthcare
medical imaging
clinical decision support systems
health monitoring, screening, and diagnosis
telehealth
wearable devices

Published Papers (14 papers)

Download All Papers

Research

16 pages, 3478 KiB

Open AccessArticle

Robust Removal of Slow Artifactual Dynamics Induced by Deep Brain Stimulation in Local Field Potential Recordings Using SVD-Based Adaptive Filtering

by Nooshin Bahador, Josh Saha, Mohammad R. Rezaei, Saha Utpal, Ayda Ghahremani, Robert Chen and Milad Lankarany

Bioengineering 2023, 10(6), 719; https://doi.org/10.3390/bioengineering10060719 - 14 Jun 2023

Viewed by 1220

Abstract

Deep brain stimulation (DBS) is widely used as a treatment option for patients with movement disorders. In addition to its clinical impact, DBS has been utilized in the field of cognitive neuroscience, wherein the answers to several fundamental questions underpinning the mechanisms of neuromodulation in decision making rely on the ways in which a burst of DBS pulses, usually delivered at a clinical frequency, i.e., 130 Hz, perturb participants’ choices. It was observed that neural activities recorded during DBS were contaminated with large artifacts, which lasts for a few milliseconds, as well as a low-frequency (slow) signal (~1–2 Hz) that can persist for hundreds of milliseconds. While the focus of most of methods for removing DBS artifacts was on the former, the artifact removal capabilities of the slow signal have not been addressed. In this work, we propose a new method based on combining singular value decomposition (SVD) and normalized adaptive filtering to remove both large (fast) and slow artifacts in local field potentials, recorded during a cognitive task in which bursts of DBS were utilized. Using synthetic data, we show that our proposed algorithm outperforms four commonly used techniques in the literature, namely, (1) normalized least mean square adaptive filtering, (2) optimal FIR Wiener filtering, (3) Gaussian model matching, and (4) moving average. The algorithm’s capabilities are further demonstrated by its ability to effectively remove DBS artifacts in local field potentials recorded from the subthalamic nucleus during a verbal Stroop task, highlighting its utility in real-world applications. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

15 pages, 3092 KiB

Open AccessArticle

An Explainable Machine-Learning Model for Compensatory Reserve Measurement: Methods for Feature Selection and the Effects of Subject Variability

by Carlos N. Bedolla, Jose M. Gonzalez, Saul J. Vega, Víctor A. Convertino and Eric J. Snider

Bioengineering 2023, 10(5), 612; https://doi.org/10.3390/bioengineering10050612 - 19 May 2023

Cited by 3 | Viewed by 1325

Abstract

Tracking vital signs accurately is critical for triaging a patient and ensuring timely therapeutic intervention. The patient’s status is often clouded by compensatory mechanisms that can mask injury severity. The compensatory reserve measurement (CRM) is a triaging tool derived from an arterial waveform that has been shown to allow for earlier detection of hemorrhagic shock. However, the deep-learning artificial neural networks developed for its estimation do not explain how specific arterial waveform elements lead to predicting CRM due to the large number of parameters needed to tune these models. Alternatively, we investigate how classical machine-learning models driven by specific features extracted from the arterial waveform can be used to estimate CRM. More than 50 features were extracted from human arterial blood pressure data sets collected during simulated hypovolemic shock resulting from exposure to progressive levels of lower body negative pressure. A bagged decision tree design using the ten most significant features was selected as optimal for CRM estimation. This resulted in an average root mean squared error in all test data of 0.171, similar to the error for a deep-learning CRM algorithm at 0.159. By separating the dataset into sub-groups based on the severity of simulated hypovolemic shock withstood, large subject variability was observed, and the key features identified for these sub-groups differed. This methodology could allow for the identification of unique features and machine-learning models to differentiate individuals with good compensatory mechanisms against hypovolemia from those that might be poor compensators, leading to improved triage of trauma patients and ultimately enhancing military and emergency medicine. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

