Biocybernetics and Biomedical Engineering最新文献

{"title":"Automated malarial retinopathy detection using transfer learning and multi-camera retinal images","authors":"Aswathy Rajendra Kurup ,&nbsp;Jeff Wigdahl ,&nbsp;Jeremy Benson ,&nbsp;Manel Martínez-Ramón ,&nbsp;Peter Solíz ,&nbsp;Vinayak Joshi","doi":"10.1016/j.bbe.2022.12.003","DOIUrl":"10.1016/j.bbe.2022.12.003","url":null,"abstract":"<div><p><span><span>Cerebral malaria (CM) is a fatal syndrome found commonly in children less than 5 years old in Sub-saharan Africa and Asia. The retinal signs associated with CM are known as malarial retinopathy (MR), and they include highly specific retinal lesions such as whitening and hemorrhages. Detecting these lesions allows the detection of CM with high specificity. Up to 23% of CM, patients are over-diagnosed due to the presence of clinical symptoms also related to </span>pneumonia, meningitis, or others. Therefore, patients go untreated for these pathologies, resulting in death or neurological disability. It is essential to have a low-cost and high-specificity diagnostic technique for CM detection, for which We developed a method based on </span>transfer learning<span> (TL). Models pre-trained with TL select the good quality retinal images, which are fed into another TL model to detect CM. This approach shows a 96% specificity with low-cost retinal cameras.</span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9851283/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"10618688","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":"A new super resolution Faster R-CNN model based detection and classification of urine sediments","authors":"Derya Avci ,&nbsp;Eser Sert ,&nbsp;Esin Dogantekin ,&nbsp;Ozal Yildirim ,&nbsp;Ryszard Tadeusiewicz ,&nbsp;Pawel Plawiak","doi":"10.1016/j.bbe.2022.12.001","DOIUrl":"10.1016/j.bbe.2022.12.001","url":null,"abstract":"<div><p>The diagnosis of urinary tract infections and kidney diseases using urine microscopy images has gained significant attention of medical community in recent years. These images are usually created by physicians’ own rule of thumb<span><span> manually. However, this manual urine sediment analysis is usually labor-intensive and time-consuming. In addition, even when physicians carefully examine an image, an erroneous cell recognition may occur due to some optical illusions. In order to achieve cell recognition in low-resolution urine microscopy images with a higher level of accuracy, a new super resolution Faster Region-based Convolutional </span>Neural Network<span><span> (Faster R-CNN) method is proposed. It aims to increase resolution in low-resolution urine microscopy images using self-similarity based single image super resolution which was used during the pre-processing. De-noising based Wiener filter and </span>Discrete Wavelet Transform (DWT) are used to de-noise high resolution images, respectively, to increase the level of accuracy for image recognition. Finally, for the feature extraction and classification stages, AlexNet, VGFG16 and VGG19 based Faster R-CNN models are used for the recognition and detection of multi-class cells. The model yielded accuracy rates are 98.6%, 96.4% and 96.2% respectively.</span></span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43531471","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":"Identifying epileptic EEGs and congestive heart failure ECGs under unified framework of wavelet scattering transform, bidirectional weighted (2D)2PCA and KELM","authors":"Tao Zhang ,&nbsp;Wanzhong Chen ,&nbsp;Xiaojuan Chen","doi":"10.1016/j.bbe.2023.01.002","DOIUrl":"10.1016/j.bbe.2023.01.002","url":null,"abstract":"<div><p><span>In order to achieve the accurate identifications of various electroencephalograms (EEGs) and electrocardiograms (ECGs), a unified framework of wavelet scattering transform (WST), bidirectional weighted two-directional two-dimensional principal component analysis (BW(2D)</span>²<span>PCA) and grey wolf<span> optimization based kernel extreme learning machine (KELM) was put forward in this study. To extract more discriminating features in the WST domain, the BW(2D)</span></span>²<span>PCA was proposed based on original two-directional two-dimensional principal component analysis, by considering both the contribution of eigenvalue and the variation of two adjacent eigenvalues. Totally fifteen classification tasks of classifying normal </span><em>vs</em> interictal <em>vs</em><span> ictal EEGs, non-seizure </span><em>vs</em> seizure EEGs and normal <em>vs</em> congestive heart failure (CHF) ECGs were investigated. Applying patient non-specific strategy, the proposed scheme reported ACCs of no less than 99.300 ± 0.121 % for all the thirteen classification cases of Bonn dataset in classifying normal <em>vs</em> interictal <em>vs</em><span> ictal EEGs, MCC of 90.947 ± 0.128 % in distinguishing non-seizure </span><em>vs</em> seizure EEGs of CHB-MIT dataset, and MCC of 99.994 ± 0.001 % in identifying normal <em>vs</em> CHF ECGs of BBIH dataset. Experimental results indicate BW(2D)²PCA based framework outperforms (2D)²PCA based scheme, the high-performance results manifest the effectiveness of the proposed framework and our proposal is superior to most existing approaches.