Biomedical Signal Processing and Control最新文献

{"title":"CSA-Net: A lightweight channel split attention network with residual feature fusion for retinal vessel segmentation","authors":"MinShan Jiang,&nbsp;Hongkai Liu,&nbsp;Shuai Huang,&nbsp;Jihui Mao,&nbsp;Yongfei Zhu,&nbsp;Xuedian Zhang","doi":"10.1016/j.bspc.2026.109834","DOIUrl":"10.1016/j.bspc.2026.109834","url":null,"abstract":"<div><div>Automatic retinal vessel segmentation is vital for clinical assessment and therapeutic intervention. Extracting global and local features from fundus images remains a significant challenge for current methods. To address this, we propose a lightweight channel split attention network (CSA-Net), which integrates channel split attention and residual feature fusion, and can effectively capture global context information and fine-grained vascular details. In our model, we first suggest a channel split attention (CSA) module to facilitate multiscale feature aggregation and acquisition of global information. Then, we introduce a residual feature fusion (RFF) module to reduce information loss by incorporating residuals and enhancing feature maps during the multiscale fusion process. In addition, we setup a lightweight design using adaptive inverted residual encoders with varied kernel sizes to increase the computational efficiency. Five publicly available fundus datasets (DRIVE, CHASEDB1, STARE, HRF, LES-AV) were used to test our model. Experimental results demonstrate that CSA-Net achieves state-of-the-art performance, with ACC values up to 0.9830 and AUC values of 0.9948 with only 2.39 M parameters. Ablation studies validate the effectiveness of individual modules. The proposed CSA-Net achieves a good balance between segmentation accuracy and model complexity. In multiple retinal vascular segmentation benchmark tests, it achieves competitive or better performance with fewer parameters.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109834"},"PeriodicalIF":4.9,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192613","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}

{"title":"Dynamic regulation of brain network and muscle activity in upper limb force generation among older adults: A temporal dynamic graph Fourier transform approach","authors":"Mingxia Zhang ,&nbsp;Huijing Hu ,&nbsp;Di Ao ,&nbsp;Li Yan ,&nbsp;Qinghua Huang ,&nbsp;Zhengxiang Zhang ,&nbsp;Le Li","doi":"10.1016/j.bspc.2026.109829","DOIUrl":"10.1016/j.bspc.2026.109829","url":null,"abstract":"<div><div>This study investigates the neural mechanisms underlying age-related declines in motor control by proposing a novel Temporal Dynamic Graph Fourier Transform (TDGFT) method. TDGFT integrates graph signal processing with dynamic brain networks analysis to characterize time-varying corticomuscular interactions in the spectral domain, thereby linking global and local brain connectivity patterns to motor behavior. Integrating functional near-infrared spectroscopy (fNIRS) and electromyography (EMG), we systematically examine the dynamic regulation of brain network and muscle activity in older adults and younger adults during elbow flexion tasks at 30% and 70% of maximum voluntary contraction (MVC). Sixteen older adults and sixteen younger adults are recruited for the study. Our findings reveal that older adults exhibit weaker dynamic regulation of brain regions during high-load tasks, accompanied by significantly increased constraints of structural brain networks on functional activity, reflecting a decline in cognitive control. Additionally, older adults rely on multi-regional brain coordination for motor control during low-intensity tasks, while reducing cognitive load to enhance motor efficiency during high-intensity tasks. By providing an interpretable spectral representation of corticomuscular dynamics, TDGFT advances the understanding of how aging reshapes motor-related brain connectivity. These findings may help identify changes of age-related motor decline and facilitate the design of individualized motor rehabilitation strategies for older adults.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109829"},"PeriodicalIF":4.9,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192617","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}