16 pages, 5437 KiB

Open AccessArticle

Epileptic Tissue Localization through Skewness-Based Functional Connectivity in the High-Frequency Band of Intracranial EEG

by Mu Shen, Lin Zhang, Yi Gong, Lei Li and Xianzeng Liu

Bioengineering 2023, 10(4), 461; https://doi.org/10.3390/bioengineering10040461 - 10 Apr 2023

Viewed by 1189

Abstract

Functional connectivity analysis of intracranial electroencephalography (iEEG) plays an important role in understanding the mechanism of epilepsy and seizure dynamics. However, existing connectivity analysis is only suitable for low-frequency bands below 80 Hz. High-frequency oscillations (HFOs) and high-frequency activity (HFA) in the high-frequency band (80–500 Hz) are thought to be specific biomarkers in epileptic tissue localization. However, the transience in duration and variability of occurrence time and amplitudes of these events pose a challenge for conducting effective connectivity analysis. To deal with this problem, we proposed skewness-based functional connectivity (SFC) in the high-frequency band and explored its utility in epileptic tissue localization and surgical outcome evaluation. SFC comprises three main steps. The first step is the quantitative measurement of amplitude distribution asymmetry between HFOs/HFA and baseline activity. The second step is functional network construction on the basis of rank correlation of asymmetry across time. The third step is connectivity strength extraction from the functional network. Experiments were conducted in two separate datasets which consist of iEEG recordings from 59 patients with drug-resistant epilepsy. Significant difference (

p < 0.001

) in connectivity strength was found between epileptic and non-epileptic tissue. Results were quantified via the receiver operating characteristic curve and the area under the curve (AUC). Compared with low-frequency bands, SFC demonstrated superior performance. With respect to pooled and individual epileptic tissue localization for seizure-free patients, AUCs were 0.66 (95% confidence interval (CI): 0.63–0.69) and (0.63 95% CI 0.56–0.71), respectively. For surgical outcome classification, the AUC was 0.75 (95% CI 0.59–0.85). Therefore, SFC can act as a promising assessment tool in characterizing the epileptic network and potentially provide better treatment options for patients with drug-resistant epilepsy. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

24 pages, 4107 KiB

Open AccessArticle

Use of Surface Electromyography to Estimate End-Point Force in Redundant Systems: Comparison between Linear Approaches

by Daniele Borzelli, Sergio Gurgone, Paolo De Pasquale, Nicola Lotti, Andrea d’Avella and Laura Gastaldi

Bioengineering 2023, 10(2), 234; https://doi.org/10.3390/bioengineering10020234 - 10 Feb 2023

Cited by 1 | Viewed by 1475

Abstract

Estimation of the force exerted by muscles from their electromyographic (EMG) activity may be useful to control robotic devices. Approximating end-point forces as a linear combination of the activities of multiple muscles acting on a limb may lead to an inaccurate estimation because of the dependency between the EMG signals, i.e., multi-collinearity. This study compared the EMG-to-force mapping estimation performed with standard multiple linear regression and with three other algorithms designed to reduce different sources of the detrimental effects of multi-collinearity: Ridge Regression, which performs an L2 regularization through a penalty term; linear regression with constraints from foreknown anatomical boundaries, derived from a musculoskeletal model; linear regression of a reduced number of muscular degrees of freedom through the identification of muscle synergies. Two datasets, both collected during the exertion of submaximal isometric forces along multiple directions with the upper limb, were exploited. One included data collected across five sessions and the other during the simultaneous exertion of force and generation of different levels of co-contraction. The accuracy and consistency of the EMG-to-force mappings were assessed to determine the strengths and drawbacks of each algorithm. When applied to multiple sessions, Ridge Regression achieved higher accuracy (R² = 0.70) but estimations based on muscle synergies were more consistent (differences between the pulling vectors of mappings extracted from different sessions: 67%). In contrast, the implementation of anatomical constraints was the best solution, both in terms of consistency (R² = 0.64) and accuracy (74%), in the case of different co-contraction conditions. These results may be used for the selection of the mapping between EMG and force to be implemented in myoelectrically controlled robotic devices. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Graphical abstract

