Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
6.8
3.9
Journals
Sensors
Special Issues
Healthcare Monitoring and Management with Artificial Intelligence
sensors-logo
Submit to Sensors Review for Sensors Propose a Special Issue

Journal Menu

► Journal Menu

Journal Browser

► Journal Browser
share announcement

Healthcare Monitoring and Management with Artificial Intelligence

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

Deadline for manuscript submissions: closed (20 April 2021) | Viewed by 72401

Special Issue Editors

Dr. Zongyuan Ge

E-Mail Website
Guest Editor
eResearch Center, Monash University, Clayton, VIC 3800, Australia
Interests: medical artificial intelligence
Special Issues, Collections and Topics in MDPI journals
Dr. Yingying Zhu

E-Mail Website
Guest Editor
National Institutes of Health, Bethesda, USA
Interests: image reconstruction; graph learning; medical imaging
Prof. Dr. Xiaofeng Zhu

E-Mail Website
Guest Editor
Massey University, New Zealand
Interests: data science; big data; machine learning; medical imaging analysis

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) and machine learning (ML) show that computers have the ability to accomplish tasks that are normally completed by intelligent beings such as humans and animals. Among current AI applications, machine learning (ML) is a tool that combines computer science with statistics for generating advanced algorithms capable of identifying the complex relationships within large datasets. At present, some of the greatest successes of machine learning have been in the field of vision and neural language understanding. Many tasks such as object classification, detection, and segmentation have demonstrated superhuman performances.

Medicine and healthcare, even from the early time of intelligence system research, has been one of the most promising and inspiring domains for the application of automatic decision-making approaches. On the other hand, it has been one of the most challenging areas for effective adoption. AI is transforming healthcare in various domains such as oncology, dermatology, ophthalmology, and radiology. Medical imaging modalities like EEG, ECG, PCG, X-ray, magnetic resonance imaging, computerized tomography, single-photon emission computed tomography, positron emission tomography (PET), and fundus and ultrasound images have provided valuable information from various body parts for diagnosis, prognosis, and treatment. Biosensors, which integrates biology, chemistry, physics, information science, and technology, is an active branch in the field of science and technology. It has a broad application prospect in disease detection, environmental pollution monitoring, immune analysis, drug screening, and other areas.

However, there are many challenges that remain to be solved. The ability of a model to find statistical patterns across millions of samples and features is what enables superior performance for the intelligence system. However, most of the time, the identified patterns do not necessarily correspond to the underlying biologic pathways. Moreover, the numerical results driven by the machines, without a measure of their certainty and confidence level, do not provide trusted decisions. Finally, in practice, it is likely that a deployed medical decision-making system will encounter unseen disease conditions, where most of the existing system assumes that the universe of conditions is limited to what has been encoded in the models.

The objective of this Special Issue is to generate a comprehensive understanding of medical AI and biosensors in clinical applications. It will also highlight recent advances in the diverse implementations in healthcare management and monitoring. Authors are invited to submit outstanding and original unpublished research manuscripts focused on the latest findings in this field. The topics of interest are limited to the following:

  • Artificial intelligence for healthcare sensoring data with applications;
  • Artificial intelligence for healthcare sensoring and monitoring;
  • Interventional tracking and navigation;
  • Medical robotics and haptics;
  • Biosensors;
  • Biosensing technique;
  • Biochips;
  • Wearable devices;
  • Medical artificial intelligence;
  • Diagnosis artificial intelligence;
  • Predication medical artificial intelligence;
  • Medicine artificial intelligence ethical study;
  • Explainable medical artificial intelligence;
  • Medical imaging understanding;
  • Image segmentation, registration, and fusion;
  • Image reconstruction and image quality;
  • Computer-aided diagnosis;
  • Population imaging and imaging genetics;
  • Applications of big data in imaging;
  • Integration of imaging with non-imaging biomarkers;
  • Visualisation in biomedical Imaging;
  • Surgical data science;
  • Interventional imaging systems;
  • Image-guided interventions and surgery.

