Pub Date : 2025-02-19DOI: 10.1016/j.bspc.2025.107740
Yusuf Uzun , Mehmet Bilgin
In medical images, especially Magnetic Resonance Images (MRI), the quality of the image may be poor due to low sharpness value. This makes diagnosing the disease difficult and can even lead to misdiagnosis. In this study, the sharpness values of the images were increased by using the real-coded Genetic Algorithm (GA) and the War Strategy Optimization (WSO) algorithm in the adaptive histogram equalization method. Multiple fitness functions were used in the study. Image entropy, energy, sharpness, peak signal-to-noise ratio, gray level co-occurrence matrix, and Sobel edge feature extraction methods were used in the fitness function. In this study, a without elitism WSO algorithm was developed. The developed method was compared with the real coded GA with elitism, the GA without elitism, and the WSO with elitism. The proposed without elitism WSO method increased the contrast value by 15 % and the entropy level by 10 % in MRI images, thus making image details more distinct. While homogeneity was achieved with a 12 % increase in energy metric, the PSNR value increased from 25 dB to 30 dB because of noise reduction. Improved image sharpness and contrast enhancement will significantly increase doctors’ diagnostic accuracy on disease. It has been determined that the proposed without elitism WSO algorithm gives better results and works faster than other compared methods in some images. Elitism has generally shortened the speed of convergence but has not improved the outcome.
{"title":"Medical image enhancement using war strategy optimization algorithm","authors":"Yusuf Uzun , Mehmet Bilgin","doi":"10.1016/j.bspc.2025.107740","DOIUrl":"10.1016/j.bspc.2025.107740","url":null,"abstract":"<div><div>In medical images, especially Magnetic Resonance Images (MRI), the quality of the image may be poor due to low sharpness value. This makes diagnosing the disease difficult and can even lead to misdiagnosis. In this study, the sharpness values of the images were increased by using the real-coded Genetic Algorithm (GA) and the War Strategy Optimization (WSO) algorithm in the adaptive histogram equalization method. Multiple fitness functions were used in the study. Image entropy, energy, sharpness, peak signal-to-noise ratio, gray level co-occurrence matrix, and Sobel edge feature extraction methods were used in the fitness function. In this study, a without elitism WSO algorithm was developed. The developed method was compared with the real coded GA with elitism, the GA without elitism, and the WSO with elitism. The proposed without elitism WSO method increased the contrast value by 15 % and the entropy level by 10 % in MRI images, thus making image details more distinct. While homogeneity was achieved with a 12 % increase in energy metric, the PSNR value increased from 25 dB to 30 dB because of noise reduction. Improved image sharpness and contrast enhancement will significantly increase doctors’ diagnostic accuracy on disease. It has been determined that the proposed without elitism WSO algorithm gives better results and works faster than other compared methods in some images. Elitism has generally shortened the speed of convergence but has not improved the outcome.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107740"},"PeriodicalIF":4.9,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437485","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-18DOI: 10.1016/j.bspc.2025.107705
Muhammad Sajid , Ali Hassan , Dilshad Ahmed Khan , Shoab Ahmed Khan , Asim Dilawar Bakhshi , Sayed Tanveer Abbas Gilani , Muhammad Usman Akram , Mustansar Ali Ghazanfar
Coronary artery disease (CAD) is one of the leading causes of sudden cardiac arrest and accounts for a substantial proportion of global mortality. An early and accurate diagnosis is essential and can save lives. This study presents a methodological framework for the automated detection and severity evaluation of CAD, utilizing novel biomarkers. A comprehensive evaluation of the biomarker feature space was performed, resulting in the selection of an optimal feature set for further analysis. Subsequently, twelve machine learning classifiers were applied to this refined input, which included clinical, chemical, and molecular cardiac biomarkers obtained from the specially curated NUMS-NIHD dataset. Experimental validation was performed using K-fold cross-validation and leave-p-out cross-validation (LpOCV) to identify the most effective biomarker–classifier combinations for CAD detection and severity evaluation. The proposed combinations were then integrated into a framework aligned with clinical protocols. Benchmarking against state-of-the-art methodologies demonstrated the framework’s efficacy, achieving a detection accuracy of 97.18%, sensitivity of 96.67%, and specificity of 100.00%. For severity evaluation, the framework achieved an accuracy of 90.91%. These results indicate that the proposed framework is both effective and clinically viable.