28 pages, 6222 KiB

Open AccessArticle

Two Operational Modes of Cardio-Respiratory Coupling Revealed by Pulse-Respiration Quotient

by Aleksandar Kalauzi, Zoran Matić, Mirjana M. Platiša and Tijana Bojić

Bioengineering 2023, 10(2), 180; https://doi.org/10.3390/bioengineering10020180 - 31 Jan 2023

Cited by 3 | Viewed by 1511

Abstract

Due to the fact that respiratory breath-to-breath and cardiac intervals between two successive R peaks (BBI and RRI, respectively) are not temporally concurrent, in a previous paper, we proposed a method to calculate both the integer and non-integer parts of the pulse respiration quotient (PRQ = BBI/RRI = PRQ_int + b1 + b2), b1 and b2 being parts of the border RRIs for each BBI. In this work, we study the correlations between BBI and PRQ, as well as those between BBI and mean RRI within each BBI (mRRI), on a group of twenty subjects in four conditions: in supine and standing positions, in combination with spontaneous and slow breathing. Results show that the BBI vs. PRQ correlations are positive; whereas the breathing regime had little or no effect on the linear regression slopes, body posture did. Two types of scatter plots were obtained with the BBI vs. mRRI correlations: one showed points aggregated around the concurrent PRQ_int lines, while the other showed randomly distributed points. Five out of six of the proposed aggregation measures confirmed the existence of these two cardio-respiratory coupling regimes. We also used b1 to study the positions of R pulses relative to the respiration onsets and showed that they were more synchronous with sympathetic activation. Overall, this method should be used in different pathological states. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

23 pages, 2014 KiB

Open AccessArticle

A Framework for Susceptibility Analysis of Brain Tumours Based on Uncertain Analytical Cum Algorithmic Modeling

by Atiqe Ur Rahman, Muhammad Saeed, Muhammad Haris Saeed, Dilovan Asaad Zebari, Marwan Albahar, Karrar Hameed Abdulkareem, Alaa S. Al-Waisy and Mazin Abed Mohammed

Bioengineering 2023, 10(2), 147; https://doi.org/10.3390/bioengineering10020147 - 22 Jan 2023

Cited by 11 | Viewed by 1385

Abstract

Susceptibility analysis is an intelligent technique that not only assists decision makers in assessing the suspected severity of any sort of brain tumour in a patient but also helps them diagnose and cure these tumours. This technique has been proven more useful in those developing countries where the available health-based and funding-based resources are limited. By employing set-based operations of an arithmetical model, namely fuzzy parameterised complex intuitionistic fuzzy hypersoft set (FPCIFHSS), this study seeks to develop a robust multi-attribute decision support mechanism for appraising patients’ susceptibility to brain tumours. The FPCIFHSS is regarded as more reliable and generalised for handling information-based uncertainties because its complex components and fuzzy parameterisation are designed to deal with the periodic nature of the data and dubious parameters (sub-parameters), respectively. In the proposed FPCIFHSS-susceptibility model, some suitable types of brain tumours are approximated with respect to the most relevant symptoms (parameters) based on the expert opinions of decision makers in terms of complex intuitionistic fuzzy numbers (CIFNs). After determining the fuzzy parameterised values of multi-argument-based tuples and converting the CIFNs into fuzzy values, the scores for such types of tumours are computed based on a core matrix which relates them with fuzzy parameterised multi-argument-based tuples. The sub-intervals within [0, 1] denote the susceptibility degrees of patients corresponding to these types of brain tumours. The susceptibility of patients is examined by observing the membership of score values in the sub-intervals. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