Dr. Zongyuan Ge
Dr. Yingying Zhu
Prof. Dr. Xiaofeng Zhu
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

  • Artificial intelligence
  • Medical sensors
  • Biosensors
  • Medical imaging
  • Vision technology.

Published Papers (16 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review, Other

22 pages, 15597 KiB  
Article
Learning Explainable Time-Morphology Patterns for Automatic Arrhythmia Classification from Short Single-Lead ECGs
by Hyeonjeong Lee and Miyoung Shin
Sensors 2021, 21(13), 4331; https://doi.org/10.3390/s21134331 - 24 Jun 2021
Cited by 18 | Viewed by 4644
Abstract
Automatic detection of abnormal heart rhythms, including atrial fibrillation (AF), using signals obtained from a single-lead wearable electrocardiogram (ECG) device, is useful for daily cardiac health monitoring. In this study, we propose a novel image-based deep learning framework to classify single-lead ECG recordings [...] Read more.
Automatic detection of abnormal heart rhythms, including atrial fibrillation (AF), using signals obtained from a single-lead wearable electrocardiogram (ECG) device, is useful for daily cardiac health monitoring. In this study, we propose a novel image-based deep learning framework to classify single-lead ECG recordings of short variable length into several different rhythms associated with arrhythmias. By transforming variable-length 1D ECG signals into fixed-size 2D time-morphology representations and feeding them to the beat–interval–texture convolutional neural network (BIT-CNN) model, we aimed to learn the comprehensible characteristics of beat shape and inter-beat patterns over time for arrhythmia classification. The proposed approach allows feature embedding vectors to provide interpretable time-morphology patterns focused at each step of the learning process. In addition, this method reduces the number of model parameters needed to be trained and aids visual interpretation, while maintaining similar performance to other CNN-based approaches to arrhythmia classification. For experiments, we used the PhysioNet/CinC Challenge 2017 dataset and achieved an overall F1_NAO of 81.75% and F1_NAOP of 76.87%, which are comparable to those of the state-of-the-art methods for variable-length ECGs. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

19 pages, 868 KiB  
Article
Autoencoder-Based Extrasystole Detection and Modification of RRI Data for Precise Heart Rate Variability Analysis
by Koichi Fujiwara, Shota Miyatani, Asuka Goda, Miho Miyajima, Tetsuo Sasano and Manabu Kano
Sensors 2021, 21(9), 3235; https://doi.org/10.3390/s21093235 - 07 May 2021
Cited by 6 | Viewed by 3313
Abstract
Heart rate variability, which is the fluctuation of the R-R interval (RRI) in electrocardiograms (ECG), has been widely adopted for autonomous evaluation. Since the HRV features that are extracted from RRI data easily fluctuate when arrhythmia occurs, RRI data with arrhythmia need to [...] Read more.
Heart rate variability, which is the fluctuation of the R-R interval (RRI) in electrocardiograms (ECG), has been widely adopted for autonomous evaluation. Since the HRV features that are extracted from RRI data easily fluctuate when arrhythmia occurs, RRI data with arrhythmia need to be modified appropriately before HRV analysis. In this study, we consider two types of extrasystoles—premature ventricular contraction (PVC) and premature atrial contraction (PAC)—which are types of extrasystoles that occur every day, even in healthy persons who have no cardiovascular diseases. A unified framework for ectopic RRI detection and a modification algorithm that utilizes an autoencoder (AE) type of neural network is proposed. The proposed framework consists of extrasystole occurrence detection from the RRI data and modification, whose targets are PVC and PAC. The RRI data are monitored by means of the AE in real time in the detection phase, and a denoising autoencoder (DAE) modifies the ectopic RRI caused by the detected extrasystole. These are referred to as AE-based extrasystole detection (AED) and DAE-based extrasystole modification (DAEM), respectively. The proposed framework was applied to real RRI data with PVC and PAC. The result showed that AED achieved a sensitivity of 93% and a false positive rate of 0.08 times per hour. The root mean squared error of the modified RRI decreased to 31% in PVC and 73% in PAC from the original RRI data by DAEM. In addition, the proposed framework was validated through application to a clinical epileptic seizure problem, which showed that it correctly suppressed the false positives caused by PVC. Thus, the proposed framework can contribute to realizing accurate HRV-based health monitoring and medical sensing systems. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