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44868358","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 deformable CNN architecture for predicting clinical acceptability of ECG signal","authors":"Jaya Prakash Allam ,&nbsp;Saunak Samantray ,&nbsp;Suraj Prakash Sahoo ,&nbsp;Samit Ari","doi":"10.1016/j.bbe.2023.01.006","DOIUrl":"10.1016/j.bbe.2023.01.006","url":null,"abstract":"<div><p><span>The degraded quality of the electrocardiogram (ECG) signals is the main source of false alarms in critical care units<span>. Therefore, a preliminary analysis of the ECG signal is required to decide its clinical acceptability. In conventional techniques, different handcrafted features are extracted from the ECG signal based on signal quality indices (SQIs) to predict clinical acceptability. A one-dimensional deformable convolutional neural network<span> (1D-DCNN) is proposed in this work to extract features automatically, without manual interference, to detect the clinical acceptability of ECG signals efficiently. In order to create DCNN, the deformable convolution and pooling layers are merged into the regular convolutional neural network (CNN) architecture. In DCNN, the equidistant sampling locations of a regular CNN are replaced with adaptive sampling locations, which improves the network’s ability to learn based on the input. Deformable convolution layers concentrate more on significant segments of the ECG signals rather than giving equal attention to all segments. The proposed method is able to detect acceptable and unacceptable ECG signals with an accuracy of 99.50%, recall of 99.78%, specificity of 99.60%, precision of 99.47%, and </span></span></span><em>F</em>-score of 0.999. Experimental results show that the proposed method performs better than earlier state-of-the-art techniques.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45522958","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":"COVID-19 detection on chest X-ray images using Homomorphic Transformation and VGG inspired deep convolutional neural network","authors":"Gerosh Shibu George ,&nbsp;Pratyush Raj Mishra ,&nbsp;Panav Sinha ,&nbsp;Manas Ranjan Prusty","doi":"10.1016/j.bbe.2022.11.003","DOIUrl":"10.1016/j.bbe.2022.11.003","url":null,"abstract":"<div><p>COVID-19 had caused the whole world to come to a standstill. The current detection methods are time consuming as well as costly. Using Chest X-rays (CXRs) is a solution to this problem, however, manual examination of CXRs is a cumbersome and difficult process needing specialization in the domain. Most of existing methods used for this application involve the usage of pretrained models such as VGG19, ResNet, DenseNet, Xception, and EfficeintNet which were trained on RGB image datasets. X-rays are fundamentally single channel images, hence using RGB trained model is not appropriate since it increases the operations by involving three channels instead of one. A way of using pretrained model for grayscale images is by replicating the one channel image data to three channel which introduces redundancy and another way is by altering the input layer of pretrained model to take in one channel image data, which comprises the weights in the forward layers that were trained on three channel images which weakens the use of pre-trained weights in a transfer learning approach. A novel approach for identification of COVID-19 using CXRs, Contrast Limited Adaptive Histogram Equalization (CLAHE) along with Homomorphic Transformation Filter which is used to process the pixel data in images and extract features from the CXRs is suggested in this paper. These processed images are then provided as input to a VGG inspired deep Convolutional Neural Network (CNN) model which takes one channel image data as input (grayscale images) to categorize CXRs into three class labels, namely, No-Findings, COVID-19, and Pneumonia. Evaluation of the suggested model is done with the help of two publicly available datasets; one to obtain COVID-19 and No-Finding images and the other to obtain Pneumonia CXRs. The dataset comprises 6750 images in total; 2250 images for each class. Results obtained show that the model has achieved 96.56% for multi-class classification and 98.06% accuracy for binary classification using 5-fold stratified cross validation (CV) method. This result is competitive and up to the mark when compared with the performance shown by existing approaches for COVID-19 classification.