Biomedical Signal Processing and Control最新文献_第3页

MAR-GCNet: Multi-label abnormal detection of electrocardiograms by combining multiscale features and graph convolutional networks MAR-GCNet：结合多尺度特征和图卷积网络的多标签心电图异常检测

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-12 DOI: 10.1016/j.bspc.2026.109841

Kan Luo , Haixin He , Yu Chen , Lu You , Jiajia Yang , Dengke Hong , Jianxing Li , Chitin Hon

Cardiovascular diseases (CVDs) are the leading cause of global mortality, and accurate electrocardiogram (ECG) diagnoses are essential for effective clinical interventions. This paper introduces MAR-GCNet, a novel deep learning framework for multi-label ECG anomaly detection that integrates multi-scale feature extraction and inter-class correlation modeling. It combines multi-attention residual networks (MARNs), graph convolutional networks (GCNs) and a weighted fusion strategy. The MARNs incorporate ECA-ResNet blocks with convolutional kernels of sizes 3, 5, and 7 to capture both local and global temporal characteristics in 12-lead ECG signals. The GCNs use a conditional probability matrix (CPM) and a multi-label feature matrix (MLFM) to model inter-class dependencies and mutual exclusivity among cardiac abnormalities. A weighted fusion loss function is employed to integrate the outputs of the MARNs and GCNs branches, enabling optimal multi-label predictions. Experiments on the PTB-XL dataset show that MAR-GCNet outperforms several state-of-the-art (SOTA) models across various annotation levels, achieving the F1 scores of 72.68%, 66.80%, 69.46%, 76.84%, 52.06%, and 90.97% in the “all”, “diag.”, “sub-diag.”, “super-diag.”, “form”, and “rhythm” tasks, respectively. Ablation studies confirm that the integration of multi-scale feature extraction and the two-layer GCN configuration significantly enhance the model performance. These results indicate that MAR-GCNet is a promising approach for accurate and robust automated ECG analysis.

心血管疾病（cvd）是全球死亡的主要原因，准确的心电图（ECG）诊断对于有效的临床干预至关重要。本文介绍了一种新的多标签心电异常检测深度学习框架MAR-GCNet，该框架集成了多尺度特征提取和类间相关建模。它结合了多注意残差网络（marn）、图卷积网络（GCNs）和加权融合策略。marn将ECA-ResNet块与大小为3、5和7的卷积核结合起来，以捕获12导联心电信号的局部和全局时间特征。GCNs使用条件概率矩阵（CPM）和多标签特征矩阵（MLFM）来模拟心脏异常之间的类间依赖性和互斥性。采用加权融合损失函数对marn和GCNs分支的输出进行整合，实现最优的多标签预测。在PTB-XL数据集上的实验表明，MAR-GCNet在不同标注级别上的表现优于几种最先进的（SOTA）模型，在“all”、“diag.”、“sub-diag”上的F1得分分别为72.68%、66.80%、69.46%、76.84%、52.06%和90.97%。”、“super-diag。，“形式”和“节奏”任务。烧蚀研究证实，将多尺度特征提取与两层GCN配置相结合可以显著提高模型的性能。这些结果表明，MAR-GCNet是一种有前途的准确和鲁棒的自动心电分析方法。

{"title":"MAR-GCNet: Multi-label abnormal detection of electrocardiograms by combining multiscale features and graph convolutional networks","authors":"Kan Luo , Haixin He , Yu Chen , Lu You , Jiajia Yang , Dengke Hong , Jianxing Li , Chitin Hon","doi":"10.1016/j.bspc.2026.109841","DOIUrl":"10.1016/j.bspc.2026.109841","url":null,"abstract":"<div><div>Cardiovascular diseases (CVDs) are the leading cause of global mortality, and accurate electrocardiogram (ECG) diagnoses are essential for effective clinical interventions. This paper introduces MAR-GCNet, a novel deep learning framework for multi-label ECG anomaly detection that integrates multi-scale feature extraction and inter-class correlation modeling. It combines multi-attention residual networks (MARNs), graph convolutional networks (GCNs) and a weighted fusion strategy. The MARNs incorporate ECA-ResNet blocks with convolutional kernels of sizes 3, 5, and 7 to capture both local and global temporal characteristics in 12-lead ECG signals. The GCNs use a conditional probability matrix (CPM) and a multi-label feature matrix (MLFM) to model inter-class dependencies and mutual exclusivity among cardiac abnormalities. A weighted fusion loss function is employed to integrate the outputs of the MARNs and GCNs branches, enabling optimal multi-label predictions. Experiments on the PTB-XL dataset show that MAR-GCNet outperforms several state-of-the-art (SOTA) models across various annotation levels, achieving the F1 scores of 72.68%, 66.80%, 69.46%, 76.84%, 52.06%, and 90.97% in the “all”, “diag.”, “sub-diag.”, “super-diag.”, “form”, and “rhythm” tasks, respectively. Ablation studies confirm that the integration of multi-scale feature extraction and the two-layer GCN configuration significantly enhance the model performance. These results indicate that MAR-GCNet is a promising approach for accurate and robust automated ECG analysis.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109841"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192789","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

Brain tumor classification method based on segmented uniformity measure and spatial shift information fusion 基于分割均匀度测度和空间偏移信息融合的脑肿瘤分类方法

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-12 DOI: 10.1016/j.bspc.2026.109705

