Biomedical Signal Processing and Control最新文献

SCEA-Net: A hybrid framework from spatial-channel-aware external attention for accurate 3D medical image segmentation SCEA-Net：一个基于空间通道感知的外部注意力的混合框架，用于精确的3D医学图像分割

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-10 DOI: 10.1016/j.bspc.2025.108807

Gennian Peng , Xuesong Lu , Yong Chen , Hong Chen , Zhiwei Zhai , Tong Chen , Qinlan Xie

{"title":"SCEA-Net: A hybrid framework from spatial-channel-aware external attention for accurate 3D medical image segmentation","authors":"Gennian Peng , Xuesong Lu , Yong Chen , Hong Chen , Zhiwei Zhai , Tong Chen , Qinlan Xie","doi":"10.1016/j.bspc.2025.108807","DOIUrl":"10.1016/j.bspc.2025.108807","url":null,"abstract":"<div><div>Accurate medical image segmentation is essential for disease diagnosis and treatment. Although methods based on convolutional neural networks (CNNs) have delivered remarkable segmentation outcomes, they face challenges in capturing long-range dependencies due to the inherent limitations of convolution operators. On the other hand, transformer-based methods can establish such dependencies through self-attention, but they suffer from quadratic computational complexity, making it challenging to process 3D inputs. Additionally, the pooling operation in their encoding stage often results in feature loss, and their ability to extract multi-scale contextual information is limited. To overcome these challenges, we introduce SCEA-Net, a novel approach tailored for precise 3D medical image segmentation. The core of SCEA-Net is the spatial-channel-aware external attention model (SCEAM), which integrates parallel external attention mechanisms with convolutions to effectively capture crucial spatial and channel information. This attention mechanism leverages memory-based storage units to consider potential relationships among all samples in the dataset, while also reducing model complexity through linear computation methods. Furthermore, we have designed parallel pooling and convolutional down-sampling to minimize the loss of detailed features during the down-sampling process. Experimental results on the ACDC, Synapse, Tumor and cardiac left atrium segmentation datasets demonstrate that SCEA-Net outperforms other state-of-the-art methods, validating the effectiveness of our approach.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"113 ","pages":"Article 108807"},"PeriodicalIF":4.9,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145247990","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}

引用次数: 0

Deep relative motion analysis for the identification and phenotyping of scarred myocardium using cine-MRI 深相对运动分析在瘢痕心肌鉴别和表型分析中的应用

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-10 DOI: 10.1016/j.bspc.2025.108850

Gaoning Ning , Dong Zhang , Sangyin Lv , Cailing Pu , Dongsheng Ruan , Chengjin Yu , Hongjie Hu , Huafeng Liu

{"title":"Deep relative motion analysis for the identification and phenotyping of scarred myocardium using cine-MRI","authors":"Gaoning Ning , Dong Zhang , Sangyin Lv , Cailing Pu , Dongsheng Ruan , Chengjin Yu , Hongjie Hu , Huafeng Liu","doi":"10.1016/j.bspc.2025.108850","DOIUrl":"10.1016/j.bspc.2025.108850","url":null,"abstract":"<div><div>The identification and phenotyping of scarred myocardium using cine magnetic resonance imaging (cine-MRI) play a pivotal role in the diagnosis and treatment of cardiovascular diseases. Myocardial motion tracking has garnered widespread attention for cine-MRI analysis. However, the complex myocardial motion and motion-related deformations limit the performance of existing methods. In this paper, we present a deep relative motion representation and learning framework. Our relative motion descriptor focuses on two aspects: static features and dynamic features. Particularly, we first project rays at specific angles from the geometric center of the blood pool in each frame, intersecting with the endocardium and epicardium. Subsequently, we represent the myocardial motion features based on the displacement and curvature of intersection points relative to the geometric center point in different frames. To further explore the motion features, we also introduce a Multi-Orientated Spatio-Temporal Multi-Layer Perception (MOST-MLP) for myocardial motion encoding. The proposed MOST-MLP is evaluated on one private dataset comprising 450 subjects and two public datasets (ACDC and M&Ms), with its strong performance across these benchmarks demonstrating the method’s effectiveness and superiority. Our code and pre-trained models are available at <span><span>https://github.com/gaoningn/MOST-MLP</span><svg><path></path></svg></span> to facilitate reproducibility and further research.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"113 ","pages":"Article 108850"},"PeriodicalIF":4.9,"publicationDate":"2025-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145247989","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}

