sensors-logo

Journal Browser

Journal Browser

Intelligent Sensing in Biomedical Applications

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

Deadline for manuscript submissions: closed (15 February 2023) | Viewed by 13245

Special Issue Editors

Department of Neurology, Faculty of Medicine in University Hospital Hradec Králové, Charles University in Prague, Sokolská 581, 500 05, Hradec Králové, Czech Republic
Interests: neurophysiology; digital signal processing; biological systems modeling
1. Department of Computing and Control Engineering, University of Chemistry and Technology in Prague, 166 28 Prague, Czech Republic
2. Czech Institute of Informatics, Robotics and Cybernetics, Czech Technical University in Prague, 166 36 Prague, Czech Republic
Interests: digital signal processing; machine learning; computational intelligence
Special Issues, Collections and Topics in MDPI journals
Dr. Rafael Doležal
E-Mail Website
Guest Editor
Department of Chemistry, Faculty of Science, University of Hradec Kralove, Hradec Kralove, Czech Republic
Interests: computer-aided drug design; high-performance computing; machine learning

Special Issue Information

Dear Colleagues,

At present, monitoring the course of the disease and the effect of therapy in clinical practice mostly depends on clinical scales and clinical impression. Such a description of the development of the patient’s condition is subject to intra-individual and inter-individual variability. In addition, such monitoring takes place only for a short time, mostly in the unnatural conditions of medical facilities. On the other hand, modern sensors enable increasingly accurate long-term monitoring of many important quantities. Reducing the variability of patient follow-up makes it possible to reduce the number of subjects in clinical trials and thus significantly reduce the cost of the studies. It also reduces the likelihood of false-negative results, thus saving the cost of developing new treatments. Smart sensor devices make it possible to acquire, process, and transmit data to users. Smart implants like orthopedic implants instrumented with strain gauges increase their lifespan. Retina implant systems using image sensors restore vision. Wearable body sensor networks comprising various types of sensors can monitor the course of vital variables for a long time, as well as the signal needed for therapeutic intervention. Biosensors enable the monitoring of physical activities. Results of machine learning methods contribute to the diagnosis of neurological disorders and the detection of tissue changes.

This Special Issue is addressed to all types of smart sensors designed for biomedical applications.

The topic of this Special Issue concerns the following areas of interest of the magazine: biosensors, sensor networks, smart/intelligent sensors, signal processing, data fusion, and deep learning in sensor systems.

Dr. Oldřich Vyšata
Prof. Dr. Aleš Procházka
Dr. Rafael Doležal
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. 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.

Keywords

  • smart implants
  • smart biosensors
  • wearables
  • sensor fusion
  • biomedical
  • motion monitoring
  • machine learning
  • signal processing

Published Papers (6 papers)

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

Research

19 pages, 15122 KiB  
Article
Brain Connectivity Signature Extractions from TMS Invoked EEGs
Sensors 2023, 23(8), 4078; https://doi.org/10.3390/s23084078 - 18 Apr 2023
Viewed by 1102
Abstract
(1) Background: The correlations between brain connectivity abnormality and psychiatric disorders have been continuously investigated and progressively recognized. Brain connectivity signatures are becoming exceedingly useful for identifying patients, monitoring mental health disorders, and treatment. By using electroencephalography (EEG)-based cortical source localization along with [...] Read more.
(1) Background: The correlations between brain connectivity abnormality and psychiatric disorders have been continuously investigated and progressively recognized. Brain connectivity signatures are becoming exceedingly useful for identifying patients, monitoring mental health disorders, and treatment. By using electroencephalography (EEG)-based cortical source localization along with energy landscape analysis techniques, we can statistically analyze transcranial magnetic stimulation (TMS)-invoked EEG signals, for obtaining connectivity among different brain regions at a high spatiotemporal resolution. (2) Methods: In this study, we analyze EEG-based source localized alpha wave activity in response to TMS administered to three locations, namely, the left motor cortex (49 subjects), left prefrontal cortex (27 subjects), and the posterior cerebellum, or vermis (27 subjects) by using energy landscape analysis techniques to uncover connectivity signatures. We then perform two sample t-tests and use the (5 × 10−5) Bonferroni corrected p-valued cases for reporting six reliably stable signatures. (3) Results: Vermis stimulation invoked the highest number of connectivity signatures and the left motor cortex stimulation invoked a sensorimotor network state. In total, six out of 29 reliable, stable connectivity signatures are found and discussed. (4) Conclusions: We extend previous findings to localized cortical connectivity signatures for medical applications that serve as a baseline for future dense electrode studies. Full article
(This article belongs to the Special Issue Intelligent Sensing in Biomedical Applications)
Show Figures

