Machine Learning and Biomedical Sensors

Journal Name	Impact Factor	CiteScore	Launched Year	First Decision (median)	APC
Bioengineering bioengineering	3.8	4.0	2014	15.6 Days	CHF 2700
Healthcare healthcare	2.4	3.5	2013	20.5 Days	CHF 2700
Journal of Clinical Medicine jcm	3.0	5.7	2012	17.3 Days	CHF 2600
Journal of Sensor and Actuator Networks jsan	3.3	7.9	2012	22.6 Days	CHF 2000
Sensors sensors	3.4	7.3	2001	16.8 Days	CHF 2600
Applied Sciences applsci	2.5	5.3	2011	17.8 Days	CHF 2400
Biosensors biosensors	4.9	6.6	2011	17.1 Days	CHF 2700
Inventions inventions	2.1	4.8	2016	21.2 Days	CHF 1800

13 pages, 4163 KiB

Open AccessCommunication

Microwave Flow Cytometric Detection and Differentiation of Escherichia coli

by Neelima Dahal, Caroline Peak, Carl Ehrett, Jeffrey Osterberg, Min Cao, Ralu Divan and Pingshan Wang

Sensors 2024, 24(9), 2870; https://doi.org/10.3390/s24092870 - 30 Apr 2024

Viewed by 1068

Abstract

Label-free measurement and analysis of single bacterial cells are essential for food safety monitoring and microbial disease diagnosis. We report a microwave flow cytometric sensor with a microstrip sensing device with reduced channel height for bacterial cell measurement. Escherichia coli B and Escherichia [...] Read more.

Label-free measurement and analysis of single bacterial cells are essential for food safety monitoring and microbial disease diagnosis. We report a microwave flow cytometric sensor with a microstrip sensing device with reduced channel height for bacterial cell measurement. Escherichia coli B and Escherichia coli K-12 were measured with the sensor at frequencies between 500 MHz and 8 GHz. The results show microwave properties of E. coli cells are frequency-dependent. A LightGBM model was developed to classify cell types at a high accuracy of 0.96 at 1 GHz. Thus, the sensor provides a promising label-free method to rapidly detect and differentiate bacterial cells. Nevertheless, the method needs to be further developed by comprehensively measuring different types of cells and demonstrating accurate cell classification with improved machine-learning techniques. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

10 pages, 3453 KiB

Open AccessCommunication

Ballistocardial Signal-Based Personal Identification Using Deep Learning for the Non-Invasive and Non-Restrictive Monitoring of Vital Signs

by Karin Takahashi and Hitoshi Ueno

Sensors 2024, 24(8), 2527; https://doi.org/10.3390/s24082527 - 15 Apr 2024

Viewed by 1048

Abstract

Owing to accelerated societal aging, the prevalence of elderly individuals experiencing solitary or sudden death at home has increased. Therefore, herein, we aimed to develop a monitoring system that utilizes piezoelectric sensors for the non-invasive and non-restrictive monitoring of vital signs, including the [...] Read more.

Owing to accelerated societal aging, the prevalence of elderly individuals experiencing solitary or sudden death at home has increased. Therefore, herein, we aimed to develop a monitoring system that utilizes piezoelectric sensors for the non-invasive and non-restrictive monitoring of vital signs, including the heart rate and respiration, to detect changes in the health status of several elderly individuals. A ballistocardiogram with a piezoelectric sensor was tested using seven individuals. The frequency spectra of the biosignals acquired from the piezoelectric sensors exhibited multiple peaks corresponding to the harmonics originating from the heartbeat. We aimed for individual identification based on the shapes of these peaks as the recognition criteria. The results of individual identification using deep learning techniques revealed good identification proficiency. Altogether, the monitoring system integrated with piezoelectric sensors showed good potential as a personal identification system for identifying individuals with abnormal biological signals. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

17 pages, 774 KiB

Open AccessReview

The Revolution in Breast Cancer Diagnostics: From Visual Inspection of Histopathology Slides to Using Desktop Tissue Analysers for Automated Nanomechanical Profiling of Tumours

by Martin Stolz

Bioengineering 2024, 11(3), 237; https://doi.org/10.3390/bioengineering11030237 - 28 Feb 2024

Viewed by 2091

Abstract

We aim to develop new portable desktop tissue analysers (DTAs) to provide fast, low-cost, and precise test results for fast nanomechanical profiling of tumours. This paper will explain the reasoning for choosing indentation-type atomic force microscopy (IT-AFM) to reveal the functional details of [...] Read more.

We aim to develop new portable desktop tissue analysers (DTAs) to provide fast, low-cost, and precise test results for fast nanomechanical profiling of tumours. This paper will explain the reasoning for choosing indentation-type atomic force microscopy (IT-AFM) to reveal the functional details of cancer. Determining the subtype, cancer stage, and prognosis will be possible, which aids in choosing the best treatment. DTAs are based on fast IT-AFM at the size of a small box that can be made for a low budget compared to other clinical imaging tools. The DTAs can work in remote areas and all parts of the world. There are a number of direct benefits: First, it is no longer needed to wait a week for the pathology report as the test will only take 10 min. Second, it avoids the complicated steps of making histopathology slides and saves costs of labour. Third, computers and robots are more consistent, more reliable, and more economical than human workers which may result in fewer diagnostic errors. Fourth, the IT-AFM analysis is capable of distinguishing between various cancer subtypes. Fifth, the IT-AFM analysis could reveal new insights about why immunotherapy fails. Sixth, IT-AFM may provide new insights into the neoadjuvant treatment response. Seventh, the healthcare system saves money by reducing diagnostic backlogs. Eighth, the results are stored on a central server and can be accessed to develop strategies to prevent cancer. To bring the IT-AFM technology from the bench to the operation theatre, a fast IT-AFM sensor needs to be developed and integrated into the DTAs. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

