Topic Editors

Signals and Images Laboratory, Institute of Information Science and Technologies "A. Faedo" (ISTI), National Research Council of Italy (CNR), Via Moruzzi, 1, Pisa, Italy
Institute of Information Science and Technologies, National Research Council of Italy, Signals and Images Laboratory, Via Moruzzi, 1, 56124 Pisa, Italy
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

Machine Learning and Biomedical Sensors

Abstract submission deadline
31 October 2023
Manuscript submission deadline
31 December 2023
Viewed by
2613

Topic Information

Dear Colleagues,

The increase in the information collected by an ever-growing number of biomedical sensors connected to the internet, together with the availability of a network of services recording any biological, physical, clinical and other kinds of data, has made the soil fertile for the significant use of machine learning (ML). It has become possible to use the various biomedical devices in the most diverse environments (at the depths of the seas, high altitudes, in space) in hospitals as well at home or outdoors, opening up new scenarios that were not previously conceivable. In this context, machine learning has shown great potential and might provide solutions to many issues concerning life on our planet. This Topic aims to present the most recent and innovative solutions leveraging the interplay between biomedical sensors and machine learning. Advanced and modern data-driven methods and learning approaches are sought to correlate and understand heterogeneous data in providing accurate classifications and predictions. The perspective opened by pervasive and edge computing should be properly transferred to the biomedical domain by devising novel activity monitoring and physiological computing paradigms. From the point of view of innovative sensing technologies, new transducers coupled with embedded computing for obtaining smart and possibly miniaturized or minimally invasive devices should be investigated. In such a panorama, the role of machine learning and artificial intelligence, more generally, should be adequately understood together with the issues related to their perception. In addition, user acceptance and privacy issues are important aspects to be assessed in real experimentation, which is necessary for clinical validation of the proposed technological solutions. The Topic, through its participating journals, is therefore seeking contributions that explore multifaced aspects of the convergence between biomedical sensors and machine learning: from fundamental elements related to computing over sensor networks and federated learning to innovative sensing principles and technologies for smart devices, from clinical experimentation and validation in healthcare scenarios to general application in ambient assisted living, contextually with the concurrent assessment of privacy and user acceptance factors.

  • Human physiology & physiological computing
  • Multimedia data analysis
  • Digital signal and image processing
  • Computer vision in biomedical sensing
  • New materials and approaches for smart biomedical sensors
  • Artificial intelligence over networks of biomedical sensors
  • Protocols and middleware for smart biomedical sensors
  • Sensors for Active and Healthy Ageing
  • Internet of Biomedical Things (IoBT)
  • Pilot studies and clinical validation
  • User experience and acceptance of Artificial Intelligence in biomedical sensors
  • Privacy and security issues
  • Big Data
  • Teleassistance & telemedicine
  • Signals analysis & statistics methods

Dr. Massimo Martinelli
Dr. Davide Moroni
Prof. Dr. Aleš Procházka
Topic Editors

Keywords

  • machine learning
  • artificial intelligence
  • biomedicine
  • decision support systems & recommendation systems
  • pervasive and mobile computing
  • embedded computing
  • monitoring systems based on smart sensors
  • personalized services for wellbeing
  • wearable smart sensors
  • smartphone applications
  • contactless smart sensors
  • learning schemes for smart biomedical sensing
  • incremental learning
  • reinforcement learning
  • physical activities monitoring

Participating Journals

Journal Name Impact Factor CiteScore Launched Year First Decision (median) APC
Bioengineering
bioengineering
5.046 6.3 2014 14.8 Days 2000 CHF Submit
Healthcare
healthcare
3.160 2.0 2013 19.1 Days 2000 CHF Submit
Journal of Clinical Medicine
jcm
4.964 4.4 2012 18 Days 2600 CHF Submit
Journal of Sensor and Actuator Networks
jsan
- 6.9 2012 18.4 Days 1600 CHF Submit
Sensors
sensors
3.847 6.4 2001 15 Days 2400 CHF Submit
Applied Sciences
applsci
2.838 3.7 2011 14.9 Days 2300 CHF Submit
Biosensors
biosensors
5.743 5.6 2011 13.7 Days 2200 CHF Submit

Preprints is a platform dedicated to making early versions of research outputs permanently available and citable. MDPI journals allow posting on preprint servers such as Preprints.org prior to publication. For more details about reprints, please visit https://www.preprints.org.

Published Papers (3 papers)