Xiaorui Zhang , Peisen Lu , Wei Sun , Rui Jiang

As a common malignant tumor, the accurate classification of brain tumors is crucial for early diagnosis and prevention. Appropriate feature extraction and classification methods can help significantly to achieve this goal. Traditional methods like Local Ternary Patterns (LTP) are suitable for extracting complex texture features of brain tumors, despite deep learning’s excellent results in classifying brain tumor datasets. S²-MLP, while effective in processing brain tumor features extracted by LTP, lacks uniformity and discriminative power, despite enhancing correlation between input features and achieving excellent classification results when combined with LTP. The present research proposes a probability feature expression method based on partition uniformity measure, which reduces computational complexity by transforming three-dimensional coding into two-dimensional coding through partitioning. Regions are labeled based on uniformity measure, with non-uniform regions receiving different labels and uniform regions receiving the same. These labels are converted into features using occurrence probabilities. Additionally, a method for multi-spatial shift segmented attention information fusion is proposed. The classifier is redesigned by expanding the feature maps multiple times, applying spatial shifts in different directions to each feature map, and using a split attention module to fuse the shifted feature maps, enhancing the correlation between features. The internal nodes of the MLP are also optimized to improve the model’s generalization performance. The experiments achieved the highest classification accuracy on the Sa and SfB datasets, achieving 95.32% and 97.26%, respectively, indicating that this method has significant potential applications in brain tumor classification.

脑肿瘤作为一种常见的恶性肿瘤，准确分类对早期诊断和预防至关重要。适当的特征提取和分类方法可以显著帮助实现这一目标。尽管深度学习在脑肿瘤数据集分类方面取得了优异的成绩，但局部三元模式（LTP）等传统方法适用于提取脑肿瘤的复杂纹理特征。S2-MLP虽然对LTP提取的脑肿瘤特征进行了有效的处理，但与LTP结合后，虽然增强了输入特征之间的相关性，取得了很好的分类效果，但统一性和判别能力不足。本研究提出了一种基于分区均匀度测度的概率特征表达方法，通过分区将三维编码转化为二维编码，降低了计算复杂度。根据均匀性度量对区域进行标记，不均匀区域的标签不同，均匀区域的标签相同。使用发生概率将这些标签转换为特征。此外，提出了一种多空间移位分段注意信息融合方法。对分类器进行了重新设计，对特征图进行多次扩展，对每个特征图进行不同方向的空间位移，并使用分裂注意模块对位移后的特征图进行融合，增强特征之间的相关性。为了提高模型的泛化性能，还对MLP的内部节点进行了优化。实验在Sa和SfB数据集上的分类准确率最高，分别达到95.32%和97.26%，表明该方法在脑肿瘤分类中具有重要的潜在应用前景。

{"title":"Brain tumor classification method based on segmented uniformity measure and spatial shift information fusion","authors":"Xiaorui Zhang , Peisen Lu , Wei Sun , Rui Jiang","doi":"10.1016/j.bspc.2026.109705","DOIUrl":"10.1016/j.bspc.2026.109705","url":null,"abstract":"<div><div>As a common malignant tumor, the accurate classification of brain tumors is crucial for early diagnosis and prevention. Appropriate feature extraction and classification methods can help significantly to achieve this goal. Traditional methods like Local Ternary Patterns (LTP) are suitable for extracting complex texture features of brain tumors, despite deep learning’s excellent results in classifying brain tumor datasets. S<sup>2</sup>-MLP, while effective in processing brain tumor features extracted by LTP, lacks uniformity and discriminative power, despite enhancing correlation between input features and achieving excellent classification results when combined with LTP. The present research proposes a probability feature expression method based on partition uniformity measure, which reduces computational complexity by transforming three-dimensional coding into two-dimensional coding through partitioning. Regions are labeled based on uniformity measure, with non-uniform regions receiving different labels and uniform regions receiving the same. These labels are converted into features using occurrence probabilities. Additionally, a method for multi-spatial shift segmented attention information fusion is proposed. The classifier is redesigned by expanding the feature maps multiple times, applying spatial shifts in different directions to each feature map, and using a split attention module to fuse the shifted feature maps, enhancing the correlation between features. The internal nodes of the MLP are also optimized to improve the model’s generalization performance. The experiments achieved the highest classification accuracy on the Sa and SfB datasets, achieving 95.32% and 97.26%, respectively, indicating that this method has significant potential applications in brain tumor classification.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109705"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192794","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

Pain intensity classification and evaluation of individual differences in subjects based on hybrid CNN–BiLSTM approach 基于CNN-BiLSTM混合方法的受试者疼痛强度分类及个体差异评估

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-12 DOI: 10.1016/j.bspc.2026.109815

Mingxuan Sun , Yang Liu , Daoshuang Geng , Xiaobang Wu , Daoguo Yang

Pain is a complex subjective experience requiring objective assessment methods for precise diagnosis and treatment. Current approaches relying on self-reports are susceptible to bias and individual variability. This study proposes a cross-mixed model combining a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network (hybrid CNN–BiLSTM framework). It classifies pain intensity on the basis of electroencephalography (EEG) signals while explicitly modeling interindividual differences. We introduce a quantitative pain sensitivity index derived from pain threshold and tolerance measurements during cold pressor tests. It facilitates the categorization of subjects into high- and low-sensitivity groups. The CNN component extracts spatial features from EEG time–frequency representations, while the BiLSTM with self-attention captures the temporal dynamics of pain evolution. Subject-independent evaluation was performed using a Leave-One-Subject-Out (LOSO) cross-validation (LOSOCV) strategy. The model achieves accuracies of 88.64% (no pain), 95.80% (mild pain), 99.75% (moderate pain), and 82.96% (severe pain) in the undivided group. When individual sensitivity differences revealed through group-stratified training were considered, the overall accuracy increases to 93.98%, accompanied by increases in Recall and F1-scores increase. Ablation studies confirm the contributions of each architectural component (CNN: spatial feature extraction; BiLSTM: temporal modeling; attention: salient segment weighting; LOSOCV: generalization). Statistical analysis reveals significant correlation between intersubject pain score differences and prediction loss (R² = 0.45, p < 0.01), validating the effect of individual variability. The proposed framework provides not only accurate pain classification but also a methodology for personalizing pain assessment based on individual sensitivity profiles, showing potential for precise clinical pain management.

