Pub Date : 2024-06-18DOI: 10.1016/j.irbm.2024.100842
Vipin Prakash Yadav , Kamlesh Kumar Sharma
Introduction
Neonatal seizure is a common neurologic disorder in neonates. The diagnosis of a neonatal seizure can be made clinically or with an EEG. However, the clinical diagnosis of neonatal seizures is difficult, particularly in critically ill infants, because of the multitude of epileptic and nonepileptic clinical manifestations. On the other hand neonatal seizure can be effectively detected using EEG recordings. Hence, there is a need for an electroencephalograph (EEG) based automatic diagnosis framework for neonatal seizure.
Methods
This work proposed a wavelet scattering transform (WST) and histogram-based nearest component analysis (HBNCA) based framework for classifying seizures and non-seizure neonate's EEG signals. The WST converts EEG signals into its translation invariant and deformation stable representation. The HBNCA method is deployed to find the effective wavelet scattering coefficients (WSC) for classifying seizures and non-seizures EEG signals. Then, various classifiers are used to identify the effectiveness of the features.
Results
The proposed framework is managed to get an average accuracy of 98.59% and 97.83% for a 1-second duration of EEG signal for repeated random subsampling validation (RRSV) and leave one out cross-validation (LOOCV), respectively.
Conclusions
The results are compared with the other state of art methods. The accurate classification from the 1-second duration of the EEG signal shows the potential of the proposed framework for reliable neonatal seizure classification.
{"title":"Automatic Classification Framework for Neonatal Seizure Using Wavelet Scattering Transform and Nearest Component Analysis","authors":"Vipin Prakash Yadav , Kamlesh Kumar Sharma","doi":"10.1016/j.irbm.2024.100842","DOIUrl":"https://doi.org/10.1016/j.irbm.2024.100842","url":null,"abstract":"<div><h3>Introduction</h3><p>Neonatal seizure is a common neurologic disorder in neonates. The diagnosis of a neonatal seizure can be made clinically or with an EEG. However, the clinical diagnosis of neonatal seizures is difficult, particularly in critically ill infants, because of the multitude of epileptic and nonepileptic clinical manifestations. On the other hand neonatal seizure can be effectively detected using EEG recordings. Hence, there is a need for an electroencephalograph (EEG) based automatic diagnosis framework for neonatal seizure.</p></div><div><h3>Methods</h3><p>This work proposed a wavelet scattering transform (WST) and histogram-based nearest component analysis (HBNCA) based framework for classifying seizures and non-seizure neonate's EEG signals. The WST converts EEG signals into its translation invariant and deformation stable representation. The HBNCA method is deployed to find the effective wavelet scattering coefficients (WSC) for classifying seizures and non-seizures EEG signals. Then, various classifiers are used to identify the effectiveness of the features.</p></div><div><h3>Results</h3><p>The proposed framework is managed to get an average accuracy of 98.59% and 97.83% for a 1-second duration of EEG signal for repeated random subsampling validation (RRSV) and leave one out cross-validation (LOOCV), respectively.</p></div><div><h3>Conclusions</h3><p>The results are compared with the other state of art methods. The accurate classification from the 1-second duration of the EEG signal shows the potential of the proposed framework for reliable neonatal seizure classification.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":5.6,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141480568","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-18DOI: 10.1016/j.irbm.2024.100843
Kamil Bader El Dine , Noujoud Nader , Mohamad Khalil , Catherine Marque
1) Introduction: Preterm labor (PL) has globally become the leading cause of death in children under the age of 5 years. One of the most significant keys to preventing preterm labor is its early detection. 2) Objectives: The primary objectives of this study are to address the problem of PL by providing a new approach by analyzing the electrohysterographic (EHG) signals, which are recorded on the mother's abdomen during labor and pregnancy. 3) Methods: The EHG signal reflects the electrical activity that induces the mechanical contraction of the myometrium. Because EHGs are known to be non-stationary signals, and because we anticipate connectivity to alter during contraction (due to electrical diffusion and the mechanotransduction process), we applied the windowing approach on real signals to identify the best windows and the best nodes with the most significant data to be used for classification. The suggested pipeline includes: i) dividing the 16 EHG signals that are recorded from the abdomen of pregnant women in N windows; ii) apply the connectivity matrices on each window; iii) apply the Graph theory-based measures on the connectivity matrices on each window; iv) apply the consensus Matrix on each window in order to retrieve the best windows and the best nodes. Following that, several neural network and machine learning methods are applied to the best windows and best nodes to categorize pregnancy and labor contractions, based on the different input parameters (connectivity method alone, connectivity method plus graph parameters, best nodes, all nodes, best windows, all windows). 4) Results: Results showed that the best nodes are nodes 8, 9, 10, 11, and 12; while the best windows are 2, 4, and 5. The classification results obtained by using only these best nodes are better than when using the whole nodes. The results are always better when using the full burst, whatever the chosen nodes. 5) Conclusion: The windowing approach proved to be an innovative technique that can improve the differentiation between labor and pregnancy EHG signals.
