In recent times, Hacking has turn out to be more unfavorable than ever in all life fields, including the healthcare systems, with an increasing usage of information technology. By the expansion of technology development, the attacks number is too rising every few months in an exponential manner, which in turn makes the conventional IDS incapable to perceive. A healthcare system network intrusion detection method is proposed depending on the Google NET convolution neural network (Google NET). In healthcare system databases, intrusion detection (KDDs) can be seen as a search issue, which might be solved with the use of Google NET CNN algorithms. After pre-processing and characterizing the healthcare system data (including Electronic Health Records (EHR), Medical imaging data, Electronic Medical Records (EMR), etc.), the Google NET CNN model is used to simulate the intrusion into the healthcare system data. The low-level data intrusion is signified conceptually as the superior features with Google NET CNN, which in turn extracts the sample features separately, and by using MFO, network parameter is optimized (algorithm of optimization to meet the representation. At last, a sample test is conducted for the detection of healthcare system network intrusion behavior. The simulation outcome illustrate that the proposed technique has high accuracy on detection and a lower false-positive rate along with true positive rate.
近年来，随着信息技术的日益普及，在包括医疗保健系统在内的所有生活领域，黑客行为比以往任何时候都更加不利。随着技术发展的扩大，攻击数量每隔几个月就会呈指数级增长，这使得传统的IDS无法察觉。提出了一种基于Google . NET卷积神经网络的医疗系统网络入侵检测方法。在医疗系统数据库中，入侵检测(kdd)可以看作是一个搜索问题，这可以通过使用Google . NET CNN算法来解决。在对医疗系统数据(包括电子健康记录(Electronic Health Records, EHR)、医疗成像数据、电子医疗记录(Electronic Medical Records, EMR)等)进行预处理和表征后，利用Google . NET CNN模型模拟对医疗系统数据的入侵。利用Google . NET CNN将底层数据入侵在概念上表示为上级特征，再分别提取样本特征，并利用最大模糊神经网络(MFO)对网络参数进行优化(优化算法)以满足表示。最后，对医疗系统网络入侵行为的检测进行了样本测试。仿真结果表明，该方法具有较高的检测精度和较低的假阳性率和真阳性率。
{"title":"Big Data Analysis and Management of Healthcare Systems for Hacker Detection Based on Google Net Convolutional Neural Network","authors":"D. Pradeep, C. Sundar","doi":"10.1166/jmihi.2021.3881","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3881","url":null,"abstract":"In recent times, Hacking has turn out to be more unfavorable than ever in all life fields, including the healthcare systems, with an increasing usage of information technology. By the expansion of technology development, the attacks number is too rising every few months in an exponential\u0000 manner, which in turn makes the conventional IDS incapable to perceive. A healthcare system network intrusion detection method is proposed depending on the Google NET convolution neural network (Google NET). In healthcare system databases, intrusion detection (KDDs) can be seen as a search\u0000 issue, which might be solved with the use of Google NET CNN algorithms. After pre-processing and characterizing the healthcare system data (including Electronic Health Records (EHR), Medical imaging data, Electronic Medical Records (EMR), etc.), the Google NET CNN model is used to simulate\u0000 the intrusion into the healthcare system data. The low-level data intrusion is signified conceptually as the superior features with Google NET CNN, which in turn extracts the sample features separately, and by using MFO, network parameter is optimized (algorithm of optimization to meet the\u0000 representation. At last, a sample test is conducted for the detection of healthcare system network intrusion behavior. The simulation outcome illustrate that the proposed technique has high accuracy on detection and a lower false-positive rate along with true positive rate.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134500151","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Motion sickness is all around as long as there is existence of humans and motion. This sickness has been common in numerous people and due to which it has become the focus area of neurological, psychological and physiological researchers. Most common group of this motion sickness pertains to the category of visual sensitivity; also called visual dependence, wherein people become sick due to visual motion. In this research paper, classification of the levels of motion sickness is done by developing classifiers: (1) k-Nearest neighbour (kNN) classifier (2) Fuzzy c-means classifier (3) ELMAN neural classifier (4) Fuzzy-Wavelet neural network classifier. All the developed classifier models are based on variants of machine learning approaches and are designed to overcome the limitation of the conventional binary classification approach. In this work, electroencephalogram (EEG) data, centre of pressure and trajectories of head and waist motion data of 20 people were recorded and the developed classifier models were applied over them to attain the classification accuracy. Features of these multiple biosignals are denoised and extracted over which the classifier models were tested. The proposed technique is simulated in MATLAB simulation environment for the considered candidate data samples. Numerical simulation was carried out and the results prove the superiority and effectiveness of the developed classifiers over the various existing classifier models.