疼痛是一种复杂的主观体验，需要客观的评估方法来精确诊断和治疗。目前依赖自我报告的方法容易受到偏见和个体差异的影响。本研究提出了一种结合卷积神经网络（CNN）和双向长短期记忆（BiLSTM）网络（混合CNN - BiLSTM框架）的交叉混合模型。它根据脑电图（EEG）信号对疼痛强度进行分类，同时明确地模拟个体间的差异。我们介绍了一个定量的疼痛敏感性指数，从疼痛阈值和耐受性测量在冷压试验。它有助于将受试者分为高敏感组和低敏感组。CNN组件从EEG时频表征中提取空间特征，而自注意BiLSTM捕获疼痛演化的时间动态。受试者独立评估采用留一受试者（LOSO）交叉验证（LOSOCV）策略进行。在未划分组中，模型的准确率分别为88.64%（无疼痛）、95.80%（轻度疼痛）、99.75%（中度疼痛）和82.96%（重度疼痛）。当考虑群体分层训练的个体敏感性差异时，总体准确率提高到93.98%，同时召回率和f1分数也有所提高。消融研究证实了每个建筑成分的贡献（CNN：空间特征提取；BiLSTM：时间建模；注意力：显著段加权；LOSOCV：泛化）。统计分析显示受试者间疼痛评分差异与预测损失之间存在显著相关性（R2 = 0.45, p < 0.01），验证了个体差异的影响。该框架不仅提供了准确的疼痛分类，还提供了基于个体敏感性特征的个性化疼痛评估方法，显示了精确临床疼痛管理的潜力。

{"title":"Pain intensity classification and evaluation of individual differences in subjects based on hybrid CNN–BiLSTM approach","authors":"Mingxuan Sun , Yang Liu , Daoshuang Geng , Xiaobang Wu , Daoguo Yang","doi":"10.1016/j.bspc.2026.109815","DOIUrl":"10.1016/j.bspc.2026.109815","url":null,"abstract":"<div><div>Pain is a complex subjective experience requiring objective assessment methods for precise diagnosis and treatment. Current approaches relying on self-reports are susceptible to bias and individual variability. This study proposes a cross-mixed model combining a convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network (hybrid CNN–BiLSTM framework). It classifies pain intensity on the basis of electroencephalography (EEG) signals while explicitly modeling interindividual differences. We introduce a quantitative pain sensitivity index derived from pain threshold and tolerance measurements during cold pressor tests. It facilitates the categorization of subjects into high- and low-sensitivity groups. The CNN component extracts spatial features from EEG time–frequency representations, while the BiLSTM with self-attention captures the temporal dynamics of pain evolution. Subject-independent evaluation was performed using a Leave-One-Subject-Out (LOSO) cross-validation (LOSOCV) strategy. The model achieves accuracies of 88.64% (no pain), 95.80% (mild pain), 99.75% (moderate pain), and 82.96% (severe pain) in the undivided group. When individual sensitivity differences revealed through group-stratified training were considered, the overall accuracy increases to 93.98%, accompanied by increases in Recall and F1-scores increase. Ablation studies confirm the contributions of each architectural component (CNN: spatial feature extraction; BiLSTM: temporal modeling; attention: salient segment weighting; LOSOCV: generalization). Statistical analysis reveals significant correlation between intersubject pain score differences and prediction loss (<em>R</em><sup>2</sup> = 0.45, <em>p</em> < 0.01), validating the effect of individual variability. The proposed framework provides not only accurate pain classification but also a methodology for personalizing pain assessment based on individual sensitivity profiles, showing potential for precise clinical pain management.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109815"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192863","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

Intelligent diagnosis of aortic lesion using non-contrast CT: An integrated approach combining deep learning and morphological characteristics 非对比CT对主动脉病变的智能诊断：一种深度学习与形态学特征相结合的综合方法

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-12 DOI: 10.1016/j.bspc.2026.109823

Mingliang Yang , Aoxue Mei , Xiaolin Guo , Jianxing Hu , Yue Zhang , Xiangbing Bian , Jiayu Huang , Sulian Su , Jinhao Lyu , Xin Lou

Traditional diagnosis of aortic lesions typically relies on CT angiography (CTA), which provides detailed vascular structures but requires contrast agents. Non-contrast CT (NCCT) is more accessible for routine use but suffers from inherently low soft-tissue contrast, making visual assessment and manual delineation of non-calcified lesions challenging and subjective. In this study, we propose a hybrid algorithm designed to perform comprehensive segmentation and classification of various aortic lesions, including aneurysms, dissections, lumen stenosis, vessel wall calcification, and normal conditions, directly from NCCT images. The method focuses on utilizing advanced deep learning segmentation techniques along with knowledge of aortic morphology to accurately diagnose aortic lesions. Data from three centers (n = 435) were used for algorithm development, and data from three additional centers (n = 493) were used for testing. Detailed comparisons with the baseline method showed that our proposed deep learning approach outperformed other methods, achieving an accuracy of 89.7%, a sensitivity of 79.4%, a specificity of 97.1%, and an F1 score of 0.790 for multiple lesion diagnosis tasks. Further integration of morphological features improved the diagnostic accuracy to 90.3% and the overall performance metric, the F1 score, to 0.803. These experimental results demonstrate the feasibility of diagnosing aortic lesions from NCCT and validate the effectiveness of combining deep learning with morphological characteristics.