{"title":"Optimizing Uterine Synchronization Analysis in Pregnancy and Labor Through Window Selection and Node Optimization","authors":"Kamil Bader El Dine , Noujoud Nader , Mohamad Khalil , Catherine Marque","doi":"10.1016/j.irbm.2024.100843","DOIUrl":"https://doi.org/10.1016/j.irbm.2024.100843","url":null,"abstract":"<div><p>1) Introduction: Preterm labor (PL) has globally become the leading cause of death in children under the age of 5 years. One of the most significant keys to preventing preterm labor is its early detection. 2) Objectives: The primary objectives of this study are to address the problem of PL by providing a new approach by analyzing the electrohysterographic (EHG) signals, which are recorded on the mother's abdomen during labor and pregnancy. 3) Methods: The EHG signal reflects the electrical activity that induces the mechanical contraction of the myometrium. Because EHGs are known to be non-stationary signals, and because we anticipate connectivity to alter during contraction (due to electrical diffusion and the mechanotransduction process), we applied the windowing approach on real signals to identify the best windows and the best nodes with the most significant data to be used for classification. The suggested pipeline includes: i) dividing the 16 EHG signals that are recorded from the abdomen of pregnant women in N windows; ii) apply the connectivity matrices on each window; iii) apply the Graph theory-based measures on the connectivity matrices on each window; iv) apply the consensus Matrix on each window in order to retrieve the best windows and the best nodes. Following that, several neural network and machine learning methods are applied to the best windows and best nodes to categorize pregnancy and labor contractions, based on the different input parameters (connectivity method alone, connectivity method plus graph parameters, best nodes, all nodes, best windows, all windows). 4) Results: Results showed that the best nodes are nodes 8, 9, 10, 11, and 12; while the best windows are 2, 4, and 5. The classification results obtained by using only these best nodes are better than when using the whole nodes. The results are always better when using the full burst, whatever the chosen nodes. 5) Conclusion: The windowing approach proved to be an innovative technique that can improve the differentiation between labor and pregnancy EHG signals.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":5.6,"publicationDate":"2024-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141483512","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-06DOI: 10.1016/j.irbm.2024.100838
Background
The global prevalence of autism spectrum disorder (ASD) is around 1%. Yet the current diagnosis of ASD mainly depends on clinicians' experience and caregivers' report, which are subjective, time consuming, and labor demanding. An objective and efficient way to diagnose ASD is urgently needed. The objective of this study was to quantify an omnipresent yet least studied behavioral characteristic in children with ASD – interpersonal motor coordination (IMC), and to investigate the feasibility of using IMC related features to identify ASD by implementing machine learning algorithms.
Methods
Twenty children with ASD and twenty-three children with typical development (TD) were filmed in a conversation with an interviewer. Motion energy analysis was implemented to obtain the movement time series, and cross wavelet analysis (CWA) quantified the level of IMC at different movement frequencies. Machine learning algorithms were utilized to examine whether these two groups of children could be accurately classified using features of IMC.
Results
Statistical analysis revealed reduced IMC in the ASD group at relatively high movement frequencies. The establishment of machine learning (ML) models showed that the maximum classification accuracy was 85.37% (specificity = 95.24%, sensitivity = 75.00%) using five original coherence values computed with CWA. In addition, the classification accuracy could be improved to 92.68% (specificity = 95.24%, sensitivity = 90.00%) with three novel features created by taking the sum of statistically significant features.
Conclusions
Children with ASD demonstrated an atypical profile of IMC, and IMC could be used to objectively classify children with ASD and TD. In addition, our analyses showed that creating novel features based on statistically significant features could help improve classification performance. It is proposed that such economic, contactless, and calibration-free approach to data collection might well serve both ASD research and practice, particularly early objective identification. However, this study could be improved with respect to larger sample size with balanced gender ratio and different severity.