引用次数: 0

Using artificial neural networks for anomaly detection in infrared thermography images for rapid diagnosis in an emergency care unit 利用人工神经网络对红外热成像图像进行异常检测，用于急诊病房的快速诊断

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-04 DOI: 10.1016/j.bspc.2025.108734

Akam Petersen , Mikkel Brabrand , Sergey Kucheryavskiy

{"title":"Using artificial neural networks for anomaly detection in infrared thermography images for rapid diagnosis in an emergency care unit","authors":"Akam Petersen , Mikkel Brabrand , Sergey Kucheryavskiy","doi":"10.1016/j.bspc.2025.108734","DOIUrl":"10.1016/j.bspc.2025.108734","url":null,"abstract":"<div><div>Infrared thermography (IRT) has emerged as an affordable, rapid and noninvasive complement to widely adopted yet resource-demanding medical imaging techniques such as MRI, CT scans and X-rays, offering diverse applications in the medical field. While IRT hardware is well established and capable of providing high-quality thermographic images, the analysis of such images often requires well-trained experts. Current state-of-the art methods for computer-aided IRT analysis rely on statistical tests of temperature gradients between control points, which are suboptimal because they do not fully exploit the available information regarding spatial temperature distributions.</div><div>This paper addresses this issue by incorporating artificial neural networks (ANN) into the IRT analysis workflow. We focused on a particular case in which the IRT was utilized in the emergency department (ED) for predicting 30-day mortality, thereby contributing to improved diagnosis and patient care in emergency medicine. In total, the IRT images of 214 patients were analyzed. Various ANN-based approaches were considered in this study, and the best results were obtained using an anomaly detection model based on a variational autoencoder (VAE), which achieved promising results for detecting abnormal images. This paper comprehensively presents all the analysis details as well as recommendations regarding image preprocessing, augmentation, and potential enhancements of the models.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108734"},"PeriodicalIF":4.9,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219584","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}

引用次数: 0

DAGU-Net: Cascaded multi-scale aware network based on dual attention grouping module for medical image segmentation 基于双注意分组模块的级联多尺度感知网络用于医学图像分割

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-04 DOI: 10.1016/j.bspc.2025.108732

Junfeng Liu , Yinghua Fu , Jun Shi

{"title":"DAGU-Net: Cascaded multi-scale aware network based on dual attention grouping module for medical image segmentation","authors":"Junfeng Liu , Yinghua Fu , Jun Shi","doi":"10.1016/j.bspc.2025.108732","DOIUrl":"10.1016/j.bspc.2025.108732","url":null,"abstract":"<div><div>Automatic segmentation of medical images based on convolutional neural networks has achieved outstanding success in the computer-aided diagnosis owing to the powerful feature representation. Besides, numerous image feature extraction methods based on attention mechanisms have been proposed to improve the accuracy of medical image segmentation, such as methods based on spatial attention, channel attention or Transformer. However, attention based methods utilizing the specialized modules to extract valuable information from basic features increase the complexity of models only to obtain better features for specific targets. An encoder–decoder architecture based on the dual attention grouping module and cascaded multi-scale structure (DAGU-Net) is proposed for medical image segmentation, which can adaptively extract features for input images and utilize multi-scale features to generate more precise probability maps. Concretely, the dual attention grouping module designed by the spatial and channel attention is taken as the basic convolutional block of the U-shape network. In addition, the cascaded multi-scale structure is conducted on encoder features to pass multi-scale contexts to the decoder part, significantly improving the quality of semantic segmentation. Extensive comparative experiments show that our method DAGU-Net surpasses eight state-of-the-art segmentation methods on three publicly available medical image datasets.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108732"},"PeriodicalIF":4.9,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218975","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}

引用次数: 0

A co-training approach integrating CNN and Mamba for semi-supervised 3D medical image segmentation 一种集成CNN和Mamba的半监督三维医学图像分割的协同训练方法

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-04 DOI: 10.1016/j.bspc.2025.108670

Yun Jiang , Pengyu Chen , Bingxi Liu, Miaofeng Lu, Longgang Yang, Yuhang Li, Jinliang Su