15 pages, 3661 KiB

Open AccessEditor’s ChoiceArticle

Deep Learning Model for Computer-Aided Diagnosis of Urolithiasis Detection from Kidney–Ureter–Bladder Images

by Yi-Yang Liu, Zih-Hao Huang and Ko-Wei Huang

Bioengineering 2022, 9(12), 811; https://doi.org/10.3390/bioengineering9120811 - 16 Dec 2022

Cited by 5 | Viewed by 3184

Abstract

Kidney–ureter–bladder (KUB) imaging is a radiological examination with a low cost, low radiation, and convenience. Although emergency room clinicians can arrange KUB images easily as a first-line examination for patients with suspicious urolithiasis, interpreting the KUB images correctly is difficult for inexperienced clinicians. Obtaining a formal radiology report immediately after a KUB imaging examination can also be challenging. Recently, artificial-intelligence-based computer-aided diagnosis (CAD) systems have been developed to help clinicians who are not experts make correct diagnoses for further treatment more effectively. Therefore, in this study, we proposed a CAD system for KUB imaging based on a deep learning model designed to help first-line emergency room clinicians diagnose urolithiasis accurately. A total of 355 KUB images were retrospectively collected from 104 patients who were diagnosed with urolithiasis at Kaohsiung Chang Gung Memorial Hospital. Then, we trained a deep learning model with a ResNet architecture to classify KUB images in terms of the presence or absence of kidney stones with this dataset of pre-processed images. Finally, we tuned the parameters and tested the model experimentally. The results show that the accuracy, sensitivity, specificity, and F1-measure of the model were 0.977, 0.953, 1, and 0.976 on the validation set and 0.982, 0.964, 1, and 0.982 on the testing set, respectively. Moreover, the results demonstrate that the proposed model performed well compared to the existing CNN-based methods and was able to detect urolithiasis in KUB images successfully. We expect the proposed approach to help emergency room clinicians make accurate diagnoses and reduce unnecessary radiation exposure from computed tomography (CT) scans, along with the associated medical costs. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

20 pages, 4012 KiB

Open AccessEditor’s ChoiceArticle

Automatic Localization of Seizure Onset Zone Based on Multi-Epileptogenic Biomarkers Analysis of Single-Contact from Interictal SEEG

by Yiping Wang, Yanfeng Yang, Si Li, Zichen Su, Jinjie Guo, Penghu Wei, Jinguo Huang, Guixia Kang and Guoguang Zhao

Bioengineering 2022, 9(12), 769; https://doi.org/10.3390/bioengineering9120769 - 05 Dec 2022

Cited by 1 | Viewed by 2399

Abstract

Successful surgery on drug-resistant epilepsy patients (DRE) needs precise localization of the seizure onset zone (SOZ). Previous studies analyzing this issue still face limitations, such as inadequate analysis of features, low sensitivity and limited generality. Our study proposed an innovative and effective SOZ localization method based on multiple epileptogenic biomarkers (spike and HFOs), and analysis of single-contact (MEBM-SC) to address the above problems. We extracted contacts epileptic features from signal distributions and signal energy based on machine learning and end-to-end deep learning. Among them, a normalized pathological ripple rate was designed to reduce the disturbance of physiological ripple and enhance the performance of SOZ localization. Then, a feature selection algorithm based on Shapley value and hypothetical testing (ShapHT+) was used to limit interference from irrelevant features. Moreover, an attention mechanism and a focal loss algorithm were used on the classifier to learn significant features and overcome the unbalance of SOZ/nSOZ contacts. Finally, we provided an SOZ prediction and visualization on magnetic resonance imaging (MRI). Ten patients with DRE were selected to verify our method. The experiment performed cross-validation and revealed that MEBM-SC obtains higher sensitivity. Additionally, the spike has better sensitivity while HFOs have better specificity, and the combination of these biomarkers can achieve the best performance. The study confirmed that MEBM-SC can increase the sensitivity and accuracy of SOZ localization and help clinicians to perform a precise and reliable preoperative evaluation based on interictal SEEG. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Graphical abstract