{"title":"Interpersonal Motor Coordination in Children with Autism and the Establishment of Machine Learning Models to Objectively Classify Children with Autism and Typical Development","authors":"","doi":"10.1016/j.irbm.2024.100838","DOIUrl":"10.1016/j.irbm.2024.100838","url":null,"abstract":"<div><h3>Background</h3><p>The global prevalence of autism spectrum disorder (ASD) is around 1%. Yet the current diagnosis of ASD mainly depends on clinicians' experience and caregivers' report, which are subjective, time consuming, and labor demanding. An objective and efficient way to diagnose ASD is urgently needed. The objective of this study was to quantify an omnipresent yet least studied behavioral characteristic in children with ASD – interpersonal motor coordination (IMC), and to investigate the feasibility of using IMC related features to identify ASD by implementing machine learning algorithms.</p></div><div><h3>Methods</h3><p>Twenty children with ASD and twenty-three children with typical development (TD) were filmed in a conversation with an interviewer. Motion energy analysis was implemented to obtain the movement time series, and cross wavelet analysis (CWA) quantified the level of IMC at different movement frequencies. Machine learning algorithms were utilized to examine whether these two groups of children could be accurately classified using features of IMC.</p></div><div><h3>Results</h3><p>Statistical analysis revealed reduced IMC in the ASD group at relatively high movement frequencies. The establishment of machine learning (ML) models showed that the maximum classification accuracy was 85.37% (specificity = 95.24%, sensitivity = 75.00%) using five original coherence values computed with CWA. In addition, the classification accuracy could be improved to 92.68% (specificity = 95.24%, sensitivity = 90.00%) with three novel features created by taking the sum of statistically significant features.</p></div><div><h3>Conclusions</h3><p>Children with ASD demonstrated an atypical profile of IMC, and IMC could be used to objectively classify children with ASD and TD. In addition, our analyses showed that creating novel features based on statistically significant features could help improve classification performance. It is proposed that such economic, contactless, and calibration-free approach to data collection might well serve both ASD research and practice, particularly early objective identification. However, this study could be improved with respect to larger sample size with balanced gender ratio and different severity.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":5.6,"publicationDate":"2024-06-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141395742","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.1016/j.irbm.2024.100837
Alba Diaz-Martinez , Gema Prats-Boluda , Rogelio Monfort-Ortiz , Javier Garcia-Casado , Alba Roca-Prats , Enrique Tormo-Crespo , Félix Nieto-del-Amor , Vicente-José Diago-Almela , Yiyao Ye-Lin
Background for the research
Premature birth and its associated complications are one of the biggest global health problems, since there is currently no effective screening method in clinical practice to accurately identify the true Preterm Birth (PTB) from the false threatened ones. Despite the high prevalence of PTB in multiple gestation (MG) women which amounted up to 60%, in the literature there is any work about their uterine myoelectric activities in vivo system. Electrohysterography (EHG) has been emerged as an alternative technique for predicting PTB in single gestation (SG) women.
Purpose
The aim of this study was to characterize and compare the uterine myoelectrical activity in vivo system of SG and MG women in regular check-ups, to provide the basis for early detection and prevention of preterm labour in MG.
Basic procedures
A prospective observational cohort study was conducted on 31 SG and 18 MG women between the 28th and 32th WoG who underwent regular check-ups in the Polytechnic and University Hospital La Fe (Valencia, Spain). The 30-minute bipolar recording was filtered in the 0.1-4 Hz bandwidth and downsampled to 20 Hz. Signal analysis was performed in 120-second moving windows with 50% overlap, after removing artefacts by a double- blind expert process. A set of 8 temporal, spectral and non-linear parameters were calculated: root mean square (RMS), kurtosis of the Hilbert envelope (KHE), median frequency (MDF), H/L ratio, and sample entropy (SampEn) and bubble entropy (BubbEn) calculated in the whole bandwidth (WBW) and the fast wave high (FWH). The 10th, 50th and 90th percentiles of all windows analysed were calculated to obtain representative values of the recordings. For each parameter and percentile, statistically significant differences between the SG and MG groups and their statistical power (SP) were analysed to determine both the existence of an effect and substantive significance, respectively.
Main findings
In comparison to SG, MG EHG exhibited significant higher impulsiveness and higher predictability than SG which was reflected in the KHE (SP10 = 85.2, p10 < 0.001) and entropy measures (SampEn FWH: SP50 = 62.0, p50 = 0.0.016; SP90 = 52.5, p90 = 0.059. BubbEn FWH: SP50 = 75.2, p50 < 0.001; SP90 = 60.3, p90 = 0.002), suggesting an accelerated evolution of uterine electrophysiological condition. In addition, several EHG parameters were found to significantly correlate with foetal weight such as amplitude (RMS: r90 = 0.311, p90 = 0.006), signal impulsiveness (KHE: r10 = 0.311, p10 = 0.006) and entropy measures (SampEn FWH: r50 = −0.317, p50 = 0.005*; r90 = −0.279, p90 = 0.013*. BubbEn FWH: r50 = −0.3