主动脉病变的传统诊断通常依赖于CT血管造影（CTA），它提供了详细的血管结构，但需要造影剂。非对比CT （NCCT）更容易用于常规使用，但其固有的软组织对比度较低，使得视觉评估和手工描绘非钙化病变具有挑战性和主观性。在这项研究中，我们提出了一种混合算法，旨在对各种主动脉病变进行全面的分割和分类，包括动脉瘤、夹层、管腔狭窄、血管壁钙化和正常情况，直接来自NCCT图像。该方法着重于利用先进的深度学习分割技术以及主动脉形态知识来准确诊断主动脉病变。来自三个中心（n = 435）的数据用于算法开发，另外三个中心（n = 493）的数据用于测试。与基线方法的详细比较表明，我们提出的深度学习方法优于其他方法，在多病变诊断任务中，准确率为89.7%，灵敏度为79.4%，特异性为97.1%，F1评分为0.790。形态学特征的进一步整合将诊断准确率提高到90.3%，整体性能指标F1得分提高到0.803。这些实验结果证明了NCCT诊断主动脉病变的可行性，验证了深度学习与形态学特征相结合的有效性。

{"title":"Intelligent diagnosis of aortic lesion using non-contrast CT: An integrated approach combining deep learning and morphological characteristics","authors":"Mingliang Yang , Aoxue Mei , Xiaolin Guo , Jianxing Hu , Yue Zhang , Xiangbing Bian , Jiayu Huang , Sulian Su , Jinhao Lyu , Xin Lou","doi":"10.1016/j.bspc.2026.109823","DOIUrl":"10.1016/j.bspc.2026.109823","url":null,"abstract":"<div><div>Traditional diagnosis of aortic lesions typically relies on CT angiography (CTA), which provides detailed vascular structures but requires contrast agents. Non-contrast CT (NCCT) is more accessible for routine use but suffers from inherently low soft-tissue contrast, making visual assessment and manual delineation of non-calcified lesions challenging and subjective. In this study, we propose a hybrid algorithm designed to perform comprehensive segmentation and classification of various aortic lesions, including aneurysms, dissections, lumen stenosis, vessel wall calcification, and normal conditions, directly from NCCT images. The method focuses on utilizing advanced deep learning segmentation techniques along with knowledge of aortic morphology to accurately diagnose aortic lesions. Data from three centers (n = 435) were used for algorithm development, and data from three additional centers (n = 493) were used for testing. Detailed comparisons with the baseline method showed that our proposed deep learning approach outperformed other methods, achieving an accuracy of 89.7%, a sensitivity of 79.4%, a specificity of 97.1%, and an F1 score of 0.790 for multiple lesion diagnosis tasks. Further integration of morphological features improved the diagnostic accuracy to 90.3% and the overall performance metric, the F1 score, to 0.803. These experimental results demonstrate the feasibility of diagnosing aortic lesions from NCCT and validate the effectiveness of combining deep learning with morphological characteristics.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109823"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192790","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

MD-SIRNet: Multi-domain representations for EEG-based speech imagery recognition with deep learning MD-SIRNet：基于脑电图的深度学习语音图像识别的多域表示

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-11 DOI: 10.1016/j.bspc.2026.109817

Liang Dong , Hengyi Shao , Zhejun Zhang , Yingqi Zhu , Shaoting Guo , Lin Zhang , Lei Li

Speech imagery (SI) recognition from Electroencephalography (EEG), enhances the foundation of the brain-computer interface (BCI). Although some existing research has been proposed to solve the high variability and low signal-to-noise ratio of multi-channel EEG signals, the spatial–temporal-frequency information is still underutilized to improve the performance of SI recognition. We propose MD-SIRNet to obtain multi-domain features efficiently and precisely. MD-SIRNet decomposes spatial multi-channel EEG data into four sets of intrinsic mode functions (IMFs) using Multivariate Variational Mode Decomposition (MVMD). To emphasize the main features, the IMFs are summed and then transformed into time–frequency representation (TFR) images after extracting high-precision time–frequency features using the Synchrosqueezed Wavelet Transform (SSWT). TFR images are fed into the Tuned-CNN model. MD-SIRNet is validated on two publicly available EEG datasets, compared with five methods by accuracy. The results of MD-SIRNet achieve an accuracy improvement of 2.23%, 0.45%, 1.59%, 4.45%, and 5.56% for long words, long-short words, short words, vowels, and command words. The code and model are available at https://github.com/buptantEEG/MD-SIRNet.

从脑电图（EEG）中识别语音图像，增强了脑机接口（BCI）基础。虽然已有研究针对多通道脑电信号的高变异性和低信噪比提出了一些解决方案，但在提高SI识别性能方面，仍未充分利用脑电信号的时空频率信息。为了高效、精确地获取多域特征，我们提出了MD-SIRNet。MD-SIRNet利用多变量变分模态分解（Multivariate Variational mode Decomposition， MVMD）将空间多通道脑电数据分解为四组固有模态函数（IMFs）。为了突出图像的主要特征，利用同步压缩小波变换（SSWT）提取高精度时频特征后，对图像进行汇总，并将其转换为时频表示（TFR）图像。TFR图像被输入到调谐cnn模型中。MD-SIRNet在两个公开可用的EEG数据集上进行了验证，并与五种方法进行了准确率比较。MD-SIRNet对长词、长短词、短词、元音和命令词的准确率分别提高了2.23%、0.45%、1.59%、4.45%和5.56%。代码和模型可在https://github.com/buptantEEG/MD-SIRNet上获得。

