Biomedical Signal Processing and Control最新文献

{"title":"Deep learning based retinal disease classification using an autoencoder and generative adversarial network","authors":"G. Jeyasri ,&nbsp;R. Karthiyayini","doi":"10.1016/j.bspc.2025.107852","DOIUrl":"10.1016/j.bspc.2025.107852","url":null,"abstract":"<div><div>Human eyesight relies heavily on retinal tissue, vision loss include infections of the retina and either a delay in treatment or the disease remaining untreated. Identifying retinopathy from retinal fundus image is a vital and diagnostic system performance depends on image quality and quantity. Furthermore, the diagnosis is prone to errors when a large imbalanced database is used. Hence, a fully automated retina disease prediction system is indispensable to minimize human intervention, increase the performance of the disease diagnostic system, and support ophthalmologists in conducting speedy and accurate investigations. Advancements in deep learning have remarkable results in identifying retinopathy from retinal fundus images. However, conventional deep-learning approaches struggle to learn enough in-depth features to identify aspects of mild retinal disease. To address this, integrates a deep autoencoder-based diagnostic system with a ResNet-based generative adversarial network (RGAN) to find retinal disease. This integrated model exploits a ResNet-50 structure to generate synthetic images to handle higher FAR and class imbalance-related problems and a deep autoencoder to categorize the retinal fundus pictures into benign and malicious. The proposed RGAN engenders synthetic images to train the diagnostic and real systems. The experimental outcomes have been implemented, and the recommended RGAN model increases the accuracy ratio of 95.6%, sensitivity ratio of 96.4%, specificity ratio of 97.3%, and F1-score ratio of 93.4% compared to other popular techniques.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107852"},"PeriodicalIF":4.9,"publicationDate":"2025-04-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143817354","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":"Structural semantic enhancement network for low-dose CT denoising","authors":"Jinwen He ,&nbsp;Jiehang Deng ,&nbsp;Zihang Hu ,&nbsp;Guosheng Gu ,&nbsp;Guoqing Qiao","doi":"10.1016/j.bspc.2025.107870","DOIUrl":"10.1016/j.bspc.2025.107870","url":null,"abstract":"<div><div>Most research on low-dose computed tomography primarily focuses on maximizing noise reduction, often at the expense of image structure and texture details. In this paper, we propose a Structural Semantic Enhancement Network (SSEN) that emphasizes the extraction and preservation of structural semantic features at different stages of the denoising process to enhance image sharpness. Specifically, unlike conventional methods that utilize a 3 × 3 Sobel operator for edge feature extraction, our approach employs a 5 × 5 Sobel operator with dense connections, preserving<!--> <!-->richer low-level semantics. Unlike conventional coordinate attention, which relies on 1 × 1 convolutional layers for feature activation, our approach employs 1 × 5 (or 5 × 1) asymmetric convolutional layers to expand the receptive field and capture richer global attention and contextual information. Furthermore, rather than commonly employed mean squared error loss functions, we propose a compound loss function that combines <em>L</em>₁ loss, multi-scale structural similarity index measure loss, and multi-scale perceptual loss, effectively recovering structural and perceptual features. This study indicates that the proposed method can effectively extract and utilize the structural semantic features to retain more image structure and texture details. In the experiments on the AAPM-Mayo Clinic LDCT Grand Challenge dataset, SSEN achieved a SSIM of 0.9193 and a PSNR of 33.6191, outperforming the comparison methods in terms of image quality restoration and structural information recovery.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107870"},"PeriodicalIF":4.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808293","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":"Prediction of weaning failure using time-frequency analysis of electrocardiographic and respiration flow signals","authors":"Hernando González Acevedo ,&nbsp;José Luis Rodríguez-Sotelo ,&nbsp;Carlos Arizmendi ,&nbsp;Beatriz F. Giraldo","doi":"10.1016/j.bspc.2025.107872","DOIUrl":"10.1016/j.bspc.2025.107872","url":null,"abstract":"<div><div>Acute respiratory distress syndrome often necessitates prolonged periods of mechanical ventilation for patient management. Therefore, it is crucial to make appropriate decisions regarding extubation to prevent potential harm to patients and avoid the associated risks of reintubation and extubation cycles. One atypical form of acute respiratory distress syndrome is associated with COVID-19, impacting patients admitted to the intensive care unit. This study presents the design of two classifiers: the first employs machine learning techniques, while the second utilizes a convolutional neural network. Their purpose is to assess whether a patient can safely be disconnected from a mechanical ventilator following a spontaneous breathing test. The machine learning algorithm uses descriptors derived from the variability of time-frequency representations computed with the non-uniform fast Fourier transform. These representations are applied to time series data, which consist of markers extracted from the electrocardiographic and respiratory flow signals sourced from the Weandb database. The input image for the convolutional neural network is formed by combining the spectrum of the RR signal and the spectrum of two parameters recorded from the respiratory flow signal, calculated using non-uniform fast Fourier transform. Three pre-trained network architectures are analyzed: Googlenet, Alexnet and Resnet-18. The best model is obtained with a CNN with the Resnet-18 architecture, presenting an accuracy of 90.1 ± 4.3%.