Pub Date : 2025-07-10DOI: 10.1109/OJEMB.2025.3587993
MHD Jafar Mortada;Agnese Sbrollini;Ilaria Marcantoni;Erica Iammarino;Laura Burattini;Peter Van Dam
CineECG, a vectorcardiography-based method, uses standard 12-lead electrocardiography and 3D heart and torso models to depict the electrical activation path during the heart cycle, offering detailed visualization of cardiac electrical activity without numerical quantification. Our research aims to quantify CineECG outputs by defining 54 features that describe the route, shape, and direction of electrical activation. These features were used to develop a multinomial regression model classifying electrocardiography signals into normal sinus rhythm, left bundle branch block, right bundle branch block, and undetermined abnormalities. Trained and tested on 6,860 signals from the PhysioNet/Computing in Cardiology Challenge 2020 and THEW project, the model achieved an F1 score over 84% (normal sinus rhythm: 93%, left bundle branch block: 93%, right bundle branch block: 90%, undetermined abnormalities: 84%). The results suggest CineECG's potential in enhancing electrocardiography interpretation and aiding in the accurate diagnosis of various abnormalities.
CineECG是一种基于矢量心电图的方法，它使用标准的12导联心电图和3D心脏和躯干模型来描绘心脏周期中的电激活路径，在没有数值量化的情况下提供心脏电活动的详细可视化。我们的研究旨在通过定义54个特征来量化CineECG输出，这些特征描述了电激活的路径、形状和方向。利用这些特征建立多项回归模型，将心电图信号分为正常窦性心律、左束支传导阻滞、右束支传导阻滞和未确定异常。对来自PhysioNet/Computing in Cardiology Challenge 2020和THEW项目的6860个信号进行训练和测试，该模型获得了超过84%的F1评分（正常窦性心律：93%，左束支阻滞：93%，右束支阻滞：90%，未确定异常：84%）。结果表明，CineECG在增强心电图解释和帮助准确诊断各种异常方面具有潜力。
{"title":"Quantifying CineECG Output for Enhancing Electrocardiography Signals Classification","authors":"MHD Jafar Mortada;Agnese Sbrollini;Ilaria Marcantoni;Erica Iammarino;Laura Burattini;Peter Van Dam","doi":"10.1109/OJEMB.2025.3587993","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3587993","url":null,"abstract":"CineECG, a vectorcardiography-based method, uses standard 12-lead electrocardiography and 3D heart and torso models to depict the electrical activation path during the heart cycle, offering detailed visualization of cardiac electrical activity without numerical quantification. Our research aims to quantify CineECG outputs by defining 54 features that describe the route, shape, and direction of electrical activation. These features were used to develop a multinomial regression model classifying electrocardiography signals into normal sinus rhythm, left bundle branch block, right bundle branch block, and undetermined abnormalities. Trained and tested on 6,860 signals from the PhysioNet/Computing in Cardiology Challenge 2020 and THEW project, the model achieved an F1 score over 84% (normal sinus rhythm: 93%, left bundle branch block: 93%, right bundle branch block: 90%, undetermined abnormalities: 84%). The results suggest CineECG's potential in enhancing electrocardiography interpretation and aiding in the accurate diagnosis of various abnormalities.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"488-498"},"PeriodicalIF":2.9,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11077371","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144758368","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Goal: This study aims to explore the temporal dynamics of functional connectivity in drug-resistant focal epilepsy, focusing on Temporal Lobe Epilepsy (TLE) and Extra-Temporal Lobe Epilepsy (ETLE), using magnetoencephalography (MEG). Methods: Temporal metrics such as Change Between States, Entropy of Transition Patterns, Entropy of Transition Probabilities, Dwell Time, Stability, and Max L1 Distance derived from dynamic functional connectivity matrices were analyzed across eight frequency bands (delta, theta, alpha, beta, low gamma, mid gamma, high gamma and broadband) in TLE and ETLE patients. Results: Significant differences were observed between TLE and ETLE. ETLE exhibited more widespread and unpredictable connectivity transitions, while TLE demonstrated localized and structured patterns. Entropy metrics indicated higher randomness in ETLE, and dwell time analysis revealed shorter state persistence in ETLE compared to TLE. Conclusions: The findings highlight the potential of MEG-based temporal connectivity metrics in characterizing network disruptions in focal epilepsy.