{"title":"MD-SIRNet: Multi-domain representations for EEG-based speech imagery recognition with deep learning","authors":"Liang Dong , Hengyi Shao , Zhejun Zhang , Yingqi Zhu , Shaoting Guo , Lin Zhang , Lei Li","doi":"10.1016/j.bspc.2026.109817","DOIUrl":"10.1016/j.bspc.2026.109817","url":null,"abstract":"<div><div>Speech imagery (SI) recognition from Electroencephalography (EEG), enhances the foundation of the brain-computer interface (BCI). Although some existing research has been proposed to solve the high variability and low signal-to-noise ratio of multi-channel EEG signals, the spatial–temporal-frequency information is still underutilized to improve the performance of SI recognition. We propose MD-SIRNet to obtain multi-domain features efficiently and precisely. MD-SIRNet decomposes spatial multi-channel EEG data into four sets of intrinsic mode functions (IMFs) using Multivariate Variational Mode Decomposition (MVMD). To emphasize the main features, the IMFs are summed and then transformed into time–frequency representation (TFR) images after extracting high-precision time–frequency features using the Synchrosqueezed Wavelet Transform (SSWT). TFR images are fed into the Tuned-CNN model. MD-SIRNet is validated on two publicly available EEG datasets, compared with five methods by accuracy. The results of MD-SIRNet achieve an accuracy improvement of 2.23%, 0.45%, 1.59%, 4.45%, and 5.56% for long words, long-short words, short words, vowels, and command words. The code and model are available at <span><span>https://github.com/buptantEEG/MD-SIRNet</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109817"},"PeriodicalIF":4.9,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192797","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

Refined myocardium segmentation from CT using a Hybrid-Fusion transformer 利用Hybrid-Fusion变压器对CT进行精细心肌分割

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-11 DOI: 10.1016/j.bspc.2026.109712

Shihua Qin , Fangxu Xing , Jihoon Cho , Jinah Park , Xiaofeng Liu , Amir Rouhollahi , Elias J. Bou Farhat , Hoda Javadikasgari , Ashraf Sabe , Farhad R. Nezami , Jonghye Woo , Iman Aganj

Accurate segmentation of the left ventricle (LV) in cardiac CT images is crucial for assessing ventricular function and diagnosing cardiovascular diseases. Creating a sufficiently large training set with accurate manual labels of LV can be cumbersome. More efficient semi-automatic segmentation, however, often includes unwanted structures, such as papillary muscles, due to low contrast between the LV wall and surrounding tissues. This study introduces a two-input-channel method within a Hybrid-Fusion Transformer deep-learning framework to produce refined LV labels from a combination of CT images and semi-automatic rough labels, effectively removing papillary muscles. By leveraging the efficiency of semi-automatic LV segmentation, we train an automatic refined segmentation model on a small set of images with both refined manual and rough semi-automatic labels. Evaluated through quantitative cross-validation, our method outperformed models that used only either CT images or rough masks as input.

心脏CT图像中左心室（LV）的准确分割对于评估心室功能和诊断心血管疾病至关重要。创建一个足够大的训练集并使用准确的LV手动标签是很麻烦的。然而，由于左室壁和周围组织的对比度较低，更有效的半自动分割通常包括不需要的结构，如乳头肌。本研究在Hybrid-Fusion Transformer深度学习框架中引入了一种双输入通道方法，从CT图像和半自动粗糙标记的组合中生成精细的LV标记，有效地去除乳头状肌肉。利用半自动LV分割的效率，我们在一小组图像上训练了一个自动精细分割模型，其中包括精细的手动和粗糙的半自动标签。通过定量交叉验证评估，我们的方法优于仅使用CT图像或粗糙掩模作为输入的模型。

{"title":"Refined myocardium segmentation from CT using a Hybrid-Fusion transformer","authors":"Shihua Qin , Fangxu Xing , Jihoon Cho , Jinah Park , Xiaofeng Liu , Amir Rouhollahi , Elias J. Bou Farhat , Hoda Javadikasgari , Ashraf Sabe , Farhad R. Nezami , Jonghye Woo , Iman Aganj","doi":"10.1016/j.bspc.2026.109712","DOIUrl":"10.1016/j.bspc.2026.109712","url":null,"abstract":"<div><div>Accurate segmentation of the left ventricle (LV) in cardiac CT images is crucial for assessing ventricular function and diagnosing cardiovascular diseases. Creating a sufficiently large training set with accurate manual labels of LV can be cumbersome. More efficient semi-automatic segmentation, however, often includes unwanted structures, such as papillary muscles, due to low contrast between the LV wall and surrounding tissues. This study introduces a two-input-channel method within a Hybrid-Fusion Transformer deep-learning framework to produce refined LV labels from a combination of CT images and semi-automatic rough labels, effectively removing papillary muscles. By leveraging the efficiency of semi-automatic LV segmentation, we train an automatic refined segmentation model on a small set of images with both refined manual and rough semi-automatic labels. Evaluated through quantitative cross-validation, our method outperformed models that used only either CT images or rough masks as input.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109712"},"PeriodicalIF":4.9,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192795","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

Component-wise score diffusion model with momentum-accelerated updates for low-dose CT reconstruction 基于动量加速更新的低剂量CT重建成分评分扩散模型

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-11 DOI: 10.1016/j.bspc.2026.109765

Dalin Wang , Xuemei Wu , Chao He

Low-dose CT reconstruction remains challenging because dose reduction amplifies noise and streak artifacts, while strong priors risk removing subtle anatomical details. Score-based diffusion models provide a flexible way to model CT image distributions, yet pixel-domain diffusion couples low-frequency structure and high-frequency texture within a single score function and the sampling process can be slow when data consistency is enforced with generic updates. We present a component-wise score diffusion model that performs diffusion on wavelet subbands and interleaves reverse sampling with a momentum-accelerated OS-SART projection step. This design decouples structural and textural priors in the wavelet domain and enforces projection fidelity throughout sampling. Experiments on the AAPM-Mayo dataset show consistent improvements over competitive baselines in both low-dose full-view and sparse-view settings, achieving 41.03 dB PSNR and 0.965 SSIM at 10 percent dose and 39.26 dB PSNR at 96 views while reducing inference time relative to other score-based methods.