Figure 1

20 pages, 11212 KiB  
Article
Conditional Generative Adversarial Networks for Data Augmentation of a Neonatal Image Dataset
Sensors 2023, 23(2), 999; https://doi.org/10.3390/s23020999 - 15 Jan 2023
Viewed by 1890
Abstract
In today’s neonatal intensive care units, monitoring vital signs such as heart rate and respiration is fundamental for neonatal care. However, the attached sensors and electrodes restrict movement and can cause medical-adhesive-related skin injuries due to the immature skin of preterm infants, which [...] Read more.
In today’s neonatal intensive care units, monitoring vital signs such as heart rate and respiration is fundamental for neonatal care. However, the attached sensors and electrodes restrict movement and can cause medical-adhesive-related skin injuries due to the immature skin of preterm infants, which may lead to serious complications. Thus, unobtrusive camera-based monitoring techniques in combination with image processing algorithms based on deep learning have the potential to allow cable-free vital signs measurements. Since the accuracy of deep-learning-based methods depends on the amount of training data, proper validation of the algorithms is difficult due to the limited image data of neonates. In order to enlarge such datasets, this study investigates the application of a conditional generative adversarial network for data augmentation by using edge detection frames from neonates to create RGB images. Different edge detection algorithms were used to validate the input images’ effect on the adversarial network’s generator. The state-of-the-art network architecture Pix2PixHD was adapted, and several hyperparameters were optimized. The quality of the generated RGB images was evaluated using a Mechanical Turk-like multistage survey conducted by 30 volunteers and the FID score. In a fake-only stage, 23% of the images were categorized as real. A direct comparison of generated and real (manually augmented) images revealed that 28% of the fake data were evaluated as more realistic. An FID score of 103.82 was achieved. Therefore, the conducted study shows promising results for the training and application of conditional generative adversarial networks to augment highly limited neonatal image datasets. Full article
(This article belongs to the Special Issue Intelligent Sensing in Biomedical Applications)
Show Figures

Figure 1

15 pages, 6679 KiB  
Article
Encouraging and Detecting Preferential Incipient Slip for Use in Slip Prevention in Robot-Assisted Surgery
Sensors 2022, 22(20), 7956; https://doi.org/10.3390/s22207956 - 19 Oct 2022
Cited by 3 | Viewed by 1175
Abstract
Robotic surgical platforms have helped to improve minimally invasive surgery; however, limitations in their force feedback and force control can result in undesirable tissue trauma or tissue slip events. In this paper, we investigate a sensing method for the early detection of slip [...] Read more.
Robotic surgical platforms have helped to improve minimally invasive surgery; however, limitations in their force feedback and force control can result in undesirable tissue trauma or tissue slip events. In this paper, we investigate a sensing method for the early detection of slip events when grasping soft tissues, which would allow surgical robots to take mitigating action to prevent tissue slip and maintain stable grasp control while minimising the applied gripping force, reducing the probability of trauma. The developed sensing concept utilises a curved grasper face to create areas of high and low normal, and thus frictional, force. In the areas of low normal force, there is a higher probability that the grasper face will slip against the tissue. If the grasper face is separated into a series of independent movable islands, then by tracking their displacement it will be possible to identify when the areas of low normal force first start to slip while the remainder of the tissue is still held securely. The system was evaluated through the simulated grasping and retraction of tissue under conditions representative of surgical practice using silicone tissue simulants and porcine liver samples. It was able to successfully detect slip before gross slip occurred with a 100% and 77% success rate for the tissue simulant and porcine liver samples, respectively. This research demonstrates the efficacy of this sensing method and the associated sensor system for detecting the occurrence of tissue slip events during surgical grasping and retraction. Full article
(This article belongs to the Special Issue Intelligent Sensing in Biomedical Applications)
Show Figures