{"title":"A co-training approach integrating CNN and Mamba for semi-supervised 3D medical image segmentation","authors":"Yun Jiang , Pengyu Chen , Bingxi Liu, Miaofeng Lu, Longgang Yang, Yuhang Li, Jinliang Su","doi":"10.1016/j.bspc.2025.108670","DOIUrl":"10.1016/j.bspc.2025.108670","url":null,"abstract":"<div><div>Accurate 3D medical image segmentation is vital for clinical applications but hindered by the scarcity of expert-annotated data, posing challenges for fully supervised models that require extensive labels. To address this issue, semi-supervised learning (SSL) has emerged as an effective solution by enabling models to learn from limited labeled data and achieve performance comparable to fully supervised learning, thereby significantly reducing the burden of manual annotation. Among various SSL strategies, deep co-training has demonstrated its effectiveness, yet current methods suffer from excessive information sharing between subnetworks or convergence during the training process. In this paper, we propose a semi-supervised 3D medical image segmentation method based on heterogeneous co-training, which combines the local feature perception capability of Convolutional Neural Networks (CNNs) with the efficient sequence modeling ability of the Mamba architecture. This integration enables more robust and complementary feature learning. To further enhance the utilization of unlabeled data, we introduce a Confidence-Aware Consistency(CAC) loss, which enforces consistency between model predictions while maintaining the learning capacity of individual networks. In addition, we propose a TriMix data augmentation strategy and incorporate a feature perturbation mechanism to increase the diversity of training samples and improve generalization. Extensive experiments were performed on three publicly available datasets: BraTS2019, left atrium (LA) and pancreas. The proposed method achieved superior performance compared to existing semi-supervised segmentation approaches, as measured by Dice score and HD95, demonstrating its effectiveness in enhancing the accuracy and robustness of 3D medical image segmentation with limited labeled data.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108670"},"PeriodicalIF":4.9,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219699","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}

引用次数: 0

A convolutional neural networks with spatial configuration and attention mechanism for Tanner-Whitehouse 3 bone age assessment 基于空间结构和注意机制的卷积神经网络taner - whitehouse 3骨龄评估

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-04 DOI: 10.1016/j.bspc.2025.108728

Yi Zhang , Jindong Wu , Wenshuang Zhang , Hongye Zhao , Kai Li , Jian Geng , Dong Yan , Xiaoguang Cheng , Tongning Wu

{"title":"A convolutional neural networks with spatial configuration and attention mechanism for Tanner-Whitehouse 3 bone age assessment","authors":"Yi Zhang , Jindong Wu , Wenshuang Zhang , Hongye Zhao , Kai Li , Jian Geng , Dong Yan , Xiaoguang Cheng , Tongning Wu","doi":"10.1016/j.bspc.2025.108728","DOIUrl":"10.1016/j.bspc.2025.108728","url":null,"abstract":"<div><h3>Objective</h3><div>Radiographic bone age assessment (BAA) is a standard clinical procedure for the diagnosis of skeletal growth abnormalities in children and infants. Existing automated BAA algorithms based on the Tanner-Whitehouse 3 (TW3) method can only assess the skeletal maturity and bone age of the radius, ulna, and short bone (TW3-RUS), lacking the capability to assess the bone age of the carpal bone (TW3-C), which hinders their wider clinical adoption.</div></div><div><h3>Methods</h3><div>We proposed a TW3-based automated BAA method to address this limitation. Firstly, a heat map regression key point detection algorithm incorporating spatial configurations was introduced to locate and segment all 20 TW3-regions of interest (ROIs). Subsequently, a skeletal maturity classification network incorporating an attention mechanism with spatial and channel features was proposed to predict the skeletal maturity scores and bone ages of the TW3-RUS and TW3-C series.</div></div><div><h3>Results</h3><div>Our approach achieved a mean absolute error (MAE) of bone age of 0.42 (TW3-RUS) and 0.44 (TW3-C) years on a dataset of 5,235 left lateral radiographs of children of different ages.</div></div><div><h3>Conclusions</h3><div>Our framework demonstrated the immense clinical potential of the proposed algorithm by achieving the impressive BAA results, while also providing clinicians with all the essential information they need to know about skeletal maturity and bone age.</div></div><div><h3>Significance</h3><div>The proposed BAA algorithm which can simultaneously evaluate skeletal maturity level and bone age for both the TW3-RUS and TW3-C series is more helpful for clinicians to analyze the progression of their patients’ conditions and to adjust their treatment plans.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108728"},"PeriodicalIF":4.9,"publicationDate":"2025-10-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218937","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}

引用次数: 0

Synergizing ECG and textual features: A multi-modal method for coronary artery disease classification 协同心电图和文本特征：冠状动脉疾病分类的多模式方法