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107872"},"PeriodicalIF":4.9,"publicationDate":"2025-04-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143808294","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":"Automatic ECG signal quality assessment using convolutional neural networks and derivative ECG signal for false alarm reduction in wearable vital signs monitoring devices","authors":"Achinta Mondal ,&nbsp;M. Sabarimalai Manikandan ,&nbsp;Ram Bilas Pachori","doi":"10.1016/j.bspc.2025.107876","DOIUrl":"10.1016/j.bspc.2025.107876","url":null,"abstract":"<div><div>The electrocardiogram (ECG) signals are often analyzed to detect cardiovascular diseases and monitor vital signs. However, analysis of noisy ECG signals leads to misdiagnosis of diseases and generates false alarms. To prevent false alarms, we present a derivative ECG (dECG) signal-based lightweight convolutional neural network (CNN) for automatic ECG signal quality assessment (ECG-SQA). The proposed CNN detects clean (“acceptable”) and noisy (“unacceptable”) ECG signals which ensures only clean ECG signals are analyzed for disease detection and monitoring vital signs with reduced false alarms in health monitoring devices. Here, we evaluated the performance, total parameters, testing time for ECG-SQA, and model size of 60 dECG-based CNNs to determine the optimal ECG-SQA method. The performance of the dECG-based CNNs are analyzed with three activation functions, five kernel sizes, different numbers of convolutional layers, and dense layers. The CNNs are trained using ECG signals from one channel and fifteen channels of standard ECG databases. On a standard unseen ECG database, the proposed CNN model has achieved accuracy, sensitivity, and specificity of 97.59%, 98.78%, and 89.23%, respectively. The optimal CNN (model size: 2,989 kB) implemented on the Raspberry Pi computing platform has testing time of 130.44±46.24 ms for quality assessment of 5 s ECG signal which confirms the real-time feasibility of the proposed method. The dECG-based ECG-SQA method is essential during continuous monitoring of vital signs and diagnosis of cardiovascular disease to reduce false alarms and improve reliability of wearable devices having limited computing capacity and onboard memory.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107876"},"PeriodicalIF":4.9,"publicationDate":"2025-04-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143791947","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":"A generative adversarial network for delineation of retinal interfaces in OCT B-scans with age-related macular degeneration","authors":"Himashree Kalita,&nbsp;Samarendra Dandapat,&nbsp;Prabin Kumar Bora","doi":"10.1016/j.bspc.2025.107856","DOIUrl":"10.1016/j.bspc.2025.107856","url":null,"abstract":"<div><div>Age-related macular degeneration (AMD) is a retinal disease that can impair the central vision permanently. Accurate delineation of the retinal pigment epithelium (RPE) and Bruch’s membrane (BM) in optical coherence tomography (OCT) B-scans is crucial for diagnosing and monitoring AMD. While automated segmentation methods exist for early AMD stages, late-stage AMD remains a challenging area due to the pronounced disruption of the RPE and BM. To ensure spatial contiguity in the boundary delineation of RPE and BM, both the global and local contextual information must be learned. In this context, we propose a generative adversarial network (GAN) to segment these significant retinal interfaces in OCT B-scans from AMD patients. A UNet++ model with its deep supervision is trained using a hybrid loss function combining adversarial loss and multi-class cross-entropy (CE) segmentation loss. The CE loss learns the local features by optimizing the per-pixel accuracy, while the adversarial loss captures a broader context by learning overall layer label statistics. This loss combination allows the model to capture fine details in the ordered retinal layer structure and guide layer boundaries along discontinuities in the RPE and BM in severe AMD cases. Additionally, a graph search algorithm refines boundary delineations from predicted segmentation maps. The model’s effectiveness is validated on the DUEIA and AROI datasets, which include OCT B-scans from both AMD-affected and healthy individuals. The proposed approach achieves Mean Absolute Errors (MAE) of 0.45 and 1.19 on the respective datasets, demonstrating its capability to handle boundary segmentation in severe AMD cases.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107856"},"PeriodicalIF":4.