17 pages, 4108 KiB

Open AccessArticle

EMD-Based Noninvasive Blood Glucose Estimation from PPG Signals Using Machine Learning Algorithms

by Shama Satter, Mrinmoy Sarker Turja, Tae-Ho Kwon and Ki-Doo Kim

Appl. Sci. 2024, 14(4), 1406; https://doi.org/10.3390/app14041406 - 8 Feb 2024

Cited by 2 | Viewed by 4951

Abstract

Effective management of diabetes requires accurate monitoring of blood glucose levels. Traditional invasive methods for such monitoring can be cumbersome and uncomfortable for patients. In this study, we introduce a noninvasive approach to estimate blood glucose levels using photoplethysmography (PPG) signals. We have [...] Read more.

Effective management of diabetes requires accurate monitoring of blood glucose levels. Traditional invasive methods for such monitoring can be cumbersome and uncomfortable for patients. In this study, we introduce a noninvasive approach to estimate blood glucose levels using photoplethysmography (PPG) signals. We have focused on blood glucose prediction using wrist PPG signals and explored various PPG waveform-based features, including AC to DC ratio (AC/DC) and intrinsic mode function (IMF)-based features derived from empirical mode decomposition (EMD). To the best of our knowledge, no studies have been found using EMD-based features to estimate blood glucose levels noninvasively. Additionally, feature importance-based selection has also been used to further improve the accuracy of the proposed model. Among the four machine learning algorithms considered in this study, CatBoost consistently outperformed XGBoost, LightGBM, and random forest across a wide number of features. The best performing model, CatBoost, achieved Pearson’s r of 0.96, MSE 0.08,

R^{2}

score 0.92, and MAE 8.01 when considering the top 50 features selected from both PPG waveform-based features and IMF-based features. The p-values for all models were <0.001, indicating statistically significant correlations. Overall, this study provides valuable insights into the feasibility and effectiveness of noninvasive blood glucose monitoring using advanced machine learning techniques. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

13 pages, 5825 KiB

Open AccessArticle

Detection of Sialic Acid to Differentiate Cervical Cancer Cell Lines Using a Sambucus nigra Lectin Biosensor

by Ricardo Zamudio Cañas, María Eugenia Jaramillo Flores, Verónica Vallejo Ruiz, Raúl Jacobo Delgado Macuil and Valentín López Gayou

Biosensors 2024, 14(1), 34; https://doi.org/10.3390/bios14010034 - 10 Jan 2024

Cited by 2 | Viewed by 2446

Abstract

Pap smear screening is a widespread technique used to detect premalignant lesions of cervical cancer (CC); however, it lacks sensitivity, leading to identifying biomarkers that improve early diagnosis sensitivity. A characteristic of cancer is the aberrant sialylation that involves the abnormal expression of [...] Read more.

Pap smear screening is a widespread technique used to detect premalignant lesions of cervical cancer (CC); however, it lacks sensitivity, leading to identifying biomarkers that improve early diagnosis sensitivity. A characteristic of cancer is the aberrant sialylation that involves the abnormal expression of α2,6 sialic acid, a specific carbohydrate linked to glycoproteins and glycolipids on the cell surface, which has been reported in premalignant CC lesions. This work aimed to develop a method to differentiate CC cell lines and primary fibroblasts using a novel lectin-based biosensor to detect α2,6 sialic acid based on attenuated total reflectance Fourier transform infrared spectroscopy (ATR-FTIR) and chemometric. The biosensor was developed by conjugating gold nanoparticles (AuNPs) with 5 µg of Sambucus nigra (SNA) lectin as the biorecognition element. Sialic acid detection was associated with the signal amplification in the 1500–1350 cm⁻¹ region observed by the surface-enhanced infrared absorption spectroscopy (SEIRA) effect from ATR-FTIR results. This region was further analyzed for the clustering of samples by applying principal component analysis (PCA) and confidence ellipses at a 95% interval. This work demonstrates the feasibility of employing SNA biosensors to discriminate between tumoral and non-tumoral cells, that have the potential for the early detection of premalignant lesions of CC. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Graphical abstract

28 pages, 9182 KiB

Open AccessArticle

Dual-Stream Spatiotemporal Networks with Feature Sharing for Monitoring Animals in the Home Cage

by Ezechukwu Israel Nwokedi, Rasneer Sonia Bains, Luc Bidaut, Xujiong Ye, Sara Wells and James M. Brown

Sensors 2023, 23(23), 9532; https://doi.org/10.3390/s23239532 - 30 Nov 2023

Cited by 2 | Viewed by 1350

Abstract

This paper presents a spatiotemporal deep learning approach for mouse behavioral classification in the home-cage. Using a series of dual-stream architectures with assorted modifications for optimal performance, we introduce a novel feature sharing approach that jointly processes the streams at regular intervals throughout [...] Read more.