{"title":"AI-CADS: An Artificial Intelligence based framework for automatic early detection and severity evaluation of coronary artery disease","authors":"Muhammad Sajid , Ali Hassan , Dilshad Ahmed Khan , Shoab Ahmed Khan , Asim Dilawar Bakhshi , Sayed Tanveer Abbas Gilani , Muhammad Usman Akram , Mustansar Ali Ghazanfar","doi":"10.1016/j.bspc.2025.107705","DOIUrl":"10.1016/j.bspc.2025.107705","url":null,"abstract":"<div><div>Coronary artery disease (CAD) is one of the leading causes of sudden cardiac arrest and accounts for a substantial proportion of global mortality. An early and accurate diagnosis is essential and can save lives. This study presents a methodological framework for the automated detection and severity evaluation of CAD, utilizing novel biomarkers. A comprehensive evaluation of the biomarker feature space was performed, resulting in the selection of an optimal feature set for further analysis. Subsequently, twelve machine learning classifiers were applied to this refined input, which included clinical, chemical, and molecular cardiac biomarkers obtained from the specially curated NUMS-NIHD dataset. Experimental validation was performed using K-fold cross-validation and leave-p-out cross-validation (LpOCV) to identify the most effective biomarker–classifier combinations for CAD detection and severity evaluation. The proposed combinations were then integrated into a framework aligned with clinical protocols. Benchmarking against state-of-the-art methodologies demonstrated the framework’s efficacy, achieving a detection accuracy of 97.18%, sensitivity of 96.67%, and specificity of 100.00%. For severity evaluation, the framework achieved an accuracy of 90.91%. These results indicate that the proposed framework is both effective and clinically viable.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107705"},"PeriodicalIF":4.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429097","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-18DOI: 10.1016/j.bspc.2025.107694
Gongsen Zhang , Zejun Jiang , Yungang Wang , Chunni Wang , Cheng Tao , Jian Zhu , Aiqin Gao , Huazhong Shu , Yankui Chang , Jinming Yu , Linlin Wang
We propose a patient-specific external-internal correlation model driven by optical surface imaging (OSI) for intra-fractional respiration-induced tumor motion and deformation tracking. A retrospective-prospective database was established enrolling 276 lung cancer patients undergoing 4D-CT imaging. Retrospective patients were divided into cohorts for training/cross-validation (Cohort-T-CV) and testing (Cohort-Test), whose body surfaces were extracted from 4D-CT phases to compensate for limited data volume of paired OSI-CT images. Prospective patients consisted of paired data for additional validation (Cohort-Add-V). Respiration-induced tumor motion and deformation are predicted in form of deformable 3D masks, with different phases as starting and ending points of prediction task. Deformable image registration (DIR) was performed to obtain Jacobian determinant map as one of input channels to enhance voxel-wise deformation details for mask inference. Residual-blocks and spatial attention gates were integrated into U-net-based architecture to build DIR-enhanced model 3D-U-RAD for external-internal correlation. Predictions of 3D-U-RAD and 3D-U-RA (simplified without DIR-enhancement) were evaluated with absolute/relative deviations of centroid (/), Dice similarity coefficient (), 95 % Hausdorff-Distance (), and absolute/relative volume changes (/). Amplitude motion prediction errors of 3D-U-RAD are 0.61 ± 0.46 mm and 0.59 ± 0.47 mm on Cohort-Test and Cohort-Add-V, respectively. In deformation prediction, are respectively 0.80 ± 0.04 and 0.81 ± 0.03, are 4.05 ± 1.25 mm and 3.90 ± 1.52 mm, and are 1.01 ± 0.65 cm3 and 1.12 ± 0.64 cm3 on the two cohorts, respectively. Except in left–right direction, results of 3D-U-RAD are significantly superior to 3D-U-RA ( < 0.05) in all other evaluation indicators. Driven by OSI, the proposed framework has feasibility to facilitate patient-specific accurate, non-radiative, and non-invasive tumor tracking for intra-fractional radiotherapy.