{"title":"Hybrid Neuro-Fuzzy Learning Models for Classification of Motion Sickness Levels Using Biosignals","authors":"Jis Paul, M. Madheswaran","doi":"10.1166/jmihi.2021.3871","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3871","url":null,"abstract":"Motion sickness is all around as long as there is existence of humans and motion. This sickness has been common in numerous people and due to which it has become the focus area of neurological, psychological and physiological researchers. Most common group of this motion sickness pertains\u0000 to the category of visual sensitivity; also called visual dependence, wherein people become sick due to visual motion. In this research paper, classification of the levels of motion sickness is done by developing classifiers: (1) k-Nearest neighbour (kNN) classifier (2) Fuzzy c-means classifier\u0000 (3) ELMAN neural classifier (4) Fuzzy-Wavelet neural network classifier. All the developed classifier models are based on variants of machine learning approaches and are designed to overcome the limitation of the conventional binary classification approach. In this work, electroencephalogram\u0000 (EEG) data, centre of pressure and trajectories of head and waist motion data of 20 people were recorded and the developed classifier models were applied over them to attain the classification accuracy. Features of these multiple biosignals are denoised and extracted over which the classifier\u0000 models were tested. The proposed technique is simulated in MATLAB simulation environment for the considered candidate data samples. Numerical simulation was carried out and the results prove the superiority and effectiveness of the developed classifiers over the various existing classifier\u0000 models.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"47 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134490005","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiang Yao, Ling Mao, Ke Yi, Yuxiao Han, Wentao Li, Ying Xiao, Jun Ji, Qingqing Wang, Ke Ren
Objectives: To discuss the application of radiomics using Computerized Tomography (CT) analysis, for improving its diagnostic efficacy in lung, specifically in distinguishing Squamous Cell Carcinoma (SCC), lung Adenocarcinoma (ADC), and Small Cell Lung Cancer (SCLC). Methods: The pathology of 189 identified cases of lung cancer was analyzed, retrospectively (60 patients with SCC, 69 patients with lung ADC and 60 patients with SCLC). A neural network was used to determine whether the pulmonary or mediastinal window was selected to extract effective radiomic features. The key features of radiomic signature were retrieved by a Least Absolute Shrinkage and Selection Operator (LASSO) multiple logistic regression model. Next, receiver operating characteristic curve and Area Under the Curve (AUC) analysis were used to evaluate the performance of the radiomic signature in both, training(129 patients) and validation cohorts (60 patients). Results: About 295 features were extracted from a manually outlined tumor region. Features extracted from mediastinal window CT scans had a better prognostic ability than pulmonary window scans. The average accuracy for mediastinal window scans was 0.933. Our analysis revealed that the radiomic features extracted from mediastinal window scans had the potential to build a prediction model for distinguishing between SCC, lung ADC, and SCLC. The performance of the radiomic signature to diagnose SCC and SCLC in validation cohorts proved effective, with AUC values of 0.869 and 0.859, respectively. Conclusions: A unique radiomic signature was constructed as a diagnostic factor for different histologic subtypes of lung cancer. Patients with lung cancer may benefit from this proposed radiomic signature.