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-03 DOI: 10.1016/j.bspc.2025.108717

Jiajun Cai , Bo Peng , Xu Li , Junmei Song

{"title":"Synergizing ECG and textual features: A multi-modal method for coronary artery disease classification","authors":"Jiajun Cai , Bo Peng , Xu Li , Junmei Song","doi":"10.1016/j.bspc.2025.108717","DOIUrl":"10.1016/j.bspc.2025.108717","url":null,"abstract":"<div><div>Exercise Stress Test (EST) is a non-invasive method widely used to diagnose Coronary Artery Disease (CAD). It generates a substantial amount of multi-modal data, which is crucial for diagnostic research. However, previous research has tended to ignore textual modalities such as patients’ subjective symptoms and clinicians’ interpretations during the diagnostic process. This research aims to improve CAD diagnosis by combining multi-modal data, including patients’ ECG, physiological data, subjective symptoms, and clinicians’ notes. This research used data from 404 patients who underwent EST. After preprocessing, a multi-modal model was developed to distinguish CAD negative, CAD positive, and suspected CAD cases. This model consisted of a Time-aware convolutional network (TACN) for extracting temporal features from ECG images and a fine-tuned pre-trained BERT model for textual modality. The proposed method demonstrated strong performance in accuracy, sensitivity, specificity, and positive predictive value, achieving macro-average scores of 87.43%, 77.06%, 91.13%, and 73.89%, respectively. This research proposes a multi-modal model that combines TACN and a fine-tuned BERT model, and improves the model’s classification accuracy for CAD by introducing textual modalities and improving ECG processing. The implementation helps clinicians diagnose CAD more accurately and better allocate medical resources.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108717"},"PeriodicalIF":4.9,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218973","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}

引用次数: 0

High-precision personalized respiratory guidance model for enhanced breathing training: effects on heart rate variability 用于增强呼吸训练的高精度个性化呼吸引导模型：对心率变异性的影响

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-03 DOI: 10.1016/j.bspc.2025.108720

Zhantu Lin , Weifei Kong , Shaoxuan Qiu , Mingyang Luo, Jing Wei, Xiaolong Guo, Yu Zhang, Lifen Wang, Xinyu Zhang, Guo Dan

{"title":"High-precision personalized respiratory guidance model for enhanced breathing training: effects on heart rate variability","authors":"Zhantu Lin , Weifei Kong , Shaoxuan Qiu , Mingyang Luo, Jing Wei, Xiaolong Guo, Yu Zhang, Lifen Wang, Xinyu Zhang, Guo Dan","doi":"10.1016/j.bspc.2025.108720","DOIUrl":"10.1016/j.bspc.2025.108720","url":null,"abstract":"<div><h3>Objectives</h3><div>While slow, controlled breathing at 6 breaths per minute(bpm) has been shown to enhance heart rate variability (HRV), the impact of key parameters such as the inhalation-to-exhalation ratio (IER) remains unclear. This study aims to develop a scientifically valid and broadly applicable respiratory model to improve the accuracy of controlled breathing training systems, explore the relationship between breathing parameters and HRV, and assess their effects on autonomic nervous system regulation.</div></div><div><h3>Methods</h3><div>A high-precision, personalized respiratory training system was developed, incorporating precise visual and auditory guidance based on a feature-fitting model using B-spline fitting and particle swarm optimization. The system adaptively generated breathing guidance according to individual respiratory features, including rate, depth, and IER. Ten healthy participants each completed 20 sessions with different distinct patterns while HRV indicators were monitored.</div></div><div><h3>Results</h3><div>The model exhibited a mean fitting error below 0.1, with 96 % of cycles closely matching target patterns, demonstrating effective and reliable training guidance. Breathing at 6 bpm with an IER of 0.5 yielded the highest HRV. Additionally, 4–7–8 and box breathing patterns also significantly enhanced HRV.</div></div><div><h3>Conclusion</h3><div>This study proposed a scientifically valid, high-precision respiratory guidance model for personalized training. It also demonstrates that slow breathing at 6 bpm significantly enhances vagal activity and parasympathetic tone. Furthermore, a lower IER was associated with increased HRV, implying that optimizing this ratio can further improve outcomes.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108720"},"PeriodicalIF":4.9,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219700","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}

引用次数: 0

Multisite T1-weighted MRI classification of Alzheimer’s disease using 3D-CNN-HSCAM architecture with contrastive domain adaptation 使用3D-CNN-HSCAM结构和对比域自适应对阿尔茨海默病的多位点t1加权MRI分类