21 pages, 618 KiB  
Article
Gated Graph Attention Network for Cancer Prediction
by Linling Qiu, Han Li, Meihong Wang and Xiaoli Wang
Sensors 2021, 21(6), 1938; https://doi.org/10.3390/s21061938 - 10 Mar 2021
Cited by 3 | Viewed by 3007
Abstract
With its increasing incidence, cancer has become one of the main causes of worldwide mortality. In this work, we mainly propose a novel attention-based neural network model named Gated Graph ATtention network (GGAT) for cancer prediction, where a gating mechanism (GM) is introduced [...] Read more.
With its increasing incidence, cancer has become one of the main causes of worldwide mortality. In this work, we mainly propose a novel attention-based neural network model named Gated Graph ATtention network (GGAT) for cancer prediction, where a gating mechanism (GM) is introduced to work with the attention mechanism (AM), to break through the previous work’s limitation of 1-hop neighbourhood reasoning. In this way, our GGAT is capable of fully mining the potential correlation between related samples, helping for improving the cancer prediction accuracy. Additionally, to simplify the datasets, we propose a hybrid feature selection algorithm to strictly select gene features, which significantly reduces training time without affecting prediction accuracy. To the best of our knowledge, our proposed GGAT achieves the state-of-the-art results in cancer prediction task on LIHC, LUAD, KIRC compared to other traditional machine learning methods and neural network models, and improves the accuracy by 1% to 2% on Cora dataset, compared to the state-of-the-art graph neural network methods. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Graphical abstract

18 pages, 5792 KiB  
Article
Classification with a Deferral Option and Low-Trust Filtering for Automated Seizure Detection
by Thijs Becker, Kaat Vandecasteele, Christos Chatzichristos, Wim Van Paesschen, Dirk Valkenborg, Sabine Van Huffel and Maarten De Vos
Sensors 2021, 21(4), 1046; https://doi.org/10.3390/s21041046 - 04 Feb 2021
Cited by 11 | Viewed by 2196
Abstract
Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under-report. Visual analysis of a 24-h EEG recording typically takes one to [...] Read more.
Wearable technology will become available and allow prolonged electroencephalography (EEG) monitoring in the home environment of patients with epilepsy. Neurologists analyse the EEG visually and annotate all seizures, which patients often under-report. Visual analysis of a 24-h EEG recording typically takes one to two hours. Reliable automated seizure detection algorithms will be crucial to reduce this analysis. We investigated such algorithms on a dataset of behind-the-ear EEG measurements. Our first aim was to develop a methodology where part of the data is deferred to a human expert, who performs perfectly, with the goal of obtaining an (almost) perfect detection sensitivity (DS). Prediction confidences are determined by temperature scaling of the classification model outputs and trust scores. A DS of approximately 90% (99%) can be achieved when deferring around 10% (40%) of the data. Perfect DS can be achieved when deferring 50% of the data. Our second contribution demonstrates that a common modelling strategy, where predictions from several short EEG segments are combined to obtain a final prediction, can be improved by filtering out untrustworthy segments with low trust scores. The false detection rate shows a relative decrease between 21% and 43%, and the DS shows a small increase or decrease. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