9 pages, 1082 KiB

Open AccessEditor’s ChoiceArticle

Heart and Breathing Rate Variations as Biomarkers for Anxiety Detection

by Florian Ritsert, Mohamed Elgendi, Valeria Galli and Carlo Menon

Bioengineering 2022, 9(11), 711; https://doi.org/10.3390/bioengineering9110711 - 19 Nov 2022

Cited by 10 | Viewed by 2685

Abstract

With advances in portable and wearable devices, it should be possible to analyze and interpret the collected biosignals from those devices to tailor a psychological intervention to help patients. This study focuses on detecting anxiety by using a portable device that collects electrocardiogram (ECG) and respiration (RSP) signals. The feature extraction focused on heart-rate variability (HRV) and breathing-rate variability (BRV). We show that a significant change in these signals occurred between the non-anxiety-induced and anxiety-induced states. The HRV biomarkers were the mean heart rate (MHR;

\bar{p}

= 0.04), the standard deviation of the heart rate (SD;

\bar{p}

= 0.01), and the standard deviation of NN intervals (SDNN;

\bar{p}

= 0.03) for ECG signals, and the mean breath rate (MBR;

\bar{p}

= 0.002), the standard deviation of the breath rate (SD;

\bar{p}

< 0.0001), the root mean square of successive differences (RMSSD;

\bar{p}

< 0.0001) and SDNN (

\bar{p}

< 0.0001) for RSP signals. This work extends the existing literature on the relationship between stress and HRV/BRV by being the first to introduce a transitional phase. It contributes to systematically processing mental and emotional impulse data in humans measured via ECG and RSP signals. On the basis of these identified biomarkers, artificial-intelligence or machine-learning algorithms, and rule-based classification, the automated biosignal-based psychological assessment of patients could be within reach. This creates a broad basis for detecting and evaluating psychological abnormalities in individuals upon which future psychological treatment methods could be built using portable and wearable devices. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

17 pages, 951 KiB

Open AccessArticle

The Assessment of Medication Effects in Omicron Patients through MADM Approach Based on Distance Measures of Interval-Valued Fuzzy Hypersoft Set

by Muhammad Arshad, Muhammad Saeed, Atiqe Ur Rahman, Dilovan Asaad Zebari, Mazin Abed Mohammed, Alaa S. Al-Waisy, Marwan Albahar and Mohammed Thanoon

Bioengineering 2022, 9(11), 706; https://doi.org/10.3390/bioengineering9110706 - 17 Nov 2022

Cited by 4 | Viewed by 1184

Abstract

Omicron, so-called COVID-2, is an emerging variant of COVID-19 which is proved to be the most fatal amongst the other variants such as alpha, beta and gamma variants (

α

β

γ

variants) due to its stern and perilous nature. It [...] Read more.

Omicron, so-called COVID-2, is an emerging variant of COVID-19 which is proved to be the most fatal amongst the other variants such as alpha, beta and gamma variants (

α

β

γ

variants) due to its stern and perilous nature. It has caused hazardous effects globally in a very short span of time. The diagnosis and medication of Omicron patients are both challenging undertakings for researchers (medical experts) due to the involvement of various uncertainties and the vagueness of its altering behavior. In this study, an algebraic approach, interval-valued fuzzy hypersoft set (iv-FHSS), is employed to assess the conditions of patients after the application of suitable medication. Firstly, the distance measures between two iv-FHSSs are formulated with a brief description some of its properties, then a multi-attribute decision-making framework is designed through the proposal of an algorithm. This framework consists of three phases of medication. In the first phase, the Omicron-diagnosed patients are shortlisted and an iv-FHSS is constructed for such patients and then they are medicated. Another iv-FHSS is constructed after their first medication. Similarly, the relevant iv-FHSSs are constructed after second and third medications in other phases. The distance measures of these post-medication-based iv-FHSSs are computed with pre-medication-based iv-FHSS and the monotone pattern of distance measures are analyzed. It is observed that a decreasing pattern of computed distance measures assures that the medication is working well and the patients are recovering. In case of an increasing pattern, the medication is changed and the same procedure is repeated for the assessment of its effects. This approach is reliable due to the consideration of parameters (symptoms) and sub parameters (sub symptoms) jointly as multi-argument approximations. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