{"title":"Optical surface imaging-driven tumor tracking with deformable image registration-enhanced deep learning model for surface-guided radiotherapy","authors":"Gongsen Zhang , Zejun Jiang , Yungang Wang , Chunni Wang , Cheng Tao , Jian Zhu , Aiqin Gao , Huazhong Shu , Yankui Chang , Jinming Yu , Linlin Wang","doi":"10.1016/j.bspc.2025.107694","DOIUrl":"10.1016/j.bspc.2025.107694","url":null,"abstract":"<div><div>We propose a patient-specific external-internal correlation model driven by optical surface imaging (OSI) for intra-fractional respiration-induced tumor motion and deformation tracking. A retrospective-prospective database was established enrolling 276 lung cancer patients undergoing 4D-CT imaging. Retrospective patients were divided into cohorts for training/cross-validation (<em>Cohort-T-CV</em>) and testing (<em>Cohort-Test</em>), whose body surfaces were extracted from 4D-CT phases to compensate for limited data volume of paired OSI-CT images. Prospective patients consisted of paired data for additional validation (<em>Cohort-Add-V</em>). Respiration-induced tumor motion and deformation are predicted in form of deformable 3D masks, with different phases as starting and ending points of prediction task. Deformable image registration (DIR) was performed to obtain Jacobian determinant map as one of input channels to enhance voxel-wise deformation details for mask inference. Residual-blocks and spatial attention gates were integrated into U-net-based architecture to build DIR-enhanced model 3D-U-RAD for external-internal correlation. Predictions of 3D-U-RAD and 3D-U-RA (simplified without DIR-enhancement) were evaluated with absolute/relative deviations of centroid (<span><math><mrow><mi>DC</mi></mrow></math></span>/<span><math><mrow><mi>rDC</mi></mrow></math></span>), Dice similarity coefficient (<span><math><mrow><mi>DSC</mi></mrow></math></span>), 95 % Hausdorff-Distance (<span><math><msub><mrow><mi>HD</mi></mrow><mn>95</mn></msub></math></span>), and absolute/relative volume changes (<span><math><mrow><mi>δ</mi><mi>V</mi></mrow></math></span>/<span><math><mrow><mi>r</mi><mi>δ</mi><mi>V</mi></mrow></math></span>). Amplitude motion prediction errors of 3D-U-RAD are 0.61 ± 0.46 mm and 0.59 ± 0.47 mm on <em>Cohort-Test</em> and <em>Cohort-Add-V</em>, respectively. In deformation prediction,<span><math><mrow><mi>DSC</mi></mrow></math></span> are respectively 0.80 ± 0.04 and 0.81 ± 0.03, <span><math><msub><mrow><mi>HD</mi></mrow><mn>95</mn></msub></math></span> are 4.05 ± 1.25 mm and 3.90 ± 1.52 mm, and <span><math><mrow><mi>δ</mi><mi>V</mi></mrow></math></span> are 1.01 ± 0.65 cm<sup>3</sup> and 1.12 ± 0.64 cm<sup>3</sup> on the two cohorts, respectively. Except <span><math><mrow><mi>rDC</mi></mrow></math></span> in left–right direction, results of 3D-U-RAD are significantly superior to 3D-U-RA (<span><math><mi>p</mi></math></span> < 0.05) in all other evaluation indicators. Driven by OSI, the proposed framework has feasibility to facilitate patient-specific accurate, non-radiative, and non-invasive tumor tracking for intra-fractional radiotherapy.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107694"},"PeriodicalIF":4.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437435","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-18DOI: 10.1016/j.bspc.2025.107675
Hanpu Zhou , Xinyi Zhang , Hong Wang
Recently, survival models have found vast applications in biostatistics, bioinformatics, reliability engineering, finance and related fields. But survival data often face the small sample size and highly censored problem due to long experimental periods and high data collection costs. The lack of sufficient samples severely hinders the predictive power of survival models, especially when data-driven machine learning methods are increasingly used in survival analysis. In this research, we propose two survival data augmentation algorithms, namely Parametric algorithm for Survival Data Augmentation via a Two-stage process (PSDATA) and non-Parametric algorithm for Survival Data Augmentation via a Two-stage process(nPSDATA), which can effectively expand the small sample survival data set. We validate the effectiveness of the algorithms on both simulated and real data sets based on RSF and Cox models. Extensive experiments have shown that both strategies can improve the predictive performance substantially. Further experiments have revealed that using the proposed approaches, the cost of data collection can be reduced by a large extent with only a slight decrease in predictability.