13 pages, 14512 KiB  
Article
A Hybrid Deep CNN Model for Abnormal Arrhythmia Detection Based on Cardiac ECG Signal
by Amin Ullah, Sadaqat ur Rehman, Shanshan Tu, Raja Majid Mehmood, Fawad and Muhammad Ehatisham-ul-haq
Sensors 2021, 21(3), 951; https://doi.org/10.3390/s21030951 - 01 Feb 2021
Cited by 78 | Viewed by 7135
Abstract
Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal even in the presence of environmental noise. A one-dimensional convolutional [...] Read more.
Electrocardiogram (ECG) signals play a vital role in diagnosing and monitoring patients suffering from various cardiovascular diseases (CVDs). This research aims to develop a robust algorithm that can accurately classify the electrocardiogram signal even in the presence of environmental noise. A one-dimensional convolutional neural network (CNN) with two convolutional layers, two down-sampling layers, and a fully connected layer is proposed in this work. The same 1D data was transformed into two-dimensional (2D) images to improve the model’s classification accuracy. Then, we applied the 2D CNN model consisting of input and output layers, three 2D-convolutional layers, three down-sampling layers, and a fully connected layer. The classification accuracy of 97.38% and 99.02% is achieved with the proposed 1D and 2D model when tested on the publicly available Massachusetts Institute of Technology-Beth Israel Hospital (MIT-BIH) arrhythmia database. Both proposed 1D and 2D CNN models outperformed the corresponding state-of-the-art classification algorithms for the same data, which validates the proposed models’ effectiveness. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

20 pages, 562 KiB  
Article
Remote Patient Monitoring Using Radio Frequency Identification (RFID) Technology and Machine Learning for Early Detection of Suicidal Behaviour in Mental Health Facilities
by Xiaohui Tao, Thanveer Basha Shaik, Niall Higgins, Raj Gururajan and Xujuan Zhou
Sensors 2021, 21(3), 776; https://doi.org/10.3390/s21030776 - 24 Jan 2021
Cited by 19 | Viewed by 5852
Abstract
Remote Patient Monitoring (RPM) has gained great popularity with an aim to measure vital signs and gain patient related information in clinics. RPM can be achieved with noninvasive digital technology without hindering a patient’s daily activities and can enhance the efficiency of healthcare [...] Read more.
Remote Patient Monitoring (RPM) has gained great popularity with an aim to measure vital signs and gain patient related information in clinics. RPM can be achieved with noninvasive digital technology without hindering a patient’s daily activities and can enhance the efficiency of healthcare delivery in acute clinical settings. In this study, an RPM system was built using radio frequency identification (RFID) technology for early detection of suicidal behaviour in a hospital-based mental health facility. A range of machine learning models such as Linear Regression, Decision Tree, Random Forest, and XGBoost were investigated to help determine the optimum fixed positions of RFID reader–antennas in a simulated hospital ward. Empirical experiments showed that Decision Tree had the best performance compared to Random Forest and XGBoost models. An Ensemble Learning model was also developed, took advantage of these machine learning models based on their individual performance. The research set a path to analyse dynamic moving RFID tags and builds an RPM system to help retrieve patient vital signs such as heart rate, pulse rate, respiration rate and subtle motions to make this research state-of-the-art in terms of managing acute suicidal and self-harm behaviour in a mental health ward. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