{"title":"Temporal Dynamics of Functional Connectivity in Temporal and Extra-Temporal Lobe Epilepsy: A Magnetoencephalography-Based Study","authors":"Suhas M.V;N. Mariyappa;Karunakar Kotegar;Ravindranadh Chowdary M;Raghavendra K;Ajay Asranna;Viswanathan L.G;Sanjib Sinha;Anitha H","doi":"10.1109/OJEMB.2025.3587954","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3587954","url":null,"abstract":"<italic>Goal:</i> This study aims to explore the temporal dynamics of functional connectivity in drug-resistant focal epilepsy, focusing on Temporal Lobe Epilepsy (TLE) and Extra-Temporal Lobe Epilepsy (ETLE), using magnetoencephalography (MEG). <italic>Methods:</i> Temporal metrics such as Change Between States, Entropy of Transition Patterns, Entropy of Transition Probabilities, Dwell Time, Stability, and Max L1 Distance derived from dynamic functional connectivity matrices were analyzed across eight frequency bands (delta, theta, alpha, beta, low gamma, mid gamma, high gamma and broadband) in TLE and ETLE patients. <italic>Results:</i> Significant differences were observed between TLE and ETLE. ETLE exhibited more widespread and unpredictable connectivity transitions, while TLE demonstrated localized and structured patterns. Entropy metrics indicated higher randomness in ETLE, and dwell time analysis revealed shorter state persistence in ETLE compared to TLE. <italic>Conclusions:</i> The findings highlight the potential of MEG-based temporal connectivity metrics in characterizing network disruptions in focal epilepsy.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"507-514"},"PeriodicalIF":2.9,"publicationDate":"2025-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11077383","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144831868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Wound healing process is associated with multifaceted complications and is a functional way to advance the therapeutic process. Polymeric biomaterials exhibit structural mimicry with the extracellular matrix of the tissue to be regenerated and they also avoid chronic inflammation and immunological responses. Chitosan, a biopolymer demonstrates exceptional healing properties because of its biocompatibility, biodegradability, antimicrobial nature and affinity for biomolecules. Biomaterials consisting of chitosan along with herbal extracts could be ideal for wound healing. Click chemistry can provide one of the best ways to combine these bio-actives with chitosan. Advancing wound healing strategies with artificial intelligence /machine learning approaches can be employed further to boost the clinical efficacies of bioactive-loaded chitosan composite hydrogels. This review article investigates functionalized wound dressings with special emphasis on chitosan-based hydrogels, their effects on wound healing, and advanced approaches to increase hydrogel benefits by adding bioactive substances to form nanocomposites.
{"title":"Biomimetic Chitosan-Based Hydrogels for Sustainable Wound Healing With AI/ML Insights","authors":"Shourya Bodla;Prince Jain;Anwesha Khanra;Chhavi Sharma;Anupam Jyoti;Shiv Dutt Purohit;Hemant Singh;Abhijeet Singh;Juhi Saxena","doi":"10.1109/OJEMB.2025.3562382","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3562382","url":null,"abstract":"Wound healing process is associated with multifaceted complications and is a functional way to advance the therapeutic process. Polymeric biomaterials exhibit structural mimicry with the extracellular matrix of the tissue to be regenerated and they also avoid chronic inflammation and immunological responses. Chitosan, a biopolymer demonstrates exceptional healing properties because of its biocompatibility, biodegradability, antimicrobial nature and affinity for biomolecules. Biomaterials consisting of chitosan along with herbal extracts could be ideal for wound healing. Click chemistry can provide one of the best ways to combine these bio-actives with chitosan. Advancing wound healing strategies with artificial intelligence /machine learning approaches can be employed further to boost the clinical efficacies of bioactive-loaded chitosan composite hydrogels. This review article investigates functionalized wound dressings with special emphasis on chitosan-based hydrogels, their effects on wound healing, and advanced approaches to increase hydrogel benefits by adding bioactive substances to form nanocomposites.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"450-458"},"PeriodicalIF":2.7,"publicationDate":"2025-04-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10969627","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143918794","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-11DOI: 10.1109/OJEMB.2025.3555346
Canan Dagdeviren
{"title":"Guest Editorial: Special Section on Conformable Decoders","authors":"Canan Dagdeviren","doi":"10.1109/OJEMB.2025.3555346","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3555346","url":null,"abstract":"","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"352-352"},"PeriodicalIF":2.7,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10963971","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143821865","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-08DOI: 10.1109/OJEMB.2025.3558620