Figure 1

12 pages, 1669 KiB  
Communication
Classification of Ataxic Gait
Sensors 2021, 21(16), 5576; https://doi.org/10.3390/s21165576 - 19 Aug 2021
Cited by 4 | Viewed by 2173
Abstract
Gait disorders accompany a number of neurological and musculoskeletal disorders that significantly reduce the quality of life. Motion sensors enable high-quality modelling of gait stereotypes. However, they produce large volumes of data, the evaluation of which is a challenge. In this publication, we [...] Read more.
Gait disorders accompany a number of neurological and musculoskeletal disorders that significantly reduce the quality of life. Motion sensors enable high-quality modelling of gait stereotypes. However, they produce large volumes of data, the evaluation of which is a challenge. In this publication, we compare different data reduction methods and classification of reduced data for use in clinical practice. The best accuracy achieved between a group of healthy individuals and patients with ataxic gait extracted from the records of 43 participants (23 ataxic, 20 healthy), forming 418 segments of straight gait pattern, is 98% by random forest classifier preprocessed by t-distributed stochastic neighbour embedding. Full article
(This article belongs to the Special Issue Intelligent Sensing in Biomedical Applications)
Show Figures

Figure 1

21 pages, 2362 KiB  
Article
Advanced Statistical Analysis of 3D Kinect Data: Mimetic Muscle Rehabilitation Following Head and Neck Surgeries Causing Facial Paresis
Sensors 2021, 21(1), 103; https://doi.org/10.3390/s21010103 - 26 Dec 2020
Cited by 8 | Viewed by 2024
Abstract
An advanced statistical analysis of patients’ faces after specific surgical procedures that temporarily negatively affect the patient’s mimetic muscles is presented. For effective planning of rehabilitation, which typically lasts several months, it is crucial to correctly evaluate the improvement of the mimetic muscle [...] Read more.
An advanced statistical analysis of patients’ faces after specific surgical procedures that temporarily negatively affect the patient’s mimetic muscles is presented. For effective planning of rehabilitation, which typically lasts several months, it is crucial to correctly evaluate the improvement of the mimetic muscle function. The current way of describing the development of rehabilitation depends on the subjective opinion and expertise of the clinician and is not very precise concerning when the most common classification (House–Brackmann scale) is used. Our system is based on a stereovision Kinect camera and an advanced mathematical approach that objectively quantifies the mimetic muscle function independently of the clinician’s opinion. To effectively deal with the complexity of the 3D camera input data and uncertainty of the evaluation process, we designed a three-stage data-analytic procedure combining the calculation of indicators determined by clinicians with advanced statistical methods including functional data analysis and ordinal (multiple) logistic regression. We worked with a dataset of 93 distinct patients and 122 sets of measurements. In comparison to the classification with the House–Brackmann scale the developed system is able to automatically monitor reinnervation of mimetic muscles giving us opportunity to discriminate even small improvements during the course of rehabilitation. Full article
(This article belongs to the Special Issue Intelligent Sensing in Biomedical Applications)
Show Figures

Figure 1

25 pages, 2405 KiB  
Article
Individualised Responsible Artificial Intelligence for Home-Based Rehabilitation
Sensors 2021, 21(1), 2; https://doi.org/10.3390/s21010002 - 22 Dec 2020
Cited by 16 | Viewed by 3783
Abstract
Socioeconomic reasons post-COVID-19 demand unsupervised home-based rehabilitation and, specifically, artificial ambient intelligence with individualisation to support engagement and motivation. Artificial intelligence must also comply with accountability, responsibility, and transparency (ART) requirements for wider acceptability. This paper presents such a patient-centric individualised home-based rehabilitation [...] Read more.
Socioeconomic reasons post-COVID-19 demand unsupervised home-based rehabilitation and, specifically, artificial ambient intelligence with individualisation to support engagement and motivation. Artificial intelligence must also comply with accountability, responsibility, and transparency (ART) requirements for wider acceptability. This paper presents such a patient-centric individualised home-based rehabilitation support system. To this end, the Timed Up and Go (TUG) and Five Time Sit To Stand (FTSTS) tests evaluate daily living activity performance in the presence or development of comorbidities. We present a method for generating synthetic datasets complementing experimental observations and mitigating bias. We present an incremental hybrid machine learning algorithm combining ensemble learning and hybrid stacking using extreme gradient boosted decision trees and k-nearest neighbours to meet individualisation, interpretability, and ART design requirements while maintaining low computation footprint. The model reaches up to 100% accuracy for both FTSTS and TUG in predicting associated patient medical condition, and 100% or 83.13%, respectively, in predicting area of difficulty in the segments of the test. Our results show an improvement of 5% and 15% for FTSTS and TUG tests, respectively, over previous approaches that use intrusive means of monitoring such as cameras. Full article
(This article belongs to the Special Issue Intelligent Sensing in Biomedical Applications)
Show Figures

Figure 1

Back to TopTop