{"title":"Overdistention Accelerates Electrophysiological Changes in Uterine Muscle Towards Labour in Multiple Gestations","authors":"Alba Diaz-Martinez , Gema Prats-Boluda , Rogelio Monfort-Ortiz , Javier Garcia-Casado , Alba Roca-Prats , Enrique Tormo-Crespo , Félix Nieto-del-Amor , Vicente-José Diago-Almela , Yiyao Ye-Lin","doi":"10.1016/j.irbm.2024.100837","DOIUrl":"10.1016/j.irbm.2024.100837","url":null,"abstract":"<div><h3>Background for the research</h3><p>Premature birth and its associated complications are one of the biggest global health problems, since there is currently no effective screening method in clinical practice to accurately identify the true Preterm Birth (PTB) from the false threatened ones. Despite the high prevalence of PTB in multiple gestation (MG) women which amounted up to 60%, in the literature there is any work about their uterine myoelectric activities in vivo system. Electrohysterography (EHG) has been emerged as an alternative technique for predicting PTB in single gestation (SG) women.</p></div><div><h3>Purpose</h3><p>The aim of this study was to characterize and compare the uterine myoelectrical activity in vivo system of SG and MG women in regular check-ups, to provide the basis for early detection and prevention of preterm labour in MG.</p></div><div><h3>Basic procedures</h3><p>A prospective observational cohort study was conducted on 31 SG and 18 MG women between the 28<sup>th</sup> and 32<sup>th</sup> WoG who underwent regular check-ups in the Polytechnic and University Hospital La Fe (Valencia, Spain). The 30-minute bipolar recording was filtered in the 0.1-4 Hz bandwidth and downsampled to 20 Hz. Signal analysis was performed in 120-second moving windows with 50% overlap, after removing artefacts by a double- blind expert process. A set of 8 temporal, spectral and non-linear parameters were calculated: root mean square (RMS), kurtosis of the Hilbert envelope (KHE), median frequency (MDF), H/L ratio, and sample entropy (SampEn) and bubble entropy (BubbEn) calculated in the whole bandwidth (WBW) and the fast wave high (FWH). The 10th, 50th and 90th percentiles of all windows analysed were calculated to obtain representative values of the recordings. For each parameter and percentile, statistically significant differences between the SG and MG groups and their statistical power (SP) were analysed to determine both the existence of an effect and substantive significance, respectively.</p></div><div><h3>Main findings</h3><p>In comparison to SG, MG EHG exhibited significant higher impulsiveness and higher predictability than SG which was reflected in the KHE (SP<sub>10</sub> = 85.2, p<sub>10</sub> < 0.001) and entropy measures (SampEn FWH: SP<sub>50</sub> = 62.0, p<sub>50</sub> = 0.0.016; SP<sub>90</sub> = 52.5, p<sub>90</sub> = 0.059. BubbEn FWH: SP<sub>50</sub> = 75.2, p<sub>50</sub> < 0.001; SP<sub>90</sub> = 60.3, p<sub>90</sub> = 0.002), suggesting an accelerated evolution of uterine electrophysiological condition. In addition, several EHG parameters were found to significantly correlate with foetal weight such as amplitude (RMS: r<sub>90</sub> = 0.311, p<sub>90</sub> = 0.006), signal impulsiveness (KHE: r<sub>10</sub> = 0.311, p<sub>10</sub> = 0.006) and entropy measures (SampEn FWH: r<sub>50</sub> = −0.317, p<sub>50</sub> = 0.005*; r<sub>90</sub> = −0.279, p<sub>90</sub> = 0.013*. BubbEn FWH: r<sub>50</sub> = −0.3","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1959031824000186/pdfft?md5=255e8c281ae55cb57d5e7fff904cfa61&pid=1-s2.0-S1959031824000186-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141252897","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.1016/j.irbm.2024.100839
Sali El Dimassi , Julien Gautier , Vincent Zalc , Sofiane Boudaoud , Dan Istrate
BioImpedance Analysis (BIA) is a safe, simple, and noninvasive technology to measure body composition. By measuring the electrical impedance of biological tissues, BIA provides valuable biological insights such as body composition, hydration status, and some health conditions. The principle is to apply an electric current to body segments, which water content and conductivity are characteristics, and to determine the electric impedance depending on body tissues passed through. However, these measurements are indirectly related to body composition and intensively depend on limited and imprecise assumptions to estimate mathematical models. This is the source of methodological and experimental challenges. BIA is very promising to offer non-invasive and portable solutions to assess health status and well-being, but challenges must be considered: they impact technological limitations, methodological standardization, and data interpretation. Advancements in BIA require to address these hurdles to improve accuracy, reliability, and applicability in diverse settings. In this article, we reviewed in depth these challenges based on a systematic review of literature.
Purpose
The objective of this systematic review is to identify key challenges of BIA to assess body composition to develop possible directions for improving this technology. Our review underlines clearly the need to reduce these challenges with the multiplication of biostatistical sources, the definition of personalized models, and the adjustment of mathematical assumptions, to improve BIA reliability and adoption in e-health or specific applications.
Methodology
The objective of this systematic review from published literature was to answer the question: “How to assess whole body composition in the average human adult with BIA, what are the scientific challenges and limits for a wider adoption in medical practice?”. We limited our research within Pubmed, ScienceDirect and IEEE complementary databases. Our research was carried out in English using the keywords “body composition” and “bioimpedance analysis” over a period from the included 1995 to 2022. We controlled inclusion criteria to collect only articles with average human adults' groups: age from 18 years, both males and females, mixed ethnics, BMI ranging from 18 to 30 kg/m2, either healthy or non-healthy status. We added the following exclusion criteria: athletics, malnourished, eating or mental disorders, pregnancy and menstrual period. Finally, we kept articles validated versus state-of-the-art methods DEXA, or isotope dilution.