17 pages, 5946 KiB

Open AccessArticle

PPG2ABP: Translating Photoplethysmogram (PPG) Signals to Arterial Blood Pressure (ABP) Waveforms

by Nabil Ibtehaz, Sakib Mahmud, Muhammad E. H. Chowdhury, Amith Khandakar, Muhammad Salman Khan, Mohamed Arselene Ayari, Anas M. Tahir and M. Sohel Rahman

Bioengineering 2022, 9(11), 692; https://doi.org/10.3390/bioengineering9110692 - 15 Nov 2022

Cited by 25 | Viewed by 4301

Abstract

Cardiovascular diseases are one of the most severe causes of mortality, annually taking a heavy toll on lives worldwide. Continuous monitoring of blood pressure seems to be the most viable option, but this demands an invasive process, introducing several layers of complexities and reliability concerns due to non-invasive techniques not being accurate. This motivates us to develop a method to estimate the continuous arterial blood pressure (ABP) waveform through a non-invasive approach using Photoplethysmogram (PPG) signals. We explore the advantage of deep learning, as it would free us from sticking to ideally shaped PPG signals only by making handcrafted feature computation irrelevant, which is a shortcoming of the existing approaches. Thus, we present PPG2ABP, a two-stage cascaded deep learning-based method that manages to estimate the continuous ABP waveform from the input PPG signal with a mean absolute error of 4.604 mmHg, preserving the shape, magnitude, and phase in unison. However, the more astounding success of PPG2ABP turns out to be that the computed values of Diastolic Blood Pressure (DBP), Mean Arterial Pressure (MAP), and Systolic Blood Pressure (SBP) from the estimated ABP waveform outperform the existing works under several metrics (mean absolute error of 3.449 ± 6.147 mmHg, 2.310 ± 4.437 mmHg, and 5.727 ± 9.162 mmHg, respectively), despite that PPG2ABP is not explicitly trained to do so. Notably, both for DBP and MAP, we achieve Grade A in the BHS (British Hypertension Society) Standard and satisfy the AAMI (Association for the Advancement of Medical Instrumentation) standard. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Graphical abstract

25 pages, 1722 KiB

Open AccessArticle

A Survey on Physiological Signal-Based Emotion Recognition

by Zeeshan Ahmad and Naimul Khan

Bioengineering 2022, 9(11), 688; https://doi.org/10.3390/bioengineering9110688 - 14 Nov 2022

Cited by 14 | Viewed by 2733

Abstract

Physiological signals are the most reliable form of signals for emotion recognition, as they cannot be controlled deliberately by the subject. Existing review papers on emotion recognition based on physiological signals surveyed only the regular steps involved in the workflow of emotion recognition such as pre-processing, feature extraction, and classification. While these are important steps, such steps are required for any signal processing application. Emotion recognition poses its own set of challenges that are very important to address for a robust system. Thus, to bridge the gap in the existing literature, in this paper, we review the effect of inter-subject data variance on emotion recognition, important data annotation techniques for emotion recognition and their comparison, data pre-processing techniques for each physiological signal, data splitting techniques for improving the generalization of emotion recognition models and different multimodal fusion techniques and their comparison. Finally, we discuss key challenges and future directions in this field. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