{"title":"SEDP-SegResnet for human eyeball and lens segmentation","authors":"Li Ning ,&nbsp;Yepei Qin ,&nbsp;Wendong Zhao ,&nbsp;Yangjiarui Yu ,&nbsp;Qingcheng Yang ,&nbsp;Chenxi Guo ,&nbsp;Xuedian Zhang ,&nbsp;Hui Chen ,&nbsp;Yinghong Ji ,&nbsp;Pei Ma","doi":"10.1016/j.bspc.2026.109838","DOIUrl":"10.1016/j.bspc.2026.109838","url":null,"abstract":"<div><div>Accurate segmentation and quantification of the eyeball and lens from MRI images are crucial for clinical diagnosis and treatment planning of ocular diseases. Traditional methods for analyzing eye structures in MRI have drawbacks including low segmentation accuracy and reliance on laborious, time-consuming manual processes. To solve these problems, we propose a SEDP-SegResnet model for segmentation of the eyeball and lens structures from 3D MRI images. The framework takes SegResnet as its backbone network and incorporates a 3D-SE layer to handle deep features from decoder, 3D-SE layer assigns different weight information to the feature map channels through squeeze and excitation mechanism. Moreover, skip connections in the U-shaped architecture model are replaced with Dynamic Deep Feature Prefusion (DDFP) modules. The DDFP can achieve in-depth fusion of encoder and decoder features based on global information, thereby enhancing 3D image context comprehension of the model. The performance of SEDP-SegResnet is evaluated through a series of experiments using a proprietary dataset of orbital MRI scans. The results show that SEDP-SegResnet outperforms current mainstream 3D deep-learning-based segmentation models across multiple evaluation metrics including the Dice Similarity Coefficient (DSC) and Intersection over Union (IoU). The model achieves robust performances in segmenting margin of eyeballs and blur-edge lenses. SEDP-SegResnet achieves a DSC of 96.81% for eyeball segmentation and 90.57% for lens segmentation, superior than a variety of commonly used segmentation models. It provides a more accurate, automated and robust method for the segmentation and quantification of eyeball and lens in MRI, offering an advanced computer-aided diagnosis tool.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109838"},"PeriodicalIF":4.9,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192610","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}

{"title":"An enhanced deep learning model for breast cancer histopathological grading based on Selective Kernel network","authors":"Yuandi Sun","doi":"10.1016/j.bspc.2026.109833","DOIUrl":"10.1016/j.bspc.2026.109833","url":null,"abstract":"&lt;div&gt;&lt;h3&gt;Background&lt;/h3&gt;&lt;div&gt;Breast cancer is one of the most common malignant tumors in women worldwide. Its early detection and accurate grading are crucial for developing individualized treatment plans and improving patient prognosis. Pathological image grading is a key step in breast cancer diagnosis, but due to the high heterogeneity of tumor cell and tissue morphology, traditional manual image reading methods have subjective bias and low efficiency. Therefore, developing an automated and accurate breast cancer pathological image grading model has important clinical value for improving diagnostic efficiency and accuracy.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Methods&lt;/h3&gt;&lt;div&gt;This study proposed a deep learning model based on the combination of DenseNet and Selective Kernel Block (SKBlock) − SKDenseNet for the automatic grading of breast cancer pathology images. DenseNet enhances feature reuse and gradient propagation efficiency through dense connection mechanism, while SKBlock realizes dynamic extraction and fusion of pathological features of different scales through multi-scale convolution operation and channel attention mechanism. The model was trained on the TCGA dataset and independently tested on the CHTN dataset to evaluate the generalization ability and stability of the model in cross-center tasks. The model parameters were optimized, and the classification performance was evaluated by accuracy (ACC), precision (PRE), recall (REC) and F1 score (F1), and the discriminability and interpretability of the model were analyzed by confusion matrix and activation heat map .&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Results&lt;/h3&gt;&lt;div&gt;The experimental results on the test set (CHTN dataset) showed that SKDenseNet significantly outperformed the baseline model in all key classification indicators. The average accuracy of SKDenseNet was 86.58%, the average precision was 87.91%, the average recall was 87.97%, and the F1 score was 86.71%, which were 7.84, 3.18, 6.24, and 7.32 percentage points higher than DenseNet121, respectively. The confusion matrix showed that SKDenseNet showed good discrimination and stability in the classification tasks of high- and low-grade breast cancer and stromal tissue. In addition, SKDenseNet also has the highest AUC, reaching 0.9693. The activation heat map generated by Grad-CAM further verified that the key areas of the model’s attention in the pathological images were highly consistent with the actual pathological features (such as nuclear morphology and glandular duct structure), which enhanced the interpretability of the model.&lt;/div&gt;&lt;/div&gt;&lt;div&gt;&lt;h3&gt;Conclusion&lt;/h3&gt;&lt;div&gt;SKDenseNet model proposed in this study combines the global feature expression ability of DenseNet with the dynamic receptive field adjustment mechanism of SKBlock, and shows excellent classification performance and cross-center adaptability in the task of breast cancer pathology image grading . The model can reduce the misdiagnosis rate and missed diagnosis rate while maintaining high accurac","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109833"},"PeriodicalIF":4.9,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192615","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}