Tarek Haloubi;Spencer Angus Thomas;Catherine Hines;Kevin Dhaliwal;James R. Hopgood
Goal: This study introduces Temporal Reliability and Accuracy via Correlation Enhanced Registration (TRACER), a novel image processing pipeline that addresses motion artefacts in real-time Fluorescence Lifetime Imaging (FLIm) data for in-vivo pulmonary Optical Endomicroscopy (OEM). Its primary objective is to improve the accuracy and reliability of FLIm image sequences. Methods: The proposed TRACER pipeline comprises a comprehensive sequence of pre-processing steps and a novel registration approach. This includes the removal of uninformative frames and motion characterisation through dense optical flow, followed by a tracking-based Normalised Cross Correlation image registration method leveraging Channel and Spatial Reliability Tracker for precise alignment. Results: The complete TRACER pipeline delivers significant performance improvements, with 20% to 30% enhancement across different metrics for all tested registration methods. In particular, the unique TRACER registration approach outperforms state-of-the-art methods in image registration performance and achieves an order-of-magnitude faster runtime than the next best-performing approach. Conclusion: By addressing motion artefacts through its integrated pre-processing and novel registration strategy, TRACER offers a robust solution that ensures improved image quality and real-time feasibility for FLIm data processing in in-vivo pulmonary OEM.
{"title":"Motion Compensation in Pulmonary Fluorescence Lifetime Imaging: An Image Processing Pipeline for Artefact Reduction and Clinical Precision","authors":"Tarek Haloubi;Spencer Angus Thomas;Catherine Hines;Kevin Dhaliwal;James R. Hopgood","doi":"10.1109/OJEMB.2025.3558620","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3558620","url":null,"abstract":"<italic>Goal:</i> This study introduces Temporal Reliability and Accuracy via Correlation Enhanced Registration (TRACER), a novel image processing pipeline that addresses motion artefacts in real-time Fluorescence Lifetime Imaging (FLIm) data for in-vivo pulmonary Optical Endomicroscopy (OEM). Its primary objective is to improve the accuracy and reliability of FLIm image sequences. <italic>Methods:</i> The proposed TRACER pipeline comprises a comprehensive sequence of pre-processing steps and a novel registration approach. This includes the removal of uninformative frames and motion characterisation through dense optical flow, followed by a tracking-based Normalised Cross Correlation image registration method leveraging Channel and Spatial Reliability Tracker for precise alignment. <italic>Results:</i> The complete TRACER pipeline delivers significant performance improvements, with 20% to 30% enhancement across different metrics for all tested registration methods. In particular, the unique TRACER registration approach outperforms state-of-the-art methods in image registration performance and achieves an order-of-magnitude faster runtime than the next best-performing approach. <italic>Conclusion:</i> By addressing motion artefacts through its integrated pre-processing and novel registration strategy, TRACER offers a robust solution that ensures improved image quality and real-time feasibility for FLIm data processing in <italic>in-vivo</i> pulmonary OEM.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"432-441"},"PeriodicalIF":2.7,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10955276","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865263","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-04-02DOI: 10.1109/OJEMB.2025.3556987
Saaid H. Arshad;Ryan L. Touzjian;Matthew C. Jones;Brian A. Telfer;Jason M. Rall;Theodore G. Hart;Marlin W. Causey
Goal: Non-compressible torso hemorrhage represents a category of lethal injuries in both civilian and military traumatically injured populations that with proper intervention, training, or technological advancements are survivable. Endovascular localization of active bleeding in the pre-hospital setting can allow faster, less invasive, and more accurate applications of life-saving interventions. In this paper, we report initial in vivo and in silico experimental results to test the feasibility of endovascular localization of hemorrhage. Methods: Endovascular pressure waveforms were acquired on five pigs with an induced aortic injury via a custom intra-aortic catheter instrumented with four pressure sensors. Pressure and velocity data were then simulated on an in silico human aortic model with the same kind of injury. Results: A decrease in pulse pressure across the injury (proximal to distal) reliably indicated the injury location to within a few centimeters. The simulated model showed a similar decrease in pulse pressure as well as an increase in velocity. Conclusions: With additional refinement, localization accuracy may be sufficient for application of a modern covered stent to stop bleeding. The simulated model results indicate relevance for humans and provide guidance for future experiments.