Summary findings
Our literature review identified seven major challenges with BIA: Rheological modeling precision represent human body as an electrical circuit made of resistors and capacitors to reflect electrical properties of tissues; Body compartments to model human body as a combination of cylind
{"title":"Body Water Volume Estimation Using Bio Impedance Analysis: Where Are We?","authors":"Sali El Dimassi , Julien Gautier , Vincent Zalc , Sofiane Boudaoud , Dan Istrate","doi":"10.1016/j.irbm.2024.100839","DOIUrl":"https://doi.org/10.1016/j.irbm.2024.100839","url":null,"abstract":"<div><p>BioImpedance Analysis (BIA) is a safe, simple, and noninvasive technology to measure body composition. By measuring the electrical impedance of biological tissues, BIA provides valuable biological insights such as body composition, hydration status, and some health conditions. The principle is to apply an electric current to body segments, which water content and conductivity are characteristics, and to determine the electric impedance depending on body tissues passed through. However, these measurements are indirectly related to body composition and intensively depend on limited and imprecise assumptions to estimate mathematical models. This is the source of methodological and experimental challenges. BIA is very promising to offer non-invasive and portable solutions to assess health status and well-being, but challenges must be considered: they impact technological limitations, methodological standardization, and data interpretation. Advancements in BIA require to address these hurdles to improve accuracy, reliability, and applicability in diverse settings. In this article, we reviewed in depth these challenges based on a systematic review of literature.</p></div><div><h3>Purpose</h3><p>The objective of this systematic review is to identify key challenges of BIA to assess body composition to develop possible directions for improving this technology. Our review underlines clearly the need to reduce these challenges with the multiplication of biostatistical sources, the definition of personalized models, and the adjustment of mathematical assumptions, to improve BIA reliability and adoption in e-health or specific applications.</p></div><div><h3>Methodology</h3><p>The objective of this systematic review from published literature was to answer the question: “How to assess whole body composition in the average human adult with BIA, what are the scientific challenges and limits for a wider adoption in medical practice?”. We limited our research within Pubmed, ScienceDirect and IEEE complementary databases. Our research was carried out in English using the keywords “body composition” and “bioimpedance analysis” over a period from the included 1995 to 2022. We controlled inclusion criteria to collect only articles with average human adults' groups: age from 18 years, both males and females, mixed ethnics, BMI ranging from 18 to 30 kg/m<sup>2</sup>, either healthy or non-healthy status. We added the following exclusion criteria: athletics, malnourished, eating or mental disorders, pregnancy and menstrual period. Finally, we kept articles validated versus state-of-the-art methods DEXA, or isotope dilution.</p></div><div><h3>Summary findings</h3><p>Our literature review identified seven major challenges with BIA: <em>Rheological modeling precision</em> represent human body as an electrical circuit made of resistors and capacitors to reflect electrical properties of tissues; <em>Body compartments</em> to model human body as a combination of cylind","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1959031824000204/pdfft?md5=689c5b6bf3f72fc512af9e5cf8afe9bb&pid=1-s2.0-S1959031824000204-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141264234","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.1016/j.irbm.2024.100840
Chengyi Qian, Yuanjun Wang
Objective: Alzheimer's disease (AD) is an irreversible neurodegenerative disease, while mild cognitive impairment (MCI) is a clinical precursor of AD, thus differentiation of AD, MCI and normal control (NC) from noninvasive magnetic resonance imaging (MRI) has positive clinical implications. Material and method: We utilize a 3D residual network to classify AD, MCI, and NC, and add a multiscale module to the original network to enhance the feature representation capability of the network, as well as a cross-dimensional attentional mechanism to enhance the network's attention to important brain regions. We experimentally verified that the network is more inclined to overestimate the brain age of patients in AD and MCI subgroups, thus proving that there is a high correlation between the brain age prediction task and the AD classification task. Therefore, we adopted a multi-task learning approach, using brain age prediction as a supplementary task for AD classification to reduce the risk of overfitting of the network during the training process. Results: Our method achieved 96.02% accuracy, 93.40% precision, 91.48% recall, and 92.24% F1 value in AD/MCI/NC classification. Conclusions: Ablation experiments confirmed that our proposed cross-dimensional attention and multiscale modules can improve the diagnostic performance of AD and MCI, and that multi-task learning in conjunction with brain age prediction can further improve the performance.