{"title":"RePrediction of chemical characteristics of individuals with HIV infection using an image processing-centric optimized deep learning-based CNN model","authors":"Yusuf Alaca ,&nbsp;Nursel Karaoğlan ,&nbsp;Erdal Başaran ,&nbsp;Yüksel Çelik","doi":"10.1016/j.bspc.2026.109816","DOIUrl":"10.1016/j.bspc.2026.109816","url":null,"abstract":"<div><div>Accurate prediction of HIV-related chemical properties is of critical importance for computational drug discovery and bioinformatics applications. In this study, an image processing–centric deep learning framework is proposed to predict HIV chemical activity using molecular images automatically generated from SMILES representations. Multi-scale deep features are extracted using two complementary convolutional neural network architectures, namely Xception and ResNet50, and subsequently fused to capture both low-level structural patterns and high-level molecular representations. The main novelty of this work lies in the integration of CNN-based molecular image feature extraction with the Manta Ray Foraging Optimization (MRFO) algorithm. The MRFO algorithm is employed to perform optimization-driven feature selection and classifier hyperparameter tuning, aiming to improve both predictive accuracy and generalization capability. The optimized feature set is finally classified using a support vector machine (SVM), enabling robust discrimination between active and inactive HIV-related compounds. Experimental evaluations conducted on the benchmark HIV SMILES dataset demonstrate that the proposed framework achieves superior and stable performance, reaching an accuracy of 81.16% and a ROC-AUC of 0.87, outperforming several state-of-the-art machine learning and deep learning approaches reported in the literature. These results confirm that combining molecular image representations with optimization-guided deep learning provides an effective and reliable strategy for HIV chemical property prediction.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109816"},"PeriodicalIF":4.9,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192616","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}

{"title":"Ensemble-MIL: deep learning-based ensemble framework for biomarker prediction from histopathological images in colorectal cancer","authors":"Geng-Yun Tien ,&nbsp;Yu-Chia Chen ,&nbsp;Liang-Chuan Lai ,&nbsp;Tzu-Pin Lu ,&nbsp;Mong-Hsun Tsai ,&nbsp;Eric Y. Chuang ,&nbsp;Hsiang-Han Chen","doi":"10.1016/j.bspc.2026.109759","DOIUrl":"10.1016/j.bspc.2026.109759","url":null,"abstract":"<div><div>Recent studies have explored histopathological whole slide images (WSIs) for predicting colorectal cancer (CRC) biomarkers, aiming to create cost-effective and efficient diagnostic tools. However, achieving strong predictive performance and generalizability across datasets remains a challenge. Here, we introduce a deep learning-based ensemble framework, Ensemble-MIL, designed to robustly predict key CRC biomarkers, including BRAF V600E, KRAS mutations, and MSI-H status, with improved cross-dataset performance. We employed two independent CRC datasets: TCGA-COAD for model training and internal evaluation, and CPTAC-COAD as an external test set to assess generalizability. All WSIs were preprocessed and divided into small image patches. A tumor detection model was applied to identify tumor regions, and patch-level; features were extracted via SimCLR, a contrastive learning method. These features were utilized to train three multiple instance learning (MIL) models: Att-MIL, Tran-MIL, and GNN-MIL. The models were then integrated into the final Ensemble-MIL framework. In internal testing with TCGA-COAD, the proposed method achieved area under the curve (AUC) scores of 0.90, 0.87, and 0.64 for MSI-H, BRAF, and KRAS, respectively. In external testing on CPTAC-COAD, it achieved AUCs of 0.78, 0.76, and 0.61 for MSI-H, BRAF, and KRAS, respectively, outperforming previous results. This framework offers a scalable and effective solution for image-based biomarker screening and demonstrates strong potential for clinical application, particularly in resource-limited settings. The code is available at <span><span>https://github.com/chenh2lab/Ensemble-MIL</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109759"},"PeriodicalIF":4.9,"publicationDate":"2026-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192619","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}