{"title":"Highly censored survival analysis via data augmentation","authors":"Hanpu Zhou , Xinyi Zhang , Hong Wang","doi":"10.1016/j.bspc.2025.107675","DOIUrl":"10.1016/j.bspc.2025.107675","url":null,"abstract":"<div><div>Recently, survival models have found vast applications in biostatistics, bioinformatics, reliability engineering, finance and related fields. But survival data often face the small sample size and highly censored problem due to long experimental periods and high data collection costs. The lack of sufficient samples severely hinders the predictive power of survival models, especially when data-driven machine learning methods are increasingly used in survival analysis. In this research, we propose two survival data augmentation algorithms, namely Parametric algorithm for Survival Data Augmentation via a Two-stage process (PSDATA) and non-Parametric algorithm for Survival Data Augmentation via a Two-stage process(nPSDATA), which can effectively expand the small sample survival data set. We validate the effectiveness of the algorithms on both simulated and real data sets based on RSF and Cox models. Extensive experiments have shown that both strategies can improve the predictive performance substantially. Further experiments have revealed that using the proposed approaches, the cost of data collection can be reduced by a large extent with only a slight decrease in predictability.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107675"},"PeriodicalIF":4.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143437486","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-18DOI: 10.1016/j.bspc.2025.107691
Monika Mokan , Goldie Gabrani , Devanjali Relan
Background and Objective:
The artery/vein classification in retinal images is the starting step towards assessing retinal features to determine the vessel abnormalities for systemic diseases. Deep learning-based automatic strategies for segmenting and classifying retinal vascular images have been proposed recently. The resultant performance of these strategies is restricted by the absence of large amount of labeled data and severe data imbalances. Less than fifty fundus photos may be found in the majority of the currently accessible publicly available fundus image collections, such as LES, HRF, DRIVE, and others. Recent artery/vein classification research has devalued the significance of pixel-wise classification. In this work, we have devised a pixel-wise classification method that will separate the whole vasculature of the retina into veins and arteries using supervised machine learning algorithm.
Material and Methods:
Initially, we pre-processed the retinal images using three different techniques dehazing, median filtering and multiscale self-quotient. Next, intensity-based features are obtained for the pixels in the vessels of the retinal images that have been pre-processed. Three supervised machine learning classifiers k-nearest neighbors, decision trees and random forests have been used to test our classification technique. Among all the mentioned pre-processing techniques and classifiers, we achieved the highest classification accuracy with dehazing technique using decision tree classifier. A decision tree classifier’s input is selected based on the features that have the greatest impact on classification accuracy. We evaluated our approaches on four publicly available retinal datasets LES-AV, HRF, RITE, and Dual Modal 2019 datasets.
Results:
We got classification accuracy of 95.60%, 89.15%, 88.66% and 84.07% for the LES-AV, HRF, RITE, and Dual Modal 2019 datasets, respectively.
{"title":"Pixel-wise classification of the whole retinal vasculature into arteries and veins using supervised learning","authors":"Monika Mokan , Goldie Gabrani , Devanjali Relan","doi":"10.1016/j.bspc.2025.107691","DOIUrl":"10.1016/j.bspc.2025.107691","url":null,"abstract":"<div><h3>Background and Objective:</h3><div>The artery/vein classification in retinal images is the starting step towards assessing retinal features to determine the vessel abnormalities for systemic diseases. Deep learning-based automatic strategies for segmenting and classifying retinal vascular images have been proposed recently. The resultant performance of these strategies is restricted by the absence of large amount of labeled data and severe data imbalances. Less than fifty fundus photos may be found in the majority of the currently accessible publicly available fundus image collections, such as LES, HRF, DRIVE, and others. Recent artery/vein classification research has devalued the significance of pixel-wise classification. In this work, we have devised a pixel-wise classification method that will separate the whole vasculature of the retina into veins and arteries using supervised machine learning algorithm.</div></div><div><h3>Material and Methods:</h3><div>Initially, we pre-processed the retinal images using three different techniques dehazing, median filtering and multiscale self-quotient. Next, intensity-based features are obtained for the pixels in the vessels of the retinal images that have been pre-processed. Three supervised machine learning classifiers k-nearest neighbors, decision trees and random forests have been used to test our classification technique. Among all the mentioned pre-processing techniques and classifiers, we achieved the highest classification accuracy with dehazing technique using decision tree classifier. A decision tree classifier’s input is selected based on the features that have the greatest impact on classification accuracy. We evaluated our approaches on four publicly available retinal datasets LES-AV, HRF, RITE, and Dual Modal 2019 datasets.</div></div><div><h3>Results:</h3><div>We got classification accuracy of 95.60%, 89.15%, 88.66% and 84.07% for the LES-AV, HRF, RITE, and Dual Modal 2019 datasets, respectively.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107691"},"PeriodicalIF":4.9,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429099","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-17DOI: 10.1016/j.bspc.2025.107672
Ekta Tiwari , Siddharth Gupta , Anudeep Pavulla , Mustafa Al-Maini , Rajesh Singh , Esma R. Isenovic , Sumit Chaudhary , John L. Laird , Laura Mantella , Amer M. Johri , Luca Saba , Jasjit S. Suri
Background
Globally, diabetes mellitus is a major health challenge with high morbidity and significant costs. Traditional methods rely on invasive biomarkers like glycated hemoglobin and lack consistency, necessitating more robust approaches.