{"title":"Radiomic Signature as a Diagnostic Factor for Classification of Histologic Subtypes of Lung Cancer","authors":"Xiang Yao, Ling Mao, Ke Yi, Yuxiao Han, Wentao Li, Ying Xiao, Jun Ji, Qingqing Wang, Ke Ren","doi":"10.1166/jmihi.2021.3564","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3564","url":null,"abstract":"Objectives: To discuss the application of radiomics using Computerized Tomography (CT) analysis, for improving its diagnostic efficacy in lung, specifically in distinguishing Squamous Cell Carcinoma (SCC), lung Adenocarcinoma (ADC),\u0000 and Small Cell Lung Cancer (SCLC). Methods: The pathology of 189 identified cases of lung cancer was analyzed, retrospectively (60 patients with SCC, 69 patients with lung ADC and 60 patients with SCLC). A neural network was used\u0000 to determine whether the pulmonary or mediastinal window was selected to extract effective radiomic features. The key features of radiomic signature were retrieved by a Least Absolute Shrinkage and Selection Operator (LASSO) multiple logistic regression model. Next, receiver operating characteristic\u0000 curve and Area Under the Curve (AUC) analysis were used to evaluate the performance of the radiomic signature in both, training(129 patients) and validation cohorts (60 patients). Results: About 295 features were extracted from\u0000 a manually outlined tumor region. Features extracted from mediastinal window CT scans had a better prognostic ability than pulmonary window scans. The average accuracy for mediastinal window scans was 0.933. Our analysis revealed that the radiomic features extracted from mediastinal window\u0000 scans had the potential to build a prediction model for distinguishing between SCC, lung ADC, and SCLC. The performance of the radiomic signature to diagnose SCC and SCLC in validation cohorts proved effective, with AUC values of 0.869 and 0.859, respectively. Conclusions:\u0000 A unique radiomic signature was constructed as a diagnostic factor for different histologic subtypes of lung cancer. Patients with lung cancer may benefit from this proposed radiomic signature.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"37 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129832142","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Brain cancer identification and segmentation is a prolonged and difficult task in Medical Image Processing, which is most significant for providing appropriate treatment and increase patient’s life span. With the advancements available in medical fields, soft computing techniques are incorporated to accurate detection and classification of brain tumors. Besides brain cancer detection, it is vital to categorize tumor stage based on their features. For that concern, this paper develops a Tumor Categorization Model (TCM) that includes image processing and soft computing techniques. Here, pre-processing is carried out using modified Gabor filter and segmentation process is performed with OTSU thresholding. Following segmentation, region growing is processed based on the pixel intensities of input MRI brain images. Further, Discrete Wavelet Transform is enforced for extorting image features as well as gray-level co-occurence matrix features are also derived for appropriate classifications. Finally, the input MRI images are classified using Boosting Support Vector Machine (BSVM) with the benchmark dataset called DICOM and BraTS dataset. The experimental results demonstrate accurate brain tumor detection and categorization by the efficient incorporation of image processing and soft computing methodologies, provides efficient clinical support in providing treatments.
脑癌的识别与分割是医学图像处理中一项耗时长、难度大的任务，对于提供合理的治疗和延长患者的生命至关重要。随着医学领域的进步，软计算技术被用于脑肿瘤的准确检测和分类。除了脑癌的检测外，根据肿瘤的特征对肿瘤分期进行分类也很重要。为此，本文开发了一种包含图像处理和软计算技术的肿瘤分类模型(TCM)。在这里，使用改进的Gabor滤波器进行预处理，并使用OTSU阈值进行分割。在分割之后，根据输入MRI脑图像的像素强度进行区域生长处理。进一步，利用离散小波变换提取图像特征，并推导出相应的灰度共生矩阵特征进行分类。最后，使用增强支持向量机(Boosting Support Vector Machine, BSVM)和基准数据集DICOM和BraTS对输入的MRI图像进行分类。实验结果表明，通过图像处理和软计算方法的有效结合，可以准确地检测和分类脑肿瘤，为临床提供有效的治疗支持。
{"title":"Tumor Categorization Model (TCM) Using Soft Computing Techniques for Providing Efficient Medical Support in Brain Tumor Treatments","authors":"V. V. Kumar, Paulchamy Balaiyah","doi":"10.1166/jmihi.2021.3872","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3872","url":null,"abstract":"Brain cancer identification and segmentation is a prolonged and difficult task in Medical Image Processing, which is most significant for providing appropriate treatment and increase patient’s life span. With the advancements available in medical fields, soft computing techniques\u0000 are incorporated to accurate detection and classification of brain tumors. Besides brain cancer detection, it is vital to categorize tumor stage based on their features. For that concern, this paper develops a Tumor Categorization Model (TCM) that includes image processing and soft computing\u0000 techniques. Here, pre-processing is carried out using modified Gabor filter and segmentation process is performed with OTSU thresholding. Following segmentation, region growing is processed based on the pixel intensities of input MRI brain images. Further, Discrete Wavelet Transform is enforced\u0000 for extorting image features as well as gray-level co-occurence matrix features are also derived for appropriate classifications. Finally, the input MRI images are classified using Boosting Support Vector Machine (BSVM) with the benchmark dataset called DICOM and BraTS dataset. The experimental\u0000 results demonstrate accurate brain tumor detection and categorization by the efficient incorporation of image processing and soft computing methodologies, provides efficient clinical support in providing treatments.