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785643","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":"Narrowing the regional attention imbalance in medical image segmentation via feature decorrelation","authors":"Mucong Zhuang ,&nbsp;Yulin Li ,&nbsp;Liying Hu ,&nbsp;Zhiling Hong ,&nbsp;Lifei Chen","doi":"10.1016/j.bspc.2025.107828","DOIUrl":"10.1016/j.bspc.2025.107828","url":null,"abstract":"<div><div>Convolutional neural networks with U-shaped architectures are widely used in medical image segmentation. However, their performance is often limited by imbalanced regional attention caused by interference from irrelevant features within localized receptive fields. To overcome this limitation, FDU-Net is proposed as a novel U-Net-based model that incorporates a feature decorrelation strategy. Specifically, FDU-Net introduces a feature decorrelation method that extracts multiple groups of features from the encoder and optimizes sample weights to reduce internal feature correlations, thereby minimizing the interference from irrelevant features. Comprehensive experiments on diverse medical imaging datasets show that FDU-Net achieves superior evaluation scores and finer segmentation results, outperforming state-of-the-art methods.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107828"},"PeriodicalIF":4.9,"publicationDate":"2025-04-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143785642","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":"Attention-based hybrid deep learning models and its scientific validation for cardiovascular disease risk stratification","authors":"Mrinalini Bhagawati ,&nbsp;Siddharth Gupta ,&nbsp;Sudip Paul ,&nbsp;Laura Mantella ,&nbsp;Amer M. Johri ,&nbsp;John R. Laird ,&nbsp;Ekta Tiwari ,&nbsp;Narendra N. Khanna ,&nbsp;Andrew Nicolaides ,&nbsp;Rajesh Singh ,&nbsp;Mustafa Al-Maini ,&nbsp;Luca Saba ,&nbsp;Jasjit S. Suri","doi":"10.1016/j.bspc.2025.107824","DOIUrl":"10.1016/j.bspc.2025.107824","url":null,"abstract":"<div><h3>Background</h3><div>Carotid plaque can be used to predict the risk of cardiovascular disease (CVD). Earlier machine learning solutions were not reliable, or accurate. The authors hypothesize that (i) attention-based unidirectional or bidirectional hybrid deep learning (HDL) is superior to non-attention-based unidirectional or bidirectional hybrid deep learning and (ii) attention-based bidirectional hybrid deep learning models are superior to attention-based unidirectional HDL paradigms. The proposed design, AtheroEdge™ 3.0_att-HDL (AtheroPoint™, Roseville, CA, USA), shows how effectively characteristics of the carotid plaque in attention-based hybrid deep learning systems predict the risk of CVD more accurately and reliably.</div></div><div><h3>Methodology</h3><div>The study involved 500 participants who underwent targeted carotid B-mode ultrasonography along with coronary angiography. Six hybrid models (four attention types) were used, totaling 6x4 = 24 models. These were benchmarked against the machine learning models. Mann-Whitney <em>U</em> test, Wilcoxon test, and paired <em>T</em>-test were used for the statistical and reliability tests. The scientific validation was performed using the unseen data. The area-under-the-curve and p-values were used for the performance evaluation of AtheroEdge™ 3.0_att-HDL.</div></div><div><h3>Results</h3><div>The best attention-based bidirectional HDL model showed a mean improvement of <strong>36.11 %</strong>, <strong>5.37 %</strong>, <strong>5.37 %</strong>, and <strong>1.04 %</strong> over Random Forest, unidirectional LSTM, bidirectional LSTM, and best attention-based unidirectional HDL models, respectively. As per the reliability and statistical test findings, the bidirectional AtheroEdge™ 3.0_att-HDL had a p-value of less than 0.001, while the unidirectional AtheroEdge™ 3.0_att-HDL also complied with regulations having a p-value &lt; 0.005.</div></div><div><h3>Conclusions</h3><div>The hypothesis was scientifically validated, assessed for reliability and stability, and deemed suitable for clinical application.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107824"},"PeriodicalIF":4.9,"publicationDate":"2025-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143783227","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":"Selection of insole pressure sensors for ground reaction force estimation through studying principal component analysis","authors":"Amal Kammoun ,&nbsp;Philippe Ravier ,&nbsp;Olivier Buttelli","doi":"10.1016/j.bspc.2025.107848","DOIUrl":"10.1016/j.bspc.2025.107848","url":null,"abstract":"<div><div>In the context of low-cost and portable device for measuring pressure using insole system, selection of the relevant sensors is addressed. In a preliminary step, we compared the accuracy of Ground Reaction Force (GRF) components estimation between two pressure insoles: Fscan and Moticon. This estimation was done using Artificial Neural Network combined with Principal Component Analysis (PCA). Secondly, the focus of this study was to identify the optimal numbers and locations of the pressure sensors by a sensor ranking procedure for both insoles using PCA and three selection strategies. The ranking is determined by analyzing the loss value obtained through PCA for each pressure