16 pages, 2421 KiB  
Article
Artificial-Intelligence-Enhanced Mobile System for Cardiovascular Health Management
by Zhaoji Fu, Shenda Hong, Rui Zhang and Shaofu Du
Sensors 2021, 21(3), 773; https://doi.org/10.3390/s21030773 - 24 Jan 2021
Cited by 30 | Viewed by 4213
Abstract
The number of patients with cardiovascular diseases is rapidly increasing in the world. The workload of existing clinicians is consequently increasing. However, the number of cardiovascular clinicians is declining. In this paper, we aim to design a mobile and automatic system to improve [...] Read more.
The number of patients with cardiovascular diseases is rapidly increasing in the world. The workload of existing clinicians is consequently increasing. However, the number of cardiovascular clinicians is declining. In this paper, we aim to design a mobile and automatic system to improve the abilities of patients’ cardiovascular health management while also reducing clinicians’ workload. Our system includes both hardware and cloud software devices based on recent advances in Internet of Things (IoT) and Artificial Intelligence (AI) technologies. A small hardware device was designed to collect high-quality Electrocardiogram (ECG) data from the human body. A novel deep-learning-based cloud service was developed and deployed to achieve automatic and accurate cardiovascular disease detection. Twenty types of diagnostic items including sinus rhythm, tachyarrhythmia, and bradyarrhythmia are supported. Experimental results show the effectiveness of our system. Our hardware device can guarantee high-quality ECG data by removing high-/low-frequency distortion and reverse lead detection with 0.9011 Area Under the Receiver Operating Characteristic Curve (ROC–AUC) score. Our deep-learning-based cloud service supports 20 types of diagnostic items, 17 of them have more than 0.98 ROC–AUC score. For a real world application, the system has been used by around 20,000 users in twenty provinces throughout China. As a consequence, using this service, we could achieve both active and passive health management through a lightweight mobile application on the WeChat Mini Program platform. We believe that it can have a broader impact on cardiovascular health management in the world. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

21 pages, 4888 KiB  
Article
Batch Similarity Based Triplet Loss Assembled into Light-Weighted Convolutional Neural Networks for Medical Image Classification
by Zhiwen Huang, Quan Zhou, Xingxing Zhu and Xuming Zhang
Sensors 2021, 21(3), 764; https://doi.org/10.3390/s21030764 - 24 Jan 2021
Cited by 8 | Viewed by 2830
Abstract
In many medical image classification tasks, there is insufficient image data for deep convolutional neural networks (CNNs) to overcome the over-fitting problem. The light-weighted CNNs are easy to train but they usually have relatively poor classification performance. To improve the classification ability of [...] Read more.
In many medical image classification tasks, there is insufficient image data for deep convolutional neural networks (CNNs) to overcome the over-fitting problem. The light-weighted CNNs are easy to train but they usually have relatively poor classification performance. To improve the classification ability of light-weighted CNN models, we have proposed a novel batch similarity-based triplet loss to guide the CNNs to learn the weights. The proposed loss utilizes the similarity among multiple samples in the input batches to evaluate the distribution of training data. Reducing the proposed loss can increase the similarity among images of the same category and reduce the similarity among images of different categories. Besides this, it can be easily assembled into regular CNNs. To appreciate the performance of the proposed loss, some experiments have been done on chest X-ray images and skin rash images to compare it with several losses based on such popular light-weighted CNN models as EfficientNet, MobileNet, ShuffleNet and PeleeNet. The results demonstrate the applicability and effectiveness of our method in terms of classification accuracy, sensitivity and specificity. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

15 pages, 426 KiB  
Article
Prediction of Postoperative Complications for Patients of End Stage Renal Disease
by Young-Seob Jeong, Juhyun Kim, Dahye Kim, Jiyoung Woo, Mun Gyu Kim, Hun Woo Choi, Ah Reum Kang and Sun Young Park
Sensors 2021, 21(2), 544; https://doi.org/10.3390/s21020544 - 14 Jan 2021
Cited by 12 | Viewed by 2547
Abstract
End stage renal disease (ESRD) is the last stage of chronic kidney disease that requires dialysis or a kidney transplant to survive. Many studies reported a higher risk of mortality in ESRD patients compared with patients without ESRD. In this paper, we develop [...] Read more.
End stage renal disease (ESRD) is the last stage of chronic kidney disease that requires dialysis or a kidney transplant to survive. Many studies reported a higher risk of mortality in ESRD patients compared with patients without ESRD. In this paper, we develop a model to predict postoperative complications, major cardiac event, for patients who underwent any type of surgery. We compare several widely-used machine learning models through experiments with our collected data yellow of size 3220, and achieved F1 score of 0.797 with the random forest model. Based on experimental results, we found that features related to operation (e.g., anesthesia time, operation time, crystal, and colloid) have the biggest impact on model performance, and also found the best combination of features. We believe that this study will allow physicians to provide more appropriate therapy to the ESRD patients by providing information on potential postoperative complications. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