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"164 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134052410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Detection of Glioma and its segmentation can be a very challenging task for clinicians and radiologists. Accuracy in classifying glioma is required where brain tumorsgrow from the star-shaped glial cells among adults. Magnetic Resonance Imaging (MRI) indicates the human soft tissue and its anatomical structure away from displaying the location, histological traits, and location of the lesions used to diagnose glioma clinically. An automated framework for the identification of gliomas is presented. Feature extraction will present much higher imaging features such as texture, color, contrast, and shape. The Gabor filters can carry out multi-resolution decomposition due to localization with regard to spatial frequency. The Shuffle Complex Evolution (SCE) algorithm will combine Controlled random search, a complex mix, competition, evolution, and the adaptation of the world’s population Nelder-Mead Simplex for all the benefits of optimal solutions. The CNN process is in an input texture that collects statistics within the spatial domain. The CNNs are normally capable of capturing spatial features, and spectral analysis can capture all scale-invariant features. This work implements an automated method for classifying the Gliomas with an optimized shuffled complex evolution CNN.
{"title":"An Automated Framework to Segment and Classify Gliomas Using Efficient Shuffled Complex Evolution Convolutional Neural Network","authors":"G. Valarmathy, K. Sekar, V. Balaji","doi":"10.1166/jmihi.2021.3868","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3868","url":null,"abstract":"Detection of Glioma and its segmentation can be a very challenging task for clinicians and radiologists. Accuracy in classifying glioma is required where brain tumorsgrow from the star-shaped glial cells among adults. Magnetic Resonance Imaging (MRI) indicates the human soft tissue\u0000 and its anatomical structure away from displaying the location, histological traits, and location of the lesions used to diagnose glioma clinically. An automated framework for the identification of gliomas is presented. Feature extraction will present much higher imaging features such as texture,\u0000 color, contrast, and shape. The Gabor filters can carry out multi-resolution decomposition due to localization with regard to spatial frequency. The Shuffle Complex Evolution (SCE) algorithm will combine Controlled random search, a complex mix, competition, evolution, and the adaptation of\u0000 the world’s population Nelder-Mead Simplex for all the benefits of optimal solutions. The CNN process is in an input texture that collects statistics within the spatial domain. The CNNs are normally capable of capturing spatial features, and spectral analysis can capture all scale-invariant\u0000 features. This work implements an automated method for classifying the Gliomas with an optimized shuffled complex evolution CNN.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132829765","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The recent past, the data volume in a media field is growing at a rapid rate, and conventional methods fail to manage such a large volume of data in healthcare systems, biomedical field, medical diagnostic systems etc. The main challenges associated with biomedical computation are the problems associated with management, storage, and analysis on extensive biomedical data. To play a significant role over such extensive data, the machine learning approach provides faster access to medical data with an improved framework. The main objective involves the detection of amblyopia condition from input images and comparing it with conventional image detection methods. The proposed method is examined in terms of detection accuracy, sensitivity, specificity, Hausdorff distance computation and Dice Coefficient. Also, the detection of an Amblyopic or Lazy Eye diseased images is still not prevalent in the field of image segmentation and detection. In this paper, we introduce a framework to process the Amblyopia image datasets using machine learning, and similarity comparison approach. The proposed image processing involves the segmentation of eye images using Recurrent Neural Networks (RNN), and the detection of Amblyopia disease is carried out with Hausdorff Distance computation and Dice coefficient similarity comparison on the segmented image. The initial subset points and threshold values are calculated from a set of 50 normal eye images. A set of 100 Amblyopic diseased image dataset is used for testing the proposed system, out of which 70 images are used for training the system. To evaluate the experimental results shows that proposed method obtains improved detection than existing Deeply-Learned Gaze Shifting Path (DLGSP), Cascade Regression Framework (CRF) and Mobile Iris Recognition System (MIRS) methods. The presence of Hausdorff Distance computation and Dice coefficient similarity comparison is used for reducing the overhead in the proposed method, and this can be used for computing large sets of images.