This paper presents a spatiotemporal deep learning approach for mouse behavioral classification in the home-cage. Using a series of dual-stream architectures with assorted modifications for optimal performance, we introduce a novel feature sharing approach that jointly processes the streams at regular intervals throughout the network. The dataset in focus is an annotated, publicly available dataset of a singly-housed mouse. We achieved even better classification accuracy by ensembling the best performing models; an Inception-based network and an attention-based network, both of which utilize this feature sharing attribute. Furthermore, we demonstrate through ablation studies that for all models, the feature sharing architectures consistently outperform the conventional dual-stream having standalone streams. In particular, the inception-based architectures showed higher feature sharing gains with their increase in accuracy anywhere between 6.59% and 15.19%. The best-performing models were also further evaluated on other mouse behavioral datasets. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

17 pages, 1945 KiB

Open AccessArticle

A Novel Convolutional Neural Network Deep Learning Implementation for Cuffless Heart Rate and Blood Pressure Estimation

by Géraud Bossavi, Rongguo Yan and Muhammad Irfan

Appl. Sci. 2023, 13(22), 12403; https://doi.org/10.3390/app132212403 - 16 Nov 2023

Cited by 1 | Viewed by 2135

Abstract

Cardiovascular diseases (CVDs) affect components of the circulatory system responsible for transporting blood through blood vessels. The measurement of the mechanical force acting on the walls of blood vessels, as well as the blood flow between heartbeats and when the heart is at [...] Read more.

Cardiovascular diseases (CVDs) affect components of the circulatory system responsible for transporting blood through blood vessels. The measurement of the mechanical force acting on the walls of blood vessels, as well as the blood flow between heartbeats and when the heart is at rest, is known as blood pressure (BP). Regular assessment of BP can aid in the prevention and early detection of CVDs. In the present research, a deep learning algorithm was developed to accurately calculate both blood pressure (BP) and heart rate (HR) by extracting relevant features from photoplethysmogram (PPG), electrocardiogram (ECG), and ABP signals. This algorithm was implemented using the Medical Information Mart for Intensive Care (MIMIC-II) dataset. It captures vital blood pressure-related features extracted from the PPG signal and accounts for the time relationship with the ECG. The algorithm also determines the values of systolic blood pressure (SBP) and diastolic blood pressure (DBP) based on the ABP waveform through a convolutional neural network and stepwise multivariate linear regression. In comparison with other established BP measurement methods, our proposed approach achieved better results, with a mean absolute error (MAE) of approximately 4.7 mmHg for SBP and 2.1 mmHg for DBP, respectively. The standard deviation (STD) for SBP and DBP was approximately 7.6 mmHg and 3.9 mmHg, respectively. This study makes a valuable contribution to the healthcare field by introducing a novel, cost-effective continuous BP measurement method with improved accuracy while also minimizing the data dimension without losing any important information. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

27 pages, 2578 KiB

Open AccessReview

A Comprehensive Review of Computer-Aided Models for Breast Cancer Diagnosis Using Histopathology Images

by Alberto Labrada and Buket D. Barkana

Bioengineering 2023, 10(11), 1289; https://doi.org/10.3390/bioengineering10111289 - 7 Nov 2023

Cited by 3 | Viewed by 2273

Abstract

Breast cancer is the second most common cancer in women who are mainly middle-aged and older. The American Cancer Society reported that the average risk of developing breast cancer sometime in their life is about 13%, and this incident rate has increased by [...] Read more.

Breast cancer is the second most common cancer in women who are mainly middle-aged and older. The American Cancer Society reported that the average risk of developing breast cancer sometime in their life is about 13%, and this incident rate has increased by 0.5% per year in recent years. A biopsy is done when screening tests and imaging results show suspicious breast changes. Advancements in computer-aided system capabilities and performance have fueled research using histopathology images in cancer diagnosis. Advances in machine learning and deep neural networks have tremendously increased the number of studies developing computerized detection and classification models. The dataset-dependent nature and trial-and-error approach of the deep networks’ performance produced varying results in the literature. This work comprehensively reviews the studies published between 2010 and 2022 regarding commonly used public-domain datasets and methodologies used in preprocessing, segmentation, feature engineering, machine-learning approaches, classifiers, and performance metrics. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

26 pages, 8465 KiB

Open AccessArticle

PhysioKit: An Open-Source, Low-Cost Physiological Computing Toolkit for Single- and Multi-User Studies

by Jitesh Joshi, Katherine Wang and Youngjun Cho

Sensors 2023, 23(19), 8244; https://doi.org/10.3390/s23198244 - 4 Oct 2023

Cited by 3 | Viewed by 2998

Abstract

The proliferation of physiological sensors opens new opportunities to explore interactions, conduct experiments and evaluate the user experience with continuous monitoring of bodily functions. Commercial devices, however, can be costly or limit access to raw waveform data, while low-cost sensors are efforts-intensive to [...] Read more.