{"title":"Endovascular Localization of Aortic Injury in a Porcine Model","authors":"Saaid H. Arshad;Ryan L. Touzjian;Matthew C. Jones;Brian A. Telfer;Jason M. Rall;Theodore G. Hart;Marlin W. Causey","doi":"10.1109/OJEMB.2025.3556987","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3556987","url":null,"abstract":"<italic>Goal</i>: Non-compressible torso hemorrhage represents a category of lethal injuries in both civilian and military traumatically injured populations that with proper intervention, training, or technological advancements are survivable. Endovascular localization of active bleeding in the pre-hospital setting can allow faster, less invasive, and more accurate applications of life-saving interventions. In this paper, we report initial in vivo and in silico experimental results to test the feasibility of endovascular localization of hemorrhage. <italic>Methods:</i> Endovascular pressure waveforms were acquired on five pigs with an induced aortic injury via a custom intra-aortic catheter instrumented with four pressure sensors. Pressure and velocity data were then simulated on an in silico human aortic model with the same kind of injury. <italic>Results:</i> A decrease in pulse pressure across the injury (proximal to distal) reliably indicated the injury location to within a few centimeters. The simulated model showed a similar decrease in pulse pressure as well as an increase in velocity<italic>. Conclusions:</i> With additional refinement, localization accuracy may be sufficient for application of a modern covered stent to stop bleeding. The simulated model results indicate relevance for humans and provide guidance for future experiments.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"425-431"},"PeriodicalIF":2.7,"publicationDate":"2025-04-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10947540","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143865277","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-28DOI: 10.1109/OJEMB.2025.3555807
Andrea Lorenzo Henri Sergio Detry;Vinny Chandran Suja;Nathaniel Merriman Sims;Robert A. Peterfreund;David E. Arney
Goal: To develop a compact, real-time microfluidic spectroscopy system capable of simultaneously measuring the concentrations of multiple solutes flowing together through a single fluid pathway with high temporal resolution. Methods: The measurement system integrates a Z-flow cell and dual-wavelength LED light sources with a compact spectrophotometer. The experimental setup consisted of two clinical infusion pumps delivering distinct marker dyes through a common fluid pathway composed of a clinical manifold and a single lumen of a clinical intravascular catheter, while a third pump delivered an inert carrier fluid. Concentration measurements of the mixed dyes were performed at high-frequency sampling intervals, with dynamic pump rate adjustments to evaluate the system's ability to detect real-time changes in solute concentration. A MATLAB-based control application enabled automated data acquisition, processing, and system control to enhance experimental efficiency. Results: The system accurately measured solute concentrations, capturing temporal variations with high precision. It demonstrated high reproducibility with a standard error of the mean no larger than $0.19 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$ for Erioglaucine and $1.32 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$ for Tartrazine at steady state, and high accuracy with a maximum deviation of $0.21 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$ for Erioglaucine and $0.5 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$ for Tartrazine from the expected steady-state concentrations. Conclusions: This system enables continuous, real-time monitoring of multiple solutes in dynamic flow conditions, offering a portable solution with high sensitivity to temporal concentration changes—advancing beyond traditional static fluid measurement methods.