{"title":"A Detection of Amblyopia Medical Condition in Biomedical Datasets Using Image Segmentation and Detection Processing","authors":"S. Lalitha, N. Shanthi, S. Gopinath","doi":"10.1166/jmihi.2021.3880","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3880","url":null,"abstract":"The recent past, the data volume in a media field is growing at a rapid rate, and conventional methods fail to manage such a large volume of data in healthcare systems, biomedical field, medical diagnostic systems etc. The main challenges associated with biomedical computation are the\u0000 problems associated with management, storage, and analysis on extensive biomedical data. To play a significant role over such extensive data, the machine learning approach provides faster access to medical data with an improved framework. The main objective involves the detection of amblyopia\u0000 condition from input images and comparing it with conventional image detection methods. The proposed method is examined in terms of detection accuracy, sensitivity, specificity, Hausdorff distance computation and Dice Coefficient. Also, the detection of an Amblyopic or Lazy Eye diseased images\u0000 is still not prevalent in the field of image segmentation and detection. In this paper, we introduce a framework to process the Amblyopia image datasets using machine learning, and similarity comparison approach. The proposed image processing involves the segmentation of eye images using Recurrent\u0000 Neural Networks (RNN), and the detection of Amblyopia disease is carried out with Hausdorff Distance computation and Dice coefficient similarity comparison on the segmented image. The initial subset points and threshold values are calculated from a set of 50 normal eye images. A set of 100\u0000 Amblyopic diseased image dataset is used for testing the proposed system, out of which 70 images are used for training the system. To evaluate the experimental results shows that proposed method obtains improved detection than existing Deeply-Learned Gaze Shifting Path (DLGSP), Cascade Regression\u0000 Framework (CRF) and Mobile Iris Recognition System (MIRS) methods. The presence of Hausdorff Distance computation and Dice coefficient similarity comparison is used for reducing the overhead in the proposed method, and this can be used for computing large sets of images.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114562433","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Internet of Things (IoT) has changed the world into a more physically connected, ensuring higher order applications. As smart devices and patients surrounding are able to freely communicate with each other, more chances and conveniences are brought to us. However, as the information is kept inside these devices is revealed and distributed, security and privacy concerns call for an effective safeguarding process more than ever. Secured data transmission with higher voluminous data indulging with noisy instances, the computational cost and overhead incurred remains the major issues for IoT based health care system. The complexity of the inferred model may increase, and thereby the overall secured data transmission accuracy of the model may decrease. In this work, the above said issues are addressed via secure data transmission method, in order to minimize the computational cost and overhead incurred during transmission of large data and also improve the data transmission accuracy with minimum running time. The method is called as Delay-aware and Energy-efficient Laplace Angular Displacement (DE-LAD). The DE-LAD method involves three steps. They are data collection, data communication and data transmission. First data collection is performed via delayaware and energy-efficient model. Second data communication is said to be established using pairing-free Laplace Estimator, minimizing computational complexity involved during data collection. Finally, secured data transmission is achieved via Angular Displacement. Moreover, in WSN, the security of data being transmitted is calculated for IoT-based healthcare system. The simulation results of DE-LAD method provides enhanced performance in terms of security and complexity as compared to conventional methods.