14 pages, 3735 KiB

Open AccessArticle

Lightweight End-to-End Deep Learning Solution for Estimating the Respiration Rate from Photoplethysmogram Signal

by Moajjem Hossain Chowdhury, Md Nazmul Islam Shuzan, Muhammad E. H. Chowdhury, Mamun Bin Ibne Reaz, Sakib Mahmud, Nasser Al Emadi, Mohamed Arselene Ayari, Sawal Hamid Md Ali, Ahmad Ashrif A. Bakar, Syed Mahfuzur Rahman and Amith Khandakar

Bioengineering 2022, 9(10), 558; https://doi.org/10.3390/bioengineering9100558 - 16 Oct 2022

Cited by 9 | Viewed by 1793

Abstract

Respiratory ailments are a very serious health issue and can be life-threatening, especially for patients with COVID. Respiration rate (RR) is a very important vital health indicator for patients. Any abnormality in this metric indicates a deterioration in health. Hence, continuous monitoring of RR can act as an early indicator. Despite that, RR monitoring equipment is generally provided only to intensive care unit (ICU) patients. Recent studies have established the feasibility of using photoplethysmogram (PPG) signals to estimate RR. This paper proposes a deep-learning-based end-to-end solution for estimating RR directly from the PPG signal. The system was evaluated on two popular public datasets: VORTAL and BIDMC. A lightweight model, ConvMixer, outperformed all of the other deep neural networks. The model provided a root mean squared error (RMSE), mean absolute error (MAE), and correlation coefficient (R) of 1.75 breaths per minute (bpm), 1.27 bpm, and 0.92, respectively, for VORTAL, while these metrics were 1.20 bpm, 0.77 bpm, and 0.92, respectively, for BIDMC. The authors also showed how fine-tuning a small subset could increase the performance of the model in the case of an out-of-distribution dataset. In the fine-tuning experiments, the models produced an average R of 0.81. Hence, this lightweight model can be deployed to mobile devices for real-time monitoring of patients. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Figure 1

13 pages, 1374 KiB

Open AccessArticle

End-to-End Convolutional Neural Network Model to Detect and Localize Myocardial Infarction Using 12-Lead ECG Images without Preprocessing

by Ryunosuke Uchiyama, Yoshifumi Okada, Ryuya Kakizaki and Sekito Tomioka

Bioengineering 2022, 9(9), 430; https://doi.org/10.3390/bioengineering9090430 - 01 Sep 2022

Cited by 4 | Viewed by 2391

Abstract

In recent years, many studies have proposed automatic detection and localization techniques for myocardial infarction (MI) using the 12-lead electrocardiogram (ECG). Most of them applied preprocessing to the ECG signals, e.g., noise removal, trend removal, beat segmentation, and feature selection, followed by model construction and classification based on machine-learning algorithms. The selection and implementation of preprocessing methods require specialized knowledge and experience to handle ECG data. In this paper, we propose an end-to-end convolutional neural network model that detects and localizes MI without such complicated multistep preprocessing. The proposed model executes comprehensive learning for the waveform features of unpreprocessed raw ECG images captured from 12-lead ECG signals. We evaluated the classification performance of the proposed model in two experimental settings: ten-fold cross-validation where ECG images were split randomly, and two-fold cross-validation where ECG images were split into one patient and the other patients. The experimental results demonstrate that the proposed model obtained MI detection accuracies of 99.82% and 93.93% and MI localization accuracies of 99.28% and 69.27% in the first and second settings, respectively. The performance of the proposed method is higher than or comparable to that of existing state-of-the-art methods. Thus, the proposed model is expected to be an effective MI diagnosis tool that can be used in intensive care units and as wearable technology. Full article

(This article belongs to the Special Issue Advances of Biomedical Signal Processing)

► Show Figures

Graphical abstract

Journal Menu

Journal Browser

Advances of Biomedical Signal Processing

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Published Papers (14 papers)

Research

Further Information

Guidelines

MDPI Initiatives

Follow MDPI