{"title":"Assessing equivalence in raw accelerometer outputs across different brands using shaker table validation: a comparative analysis with filtering and linear regression techniques","authors":"Hannah J. Coyle-Asbil ,&nbsp;Bernadette Murphy ,&nbsp;Lori Ann Vallis","doi":"10.1016/j.bspc.2026.109627","DOIUrl":"10.1016/j.bspc.2026.109627","url":null,"abstract":"<div><div>This study had two major aims, first to determine whether the raw acceleration data from ActiGraph versus non-ActiGraph accelerometers were equivalent and, second to apply and compare different equivalency approaches: 1) linear regression, 2) lowpass 15 Hz, 3) lowpass 20 Hz, and 4) lowpass 30 Hz filters. ActiGraph GT3X+ (n = 8), ActiGraph wGT3X-BT (n = 10), ActiGraph GT9X (n = 8; primary and GT9X2), OPAL (n = 6) and GENEActiv (n = 5) accelerometers were affixed to a multi-axis shaker table and sinusoidal oscillations were introduced, spanning the entire dynamic range (±0.005 G to ± 8 G). The averages of the trials were compared according to the different techniques. Linear regression models were fitted to align the non-ActiGraph to the ActiGraph data, and lowpass filters were applied to the non-Actigraph data. Equivalency was assessed using two one sided t-tests of equivalence. The results indicated either statistically insignificant or negligible mean differences at the lower frequency oscillations, however at higher oscillations the recordings were significantly distinct and vastly varied across the different techniques. For example, the mean difference between the wGT3X-BT − GA at trial 28 unprocessed was −2788.09 m<em>g</em>, −394.93 m<em>g</em> for the linear regression, 1358.56 m<em>g</em> for the 15 Hz filter, and 182.94 m<em>g</em> for both the 20 Hz and 30 Hz filters. In conclusion, there are minor differences between ActiGraph and non-ActiGraph accelerometers at low frequencies; however, at high frequencies, 20 Hz low-pass filters are effective in improving equivalency. Our findings provide insight into device equivalency and important guidance for researchers to consider when harmonizing data across accelerometer devices.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109627"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146193094","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}