17 pages, 24656 KiB  
Article
Application of Skeleton Data and Long Short-Term Memory in Action Recognition of Children with Autism Spectrum Disorder
by Yunkai Zhang, Yinghong Tian, Pingyi Wu and Dongfan Chen
Sensors 2021, 21(2), 411; https://doi.org/10.3390/s21020411 - 08 Jan 2021
Cited by 17 | Viewed by 3115
Abstract
The recognition of stereotyped action is one of the core diagnostic criteria of Autism Spectrum Disorder (ASD). However, it mainly relies on parent interviews and clinical observations, which lead to a long diagnosis cycle and prevents the ASD children from timely treatment. To [...] Read more.
The recognition of stereotyped action is one of the core diagnostic criteria of Autism Spectrum Disorder (ASD). However, it mainly relies on parent interviews and clinical observations, which lead to a long diagnosis cycle and prevents the ASD children from timely treatment. To speed up the recognition process of stereotyped actions, a method based on skeleton data and Long Short-Term Memory (LSTM) is proposed in this paper. In the first stage of our method, the OpenPose algorithm is used to obtain the initial skeleton data from the video of ASD children. Furthermore, four denoising methods are proposed to eliminate the noise of the initial skeleton data. In the second stage, we track multiple ASD children in the same scene by matching distance between current skeletons and previous skeletons. In the last stage, the neural network based on LSTM is proposed to classify the ASD children’s actions. The performed experiments show that our proposed method is effective for ASD children’s action recognition. Compared to the previous traditional schemes, our scheme has higher accuracy and is almost non-invasive for ASD children. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

23 pages, 728 KiB  
Article
Proposal of the CAD System for Melanoma Detection Using Reconfigurable Computing
by Wysterlânya K. P. Barros, Daniel S. Morais, Felipe F. Lopes, Matheus F. Torquato, Raquel de M. Barbosa and Marcelo A. C. Fernandes
Sensors 2020, 20(11), 3168; https://doi.org/10.3390/s20113168 - 03 Jun 2020
Cited by 11 | Viewed by 2658
Abstract
This work proposes dedicated hardware to real-time cancer detection using Field-Programmable Gate Arrays (FPGA). The presented hardware combines a Multilayer Perceptron (MLP) Artificial Neural Networks (ANN) with Digital Image Processing (DIP) techniques. The DIP techniques are used to extract the features from the [...] Read more.
This work proposes dedicated hardware to real-time cancer detection using Field-Programmable Gate Arrays (FPGA). The presented hardware combines a Multilayer Perceptron (MLP) Artificial Neural Networks (ANN) with Digital Image Processing (DIP) techniques. The DIP techniques are used to extract the features from the analyzed skin, and the MLP classifies the lesion into melanoma or non-melanoma. The classification results are validated with an open-access database. Finally, analysis regarding execution time, hardware resources usage, and power consumption are performed. The results obtained through this analysis are then compared to an equivalent software implementation embedded in an ARM A9 microprocessor. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