The proliferation of physiological sensors opens new opportunities to explore interactions, conduct experiments and evaluate the user experience with continuous monitoring of bodily functions. Commercial devices, however, can be costly or limit access to raw waveform data, while low-cost sensors are efforts-intensive to setup. To address these challenges, we introduce PhysioKit, an open-source, low-cost physiological computing toolkit. PhysioKit provides a one-stop pipeline consisting of (i) a sensing and data acquisition layer that can be configured in a modular manner per research needs, and (ii) a software application layer that enables data acquisition, real-time visualization and machine learning (ML)-enabled signal quality assessment. This also supports basic visual biofeedback configurations and synchronized acquisition for co-located or remote multi-user settings. In a validation study with 16 participants, PhysioKit shows strong agreement with research-grade sensors on measuring heart rate and heart rate variability metrics data. Furthermore, we report usability survey results from 10 small-project teams (44 individual members in total) who used PhysioKit for 4–6 weeks, providing insights into its use cases and research benefits. Lastly, we discuss the extensibility and potential impact of the toolkit on the research community. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

16 pages, 3365 KiB

Open AccessArticle

Microbial Colony Detection Based on Deep Learning

by Fan Yang, Yongjie Zhong, Hui Yang, Yi Wan, Zhuhua Hu and Shengsen Peng

Appl. Sci. 2023, 13(19), 10568; https://doi.org/10.3390/app131910568 - 22 Sep 2023

Cited by 1 | Viewed by 2485

Abstract

In clinical drug sensitivity experiments, it is necessary to plate culture pathogenic bacteria and pick suitable colonies for bacterial solution preparation, which is a process that is currently carried out completely by hand. Moreover, the problems of plate contamination, a long culture period, [...] Read more.

In clinical drug sensitivity experiments, it is necessary to plate culture pathogenic bacteria and pick suitable colonies for bacterial solution preparation, which is a process that is currently carried out completely by hand. Moreover, the problems of plate contamination, a long culture period, and large image annotation in colony plate image acquisition can lead to a small amount of usable data. To address the issues mentioned above, we adopt a deep learning approach and conduct experiments on the AGAR dataset. We propose to use style transfer to extend the trainable dataset and successfully obtain 4k microbial colony images using this method. In addition, we introduce the Swin Transformer as a feature extraction network in the Cascade Mask R-CNN model architecture to better extract the feature information of the images. After our experimental comparison, the model achieves a mean Average Precision (mAP) of 61.4% at the Intersection over Union (IoU) [0.50:0.95]. This performance surpasses that of the Cascade R-CNN with HRNet, which is the top-performing model in experiments conducted on the AGAR dataset, by a margin of 2.2%. Furthermore, we perform experiments using YOLOv8x on the AGAR dataset, which results in a mAP of 76.7%. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

23 pages, 4420 KiB

Open AccessArticle

Repeated Transcranial Photobiomodulation with Light-Emitting Diodes Improves Psychomotor Vigilance and EEG Networks of the Human Brain

by Akhil Chaudhari, Xinlong Wang, Anqi Wu and Hanli Liu

Bioengineering 2023, 10(9), 1043; https://doi.org/10.3390/bioengineering10091043 - 5 Sep 2023

Cited by 3 | Viewed by 2323

Abstract

Transcranial photobiomodulation (tPBM) has been suggested as a non-invasive neuromodulation tool. The repetitive administration of light-emitting diode (LED)-based tPBM for several weeks significantly improves human cognition. To understand the electrophysiological effects of LED-tPBM on the human brain, we investigated alterations by repeated tPBM [...] Read more.

Transcranial photobiomodulation (tPBM) has been suggested as a non-invasive neuromodulation tool. The repetitive administration of light-emitting diode (LED)-based tPBM for several weeks significantly improves human cognition. To understand the electrophysiological effects of LED-tPBM on the human brain, we investigated alterations by repeated tPBM in vigilance performance and brain networks using electroencephalography (EEG) in healthy participants. Active and sham LED-based tPBM were administered to the right forehead of young participants twice a week for four weeks. The participants performed a psychomotor vigilance task (PVT) during each tPBM/sham experiment. A 64-electrode EEG system recorded electrophysiological signals from each participant during the first and last visits in a 4-week study. Topographical maps of the EEG power enhanced by tPBM were statistically compared for the repeated tPBM effect. A new data processing framework combining the group’s singular value decomposition (gSVD) with eLORETA was implemented to identify EEG brain networks. The reaction time of the PVT in the tPBM-treated group was significantly improved over four weeks compared to that in the sham group. We observed acute increases in EEG delta and alpha powers during a 10 min LED-tPBM while the participants performed the PVT task. We also found that the theta, beta, and gamma EEG powers significantly increased overall after four weeks of LED-tPBM. Combining gSVD with eLORETA enabled us to identify EEG brain networks and the corresponding network power changes by repeated 4-week tPBM. This study clearly demonstrated that a 4-week prefrontal LED-tPBM can neuromodulate several key EEG networks, implying a possible causal effect between modulated brain networks and improved psychomotor vigilance outcomes. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

11 pages, 1740 KiB

Open AccessArticle

Machine Learning Techniques for Effective Pathogen Detection Based on Resonant Biosensors

by Guoguang Rong, Yankun Xu and Mohamad Sawan

Biosensors 2023, 13(9), 860; https://doi.org/10.3390/bios13090860 - 31 Aug 2023

Cited by 3 | Viewed by 2765

Abstract

We describe a machine learning (ML) approach to processing the signals collected from a COVID-19 optical-based detector. Multilayer perceptron (MLP) and support vector machine (SVM) were used to process both the raw data and the feature engineering data, and high performance for the [...] Read more.