sensor with three selection strategies. Using data from gold standard force plates, we assessed GRF components estimation accuracies and sensor locations for both insoles during walking activities. As a first result, in our context, Moticon insole yielded superior performance for estimating GRF components compared to Fscan. Secondly, the selection procedure allowed deleting 3 among 16 sensors for Moticon (both feet) and 33/30 (left foot/right foot) among 64 sensors for Fscan. Finally, we have validated these optimal numbers by showing that the quality of GRF components estimation was minimally impacted. Remarkably, both insoles with fewer sensors led to better vertical component estimations. These results should be considered in the context of this study, which does not claim to be generalizable. As these results do not reflect a wide range of activities and subject profiles, it is therefore necessary to re-evaluate these selections with other activity conditions.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"107 ","pages":"Article 107848"},"PeriodicalIF":4.9,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768532","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Slice Segmentation Propagator: Propagating the single slice annotation to 3D volume","authors":"Tianjiao Zhang ,&nbsp;Yanfeng Wang ,&nbsp;Weidi Xie ,&nbsp;Ya Zhang","doi":"10.1016/j.bspc.2025.107874","DOIUrl":"10.1016/j.bspc.2025.107874","url":null,"abstract":"<div><div>In this paper, we consider the problem of semi-automatic medical image segmentation, with the goal of segmenting the target structure in a whole 3-D volume image with only a single slice annotation to relieve the user’s annotation burden. Under such a paradigm, the segmentation of the volume is achieved by establishing the correspondence between slices and propagating the reference segmentation. We propose a more medical-suited framework denoted Slice Segmentation Propagator (SSP) that can establish reliable correspondences between slices with local attention, and maintain a running memory bank that effectively mitigates the problem of error accumulation during mask propagation. Additionally, we propose two test-time training strategies to further improve the propagation performance and generalization ability of the framework, namely, a cycle consistency mechanism to suppress error propagation, and an online adaption procedure via artificial augmentation, assisting the model to better generalize towards new structures at test time. We have conducted thorough experiments on three datasets on four anatomy structures, demonstrating promising results on both in-structure and cross-structure (test on different structures from trainset) scenarios.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"107 ","pages":"Article 107874"},"PeriodicalIF":4.9,"publicationDate":"2025-04-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143768531","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":"DeepIH: A deep learning-based near-patient system for treatment recommendation in infantile hemangiomas","authors":"Mengjie Xu ,&nbsp;Zihao Zhao ,&nbsp;Lanzhuju Mei ,&nbsp;Sheng Wang ,&nbsp;Xiaoxi Lin ,&nbsp;Shih-Jen Chang ,&nbsp;Qian Wang ,&nbsp;Yajing Qiu ,&nbsp;Dinggang Shen","doi":"10.1016/j.bspc.2025.107849","DOIUrl":"10.1016/j.bspc.2025.107849","url":null,"abstract":"<div><div>Infantile hemangiomas (IH) are a common pediatric condition that, if not diagnosed and treated early, can lead to functional impairments or permanent disfigurement. However, accurate diagnosis and timely treatment recommendations often depend on the expertise of clinicians and expensive medical imaging, which presents significant challenges in resource-limited settings, especially in low- and middle-income countries. While existing computer-aided diagnosis (CAD) methods have been developed for IH, they mainly assist clinicians rather than offering direct decision-making support, which limits their impact on patient care. To address these challenges, we propose DeepIH, the first near-patient system designed for treatment recommendation of IH based on deep learning. DeepIH is methodologically innovative in two key ways: (1) it accepts camera-shot images as input, enabling patients to conveniently access treatment recommendations through accessible edge devices like smartphones or laptops; (2) it directly generates treatment recommendations, reducing reliance on clinician oversight and enabling faster, more accessible care. Through evaluation on our established dataset, DeepIH achieves an impressive 95.8% accuracy in detecting lesion regions and 84.9% top-3 accuracy in recommending treatments, which even surpasses a fine-tuned foundation model by 1.7%. These findings, for the first time, validate the viability of near-patient diagnosis for IH, highlighting its potential significance in clinical applications as it allows patients to receive treatment recommendations through everyday devices like smartphones or laptops.</div></div>","PeriodicalId":55362,"journal":{"name":"Biomedical Signal Processing and Control","volume":"108 ","pages":"Article 107849"},"PeriodicalIF":4.9,"publicationDate":"2025-04-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143760528","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}