{"title":"A Method for Temporally Resolved Continuous Inline Measurement of Multiple Solute Concentrations With Microfluidic Spectroscopy","authors":"Andrea Lorenzo Henri Sergio Detry;Vinny Chandran Suja;Nathaniel Merriman Sims;Robert A. Peterfreund;David E. Arney","doi":"10.1109/OJEMB.2025.3555807","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3555807","url":null,"abstract":"<italic>Goal:</i> To develop a compact, real-time microfluidic spectroscopy system capable of simultaneously measuring the concentrations of multiple solutes flowing together through a single fluid pathway with high temporal resolution. <italic>Methods:</i> The measurement system integrates a Z-flow cell and dual-wavelength LED light sources with a compact spectrophotometer. The experimental setup consisted of two clinical infusion pumps delivering distinct marker dyes through a common fluid pathway composed of a clinical manifold and a single lumen of a clinical intravascular catheter, while a third pump delivered an inert carrier fluid. Concentration measurements of the mixed dyes were performed at high-frequency sampling intervals, with dynamic pump rate adjustments to evaluate the system's ability to detect real-time changes in solute concentration. A MATLAB-based control application enabled automated data acquisition, processing, and system control to enhance experimental efficiency. <italic>Results:</i> The system accurately measured solute concentrations, capturing temporal variations with high precision. It demonstrated high reproducibility with a standard error of the mean no larger than <inline-formula><tex-math>$0.19 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$</tex-math></inline-formula> for Erioglaucine and <inline-formula><tex-math>$1.32 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$</tex-math></inline-formula> for Tartrazine at steady state, and high accuracy with a maximum deviation of <inline-formula><tex-math>$0.21 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$</tex-math></inline-formula> for Erioglaucine and <inline-formula><tex-math>$0.5 ,mu mathrm{g}mathrm{/}mathrm{m}mathrm{L}$</tex-math></inline-formula> for Tartrazine from the expected steady-state concentrations. <italic>Conclusions:</i> This system enables continuous, real-time monitoring of multiple solutes in dynamic flow conditions, offering a portable solution with high sensitivity to temporal concentration changes—advancing beyond traditional static fluid measurement methods.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"442-449"},"PeriodicalIF":2.7,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10945438","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143877629","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Goal: To assess the degree of adenocarcinoma, pathologists need to manually review pathology images. To reduce their burdens and achieve good inter-observer as well as intra-observer reproducibility, instance segmentation methods can help pathologists quantify shapes of gland cells and provide an automatic solution for computer-assisted grading of adenocarcinoma. However, segmenting individual gland cells of different sizes remains a difficult challenge in computer aided diagnosis. Method: A novel cross-scale guidance integration transformer is proposed for gland cell instance segmentation. Our network contains a cross-scale guidance integration module to integrate multi-scale features learned from the pathology image. By using the integrated features from different field-of-views, the decoder with mask attention can better segment individual gland cells. Results: Compared with recent task-specific deep learning methods, our method can achieve state-of-the-art performance in two public gland cell datasets. Conclusions: By imposing cross-scale encoder information, our method can retrieve accurate gland cell segmentation to assist the pathologists for computer-assisted grading of adenocarcinoma.
{"title":"Cross-Scale Guidance Integration Transformer for Instance Segmentation in Pathology Images","authors":"Yung-Ming Kuo;Jia-Chun Sheng;Chen-Hsuan Lo;You-Jie Wu;Chun-Rong Huang","doi":"10.1109/OJEMB.2025.3555818","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3555818","url":null,"abstract":"<italic>Goal:</i> To assess the degree of adenocarcinoma, pathologists need to manually review pathology images. To reduce their burdens and achieve good inter-observer as well as intra-observer reproducibility, instance segmentation methods can help pathologists quantify shapes of gland cells and provide an automatic solution for computer-assisted grading of adenocarcinoma. However, segmenting individual gland cells of different sizes remains a difficult challenge in computer aided diagnosis. <italic>Method:</i> A novel cross-scale guidance integration transformer is proposed for gland cell instance segmentation. Our network contains a cross-scale guidance integration module to integrate multi-scale features learned from the pathology image. By using the integrated features from different field-of-views, the decoder with mask attention can better segment individual gland cells. <italic>Results:</i> Compared with recent task-specific deep learning methods, our method can achieve state-of-the-art performance in two public gland cell datasets. <italic>Conclusions:</i> By imposing cross-scale encoder information, our method can retrieve accurate gland cell segmentation to assist the pathologists for computer-assisted grading of adenocarcinoma.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"413-419"},"PeriodicalIF":2.7,"publicationDate":"2025-03-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10945390","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143830497","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Objective: High-throughput biological data, with its vast complexity and higher dimensions, continues to require innovative analytic methodologies for meaningful exploration. Most methods for reducing data dimensions overlook the shape and topology of data, even though these are vital components of the data structure and complexity. This study leverages topological data analysis (TDA) and shows, using breast cancer (BC) gene expression data as an illustrative example, the power of including the shape of data. Results: In addition to delineating the known subtypes of BC, TDA identifies a new subtype within luminal B cancer along with the features that define the subtype. The final outcome is shown via three-dimensional (3D) scatter plots which demonstrate how the underlying patterns that we identified through TDA map to 3D space. Conclusions: The new subtype, obtained unsupervised and validated by prior knowledge, demonstrates the power of embedding the topology and shape of data in the analyses.