We describe a machine learning (ML) approach to processing the signals collected from a COVID-19 optical-based detector. Multilayer perceptron (MLP) and support vector machine (SVM) were used to process both the raw data and the feature engineering data, and high performance for the qualitative detection of the SARS-CoV-2 virus with concentration down to 1 TCID₅₀/mL was achieved. Valid detection experiments contained 486 negative and 108 positive samples, and control experiments, in which biosensors without antibody functionalization were used to detect SARS-CoV-2, contained 36 negative samples and 732 positive samples. The data distribution patterns of the valid and control detection dataset, based on T-distributed stochastic neighbor embedding (t-SNE), were used to study the distinguishability between positive and negative samples and explain the ML prediction performance. This work demonstrates that ML can be a generalized effective approach to process the signals and the datasets of biosensors dependent on resonant modes as biosensing mechanism. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

16 pages, 3049 KiB

Open AccessArticle

Development of a New Wearable Device for the Characterization of Hand Tremor

by Basilio Vescio, Marida De Maria, Marianna Crasà, Rita Nisticò, Camilla Calomino, Federica Aracri, Aldo Quattrone and Andrea Quattrone

Bioengineering 2023, 10(9), 1025; https://doi.org/10.3390/bioengineering10091025 - 30 Aug 2023

Cited by 4 | Viewed by 2048

Abstract

Rest tremor (RT) is observed in subjects with Parkinson’s disease (PD) and Essential Tremor (ET). Electromyography (EMG) studies have shown that PD subjects exhibit alternating contractions of antagonistic muscles involved in tremors, while the contraction pattern of antagonistic muscles is synchronous in ET [...] Read more.

Rest tremor (RT) is observed in subjects with Parkinson’s disease (PD) and Essential Tremor (ET). Electromyography (EMG) studies have shown that PD subjects exhibit alternating contractions of antagonistic muscles involved in tremors, while the contraction pattern of antagonistic muscles is synchronous in ET subjects. Therefore, the RT pattern can be used as a potential biomarker for differentiating PD from ET subjects. In this study, we developed a new wearable device and method for differentiating alternating from a synchronous RT pattern using inertial data. The novelty of our approach relies on the fact that the evaluation of synchronous or alternating tremor patterns using inertial sensors has never been described so far, and current approaches to evaluate the tremor patterns are based on surface EMG, which may be difficult to carry out for non-specialized operators. This new device, named “RT-Ring”, is based on a six-axis inertial measurement unit and a Bluetooth Low-Energy microprocessor, and can be worn on a finger of the tremulous hand. A mobile app guides the operator through the whole acquisition process of inertial data from the hand with RT, and the prediction of tremor patterns is performed on a remote server through machine learning (ML) models. We used two decision tree-based algorithms, XGBoost and Random Forest, which were trained on features extracted from inertial data and achieved a classification accuracy of 92% and 89%, respectively, in differentiating alternating from synchronous tremor segments in the validation set. Finally, the classification response (alternating or synchronous RT pattern) is shown to the operator on the mobile app within a few seconds. This study is the first to demonstrate that different electromyographic tremor patterns have their counterparts in terms of rhythmic movement features, thus making inertial data suitable for predicting the muscular contraction pattern of tremors. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

13 pages, 4331 KiB

Open AccessArticle

Lung Tumor Image Segmentation from Computer Tomography Images Using MobileNetV2 and Transfer Learning

by Zainab Riaz, Bangul Khan, Saad Abdullah, Samiullah Khan and Md Shohidul Islam

Bioengineering 2023, 10(8), 981; https://doi.org/10.3390/bioengineering10080981 - 20 Aug 2023

Cited by 17 | Viewed by 3483

Abstract

Background: Lung cancer is one of the most fatal cancers worldwide, and malignant tumors are characterized by the growth of abnormal cells in the tissues of lungs. Usually, symptoms of lung cancer do not appear until it is already at an advanced stage. [...] Read more.

Background: Lung cancer is one of the most fatal cancers worldwide, and malignant tumors are characterized by the growth of abnormal cells in the tissues of lungs. Usually, symptoms of lung cancer do not appear until it is already at an advanced stage. The proper segmentation of cancerous lesions in CT images is the primary method of detection towards achieving a completely automated diagnostic system. Method: In this work, we developed an improved hybrid neural network via the fusion of two architectures, MobileNetV2 and UNET, for the semantic segmentation of malignant lung tumors from CT images. The transfer learning technique was employed and the pre-trained MobileNetV2 was utilized as an encoder of a conventional UNET model for feature extraction. The proposed network is an efficient segmentation approach that performs lightweight filtering to reduce computation and pointwise convolution for building more features. Skip connections were established with the Relu activation function for improving model convergence to connect the encoder layers of MobileNetv2 to decoder layers in UNET that allow the concatenation of feature maps with different resolutions from the encoder to decoder. Furthermore, the model was trained and fine-tuned on the training dataset acquired from the Medical Segmentation Decathlon (MSD) 2018 Challenge. Results: The proposed network was tested and evaluated on 25% of the dataset obtained from the MSD, and it achieved a dice score of 0.8793, recall of 0.8602 and precision of 0.93. It is pertinent to mention that our technique outperforms the current available networks, which have several phases of training and testing. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

19 pages, 3047 KiB

Open AccessArticle

WSCNet: Biomedical Image Recognition for Cell Encapsulated Microfluidic Droplets

by Xiao Zhou, Yuanhang Mao, Miao Gu and Zhen Cheng

Biosensors 2023, 13(8), 821; https://doi.org/10.3390/bios13080821 - 15 Aug 2023

Cited by 2 | Viewed by 1540

Abstract

Microfluidic droplets accommodating a single cell as independent microreactors are frequently demanded for single-cell analysis of phenotype and genotype. However, challenges exist in identifying and reducing the covalence probability (following Poisson’s distribution) of more than two cells encapsulated in one droplet. It is [...] Read more.