目的：阿尔茨海默病（AD）是一种不可逆的神经退行性疾病，而轻度认知障碍（MCI）是 AD 的临床前兆，因此通过无创磁共振成像（MRI）区分 AD、MCI 和正常对照（NC）具有积极的临床意义。材料与方法我们利用三维残差网络对AD、MCI和NC进行分类，并在原有网络的基础上增加了一个多尺度模块，以增强网络的特征表示能力，同时增加了一个跨维注意机制，以增强网络对重要脑区的注意。我们通过实验验证了该网络更倾向于高估AD和MCI亚组患者的脑年龄，从而证明了脑年龄预测任务与AD分类任务之间存在高度相关性。因此，我们采用了多任务学习方法，将脑年龄预测作为 AD 分类的辅助任务，以降低训练过程中网络过拟合的风险。结果我们的方法在AD/MCI/NC分类中取得了96.02%的准确率、93.40%的精确率、91.48%的召回率和92.24%的F1值。结论消融实验证实，我们提出的跨维注意力和多尺度模块可以提高对AD和MCI的诊断性能，多任务学习与脑年龄预测相结合可以进一步提高诊断性能。
{"title":"MMANet: A multi-task residual network for Alzheimer's disease classification and brain age prediction","authors":"Chengyi Qian, Yuanjun Wang","doi":"10.1016/j.irbm.2024.100840","DOIUrl":"10.1016/j.irbm.2024.100840","url":null,"abstract":"<div><p>Objective: Alzheimer's disease (AD) is an irreversible neurodegenerative disease, while mild cognitive impairment (MCI) is a clinical precursor of AD, thus differentiation of AD, MCI and normal control (NC) from noninvasive magnetic resonance imaging (MRI) has positive clinical implications. Material and method: We utilize a 3D residual network to classify AD, MCI, and NC, and add a multiscale module to the original network to enhance the feature representation capability of the network, as well as a cross-dimensional attentional mechanism to enhance the network's attention to important brain regions. We experimentally verified that the network is more inclined to overestimate the brain age of patients in AD and MCI subgroups, thus proving that there is a high correlation between the brain age prediction task and the AD classification task. Therefore, we adopted a multi-task learning approach, using brain age prediction as a supplementary task for AD classification to reduce the risk of overfitting of the network during the training process. Results: Our method achieved 96.02% accuracy, 93.40% precision, 91.48% recall, and 92.24% F1 value in AD/MCI/NC classification. Conclusions: Ablation experiments confirmed that our proposed cross-dimensional attention and multiscale modules can improve the diagnostic performance of AD and MCI, and that multi-task learning in conjunction with brain age prediction can further improve the performance.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141252681","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-06-01DOI: 10.1016/j.irbm.2024.100841
Ying Li , Xudong Liang , Haibing Chen , Jiang Xie , Zhuo Bi
Objective
Unstable plaques can cause acute cardiovascular and cerebrovascular diseases. The stability and instability of plaque are related to the plaque echo status in ultrasound. Carotid videos provide detailed plaque information compared to static images. Ultrasound-based plaque echo classification is challenging due to noise, interference frames, small targets (plaques), and complex shape changes.
Methods
This study proposes a Multi-dimensional Aggregation Network (MA-Net) guided by key features for plaque diagnosis based on carotid ultrasound video, which uses only video-level labels. MA-Net consists of Key-Feature (KF) and Temporal-Channel-Spatial (TCS) modules. The KF module learns the contribution of each frame to the classification at the feature level, adaptively infers the importance score of each frame, thereby reducing the influence of interference frames. The TCS module includes the Temporal-Channel (TC) and Temporal-Spatial (TS) sub-modules. In addition to studying the temporal dimension, it delves into the relationship between the channel and spatial dimensions. TC analyses the temporal dependencies among the channels and filters noise. Moreover, TS extracts features more accurately through the spatio-temporal information contained in the surrounding environment of the plaque.
Results
The performance of MA-Net on the SHU-Ultrasound-Video-2020 dataset is better than that of the state-of-the-art models of video classification, showing at least a 5% increase in accuracy, with an accuracy rate of 87.36%.
Conclusion
The outstanding diagnostic capability of the proposed model will help provide a more robust and reproducible diagnostic process with a lower labour cost for clinical carotid plaque diagnosis.
{"title":"A Multi-Dimensional Aggregation Network Guided by Key Features for Plaque Echo Classification Based on Carotid Ultrasound Video","authors":"Ying Li , Xudong Liang , Haibing Chen , Jiang Xie , Zhuo Bi","doi":"10.1016/j.irbm.2024.100841","DOIUrl":"https://doi.org/10.1016/j.irbm.2024.100841","url":null,"abstract":"<div><h3>Objective</h3><p>Unstable plaques can cause acute cardiovascular and cerebrovascular diseases. The stability and instability of plaque are related to the plaque echo status in ultrasound. Carotid videos provide detailed plaque information compared to static images. Ultrasound-based plaque echo classification is challenging due to noise, interference frames, small targets (plaques), and complex shape changes.</p></div><div><h3>Methods</h3><p>This study proposes a Multi-dimensional Aggregation Network (MA-Net) guided by key features for plaque diagnosis based on carotid ultrasound video, which uses only video-level labels. MA-Net consists of Key-Feature (KF) and Temporal-Channel-Spatial (TCS) modules. The KF module learns the contribution of each frame to the classification at the feature level, adaptively infers the importance score of each frame, thereby reducing the influence of interference frames. The TCS module includes the Temporal-Channel (TC) and Temporal-Spatial (TS) sub-modules. In addition to studying the temporal dimension, it delves into the relationship between the channel and spatial dimensions. TC analyses the temporal dependencies among the channels and filters noise. Moreover, TS extracts features more accurately through the spatio-temporal information contained in the surrounding environment of the plaque.</p></div><div><h3>Results</h3><p>The performance of MA-Net on the SHU-Ultrasound-Video-2020 dataset is better than that of the state-of-the-art models of video classification, showing at least a 5% increase in accuracy, with an accuracy rate of 87.36%.</p></div><div><h3>Conclusion</h3><p>The outstanding diagnostic capability of the proposed model will help provide a more robust and reproducible diagnostic process with a lower labour cost for clinical carotid plaque diagnosis.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":5.6,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1959031824000228/pdfft?md5=86e5deb78112b78886aff4ff00c39560&pid=1-s2.0-S1959031824000228-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141480057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-22DOI: 10.1016/j.irbm.2024.100836
Nabil I. Ajali-Hernández , Carlos M. Travieso-González , Nayara Bermudo-Mora , Patricia Reino-Cacho , Sheila Rodríguez-Saucedo
Objective
This study addresses the challenge of user-specific bias in Brain-Computer Interfaces (BCIs) by proposing a novel methodology. The primary objective is to employ a hybrid deep learning model, combining 2D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) layers, to analyze EEG signals and classify imagined tasks. The overarching goal is to create a generalized model that is applicable to a broader population and mitigates user-specific biases.