20 pages, 3355 KiB  
Article
IGRNet: A Deep Learning Model for Non-Invasive, Real-Time Diagnosis of Prediabetes through Electrocardiograms
by Liyang Wang, Yao Mu, Jing Zhao, Xiaoya Wang and Huilian Che
Sensors 2020, 20(9), 2556; https://doi.org/10.3390/s20092556 - 30 Apr 2020
Cited by 24 | Viewed by 3873
Abstract
The clinical symptoms of prediabetes are mild and easy to overlook, but prediabetes may develop into diabetes if early intervention is not performed. In this study, a deep learning model—referred to as IGRNet—is developed to effectively detect and diagnose prediabetes in a non-invasive, [...] Read more.
The clinical symptoms of prediabetes are mild and easy to overlook, but prediabetes may develop into diabetes if early intervention is not performed. In this study, a deep learning model—referred to as IGRNet—is developed to effectively detect and diagnose prediabetes in a non-invasive, real-time manner using a 12-lead electrocardiogram (ECG) lasting 5 s. After searching for an appropriate activation function, we compared two mainstream deep neural networks (AlexNet and GoogLeNet) and three traditional machine learning algorithms to verify the superiority of our method. The diagnostic accuracy of IGRNet is 0.781, and the area under the receiver operating characteristic curve (AUC) is 0.777 after testing on the independent test set including mixed group. Furthermore, the accuracy and AUC are 0.856 and 0.825, respectively, in the normal-weight-range test set. The experimental results indicate that IGRNet diagnoses prediabetes with high accuracy using ECGs, outperforming existing other machine learning methods; this suggests its potential for application in clinical practice as a non-invasive, prediabetes diagnosis technology. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

21 pages, 1934 KiB  
Article
A Study on the Application of Convolutional Neural Networks to Fall Detection Evaluated with Multiple Public Datasets
by Eduardo Casilari, Raúl Lora-Rivera and Francisco García-Lagos
Sensors 2020, 20(5), 1466; https://doi.org/10.3390/s20051466 - 06 Mar 2020
Cited by 70 | Viewed by 4754
Abstract
Due to the repercussion of falls on both the health and self-sufficiency of older people and on the financial sustainability of healthcare systems, the study of wearable fall detection systems (FDSs) has gained much attention during the last years. The core of a [...] Read more.
Due to the repercussion of falls on both the health and self-sufficiency of older people and on the financial sustainability of healthcare systems, the study of wearable fall detection systems (FDSs) has gained much attention during the last years. The core of a FDS is the algorithm that discriminates falls from conventional Activities of Daily Life (ADLs). This work presents and evaluates a convolutional deep neural network when it is applied to identify fall patterns based on the measurements collected by a transportable tri-axial accelerometer. In contrast with most works in the related literature, the evaluation is performed against a wide set of public data repositories containing the traces obtained from diverse groups of volunteers during the execution of ADLs and mimicked falls. Although the method can yield very good results when it is hyper-parameterized for a certain dataset, the global evaluation with the other repositories highlights the difficulty of extrapolating to other testbeds the network architecture that was configured and optimized for a particular dataset. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

Review

Jump to: Research, Other

50 pages, 1074 KiB  
Review
Comprehensive Review of Vision-Based Fall Detection Systems
by Jesús Gutiérrez, Víctor Rodríguez and Sergio Martin
Sensors 2021, 21(3), 947; https://doi.org/10.3390/s21030947 - 01 Feb 2021
Cited by 66 | Viewed by 7902
Abstract
Vision-based fall detection systems have experienced fast development over the last years. To determine the course of its evolution and help new researchers, the main audience of this paper, a comprehensive revision of all published articles in the main scientific databases regarding this [...] Read more.
Vision-based fall detection systems have experienced fast development over the last years. To determine the course of its evolution and help new researchers, the main audience of this paper, a comprehensive revision of all published articles in the main scientific databases regarding this area during the last five years has been made. After a selection process, detailed in the Materials and Methods Section, eighty-one systems were thoroughly reviewed. Their characterization and classification techniques were analyzed and categorized. Their performance data were also studied, and comparisons were made to determine which classifying methods best work in this field. The evolution of artificial vision technology, very positively influenced by the incorporation of artificial neural networks, has allowed fall characterization to become more resistant to noise resultant from illumination phenomena or occlusion. The classification has also taken advantage of these networks, and the field starts using robots to make these systems mobile. However, datasets used to train them lack real-world data, raising doubts about their performances facing real elderly falls. In addition, there is no evidence of strong connections between the elderly and the communities of researchers. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