Microfluidic droplets accommodating a single cell as independent microreactors are frequently demanded for single-cell analysis of phenotype and genotype. However, challenges exist in identifying and reducing the covalence probability (following Poisson’s distribution) of more than two cells encapsulated in one droplet. It is of great significance to monitor and control the quantity of encapsulated content inside each droplet. We demonstrated a microfluidic system embedded with a weakly supervised cell counting network (WSCNet) to generate microfluidic droplets, evaluate their quality, and further recognize the locations of encapsulated cells. Here, we systematically verified our approach using encapsulated droplets from three different microfluidic structures. Quantitative experimental results showed that our approach can not only distinguish droplet encapsulations (F1 score > 0.88) but also locate each cell without any supervised location information (accuracy > 89%). The probability of a “single cell in one droplet” encapsulation is systematically verified under different parameters, which shows good agreement with the distribution of the passive method (Residual Sum of Squares, RSS < 0.5). This study offers a comprehensive platform for the quantitative assessment of encapsulated microfluidic droplets. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

20 pages, 6087 KiB

Open AccessReview

Application of Intelligent Medical Sensing Technology

by Jie Fu, Qiya Gao and Shuang Li

Biosensors 2023, 13(8), 812; https://doi.org/10.3390/bios13080812 - 13 Aug 2023

Cited by 7 | Viewed by 3161

Abstract

With the popularization of intelligent sensing and the improvement of modern medical technology, intelligent medical sensing technology has emerged as the times require. This technology combines basic disciplines such as physics, mathematics, and materials with modern technologies such as semiconductors, integrated circuits, and [...] Read more.

With the popularization of intelligent sensing and the improvement of modern medical technology, intelligent medical sensing technology has emerged as the times require. This technology combines basic disciplines such as physics, mathematics, and materials with modern technologies such as semiconductors, integrated circuits, and artificial intelligence, and has become one of the most promising in the medical field. The core of intelligent medical sensor technology is to make existing medical sensors intelligent, portable, and wearable with full consideration of ergonomics and sensor power consumption issues in order to conform to the current trends in cloud medicine, personalized medicine, and health monitoring. With the development of automation and intelligence in measurement and control systems, it is required that sensors have high accuracy, reliability, and stability, as well as certain data processing capabilities, self-checking, self-calibration, and self-compensation, while traditional medical sensors cannot meet such requirements. In addition, to manufacture high-performance sensors, it is also difficult to improve the material process alone, and it is necessary to combine computer technology with sensor technology to make up for its performance shortcomings. Intelligent medical sensing technology combines medical sensors with microprocessors to produce powerful intelligent medical sensors. Based on the original sensor functions, intelligent medical sensors also have functions such as self-compensation, self-calibration, self-diagnosis, numerical processing, two-way communication, information storage, and digital output. This review focuses on the application of intelligent medical sensing technology in biomedical sensing detection from three aspects: physical sensor, chemical sensor, and biosensor. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

15 pages, 28339 KiB

Open AccessArticle

Efficient Lung Ultrasound Classification

by Antonio Bruno, Giacomo Ignesti, Ovidio Salvetti, Davide Moroni and Massimo Martinelli

Bioengineering 2023, 10(5), 555; https://doi.org/10.3390/bioengineering10050555 - 5 May 2023

Cited by 3 | Viewed by 2409

Abstract

A machine learning method for classifying lung ultrasound is proposed here to provide a point of care tool for supporting a safe, fast, and accurate diagnosis that can also be useful during a pandemic such as SARS-CoV-2. Given the advantages (e.g., safety, speed, [...] Read more.

A machine learning method for classifying lung ultrasound is proposed here to provide a point of care tool for supporting a safe, fast, and accurate diagnosis that can also be useful during a pandemic such as SARS-CoV-2. Given the advantages (e.g., safety, speed, portability, cost-effectiveness) provided by the ultrasound technology over other examinations (e.g., X-ray, computer tomography, magnetic resonance imaging), our method was validated on the largest public lung ultrasound dataset. Focusing on both accuracy and efficiency, our solution is based on an efficient adaptive ensembling of two EfficientNet-b0 models reaching 100% of accuracy, which, to our knowledge, outperforms the previous state-of-the-art models by at least 5%. The complexity is restrained by adopting specific design choices: ensembling with an adaptive combination layer, ensembling performed on the deep features, and minimal ensemble using two weak models only. In this way, the number of parameters has the same order of magnitude of a single EfficientNet-b0 and the computational cost (FLOPs) is reduced at least by 20%, doubled by parallelization. Moreover, a visual analysis of the saliency maps on sample images of all the classes of the dataset reveals where an inaccurate weak model focuses its attention versus an accurate one. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

16 pages, 1666 KiB

Open AccessArticle

Semantic Segmentation of Medical Images Based on Runge–Kutta Methods

by Mai Zhu, Chong Fu and Xingwei Wang

Bioengineering 2023, 10(5), 506; https://doi.org/10.3390/bioengineering10050506 - 23 Apr 2023

Cited by 2 | Viewed by 1517

Abstract

In recent years, deep learning has achieved good results in the semantic segmentation of medical images. A typical architecture for segmentation networks is an encoder–decoder structure. However, the design of the segmentation networks is fragmented and lacks a mathematical explanation. Consequently, segmentation networks [...] Read more.