{"title":"Topological Data Analysis Reveals a Subgroup of Luminal B Breast Cancer","authors":"Zahra Rostami;David Fooshee;Gunnar Carlsson;Shankar Subramaniam","doi":"10.1109/OJEMB.2025.3558670","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3558670","url":null,"abstract":"<italic><b>Objective:</b></i> High-throughput biological data, with its vast complexity and higher dimensions, continues to require innovative analytic methodologies for meaningful exploration. Most methods for reducing data dimensions overlook the shape and topology of data, even though these are vital components of the data structure and complexity. This study leverages topological data analysis (TDA) and shows, using breast cancer (BC) gene expression data as an illustrative example, the power of including the shape of data. <italic><b>Results:</b></i> In addition to delineating the known subtypes of BC, TDA identifies a new subtype within luminal B cancer along with the features that define the subtype. The final outcome is shown via three-dimensional (3D) scatter plots which demonstrate how the underlying patterns that we identified through TDA map to 3D space. <italic><b>Conclusions:</b></i> The new subtype, obtained unsupervised and validated by prior knowledge, demonstrates the power of embedding the topology and shape of data in the analyses.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"465-471"},"PeriodicalIF":2.7,"publicationDate":"2025-03-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11008859","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144117348","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-03-10DOI: 10.1109/OJEMB.2025.3549594
W. K. Wong;Filbert H. Juwono;Catur Apriono;Ismi Rosyiana Fitri
Goal: Cardiotocograph (CTG) is a widely used device for monitoring fetal health during the labor phase. However, its interpretation remains challenging due to the complex and nonlinear nature of the data. Therefore, this paper aims to propose a reliable machine learning model for predicting fetal health. Methods: This paper introduces a state-of-the-art approach for predicting fetal health from CTG recordings (statistical features) using the Kolmogorov-Arnold Networks (KANs). KANs have recently been proposed asa powerful competitor to the conventional transfer function approach in feedforward neural networks. The proposed method leverages the powerful capabilities of KANs to model the intricate relationships within the CTG data, leading to improved classification accuracy. We validate our approach on a publicly available CTG dataset, which consists of statistical features of the acquired recordings and labeled fetal health conditions. Results: The results show that KANs outperform traditional machine learning models, achieving average classification accuracy values of 93.6% and 92.6% for two-class and three-class classification tasks, respectively. Conclusion: Our results indicate that the KAN model is particularly effective in handling the nonlinearity inherent in CTG recordings, making it a promising tool for enhancing automated fetal health assessment.
{"title":"Fetal Health Prediction From Cardiotocography Recordings Using Kolmogorov–Arnold Networks","authors":"W. K. Wong;Filbert H. Juwono;Catur Apriono;Ismi Rosyiana Fitri","doi":"10.1109/OJEMB.2025.3549594","DOIUrl":"https://doi.org/10.1109/OJEMB.2025.3549594","url":null,"abstract":"<italic>Goal:</i> Cardiotocograph (CTG) is a widely used device for monitoring fetal health during the labor phase. However, its interpretation remains challenging due to the complex and nonlinear nature of the data. Therefore, this paper aims to propose a reliable machine learning model for predicting fetal health. <italic>Methods:</i> This paper introduces a state-of-the-art approach for predicting fetal health from CTG recordings (statistical features) using the Kolmogorov-Arnold Networks (KANs). KANs have recently been proposed asa powerful competitor to the conventional transfer function approach in feedforward neural networks. The proposed method leverages the powerful capabilities of KANs to model the intricate relationships within the CTG data, leading to improved classification accuracy. We validate our approach on a publicly available CTG dataset, which consists of statistical features of the acquired recordings and labeled fetal health conditions. <italic>Results:</i> The results show that KANs outperform traditional machine learning models, achieving average classification accuracy values of 93.6% and 92.6% for two-class and three-class classification tasks, respectively. <italic>Conclusion:</i> Our results indicate that the KAN model is particularly effective in handling the nonlinearity inherent in CTG recordings, making it a promising tool for enhancing automated fetal health assessment.","PeriodicalId":33825,"journal":{"name":"IEEE Open Journal of Engineering in Medicine and Biology","volume":"6 ","pages":"345-351"},"PeriodicalIF":2.7,"publicationDate":"2025-03-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10918772","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143726439","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：