低剂量CT重建仍然具有挑战性，因为剂量降低会放大噪声和条纹伪影，而强先验可能会去除细微的解剖细节。基于分数的扩散模型提供了一种灵活的方法来模拟CT图像分布，然而像素域扩散在单个分数函数中耦合了低频结构和高频纹理，并且当使用通用更新强制数据一致性时，采样过程可能很慢。我们提出了一种基于分量的分数扩散模型，该模型在小波子带上进行扩散，并通过动量加速的OS-SART投影步骤交织反向采样。该设计解耦了小波域的结构和纹理先验，并在整个采样过程中增强了投影保真度。在AAPM-Mayo数据集上的实验表明，在低剂量全视图和稀疏视图设置下，与竞争基线相比，该方法在低剂量全视图和稀疏视图设置下均有一致的改进，在10%剂量下达到41.03 dB PSNR和0.965 SSIM，在96视图下达到39.26 dB PSNR，同时相对于其他基于分数的方法减少了推理时间。

引用次数: 0

Attention-assisted ensemble CNN–MobileNetV2–transformer architecture for automated TB diagnosis 用于自动结核病诊断的注意力辅助集成CNN-MobileNetV2-transformer架构

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-11 DOI: 10.1016/j.bspc.2026.109778

Beaulah Jeyavathana R , Kalaivani Chellappan , M. Sai Ganeshan

Tuberculosis (TB) is considered an airborne disease, causing a high death rate globally by affecting the lungs. The early detection of TB remains a challenge owing to the lack of screening facilities. The availability of public datasets, the advancement of artificial intelligence (AI), computerized systems have enabled the automatic diagnosis of tuberculosis using chest X-rays. The existing AI algorithms utilize complicated architectures; therefore, the procedure is time-consuming and costly. To overcome these limitations, Research proposes a novel lightweight ensemble deep learning (DL) model for detecting and localizing TB from Chest X-Ray (CXR) images. The proposed research gathered the CXR images from the Kaggle repository. The images are standardized before being input to the DL models to ensure enhanced learning and stability. Further, make the image dimensions suited for DL models, the images are resized. The lung regions are segmented from the pre-processed images using a spatial attention based residual U-net model (SA-Res-UNet) to ensure accurate detection of TB. Finally, the CXR images are classified as normal and TB using the ensemble model. The proposed model has an ensemble of custom convolutional neural network (CNN), MobileNetV2, and Swin Transformer (ST) models. Individual model predictions are combined based on majority voting. Finally, the classified images are explained and interpreted by providing visualization through self-attention-based class activation mapping (SA-CAM). The experiments are conducted in the Python programming language. The proposed model attained 99% accuracy in detecting TB disease. The proposed model’s exceptional results demonstrate its efficacy in TB detection, allowing for practical application.

结核病被认为是一种空气传播疾病，通过影响肺部在全球造成高死亡率。由于缺乏筛查设施，结核病的早期发现仍然是一项挑战。公共数据集的可用性、人工智能（AI）的进步和计算机化系统使利用胸部x光自动诊断结核病成为可能。现有的人工智能算法使用复杂的架构；因此，这个过程既耗时又昂贵。为了克服这些限制，研究人员提出了一种新的轻量级集成深度学习（DL）模型，用于从胸部x射线（CXR）图像中检测和定位结核病。拟议的研究从Kaggle存储库中收集了CXR图像。图像在输入到DL模型之前经过标准化处理，以确保增强的学习性和稳定性。此外，使图像尺寸适合深度学习模型，图像被调整大小。使用基于空间注意的残差U-net模型（SA-Res-UNet）从预处理图像中分割肺区域，以确保准确检测结核病。最后，使用集成模型将CXR图像分类为normal和TB。该模型集成了自定义卷积神经网络（CNN）、MobileNetV2和Swin Transformer （ST）模型。单个模型的预测是基于多数投票组合的。最后，通过基于自我注意的类激活映射（SA-CAM）提供可视化来解释和解释分类图像。实验是用Python编程语言进行的。该模型检测结核病的准确率达到99%。该模型的优异结果证明了其在结核病检测中的有效性，为实际应用提供了可能。

{"title":"Attention-assisted ensemble CNN–MobileNetV2–transformer architecture for automated TB diagnosis","authors":"Beaulah Jeyavathana R , Kalaivani Chellappan , M. Sai Ganeshan","doi":"10.1016/j.bspc.2026.109778","DOIUrl":"10.1016/j.bspc.2026.109778","url":null,"abstract":"<div><div>Tuberculosis (TB) is considered an airborne disease, causing a high death rate globally by affecting the lungs. The early detection of TB remains a challenge owing to the lack of screening facilities. The availability of public datasets, the advancement of artificial intelligence (AI), computerized systems have enabled the automatic diagnosis of tuberculosis using chest X-rays. The existing AI algorithms utilize complicated architectures; therefore, the procedure is time-consuming and costly. To overcome these limitations, Research proposes a novel lightweight ensemble deep learning (DL) model for detecting and localizing TB from Chest X-Ray (CXR) images. The proposed research gathered the CXR images from the Kaggle repository. The images are standardized before being input to the DL models to ensure enhanced learning and stability. Further, make the image dimensions suited for DL models, the images are resized. The lung regions are segmented from the pre-processed images using a spatial attention based residual U-net model (SA-Res-UNet) to ensure accurate detection of TB. Finally, the CXR images are classified as normal and TB using the ensemble model. The proposed model has an ensemble of custom convolutional neural network (CNN), MobileNetV2, and Swin Transformer (ST) models. Individual model predictions are combined based on majority voting. Finally, the classified images are explained and interpreted by providing visualization through self-attention-based class activation mapping (SA-CAM). The experiments are conducted in the Python programming language. The proposed model attained 99% accuracy in detecting TB disease. The proposed model’s exceptional results demonstrate its efficacy in TB detection, allowing for practical application.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109778"},"PeriodicalIF":4.9,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192857","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