Methodology
This study uses attention-based deep learning for enhanced diabetes risk stratification. We focus on exploring recurrent neural networks with attention mechanisms. We used K-fold (K = 5) cross-validation and implemented 14 models for robustness. Further, we integrate an explainability paradigm by validating model outputs through reliability-focused statistical tests. Finally, we present the training time comparison between different hardware.
Results
The attention-based models employed demonstrated superior performance in handling multi-dimensional data, resulting in highly accurate diabetes risk stratification predictions. We went on to evaluate these models and benchmarked them against classical methods, proving significant improvements over traditional ones with metrics such as the area under the curve scores reaching 0.99 for attention models. The percentage improvement over non attention-based models was 3.67%. Also, the models were able to show generalization at 60% of training data.
Conclusion
The attention-based models employed in this study substantially enhance diabetes risk stratification, offering a promising tool for healthcare professionals. They allow for early and precise detection of diabetes risk stratification, thereby potentially improving patient outcomes through timely and tailored interventions. This research underscores the potential of sophisticated deep learning models in transforming the landscape of chronic disease management.
{"title":"Artificial intelligence-based multiclass diabetes risk stratification for big data embedded with explainability: From machine learning to attention models","authors":"Ekta Tiwari , Siddharth Gupta , Anudeep Pavulla , Mustafa Al-Maini , Rajesh Singh , Esma R. Isenovic , Sumit Chaudhary , John L. Laird , Laura Mantella , Amer M. Johri , Luca Saba , Jasjit S. Suri","doi":"10.1016/j.bspc.2025.107672","DOIUrl":"10.1016/j.bspc.2025.107672","url":null,"abstract":"<div><h3>Background</h3><div>Globally, diabetes mellitus is a major health challenge with high morbidity and significant costs. Traditional methods rely on invasive biomarkers like glycated hemoglobin and lack consistency, necessitating more robust approaches.</div></div><div><h3>Methodology</h3><div>This study uses attention-based deep learning for enhanced diabetes risk stratification. We focus on exploring recurrent neural networks with attention mechanisms. We used K-fold (K = 5) cross-validation and implemented 14 models for robustness. Further, we integrate an explainability paradigm by validating model outputs through reliability-focused statistical tests. Finally, we present the training time comparison between different hardware.</div></div><div><h3>Results</h3><div>The attention-based models employed demonstrated superior performance in handling multi-dimensional data, resulting in highly accurate diabetes risk stratification predictions. We went on to evaluate these models and benchmarked them against classical methods, proving significant improvements over traditional ones with metrics such as the area under the curve scores reaching 0.99 for attention models. The percentage improvement over non attention-based models was 3.67%. Also, the models were able to show generalization at 60% of training data.</div></div><div><h3>Conclusion</h3><div>The attention-based models employed in this study substantially enhance diabetes risk stratification, offering a promising tool for healthcare professionals. They allow for early and precise detection of diabetes risk stratification, thereby potentially improving patient outcomes through timely and tailored interventions. This research underscores the potential of sophisticated deep learning models in transforming the landscape of chronic disease management.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107672"},"PeriodicalIF":4.9,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429094","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-17DOI: 10.1016/j.bspc.2025.107634
Junding Sun , Jianxiang Xue , Zhaozhao Xu , Ningshu Li , Chaosheng Tang , Lei Zhao , Bin Pu , Yudong Zhang
Pneumonia, due to its high incidence and potential lethality, necessitates rapid and accurate diagnostic methods. Chest X-rays and CT scans are pivotal tools in pneumonia diagnosis. While traditional image analysis techniques heavily depend on the expertise of radiologists, they result in subjectivity and inconsistency. Moreover, these techniques exhibit inefficiency when processing large datasets. Deep learning techniques, especially Convolutional Neural Networks (CNNs), have made significant advances in the field of medical image analysis, improving the accuracy and efficiency of pneumonia detection. However, CNNs face challenges in processing lung images with irregular shape and distribution, and mainly extract local features, with limited performance for global structural information and lesion correlation. Graph Convolutional Networks (GCNs) successfully extend the convolution operation from regular grid data to irregular graph data by using adjacency matrix and node features, and better capture the global correlation in irregular image structures. To address the limitations of the traditional message passing mechanism of GCN, we propose a novel -hop graph construction algorithm that minimizes the introduction of redundant connections in higher-order graphs. We also introduce the Self-Adaptive Graph Convolutional Network (SAGCN), which incorporates an innovative graph convolution method that aggregates information across various hop distances. This method allows the adjustment of the aggregation range by varying the hop value. Additionally, we integrate a graph attention mechanism to mitigate the impacts of higher-order graph alterations on node connectivity. Moreover, our Node Adaptive Range Fusion (NARF) module enables effective multi-hop feature fusion and eliminates the issues associated with non-interactive nodes. We evaluated the SAGCN on two public pneumatic datasets, where it demonstrated superior performance with accuracies of 98.34% and 97.22%, respectively. These results significantly surpass several state-of-the-art methods, confirming the efficacy of SAGCN in pneumonia detection.