Materials and Methods
EEG signals from imagined motor tasks in the public dataset Physionet form the basis of the study. This is due to the need to use other databases in addition to the BCI competition. A model of arrays emulating the electrode arrangement in the head is proposed to capture spatial information using CNN, and LSTM algorithms are used to capture temporal information, followed by signal classification.
Results
The hybrid model is implemented to achieve a high classification rate, reaching up to 90% for specific users and averaging 74.54%. Error detection thresholds are set to eliminate subjects with low task affinity, resulting in a significant improvement in classification accuracy of up to 21.34%.
Conclusion
The proposed methodology makes a significant contribution to the BCI field by providing a generalized system trained on diverse user data that effectively captures spatial and temporal EEG signal features. This study emphasizes the value of the hybrid model in advancing BCIs, highlighting its potential for improved reliability and accuracy in human-computer interaction. It also suggests the exploration of additional advanced layers, such as transformers, to further enhance the proposed methodology.
{"title":"Study of an Optimization Tool Avoided Bias for Brain-Computer Interfaces Using a Hybrid Deep Learning Model","authors":"Nabil I. Ajali-Hernández , Carlos M. Travieso-González , Nayara Bermudo-Mora , Patricia Reino-Cacho , Sheila Rodríguez-Saucedo","doi":"10.1016/j.irbm.2024.100836","DOIUrl":"https://doi.org/10.1016/j.irbm.2024.100836","url":null,"abstract":"<div><h3>Objective</h3><p>This study addresses the challenge of user-specific bias in Brain-Computer Interfaces (BCIs) by proposing a novel methodology. The primary objective is to employ a hybrid deep learning model, combining 2D Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) layers, to analyze EEG signals and classify imagined tasks. The overarching goal is to create a generalized model that is applicable to a broader population and mitigates user-specific biases.</p></div><div><h3>Materials and Methods</h3><p>EEG signals from imagined motor tasks in the public dataset Physionet form the basis of the study. This is due to the need to use other databases in addition to the BCI competition. A model of arrays emulating the electrode arrangement in the head is proposed to capture spatial information using CNN, and LSTM algorithms are used to capture temporal information, followed by signal classification.</p></div><div><h3>Results</h3><p>The hybrid model is implemented to achieve a high classification rate, reaching up to 90% for specific users and averaging 74.54%. Error detection thresholds are set to eliminate subjects with low task affinity, resulting in a significant improvement in classification accuracy of up to 21.34%.</p></div><div><h3>Conclusion</h3><p>The proposed methodology makes a significant contribution to the BCI field by providing a generalized system trained on diverse user data that effectively captures spatial and temporal EEG signal features. This study emphasizes the value of the hybrid model in advancing BCIs, highlighting its potential for improved reliability and accuracy in human-computer interaction. It also suggests the exploration of additional advanced layers, such as transformers, to further enhance the proposed methodology.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.sciencedirect.com/science/article/pii/S1959031824000174/pdfft?md5=982cd018a44984ae08fa196f365f8d5a&pid=1-s2.0-S1959031824000174-main.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140644996","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-04-16DOI: 10.1016/j.irbm.2024.100835
Yu-Hui Wang
Objectives
This paper is proposed to identify both promising technologies and potential products in the domain of biosensor using patent-based Technology-Driven Technology Roadmaps (TRM).
Materials and methods
The technology-driven TRM with timelines in this study is developed in three layers: technology, function and product. Patent applications are collected and identified to interpret technologies and functions for biosensors in healthcare, and product manuals or releases can be used as product introductions.
Results
Most biosensors in healthcare patents are concentrated in biochemical (T2) and electroencephalography (T5). Glycated hemoglobin (F1), measuring of glucose (F3), and biological process and molecular systems (F6) have a relatively larger patent count. Biochemical (T2) can combine with biological process and molecular systems (F6), and then brain's real-time electrical activity monitoring can be handled. Biochemical (T2) can also devote to glycated hemoglobin (F1), and glucose monitoring (F3), and thus create QCM sensor, CGM and GlucoWatch etc. applications.
Conclusion
Biochemical (T2) has a wide application among different functions for wearable biosensors in healthcare. This paper identifies and explores new developments biochemical (T2), and electroencephalography (T5) in wearable biosensors are expected to play a significant role over the coming decade in improving the current healthcare infrastructure, and enhancing the democratization of information and allocation of medical resources.