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-03 DOI: 10.1016/j.bspc.2025.108686

Francis Sam , Zhiguang Qin , Collins Sey , Joseph Roger Arhin , Daniel Addo , Linda Delali Fiasam , Williams Ayivi , Gladys Wavinya Muoka

{"title":"Multisite T1-weighted MRI classification of Alzheimer’s disease using 3D-CNN-HSCAM architecture with contrastive domain adaptation","authors":"Francis Sam , Zhiguang Qin , Collins Sey , Joseph Roger Arhin , Daniel Addo , Linda Delali Fiasam , Williams Ayivi , Gladys Wavinya Muoka","doi":"10.1016/j.bspc.2025.108686","DOIUrl":"10.1016/j.bspc.2025.108686","url":null,"abstract":"<div><div>Alzheimer’s Disease (AD) presents a significant diagnostic problem due to the considerable diversity in imaging data over several clinical settings. This study presents a new architecture based on Convolutional Neural Networks (CNN) to minimize variability in AD classification. Our model integrates a Hybrid Spatial-Channel Attention Mechanism (HSCAM) with contrastive learning, targeting the challenge of consistent AD diagnosis across four diverse Magnetic Resonance Imaging (MRI) domains. The HSCAM enhances the model’s capability to focus on salient features by adjusting both spatial and channel-wise feature representations, facilitating the extraction of intricate global and local patterns critical for accurate AD detection. Simultaneously, incorporating contrastive learning enables extracting domain-invariant features, significantly boosting the model’s efficacy on unseen datasets. We validated our approach using four classical machine learning classifiers to demonstrate the enhanced feature quality and robustness. Results indicate a marked improvement in classification accuracy, achieving 98.33% accuracy on AD classification, demonstrating a 1.35% improvement over state-of-the-art methods, and a reduction in variability by 1.28% when tested across multiple imaging protocols. This dual-enhancement approach not only sets an innovative mark for AD classification models but also offers substantial potential for application in real-world clinical settings, where imaging protocol variability hinders diagnostic consistency. To ensure clinical relevance, we provided visualizations highlighting influential brain regions in the model’s decisions.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108686"},"PeriodicalIF":4.9,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145219697","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}

引用次数: 0

EEG-based classification framework for the detection of Alzheimer’s disease and mild cognitive impairment 基于脑电图的阿尔茨海默病和轻度认知障碍检测分类框架

IF 4.9 2区医学

Biomedical Signal Processing and Control Pub Date : 2025-10-03 DOI: 10.1016/j.bspc.2025.108733

Mariana Escobar-López, Rocío Salazar-Varas

{"title":"EEG-based classification framework for the detection of Alzheimer’s disease and mild cognitive impairment","authors":"Mariana Escobar-López, Rocío Salazar-Varas","doi":"10.1016/j.bspc.2025.108733","DOIUrl":"10.1016/j.bspc.2025.108733","url":null,"abstract":"<div><div>Dementia has no cure, but if diagnosed in early stages, its progress can be slowed. For this reason, it is necessary to implement and improve the techniques that aid the diagnosis of this disease. Electroencephalography has been shown to be a potential candidate to support the diagnosis of dementia. Applying correct processing to the EEG signal and a good selection of features will allow a more accurate diagnosis. This paper presents a methodology to discriminate healthy subjects from subjects with Alzheimer’s disease and mild cognitive impairment. The work focuses mainly on the pre-processing stage and feature selection to establish a robust methodology that addresses inter-subject variability. In the pre-processing, a spatial filter is applied conditionally based on a threshold derived from the Signal-to-Noise ratio of the EEG signals; additionally, independent component analysis is used to remove noise present in the signal. For feature extraction, different techniques widely used in the frequency and time domains such as relative power and entropy were employed, obtaining a total of 133 features. Feature selection is performed through particle swarm optimization, where the objective function is based on the distance between the correlation matrix of the two classes considered; out of the 133 extracted features, 26 were selected, with relative power and entropy in the frontal and parietal electrodes being the most relevant in the detection of Alzheimer’s disease. The results obtained demonstrate that the methodology is successfully applied to different datasets achieving an accuracy greater than 95% in most of the tests carried out.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"112 ","pages":"Article 108733"},"PeriodicalIF":4.9,"publicationDate":"2025-10-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145218974","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}

引用次数: 0