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9684127/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"9312845","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":"Influence of the position of the distal pressure measurement point on the Fractional Flow Reserve using in-silico simulations","authors":"Rafael Agujetas ,&nbsp;Conrado Ferrera ,&nbsp;Reyes González-Fernández ,&nbsp;Juan M. Nogales-Asensio ,&nbsp;Ana Fernández-Tena","doi":"10.1016/j.bbe.2022.11.006","DOIUrl":"https://doi.org/10.1016/j.bbe.2022.11.006","url":null,"abstract":"<div><p><span>Coronary stenosis is mainly responsible for myocardial ischemia as the blood supply to a portion of the heart stops or is severely reduced. The Fractional Flow Reserve is the benchmark for the </span>hemodynamic significance assessment of coronary stenoses. Its value is employed as a gatekeeper/planning tool for revascularization in clinical practice.</p><p>Non-invasive alternatives have been successfully proposed to guide cardiologists. However, simulation values are not accurate enough in the 0.75–0.85 range, so invasive Fractional Flow Reserve should be used.</p><p>Several authors argue about where distal pressure should be measured. Therefore, our aim is to use simulation to assess how this value changes and to detect the correct measurement region.</p><p>First, we have adjusted the simulation method to the segmentations of two patients whose invasive Fractional Flow Reserve is known. We then extended our analysis to four patients and obtained the simulated value at multiple points distal to the stenosis. This is an advantage over invasive measurements, whose locations are restricted. The results are also essential for locating the best region for invasive distal pressure measurements.</p><p>We propose a hybrid invasive and in-silico procedure that would avoid false results and prevent cardiologists from making erroneous clinical decisions.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49732055","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":"Drug-device systems based on biodegradable metals for bone applications: Potential, development and challenges","authors":"Abdul Hakim Md Yusop ,&nbsp;Murni Nazira Sarian ,&nbsp;Fatihhi Szali Januddi ,&nbsp;Hadi Nur","doi":"10.1016/j.bbe.2022.11.002","DOIUrl":"10.1016/j.bbe.2022.11.002","url":null,"abstract":"<div><p><span><span>Drug-device systems based on biodegradable metals have been of great interest in the last decade due to their local-release regime and the ability of the biodegradable metals to degrade in the physiological environment facilitating tissue growth and gradual load transfer. The </span>biodegradability of the biodegradable metals provides a promising medium that might enable other materials – such as drugs, </span>bioactive materials and therapeutic agents - to be incorporated into the degradable metals to act as a drug-device system that would locally release the drugs or therapeutic agents onto the healing tissue. In comparison to systemic drug delivery, the locally released drug-device system makes the dose control over a specific targeted tissue more efficient and reduces the side effects on non-targeted tissues. This review outlines the current state of development of the biodegradable metals-based drug-device system and focuses in-depth on the potential interactions between the drugs, degradable metallic surfaces, drug carriers, ions and proteins inside the body fluids, which can be a challenge to producing a highly efficient drug-device system.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42483795","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":"Automated detection of cybersecurity attacks in healthcare systems with recursive feature elimination and multilayer perceptron optimization","authors":"Ilhan Firat Kilincer ,&nbsp;Fatih Ertam ,&nbsp;Abdulkadir Sengur ,&nbsp;Ru-San Tan ,&nbsp;U. Rajendra Acharya","doi":"10.1016/j.bbe.2022.11.005","DOIUrl":"10.1016/j.bbe.2022.11.005","url":null,"abstract":"<div><p><span>Widespread proliferation of interconnected healthcare equipment, accompanying software, operating systems, and networks in the Internet of Medical Things (IoMT) raises the risk of security compromise as the bulk of IoMT devices are not built to withstand internet attacks. In this work, we have developed a cyber-attack and anomaly detection model based on recursive feature elimination (RFE) and multilayer </span>perceptron<span> (MLP). The RFE approach selected optimal features using logistic regression<span> (LR) and extreme gradient boosting regression (XGBRegressor) kernel functions. MLP parameters were adjusted by using a hyperparameter optimization and 10-fold cross-validation approach was performed for performance evaluations. The developed model was performed on various IoMT cybersecurity datasets, and attained the best accuracy rates of 99.99%, 99.94%, 98.12%, and 96.2%, using Edith Cowan University- Internet of Health Things (ECU-IoHT), Intensive Care Unit (ICU Dataset), Telemetry data, Operating systems’ data, and Network data from the testbed IoT/IIoT network (TON-IoT), and Washington University in St. Louis enhanced healthcare monitoring system (WUSTL-EHMS) datasets, respectively. The proposed method has the ability to counter cyber attacks in healthcare applications.</span></span></p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47205147","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":"Gray-level co-occurrence matrix of Smooth Pseudo Wigner-Ville distribution for cognitive workload estimation","authors":"Rezvan Mirzaeian ,&nbsp;Peyvand Ghaderyan","doi":"10.1016/j.bbe.2023.01.001","DOIUrl":"10.1016/j.bbe.2023.01.001","url":null,"abstract":"<div><p>Automatic, cost-effective, and reliable cognitive workload estimation (CWE) is one of the important issues in diagnosis and treatment of neurocognitive diseases, cognitive performance improvement and error preventive strategies. To address this issue, this paper has proposed a novel and robust CWE method by detecting the time–frequency (TF) changes of electrodermal activities (EDA). Firstly, the local and global properties of the time-variant characteristics of EDA have been presented using Smooth Pseudo Wigner-Ville distribution with enhanced TF resolution. Then, the transient changes in TF images of EDA signals have been quantified using a set of textural features based on Gray Level Co-occurrence Matrix descriptor (GLCM). Several static and dynamic classifiers, such as support vector machine, K- k-nearest neighbor, cascade forward neural network, and recurrent neural network have been explored. A real EDA data experiment recorded during arithmetic task with different workload levels have been used to evaluate the performance of the proposed method. The obtained results have confirmed that it can achieve a high estimation performance of 97.71% using contrast feature for discrimination of three workload levels. Further analysis has also suggested that the model is robust to GLCM parameters and classifiers and can provide a better tradeoff between computational complexity and high performance using minimum number of textural features in comparison with previous studies.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46943811","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":"Deep brain stimulation of the entorhinal cortex modulates CA1 theta-gamma oscillations in mouse models of preclinical Alzheimer's disease","authors":"Yinpei Luo ,&nbsp;Yuwei Sun ,&nbsp;Huizhong Wen ,&nbsp;Xing Wang ,&nbsp;Xiaolin Zheng ,&nbsp;Hongfei Ge ,&nbsp;Yi Yin ,&nbsp;Xiaoying Wu ,&nbsp;Weina Li ,&nbsp;Wensheng Hou","doi":"10.1016/j.bbe.2022.12.010","DOIUrl":"https://doi.org/10.1016/j.bbe.2022.12.010","url":null,"abstract":"<div><p>Deep brain stimulation (DBS) is a neuromodulation method that modulates neuronal activity. A trend in the treatment of Alzheimer’s disease (AD) is targeting key points of neural circuits with DBS. Here, we explored the effects of DBS targeted to the entorhinal cortex (EC) on neurons in the hippocampal CA1 in a mouse model of preclinical AD. Specifically, we recorded field potential signals from CA1 in preclinical AD mice after DBS of the EC (1 h/day for 21 days of 100 μA, 90 μs, 10 Hz, biphasic square wave pulse) with in-vivo electrophysiology and evaluated corresponding changes in behavior with the open field task and Morris water maze (MWM) task. We also assessed changes in pathological markers and neurogenesis in the hippocampus with immunohistological staining. DBS of the EC increased theta and gamma power and modulated theta in the high gamma band (50–100 Hz) in preclinical AD mice. After DBS of the EC, these mice performed better in the MWM task and exhibited reduced deposition of beta-amyloid and neuronal changes including significant increases in proliferating neurons and immature neurons. This is the first study to target the EC with DBS and analyze resulting neural oscillations in the hippocampal CA1 in a model of preclinical AD. The findings support the use of DBS as a potential treatment for AD.</p></div>","PeriodicalId":55381,"journal":{"name":"Biocybernetics and Biomedical Engineering","volume":null,"pages":null},"PeriodicalIF":6.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49731793","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}