{"title":"Exploring Technology-Driven Technology Roadmaps (TRM) for Wearable Biosensors in Healthcare","authors":"Yu-Hui Wang","doi":"10.1016/j.irbm.2024.100835","DOIUrl":"https://doi.org/10.1016/j.irbm.2024.100835","url":null,"abstract":"<div><h3>Objectives</h3><p>This paper is proposed to identify both promising technologies and potential products in the domain of biosensor using patent-based Technology-Driven Technology Roadmaps (TRM).</p></div><div><h3>Materials and methods</h3><p>The technology-driven TRM with timelines in this study is developed in three layers: technology, function and product. Patent applications are collected and identified to interpret technologies and functions for biosensors in healthcare, and product manuals or releases can be used as product introductions.</p></div><div><h3>Results</h3><p>Most biosensors in healthcare patents are concentrated in biochemical (T2) and electroencephalography (T5). Glycated hemoglobin (F1), measuring of glucose (F3), and biological process and molecular systems (F6) have a relatively larger patent count. Biochemical (T2) can combine with biological process and molecular systems (F6), and then brain's real-time electrical activity monitoring can be handled. Biochemical (T2) can also devote to glycated hemoglobin (F1), and glucose monitoring (F3), and thus create QCM sensor, CGM and GlucoWatch etc. applications.</p></div><div><h3>Conclusion</h3><p>Biochemical (T2) has a wide application among different functions for wearable biosensors in healthcare. This paper identifies and explores new developments biochemical (T2), and electroencephalography (T5) in wearable biosensors are expected to play a significant role over the coming decade in improving the current healthcare infrastructure, and enhancing the democratization of information and allocation of medical resources.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-04-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140644997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This study was performed to prove the concept that transfer learning techniques, assisted with a generative model, could be used to alleviate the ‘big data’ requirement for training high-fidelity deep learning (DL) models in prediction of stiffness tensor of trabecular bone cubes.
Material and methods
Transfer learning approaches of domain adaptation were used, in which a source domain included 1,641 digital trabecular bone cubes synthesized from a generative model, and a target domain included 868 real trabecular bone cubes from human cadaver femurs. Simulated quantitative computed tomography (QCT) images of both the synthesized and real bone cubes were used as input, whereas the stiffness tensor of these cubes determined using finite element simulations were used as output. Three transfer learning algorithms, including instance-based (TrAdaBoostR2 and WANN) and parameter-based (RNN) methods, were used. Two case studies, one with varying sizes of training dataset and the other with a gender-biased training dataset, were performed to evaluate these deep transfer learning models in comparison with a base deep learning (DL) model trained using the dataset from the target domain.
Results
The results indicated that these deep transfer learning models were robust both to sample size and to the gender-biased training dataset, whereas the base DL model was very sensitive to such changes. Among the three transfer learning algorithms, the prediction accuracy of the RNN-based deep transfer learning model was the best (0.92-0.96%) and comparable to that of the base DL model trained using the dataset from the target domain.
Conclusion
This study proved the proposed concept and confirmed that high fidelity QCT-based deep learning models could be obtained for prediction of stiffness tensor of trabecular bone cubes.
{"title":"A Novel QCT-Based Deep Transfer Learning Approach for Predicting Stiffness Tensor of Trabecular Bone Cubes","authors":"Pengwei Xiao , Tinghe Zhang , Yufei Huang , Xiaodu Wang","doi":"10.1016/j.irbm.2024.100831","DOIUrl":"10.1016/j.irbm.2024.100831","url":null,"abstract":"<div><h3>Objectives</h3><p>This study was performed to prove the concept that transfer learning techniques, assisted with a generative model, could be used to alleviate the ‘big data’ requirement for training high-fidelity deep learning (DL) models in prediction of stiffness tensor of trabecular bone cubes.</p></div><div><h3>Material and methods</h3><p>Transfer learning approaches of domain adaptation were used, in which a source domain included 1,641 digital trabecular bone cubes synthesized from a generative model, and a target domain included 868 real trabecular bone cubes from human cadaver femurs. Simulated quantitative computed tomography (QCT) images of both the synthesized and real bone cubes were used as input, whereas the stiffness tensor of these cubes determined using finite element simulations were used as output. Three transfer learning algorithms, including instance-based (TrAdaBoostR2 and WANN) and parameter-based (RNN) methods, were used. Two case studies, one with varying sizes of training dataset and the other with a gender-biased training dataset, were performed to evaluate these deep transfer learning models in comparison with a base deep learning (DL) model trained using the dataset from the target domain.</p></div><div><h3>Results</h3><p>The results indicated that these deep transfer learning models were robust both to sample size and to the gender-biased training dataset, whereas the base DL model was very sensitive to such changes. Among the three transfer learning algorithms, the prediction accuracy of the RNN-based deep transfer learning model was the best (0.92-0.96%) and comparable to that of the base DL model trained using the dataset from the target domain.</p></div><div><h3>Conclusion</h3><p>This study proved the proposed concept and confirmed that high fidelity QCT-based deep learning models could be obtained for prediction of stiffness tensor of trabecular bone cubes.</p></div>","PeriodicalId":14605,"journal":{"name":"Irbm","volume":null,"pages":null},"PeriodicalIF":4.8,"publicationDate":"2024-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140166332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号