{"title":"PEEG-HAR: A novel pain-evoked EEG extraction method guided by the adaptive localization of high-activation-rate pain-related EEG sources","authors":"Wenjia Gao,&nbsp;Dan Liu,&nbsp;Qisong Wang,&nbsp;Yongping Zhao,&nbsp;Jinwei Sun","doi":"10.1016/j.bspc.2026.109725","DOIUrl":"10.1016/j.bspc.2026.109725","url":null,"abstract":"<div><div>Laser-evoked potentials (LEPs) are widely recognized as optimal for pain assessment, but raw EEG signals are often contaminated by noise and background activity, making LEPs extraction challenging. Existing wavelet-based methods construct templates using all trials. However, since LEPs exhibit variations across different pain intensities, the use of all trials may result in the loss of discriminative features essential for distinguishing between varying levels of pain intensity. In this study, EEG source signals are obtained using electrophysiological source imaging, and high-activation-rate pain-related EEG sources are identified based on their activation characteristics. A within-subject pain intensity model based on a support vector machine is then developed to link recorded EEG signals with historical EEG samples. The model guides the selection of suitable EEG segments to construct a pain-specific template, which is subsequently used to reconstruct the recorded EEG signals by exploiting the time–frequency distribution of pain-related wavelet coefficients, thereby facilitating more effective extraction of LEPs. Experiments on real EEG recordings confirm that the proposed method can extract signals that more closely reflect genuine pain-evoked EEG activity, thereby enhancing the representation of pain and significantly improving subsequent classification performance, with binary accuracy increasing from 59.61% to 81.13% and three-class accuracy from 39.22% to 64.23%. The method addresses the challenge of insufficient pain expression in raw signals and provides a data foundation for developing objective pain biomarkers.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109725"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192618","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}

{"title":"Enhancing deep learning reliability in MRI images of Alzheimer’s disease using pairwise probability differential reliability quantification","authors":"Junaidul Islam ,&nbsp;Isack Farady ,&nbsp;Chia-Chen Kuo ,&nbsp;Fu-Yu Lin ,&nbsp;Chih-Yang Lin","doi":"10.1016/j.bspc.2026.109717","DOIUrl":"10.1016/j.bspc.2026.109717","url":null,"abstract":"<div><div>In domains where safety is crucial, such as medical imaging, achieving a high degree of classification accuracy is inadequate unless it is complemented by predictions that are both reliable and interpretable. Traditional measures of uncertainty frequently yield global assessments that obscure localized fluctuations in model confidence, a factor that can be pivotal when differentiating between closely related clinical conditions. This paper presents Pairwise Probability Differential Reliability Quantification (PPDRQ), an innovative framework that assesses the reliability of predictions made by deep neural networks through the evaluation of pairwise discrepancies among class probability estimates. By incorporating PPDRQ into a custom loss function enhanced with a triplet loss to refine the feature space. The proposed approach incentivizes the network to generate outputs that are both more distinct and trustworthy. Comprehensive experiments conducted on MRI-based Alzheimer’s disease diagnosis indicate that models with PPDRQ exhibit enhanced reliability, improved interpretability, and superior performance, thereby offering significant insights for clinical decision-making.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109717"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192775","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}

{"title":"Medical image fusion for enhanced edge adaptive Level Set","authors":"Jiao Du ,&nbsp;Xiaoyu Yu ,&nbsp;Chengxin Su ,&nbsp;Qun Zhao","doi":"10.1016/j.bspc.2026.109525","DOIUrl":"10.1016/j.bspc.2026.109525","url":null,"abstract":"<div><div>Brain tumors are serious disease, and lesion areas detected by medical imaging typically exhibit distinct edge and contrast information. The aim of medical image fusion method is to synthesize multiple-image information. However, existing methods, while effective in preserving rich information, often struggle to enhance edge and contrast, resulting in artifacts or noise that influencing image quality. In this paper, the input images are first enhanced, and then, based on the model of level set segmentation, an additive bias correction (ABC) level set method is used to adaptively decompose the image into a base layer, a strong edge layer, and a weak edge layer. The sum of the eigenvalues of the covariance matrices (COV) in different directions is used to obtain the weight map for the strong edge layer, while the covariance matrix between image channels is utilized to evaluate the correlation among channels, thereby calculating the weight for fusing the weak edge layer. The experimental results demonstrate that the proposed method achieves an approximately 5% increase in the objective evaluation metrics of Standard Deviation (SD) and Visual Information Fidelity (VIF).To help doctors better observe the characteristics of the lesions.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"119 ","pages":"Article 109525"},"PeriodicalIF":4.9,"publicationDate":"2026-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192793","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}