{"title":"SAGCN: Self-adaptive Graph Convolutional Network for pneumonia detection","authors":"Junding Sun , Jianxiang Xue , Zhaozhao Xu , Ningshu Li , Chaosheng Tang , Lei Zhao , Bin Pu , Yudong Zhang","doi":"10.1016/j.bspc.2025.107634","DOIUrl":"10.1016/j.bspc.2025.107634","url":null,"abstract":"<div><div>Pneumonia, due to its high incidence and potential lethality, necessitates rapid and accurate diagnostic methods. Chest X-rays and CT scans are pivotal tools in pneumonia diagnosis. While traditional image analysis techniques heavily depend on the expertise of radiologists, they result in subjectivity and inconsistency. Moreover, these techniques exhibit inefficiency when processing large datasets. Deep learning techniques, especially Convolutional Neural Networks (CNNs), have made significant advances in the field of medical image analysis, improving the accuracy and efficiency of pneumonia detection. However, CNNs face challenges in processing lung images with irregular shape and distribution, and mainly extract local features, with limited performance for global structural information and lesion correlation. Graph Convolutional Networks (GCNs) successfully extend the convolution operation from regular grid data to irregular graph data by using adjacency matrix and node features, and better capture the global correlation in irregular image structures. To address the limitations of the traditional message passing mechanism of GCN, we propose a novel <span><math><mi>k</mi></math></span>-hop graph construction algorithm that minimizes the introduction of redundant connections in higher-order graphs. We also introduce the Self-Adaptive Graph Convolutional Network (SAGCN), which incorporates an innovative graph convolution method that aggregates information across various hop distances. This method allows the adjustment of the aggregation range by varying the hop <span><math><mi>k</mi></math></span> value. Additionally, we integrate a graph attention mechanism to mitigate the impacts of higher-order graph alterations on node connectivity. Moreover, our Node Adaptive Range Fusion (NARF) module enables effective multi-hop feature fusion and eliminates the issues associated with non-interactive nodes. We evaluated the SAGCN on two public pneumatic datasets, where it demonstrated superior performance with accuracies of 98.34% and 97.22%, respectively. These results significantly surpass several state-of-the-art methods, confirming the efficacy of SAGCN in pneumonia detection.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107634"},"PeriodicalIF":4.9,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the field of ophthalmology, the accurate classification of different types of keratoconus (KCN) is vital for effective surgical planning and the successful implantation of intracorneal ring segments (ICRS). During the diagnostic process, ophthalmologists are required to review demographic and clinical ophthalmic examinations to make an accurate diagnosis. This process can be time-consuming and prone to errors. This research conducted a comprehensive study on the diagnosis and treatment of different types of KCN using a novel approach that employed a few-shot learning (FSL) technique with deep learning models based on corneal topography images and the Keraring nomogram. The retrospective cross-sectional study included 268 corneal images from 175 patients who underwent keraring segments implantation and were enrolled between May 2020 and September 2022. We developed multiple transfer learning techniques and a prototypical network to identify and classify corneal disorders. The study achieved high accuracy rates ranging from 88% for AlexNet to 98% for MobileNet-V3 and GoogLeNet, and AUC values ranging from 0.96 for VGG16 to 0.99 for MNASNet, EfficientNet-V2, and GoogLeNet to classify different corneal types of KCN. The results demonstrated the potential of FSL in addressing the challenge of limited medical image datasets, providing reliable performance in accurately categorizing different types of KCN and improving surgical decision-making. Our application provided the detection of KCN patterns and proposed personalized, fully automated surgical planning for each patient, thus supplanting the former manual calculations.