DS-Mamba: Dynamic snake visual state space model for vessel segmentation DS-Mamba：用于血管分割的动态蛇形视觉状态空间模型

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-11 DOI: 10.1016/j.bspc.2026.109783

Zixuan Liu , Yao Cheng , Zhaoqin Huang , Wanqiang Cai , Kidiyo Kpalma , Dengwang Li , Hua Lu

Accurately segmenting vascular networks holds significant clinical implications for disease diagnosis and analysis. However, the intrinsically elongated, serpentine, and multi-scale nature of these structures poses a significant challenge, with existing methods often struggling to preserve both global connectivity and local morphological fidelity. To address this challenge, we propose a novel deep-learning architecture, termed Dynamic Snake Mamba (DS-Mamba), inspired by the sinuous morphology of vessels. DS-Mamba first leverages a Mamba backbone, composed of Residual Visual State Space (ResVSS) blocks, to establish a topologically coherent global representation of the vascular network. Subsequently, Dynamic Snake Convolutions (DSC) are strategically embedded to enhance the feature extraction of local serpentine details. To further improve its capabilities, the architecture incorporates three key components: (1) a Multi-scale Information Mamba Fusion (MIMF) mechanism that aggregates features from all encoder stages; (2) a Snake Tokenized Kolmogorov-Arnold Network (STK) at the bottleneck to manage complex feature interactions; and (3) Global–Local Information Fusion (GLIF) blocks that merge the global context with serpentine details. The efficacy of DS-Mamba was validated through comprehensive experiments on eight diverse tubular structure datasets. Results demonstrate that our approach not only achieves state-of-the-art performance in connectivity and morphological fidelity but also exhibits superior accuracy in segmenting thin, low-contrast vessels and robust resilience against high-intensity image noise. Furthermore, rigorous capacity-controlled ablation studies confirm that the performance gains stem from the synergistic architectural design rather than parameter scaling. Finally, inference speed analysis verifies the model’s feasibility for real-time clinical applications.

准确分割血管网络对疾病的诊断和分析具有重要的临床意义。然而，这些结构固有的细长、蛇形和多尺度性质带来了重大挑战，现有的方法往往难以保持全局连通性和局部形态保真度。为了解决这一挑战，我们提出了一种新的深度学习架构，称为动态蛇曼巴（DS-Mamba），灵感来自血管的弯曲形态。DS-Mamba首先利用由残余视觉状态空间（ResVSS）块组成的曼巴主干来建立血管网络的拓扑一致的全局表示。随后，策略性地嵌入动态蛇形卷积（DSC）来增强局部蛇形细节的特征提取。为了进一步提高其功能，该架构包含三个关键组件：(1)多尺度信息曼巴融合（MIMF）机制，该机制聚合了所有编码器阶段的功能；(2)在瓶颈处使用蛇形token化Kolmogorov-Arnold网络（STK）来管理复杂的特征交互；(3)全局-局部信息融合（GLIF）块，将全局上下文与蛇形细节合并。通过8个不同管状结构数据集的综合实验，验证了DS-Mamba的有效性。结果表明，我们的方法不仅在连通性和形态保真度方面实现了最先进的性能，而且在分割薄、低对比度血管方面表现出卓越的准确性，并且对高强度图像噪声具有强大的恢复能力。此外，严格的容量控制消融研究证实，性能的提高源于协同的建筑设计，而不是参数缩放。最后，通过推理速度分析验证了该模型在实时临床应用中的可行性。

{"title":"DS-Mamba: Dynamic snake visual state space model for vessel segmentation","authors":"Zixuan Liu , Yao Cheng , Zhaoqin Huang , Wanqiang Cai , Kidiyo Kpalma , Dengwang Li , Hua Lu","doi":"10.1016/j.bspc.2026.109783","DOIUrl":"10.1016/j.bspc.2026.109783","url":null,"abstract":"<div><div>Accurately segmenting vascular networks holds significant clinical implications for disease diagnosis and analysis. However, the intrinsically elongated, serpentine, and multi-scale nature of these structures poses a significant challenge, with existing methods often struggling to preserve both global connectivity and local morphological fidelity. To address this challenge, we propose a novel deep-learning architecture, termed Dynamic Snake Mamba (DS-Mamba), inspired by the sinuous morphology of vessels. DS-Mamba first leverages a Mamba backbone, composed of Residual Visual State Space (ResVSS) blocks, to establish a topologically coherent global representation of the vascular network. Subsequently, Dynamic Snake Convolutions (DSC) are strategically embedded to enhance the feature extraction of local serpentine details. To further improve its capabilities, the architecture incorporates three key components: (1) a Multi-scale Information Mamba Fusion (MIMF) mechanism that aggregates features from all encoder stages; (2) a Snake Tokenized Kolmogorov-Arnold Network (STK) at the bottleneck to manage complex feature interactions; and (3) Global–Local Information Fusion (GLIF) blocks that merge the global context with serpentine details. The efficacy of DS-Mamba was validated through comprehensive experiments on eight diverse tubular structure datasets. Results demonstrate that our approach not only achieves state-of-the-art performance in connectivity and morphological fidelity but also exhibits superior accuracy in segmenting thin, low-contrast vessels and robust resilience against high-intensity image noise. Furthermore, rigorous capacity-controlled ablation studies confirm that the performance gains stem from the synergistic architectural design rather than parameter scaling. Finally, inference speed analysis verifies the model’s feasibility for real-time clinical applications.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109783"},"PeriodicalIF":4.9,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192774","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 novel diagnosis framework of melanoma skin cancer using adaptive and attention-based deep network with mamba-efficient-UNet-aided abnormality segmentation 基于mamba-efficient- unet辅助异常分割的适应性和基于注意力的深度网络的黑色素瘤皮肤癌诊断新框架