In recent years, deep learning has achieved good results in the semantic segmentation of medical images. A typical architecture for segmentation networks is an encoder–decoder structure. However, the design of the segmentation networks is fragmented and lacks a mathematical explanation. Consequently, segmentation networks are inefficient and less generalizable across different organs. To solve these problems, we reconstructed the segmentation network based on mathematical methods. We introduced the dynamical systems view into semantic segmentation and proposed a novel segmentation network based on Runge–Kutta methods, referred to hereafter as the Runge–Kutta segmentation network (RKSeg). RKSegs were evaluated on ten organ image datasets from the Medical Segmentation Decathlon. The experimental results show that RKSegs far outperform other segmentation networks. RKSegs use few parameters and short inference time, yet they can achieve competitive or even better segmentation results compared to other models. RKSegs pioneer a new architectural design pattern for segmentation networks. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

19 pages, 3252 KiB

Open AccessArticle

Comparison of Machine Learning Models for Brain Age Prediction Using Six Imaging Modalities on Middle-Aged and Older Adults

by Min Xiong, Lan Lin, Yue Jin, Wenjie Kang, Shuicai Wu and Shen Sun

Sensors 2023, 23(7), 3622; https://doi.org/10.3390/s23073622 - 30 Mar 2023

Cited by 14 | Viewed by 3924

Abstract

Machine learning (ML) has transformed neuroimaging research by enabling accurate predictions and feature extraction from large datasets. In this study, we investigate the application of six ML algorithms (Lasso, relevance vector regression, support vector regression, extreme gradient boosting, category boost, and multilayer perceptron) [...] Read more.

Machine learning (ML) has transformed neuroimaging research by enabling accurate predictions and feature extraction from large datasets. In this study, we investigate the application of six ML algorithms (Lasso, relevance vector regression, support vector regression, extreme gradient boosting, category boost, and multilayer perceptron) to predict brain age for middle-aged and older adults, which is a crucial area of research in neuroimaging. Despite the plethora of proposed ML models, there is no clear consensus on how to achieve better performance in brain age prediction for this population. Our study stands out by evaluating the impact of both ML algorithms and image modalities on brain age prediction performance using a large cohort of cognitively normal adults aged 44.6 to 82.3 years old (N = 27,842) with six image modalities. We found that the predictive performance of brain age is more reliant on the image modalities used than the ML algorithms employed. Specifically, our study highlights the superior performance of T1-weighted MRI and diffusion-weighted imaging and demonstrates that multi-modality-based brain age prediction significantly enhances performance compared to unimodality. Moreover, we identified Lasso as the most accurate ML algorithm for predicting brain age, achieving the lowest mean absolute error in both single-modality and multi-modality predictions. Additionally, Lasso also ranked highest in a comprehensive evaluation of the relationship between BrainAGE and the five frequently mentioned BrainAGE-related factors. Notably, our study also shows that ensemble learning outperforms Lasso when computational efficiency is not a concern. Overall, our study provides valuable insights into the development of accurate and reliable brain age prediction models for middle-aged and older adults, with significant implications for clinical practice and neuroimaging research. Our findings highlight the importance of image modality selection and emphasize Lasso as a promising ML algorithm for brain age prediction. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

13 pages, 5166 KiB

Open AccessArticle

Sensitivity Improvement of an Optical Fiber Sensor Based on Surface Plasmon Resonance with Pure Higher-Order Modes

by Chuanhao Yang, Bing Yan, Qi Wang, Jing Zhao, Hongxia Zhang, Hui Yu, Haojun Fan and Dagong Jia

Appl. Sci. 2023, 13(6), 4020; https://doi.org/10.3390/app13064020 - 22 Mar 2023

Cited by 6 | Viewed by 2074

Abstract

In this paper, we propose an approach to improve the sensitivity of an optical fiber surface plasmon resonance (SPR) sensor with a pure higher-order mode excited by a designed mode selective coupler (MSC). We calculate the proportion of the power of the higher-order [...] Read more.

In this paper, we propose an approach to improve the sensitivity of an optical fiber surface plasmon resonance (SPR) sensor with a pure higher-order mode excited by a designed mode selective coupler (MSC). We calculate the proportion of the power of the higher-order mode in the cladding. Compared to the

{LP}_{01}

mode, the power proportion of the

{LP}_{11}

mode (

{LP}_{21}

mode) in the cladding theoretically improves by 100% (150%). To generate a relatively pure

{LP}_{11}

mode or

{LP}_{21}

mode, a mode selective coupler (MSC, 430–580 nm) is designed. The coupling efficiency of the

{LP}_{01} - {LP}_{11}

mode coupler is over 80%, and that of the

{LP}_{01} - {LP}_{21}

mode coupler is over 50%. The simulation results show that the sensitivity of the

{LP}_{11}

mode and the

{LP}_{21}

mode increases by approximately 330% and 360%, respectively, using the intensity modulation (n = 1.33–1.38, 430–580 nm); the resolution of the refractive indices of our sensor, using the

{LP}_{11}

mode (

{LP}_{21}

mode), is

2.6 \times 10^{- 4}

RIU (

2.4 \times 10^{- 4}

RIU). The higher sensitivity and resolution of our presented fiber SPR sensor containing a visible MSC make it a promising candidate for the measurement of refractive indices. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

18 pages, 3686 KiB

Open AccessArticle

Photoplethysmography Driven Hypertension Identification: A Pilot Study

by Liangwen Yan, Mingsen Wei, Sijung Hu and Bo Sheng

Sensors 2023, 23(6), 3359; https://doi.org/10.3390/s23063359 - 22 Mar 2023

Cited by 4 | Viewed by 2080

Abstract

To prevent and diagnose hypertension early, there has been a growing demand to identify its states that align with patients. This pilot study aims to research how a non-invasive method using photoplethysmographic (PPG) signals works together with deep learning algorithms. A portable PPG [...] Read more.