Other

Jump to: Research, Review

14 pages, 4698 KiB  
Case Report
A Knowledge-Based Algorithm for Automatic Monitoring of Orthodontic Treatment: The Dental Monitoring System. Two Cases
by Silvia Caruso, Sara Caruso, Marianna Pellegrino, Rayan Skafi, Alessandro Nota and Simona Tecco
Sensors 2021, 21(5), 1856; https://doi.org/10.3390/s21051856 - 07 Mar 2021
Cited by 29 | Viewed by 7454
Abstract
Background: In the dental field, digital technology has created new opportunities for orthodontists to integrate their clinical practice, and for patients to collect information about orthodontics and their treatment, which is called “teledentistry.” Dental monitoring (DM) is a recently introduced orthodontic application that [...] Read more.
Background: In the dental field, digital technology has created new opportunities for orthodontists to integrate their clinical practice, and for patients to collect information about orthodontics and their treatment, which is called “teledentistry.” Dental monitoring (DM) is a recently introduced orthodontic application that combines safe teledentistry with artificial intelligence (AI) using a knowledge-based algorithm, allowing an accurate semi-automatic monitoring of the treatment. Dental Monitoring is the world’s first SaaS (Software as a Service) application designed for remote monitoring of dental treatment, developed in Paris, France, with Philippe Salah as the Co-founder and CEO. Cases presentation: This report describes two cases in which DM system was essential to achieve the control of certain movements: it was possible to follow the movement, even if complex, such as the anterior cross of an adult patient and a lack of space in the canine of the growing patient. The software analyzed the fit and retention of the aligner, thus ensuring correct biomechanics. They were treated during the COVID-19 pandemic lockdown with aligners. The first case is a growing patient who was monitored during an interceptive orthodontic treatment to manage a retained upper canine. The second case is an adult patient forced to finalize his treatment of upper lateral incisor crossbite. The software analyzed the fit and retention of the aligner, thus ensuring correct biomechanics. Conclusions: DM system appears to be a promising method, useful for improving the interaction between doctor and patient, generally acceptable and useful to patients, even in critical clinical situations, at least in cases with optimal compliance and ability to use the tool properly. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

16 pages, 1868 KiB  
Letter
TumorGAN: A Multi-Modal Data Augmentation Framework for Brain Tumor Segmentation
by Qingyun Li, Zhibin Yu, Yubo Wang and Haiyong Zheng
Sensors 2020, 20(15), 4203; https://doi.org/10.3390/s20154203 - 28 Jul 2020
Cited by 50 | Viewed by 4629
Abstract
The high human labor demand involved in collecting paired medical imaging data severely impedes the application of deep learning methods to medical image processing tasks such as tumor segmentation. The situation is further worsened when collecting multi-modal image pairs. However, this issue can [...] Read more.
The high human labor demand involved in collecting paired medical imaging data severely impedes the application of deep learning methods to medical image processing tasks such as tumor segmentation. The situation is further worsened when collecting multi-modal image pairs. However, this issue can be resolved through the help of generative adversarial networks, which can be used to generate realistic images. In this work, we propose a novel framework, named TumorGAN, to generate image segmentation pairs based on unpaired adversarial training. To improve the quality of the generated images, we introduce a regional perceptual loss to enhance the performance of the discriminator. We also develop a regional L1 loss to constrain the color of the imaged brain tissue. Finally, we verify the performance of TumorGAN on a public brain tumor data set, BraTS 2017. The experimental results demonstrate that the synthetic data pairs generated by our proposed method can practically improve tumor segmentation performance when applied to segmentation network training. Full article
(This article belongs to the Special Issue Healthcare Monitoring and Management with Artificial Intelligence)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-16
Back to TopTop