IF 4.9 2区医学 Q1 ENGINEERING, BIOMEDICAL

Biomedical Signal Processing and Control

Pub Date : 2026-02-11 DOI: 10.1016/j.bspc.2026.109751

R. Lakshmi , B. Arthi

Melanoma is one of the most harmful dermatologic cancers worldwide. Recently, medical sector has undergone a significant evolution through the utilization of automatic detection frameworks that assist medical professionals for identifying cancer tissues growth more precisely. However, machine learning approaches struggle to present accurate diagnosis results because of their inability to determine the visual similarity among the malignant as well as benign tissues. Addressing this limitation, involves deep learning techniques in medical sector, due to their competence in detection tasks. However, imbalanced databases and image occlusion negatively impacted the accuracy of the detection model. Thus, a promising diagnosis framework is designed for melanoma skin cancer. Initially, required images were aggregated from available datasets. Furthermore, input images were subjected into Mamba-Efficient-UNet (MEUNet) for segmenting abnormalities. Segmented images were fed into Adaptive and Attention-based Efficient Net B7 with Long Short Term Memory (AAENB7-LSTM) layer for diagnosing melanoma skin cancer. Here, the AAENB7-LSTM parameters are tuned by Modified Random Variable-based Dollmaker Optimization Algorithm (MRV-DOA). Lastly, efficiency assessment of developed model is carried out by analyzing with other related techniques to showcase its effectiveness in melanoma skin cancer. The findings of recommended method attain 98.1% in terms of F1-score on dataset 1 with batch size 32. In addition, efficiency of suggested network is analyzed with existing classifiers to demonstrate 98.2% for precision with batch size 8 on dataset 2 than other existing CNN, MFEUsLNet, Grand-CAM, and AENB7-LSTM model.

黑色素瘤是世界上最有害的皮肤癌症之一。最近，医疗部门通过利用自动检测框架，帮助医疗专业人员更准确地识别癌症组织的生长，经历了重大的演变。然而，机器学习方法难以提供准确的诊断结果，因为它们无法确定恶性组织和良性组织之间的视觉相似性。解决这一限制涉及医疗部门的深度学习技术，因为它们在检测任务中的能力。然而，数据库不平衡和图像遮挡对检测模型的准确性产生了负面影响。因此，为黑色素瘤皮肤癌设计了一个有希望的诊断框架。最初，从可用的数据集中聚合所需的图像。此外，对输入图像进行Mamba-Efficient-UNet （MEUNet）分割异常。将分割后的图像输入到具有长短期记忆的Adaptive and Attention-based Efficient Net B7 （AAENB7-LSTM）层，用于黑色素瘤皮肤癌的诊断。在这里，AAENB7-LSTM参数通过基于改进随机变量的模型优化算法（MRV-DOA）进行调整。最后，通过与其他相关技术的分析，对所开发的模型进行有效性评估，展示其在黑色素瘤皮肤癌中的有效性。推荐的方法在批大小为32的数据集1上的f1得分达到98.1%。此外，使用现有的分类器对所建议网络的效率进行了分析，在数据集2上，批大小为8的网络的准确率比其他现有的CNN、MFEUsLNet、grande - cam和AENB7-LSTM模型高98.2%。

{"title":"A novel diagnosis framework of melanoma skin cancer using adaptive and attention-based deep network with mamba-efficient-UNet-aided abnormality segmentation","authors":"R. Lakshmi , B. Arthi","doi":"10.1016/j.bspc.2026.109751","DOIUrl":"10.1016/j.bspc.2026.109751","url":null,"abstract":"<div><div>Melanoma is one of the most harmful dermatologic cancers worldwide. Recently, medical sector has undergone a significant evolution through the utilization of automatic detection frameworks that assist medical professionals for identifying cancer tissues growth more precisely. However, machine learning approaches struggle to present accurate diagnosis results because of their inability to determine the visual similarity among the malignant as well as benign tissues. Addressing this limitation, involves deep learning techniques in medical sector, due to their competence in detection tasks. However, imbalanced databases and image occlusion negatively impacted the accuracy of the detection model. Thus, a promising diagnosis framework is designed for melanoma skin cancer. Initially, required images were aggregated from available datasets. Furthermore, input images were subjected into Mamba-Efficient-UNet (MEUNet) for segmenting abnormalities. Segmented images were fed into Adaptive and Attention-based Efficient Net B7 with Long Short Term Memory (AAENB7-LSTM) layer for diagnosing melanoma skin cancer. Here, the AAENB7-LSTM parameters are tuned by Modified Random Variable-based Dollmaker Optimization Algorithm (MRV-DOA). Lastly, efficiency assessment of developed model is carried out by analyzing with other related techniques to showcase its effectiveness in melanoma skin cancer. The findings of recommended method attain 98.1% in terms of F1-score on dataset 1 with batch size 32. In addition, efficiency of suggested network is analyzed with existing classifiers to demonstrate 98.2% for precision with batch size 8 on dataset 2 than other existing CNN, MFEUsLNet, Grand-CAM, and AENB7-LSTM model.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109751"},"PeriodicalIF":4.9,"publicationDate":"2026-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192792","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