Order results
Result details
Journals
Select all
Export citation of selected articles as:
Communication
MindReader: Unsupervised Classification of Electroencephalographic Data
Sensors 2023, 23(6), 2971; https://doi.org/10.3390/s23062971 - 09 Mar 2023
Viewed by 325
Abstract
Electroencephalogram (EEG) interpretation plays a critical role in the clinical assessment of neurological conditions, most notably epilepsy. However, EEG recordings are typically analyzed manually by highly specialized and heavily trained personnel. Moreover, the low rate of capturing abnormal events during the procedure makes [...] Read more.
Electroencephalogram (EEG) interpretation plays a critical role in the clinical assessment of neurological conditions, most notably epilepsy. However, EEG recordings are typically analyzed manually by highly specialized and heavily trained personnel. Moreover, the low rate of capturing abnormal events during the procedure makes interpretation time-consuming, resource-hungry, and overall an expensive process. Automatic detection offers the potential to improve the quality of patient care by shortening the time to diagnosis, managing big data and optimizing the allocation of human resources towards precision medicine. Here, we present MindReader, a novel unsupervised machine-learning method comprised of the interplay between an autoencoder network, a hidden Markov model (HMM), and a generative component: after dividing the signal into overlapping frames and performing a fast Fourier transform, MindReader trains an autoencoder neural network for dimensionality reduction and compact representation of different frequency patterns for each frame. Next, we processed the temporal patterns using a HMM, while a third and generative component hypothesized and characterized the different phases that were then fed back to the HMM. MindReader then automatically generates labels that the physician can interpret as pathological and non-pathological phases, thus effectively reducing the search space for trained personnel. We evaluated MindReader’s predictive performance on 686 recordings, encompassing more than 980 h from the publicly available Physionet database. Compared to manual annotations, MindReader identified 197 of 198 epileptic events (99.45%), and is, as such, a highly sensitive method, which is a prerequisite for clinical use. Full article
(This article belongs to the Topic Machine Learning and Biomedical Sensors)
Show Figures

Figure 1

Article
Automatic Segmentation of Cervical Cells Based on Star-Convex Polygons in Pap Smear Images
Bioengineering 2023, 10(1), 47; https://doi.org/10.3390/bioengineering10010047 - 30 Dec 2022
Viewed by 847
Abstract
Cervical cancer is one of the most common cancers that threaten women’s lives, and its early screening is of great significance for the prevention and treatment of cervical diseases. Pathologically, the accurate segmentation of cervical cells plays a crucial role in the diagnosis [...] Read more.
Cervical cancer is one of the most common cancers that threaten women’s lives, and its early screening is of great significance for the prevention and treatment of cervical diseases. Pathologically, the accurate segmentation of cervical cells plays a crucial role in the diagnosis of cervical cancer. However, the frequent presence of adherent or overlapping cervical cells in Pap smear images makes separating them individually a difficult task. Currently, there are few studies on the segmentation of adherent cervical cells, and the existing methods commonly suffer from low segmentation accuracy and complex design processes. To address the above problems, we propose a novel star-convex polygon-based convolutional neural network with an encoder-decoder structure, called SPCNet. The model accomplishes the segmentation of adherent cells relying on three steps: automatic feature extraction, star-convex polygon detection, and non-maximal suppression (NMS). Concretely, a new residual-based attentional embedding (RAE) block is suggested for image feature extraction. It fuses the deep features from the attention-based convolutional layers with the shallow features from the original image through the residual connection, enhancing the network’s ability to extract the abundant image features. And then, a polygon-based adaptive NMS (PA-NMS) algorithm is adopted to screen the generated polygon proposals and further achieve the accurate detection of adherent cells, thus allowing the network to completely segment the cell instances in Pap smear images. Finally, the effectiveness of our method is evaluated on three independent datasets. Extensive experimental results demonstrate that the method obtains superior segmentation performance compared to other well-established algorithms. Full article
(This article belongs to the Topic Machine Learning and Biomedical Sensors)
Show Figures

Figure 1

Article
Feasibility of Brachial Occlusion Technique for Beat-to-Beat Pulse Wave Analysis
Sensors 2022, 22(19), 7285; https://doi.org/10.3390/s22197285 - 26 Sep 2022
Viewed by 629
Abstract
Czech physiologist Penaz tried to overcome limitations of invasive pulse-contour methods (PCM) in clinical applications by a non-invasive method (finger mounted BP cuff) for continuous arterial waveform detection and beat-to-beat analysis. This discovery resulted in significant interest in human physiology and non-invasive examination [...] Read more.
Czech physiologist Penaz tried to overcome limitations of invasive pulse-contour methods (PCM) in clinical applications by a non-invasive method (finger mounted BP cuff) for continuous arterial waveform detection and beat-to-beat analysis. This discovery resulted in significant interest in human physiology and non-invasive examination of hemodynamic parameters, however has limitations because of the distal BP recording using a volume-clamp method. Thus, we propose a validation of beat-to-beat signal analysis acquired by novel a brachial occlusion-cuff (suprasystolic) principle and signal obtained from Finapres during a forced expiratory effort against an obstructed airway (Valsalva maneuver). Twelve healthy adult subjects [2 females, age = (27.2 ± 5.1) years] were in the upright siting position, breathe through the mouthpiece (simultaneously acquisition by brachial blood pressure monitor and Finapres) and at a defined time were asked to generate positive mouth pressure for 20 s (Valsalva). For the purpose of signal analysis, we proposed parameter a “Occlusion Cuff Index” (OCCI). The assumption about similarities between measured signals (suprasystolic brachial pulse waves amplitudes and Finapres’s MAP) were proved by averaged Pearson’s correlation coefficient (r- = 0.60, p < 0.001). The averaged Pearson’s correlation coefficient for the comparative analysis of OCCI between methods was r- = 0.88, p < 0.001. The average percent change of OCCI during maneuver: 8% increase, 19% decrease and percent change of max/min ratio is 35%. The investigation of brachial pulse waves measured by novel brachial blood pressure monitor shows positive correlation with Finapres and the parameter OCCI shows promise as an index, which could describe changes during beat-to-beat cardiac cycles. Full article
(This article belongs to the Topic Machine Learning and Biomedical Sensors)
Show Figures

Figure 1

Back to TopTop