{"title":"A new morphological classification of keratoconus using few-shot learning in candidates for intrastromal corneal ring implants","authors":"Zhila Agharezaei , Mohammad Shirshekar , Reza Firouzi , Samira Hassanzadeh , Siamak Zarei-Ghanavati , Kambiz Bahaadinbeigy , Amin Golabpour , Laleh Agharezaei , Amin Amiri Tehranizadeh , Amir Hossein Taherinia , Mohammadreza Hoseinkhani , Reyhaneh Akbarzadeh , Mohammad Reza Sedaghat , Saeid Eslami","doi":"10.1016/j.bspc.2025.107664","DOIUrl":"10.1016/j.bspc.2025.107664","url":null,"abstract":"<div><div>In the field of ophthalmology, the accurate classification of different types of keratoconus (KCN) is vital for effective surgical planning and the successful implantation of intracorneal ring segments (ICRS). During the diagnostic process, ophthalmologists are required to review demographic and clinical ophthalmic examinations to make an accurate diagnosis. This process can be time-consuming and prone to errors. This research conducted a comprehensive study on the diagnosis and treatment of different types of KCN using a novel approach that employed a few-shot learning (FSL) technique with deep learning models based on corneal topography images and the Keraring nomogram. The retrospective cross-sectional study included 268 corneal images from 175 patients who underwent keraring segments implantation and were enrolled between May 2020 and September 2022. We developed multiple transfer learning techniques and a prototypical network to identify and classify corneal disorders. The study achieved high accuracy rates ranging from 88% for AlexNet to 98% for MobileNet-V3 and GoogLeNet, and AUC values ranging from 0.96 for VGG16 to 0.99 for MNASNet, EfficientNet-V2, and GoogLeNet to classify different corneal types of KCN. The results demonstrated the potential of FSL in addressing the challenge of limited medical image datasets, providing reliable performance in accurately categorizing different types of KCN and improving surgical decision-making. Our application provided the detection of KCN patterns and proposed personalized, fully automated surgical planning for each patient, thus supplanting the former manual calculations.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107664"},"PeriodicalIF":4.9,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419861","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-17DOI: 10.1016/j.bspc.2025.107605
Tong Xiong , Xin Zhang , Jiale Cheng , Xiangmin Xu , Gang Li
Early prediction of cognitive development holds significant importance in neonatal healthcare, especially given the high incidence of cognitive deficits or developmental delays in preterm infants. Previous advances have already investigated the interior relation between brain cortical morphology and cognitive skills, leveraging this connection for prognostication. However, the small proportion of subjects with cognitive deficits in the cohort limits the predictive power of previous models, i.e., the data imbalance issue. To tackle this challenge, in this paper, we present the Calibrated Multi-view Graph Learning (CMGL) framework for cognition score prediction, a cortical graph learning model with capabilities for the imbalanced regression scenario. In order to collaboratively capture the morphological relations among brain regions, a multi-view cortical graph is constructed based on cortex developmental correlation and adaptive morphology similarity. On top of this graph, we train a diffusion graph convolutional backbone to obtain the cortical graph representation. Considering the data imbalance challenge, we propose a feature clustering module to calibrate the learned feature space, reducing training bias towards dominant classes. Moreover, we introduce smoothed reweighted mean absolute error loss based on label distribution smoothing to guide the training process in continuous imbalanced scenario. In the cross-validation experiment on our in-house dataset, the proposed CMGL achieves a mean square error of 0.1596, demonstrating state-of-the-art performance compared to other related methods.