To prevent and diagnose hypertension early, there has been a growing demand to identify its states that align with patients. This pilot study aims to research how a non-invasive method using photoplethysmographic (PPG) signals works together with deep learning algorithms. A portable PPG acquisition device (Max30101 photonic sensor) was utilized to (1) capture PPG signals and (2) wirelessly transmit data sets. In contrast to traditional feature engineering machine learning classification schemes, this study preprocessed raw data and applied a deep learning algorithm (LSTM-Attention) directly to extract deeper correlations between these raw datasets. The Long Short-Term Memory (LSTM) model underlying a gate mechanism and memory unit enables it to handle long sequence data more effectively, avoiding gradient disappearance and possessing the ability to solve long-term dependencies. To enhance the correlation between distant sampling points, an attention mechanism was introduced to capture more data change features than a separate LSTM model. A protocol with 15 healthy volunteers and 15 hypertension patients was implemented to obtain these datasets. The processed result demonstrates that the proposed model could present satisfactory performance (accuracy: 0.991; precision: 0.989; recall: 0.993; F1-score: 0.991). The model we proposed also demonstrated superior performance compared to related studies. The outcome indicates the proposed method could effectively diagnose and identify hypertension; thus, a paradigm to cost-effectively screen hypertension could rapidly be established using wearable smart devices. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

13 pages, 1628 KiB

Open AccessArticle

EMG-Based Estimation of Lower Limb Joint Angles and Moments Using Long Short-Term Memory Network

by Minh Tat Nhat Truong, Amged Elsheikh Abdelgadir Ali, Dai Owaki and Mitsuhiro Hayashibe

Sensors 2023, 23(6), 3331; https://doi.org/10.3390/s23063331 - 22 Mar 2023

Cited by 12 | Viewed by 3899

Abstract

One of the fundamental limitations in human biomechanics is that we cannot directly obtain joint moments during natural movements without affecting the motion. However, estimating these values is feasible with inverse dynamics computation by employing external force plates, which can cover only a [...] Read more.

One of the fundamental limitations in human biomechanics is that we cannot directly obtain joint moments during natural movements without affecting the motion. However, estimating these values is feasible with inverse dynamics computation by employing external force plates, which can cover only a small area of the plate. This work investigated the Long Short-Term Memory (LSTM) network for the kinetics and kinematics prediction of human lower limbs when performing different activities without using force plates after the learning. We measured surface electromyography (sEMG) signals from 14 lower extremities muscles to generate a 112-dimensional input vector from three sets of features: root mean square, mean absolute value, and sixth-order autoregressive model coefficient parameters for each muscle in the LSTM network. With the recorded experimental data from the motion capture system and the force plates, human motions were reconstructed in a biomechanical simulation created using OpenSim v4.1, from which the joint kinematics and kinetics from left and right knees and ankles were retrieved to serve as output for training the LSTM. The estimation results using the LSTM model deviated from labels with average R² scores (knee angle: 97.25%, knee moment: 94.9%, ankle angle: 91.44%, and ankle moment: 85.44%). These results demonstrate the feasibility of the joint angle and moment estimation based solely on sEMG signals for multiple daily activities without requiring force plates and a motion capture system once the LSTM model is trained. Full article

(This article belongs to the Topic Machine Learning and Biomedical Sensors)

► Show Figures

Figure 1

10 pages, 1955 KiB

Open AccessCommunication

MindReader: Unsupervised Classification of Electroencephalographic Data

by Salvador Daniel Rivas-Carrillo, Evgeny E. Akkuratov, Hector Valdez Ruvalcaba, Angel Vargas-Sanchez, Jan Komorowski, Daniel San-Juan and Manfred G. Grabherr

Sensors 2023, 23(6), 2971; https://doi.org/10.3390/s23062971 - 9 Mar 2023

Viewed by 2356

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

17 pages, 3511 KiB

Open AccessArticle

Automatic Segmentation of Cervical Cells Based on Star-Convex Polygons in Pap Smear Images

by Yanli Zhao, Chong Fu, Wenchao Zhang, Chen Ye, Zhixiao Wang and Hong-feng Ma

Bioengineering 2023, 10(1), 47; https://doi.org/10.3390/bioengineering10010047 - 30 Dec 2022

Cited by 8 | Viewed by 3022

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

11 pages, 1765 KiB

Open AccessArticle

Feasibility of Brachial Occlusion Technique for Beat-to-Beat Pulse Wave Analysis

by Lukas Matera, Pavol Sajgalik, Vratislav Fabian, Yegor Mikhailov, David Zemanek and Bruce D. Johnson

Sensors 2022, 22(19), 7285; https://doi.org/10.3390/s22197285 - 26 Sep 2022

Viewed by 1710

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 (

\bar{r}

= 0.60, p < 0.001). The averaged Pearson’s correlation coefficient for the comparative analysis of OCCI between methods was

\bar{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

Topic Menu

Topic Editors

Machine Learning and Biomedical Sensors

Topic Information

Keywords

Participating Journals

Published Papers (25 papers)

Further Information

Guidelines

MDPI Initiatives

Follow MDPI