{"title":"Calibrated multi-view graph learning framework for infant cognitive abilities prediction","authors":"Tong Xiong , Xin Zhang , Jiale Cheng , Xiangmin Xu , Gang Li","doi":"10.1016/j.bspc.2025.107605","DOIUrl":"10.1016/j.bspc.2025.107605","url":null,"abstract":"<div><div>Early prediction of cognitive development holds significant importance in neonatal healthcare, especially given the high incidence of cognitive deficits or developmental delays in preterm infants. Previous advances have already investigated the interior relation between brain cortical morphology and cognitive skills, leveraging this connection for prognostication. However, the small proportion of subjects with cognitive deficits in the cohort limits the predictive power of previous models, i.e., the data imbalance issue. To tackle this challenge, in this paper, we present the Calibrated Multi-view Graph Learning (CMGL) framework for cognition score prediction, a cortical graph learning model with capabilities for the imbalanced regression scenario. In order to collaboratively capture the morphological relations among brain regions, a multi-view cortical graph is constructed based on cortex developmental correlation and adaptive morphology similarity. On top of this graph, we train a diffusion graph convolutional backbone to obtain the cortical graph representation. Considering the data imbalance challenge, we propose a feature clustering module to calibrate the learned feature space, reducing training bias towards dominant classes. Moreover, we introduce smoothed reweighted mean absolute error loss based on label distribution smoothing to guide the training process in continuous imbalanced scenario. In the cross-validation experiment on our in-house dataset, the proposed CMGL achieves a mean square error of 0.1596, demonstrating state-of-the-art performance compared to other related methods.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"106 ","pages":"Article 107605"},"PeriodicalIF":4.9,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419931","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2025-02-16DOI: 10.1016/j.bspc.2025.107693
Sa-Yoon Park , Ji Soo Park , Jisoo Lee , Hyesu Lee , Yelin Kim , Dong In Suh , Kwangsoo Kim
Auscultation is critical for assessing the respiratory system in children; however, the lack of pediatric lung sound databases impedes the development of automated analysis tools. This study introduces an object detection-based transfer learning method to accurately predict breath cycles in pediatric lung sounds. We utilized a model based on the YOLOv1 architecture, initially pre-trained on an adult lung sound dataset (HF_Lung_v1) and subsequently fine-tuned on a pediatric dataset (SNUCH_Lung). The input feature was the log Mel spectrogram, which effectively captured the relevant frequency and temporal information. The pre-trained model achieved an F1 score of 0.900 ± 0.003 on the HF_Lung_v1 dataset. After fine-tuning, it reached an F1 score of 0.824 ± 0.009 on the SNUCH_Lung dataset, confirming the efficacy of transfer learning. This model surpassed the performance of a baseline model trained solely on the SNUCH_Lung dataset without transfer learning. We also explored the impact of segment length, width, and various audio feature extraction techniques; the optimal results were obtained with 15 s segments, a 2-second width, and the log Mel spectrogram. The model is promising for clinical applications, such as generating large-scale annotated datasets, visualizing and labeling individual breath cycles, and performing correlation analysis with physiological indicators. Future research will focus on expanding the pediatric lung sound database through auto-labeling techniques and integrating the model into stethoscopes for real-time analysis. This study highlights the potential of object detection-based transfer learning in enhancing the accuracy of breath cycle prediction in pediatric lung sounds and advancing pediatric respiratory sound analysis tools.
{"title":"Detection of breath cycles in pediatric lung sounds via an object detection-based transfer learning method","authors":"Sa-Yoon Park , Ji Soo Park , Jisoo Lee , Hyesu Lee , Yelin Kim , Dong In Suh , Kwangsoo Kim","doi":"10.1016/j.bspc.2025.107693","DOIUrl":"10.1016/j.bspc.2025.107693","url":null,"abstract":"<div><div>Auscultation is critical for assessing the respiratory system in children; however, the lack of pediatric lung sound databases impedes the development of automated analysis tools. This study introduces an object detection-based transfer learning method to accurately predict breath cycles in pediatric lung sounds. We utilized a model based on the YOLOv1 architecture, initially pre-trained on an adult lung sound dataset (HF_Lung_v1) and subsequently fine-tuned on a pediatric dataset (SNUCH_Lung). The input feature was the log Mel spectrogram, which effectively captured the relevant frequency and temporal information. The pre-trained model achieved an F1 score of 0.900 ± 0.003 on the HF_Lung_v1 dataset. After fine-tuning, it reached an F1 score of 0.824 ± 0.009 on the SNUCH_Lung dataset, confirming the efficacy of transfer learning. This model surpassed the performance of a baseline model trained solely on the SNUCH_Lung dataset without transfer learning. We also explored the impact of segment length, width, and various audio feature extraction techniques; the optimal results were obtained with 15 s segments, a 2-second width, and the log Mel spectrogram. The model is promising for clinical applications, such as generating large-scale annotated datasets, visualizing and labeling individual breath cycles, and performing correlation analysis with physiological indicators. Future research will focus on expanding the pediatric lung sound database through auto-labeling techniques and integrating the model into stethoscopes for real-time analysis. This study highlights the potential of object detection-based transfer learning in enhancing the accuracy of breath cycle prediction in pediatric lung sounds and advancing pediatric respiratory sound analysis tools.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"105 ","pages":"Article 107693"},"PeriodicalIF":4.9,"publicationDate":"2025-02-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143419957","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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