{"title":"Laplace Angular Displaced Secure Data Transmission for Internet of Things Based Health Care Systems","authors":"P. Srinivasan, A. Kannagi, P. Rajendiran","doi":"10.1166/jmihi.2021.3883","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3883","url":null,"abstract":"The Internet of Things (IoT) has changed the world into a more physically connected, ensuring higher order applications. As smart devices and patients surrounding are able to freely communicate with each other, more chances and conveniences are brought to us. However, as the information\u0000 is kept inside these devices is revealed and distributed, security and privacy concerns call for an effective safeguarding process more than ever. Secured data transmission with higher voluminous data indulging with noisy instances, the computational cost and overhead incurred remains the\u0000 major issues for IoT based health care system. The complexity of the inferred model may increase, and thereby the overall secured data transmission accuracy of the model may decrease. In this work, the above said issues are addressed via secure data transmission method, in order to minimize\u0000 the computational cost and overhead incurred during transmission of large data and also improve the data transmission accuracy with minimum running time. The method is called as Delay-aware and Energy-efficient Laplace Angular Displacement (DE-LAD). The DE-LAD method involves three steps.\u0000 They are data collection, data communication and data transmission. First data collection is performed via delayaware and energy-efficient model. Second data communication is said to be established using pairing-free Laplace Estimator, minimizing computational complexity involved during data\u0000 collection. Finally, secured data transmission is achieved via Angular Displacement. Moreover, in WSN, the security of data being transmitted is calculated for IoT-based healthcare system. The simulation results of DE-LAD method provides enhanced performance in terms of security and complexity\u0000 as compared to conventional methods.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"49 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129438268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Xiaoqi Huang, Ke Shi, Jie Zhou, Yuxuan Liang, Yaliang Liu, Jinpin Zhang, Youmin Guo, C. Jin
Purpose: This study aimed to identify severe Coronavirus Disease 2019 (COVID-19) cases combining blood test results and imaging parameters based on a machine learning classifier at the initial admission. Materials and methods: Ninety-five non-severe and 22 severe laboratory-confirmed COVID-19 cases treated between January 23, 2020 and March 25, 2020 were examined in this retrospective trial. Blood test results and chest computed tomography (CT) images were obtained at the initial admission. The lesions on CT images were segmented using an artificial intelligent (AI) tool. Then, quantitative CT (QCT) parameters, including the volume, percentage, ground glass opacity (GGO) percentage and heterogeneity of the lesions were calculated. Correlations of blood test results and QCT parameters were analyzed by the Pearson test first. Then, discriminative features for detecting severe cases were selected by both the independent samples t test and least absolute shrinkage and selection operator (LASSO) regression. Next, support vector machine (SVM), Gaussian naïve Bayes (GNB), Knearest neighbor (KNN), decision tree (DT), random forest (RF) and multi-layer perceptron-neural net (MLP-NN) algorithms were used as classifiers, and their accuracies were assessed by 10-fold-cross-validation. Results: Blood test indexes and CT parameters were moderately to medially correlated. Of all selected features, lesion percentage contributed mostly to the classification of the two groups, followed by lesion volume, patient age, lymphocyte count, neutrophil count, GGO percentage and tumor heterogeneity. RF-assisted identification had the highest accuracy of 91.38%, followed by GNB (87.83%), KNN (87.93%), SVM (86.21%), MLP-NN (85.34%) and DT (84.48%). Conclusions: The RF-assisted model combining blood test and QCT parameters is helpful in the identification of severe COVID-19 cases.
{"title":"Development of a Machine Learning-Assisted Model for the Early Detection of Severe COVID-19 Cases Combining Blood Test and Quantitative Computed Tomography Parameters","authors":"Xiaoqi Huang, Ke Shi, Jie Zhou, Yuxuan Liang, Yaliang Liu, Jinpin Zhang, Youmin Guo, C. Jin","doi":"10.1166/jmihi.2021.3866","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3866","url":null,"abstract":"Purpose: This study aimed to identify severe Coronavirus Disease 2019 (COVID-19) cases combining blood test results and imaging parameters based on a machine learning classifier at the initial admission. Materials\u0000 and methods: Ninety-five non-severe and 22 severe laboratory-confirmed COVID-19 cases treated between January 23, 2020 and March 25, 2020 were examined in this retrospective trial. Blood test results and chest computed tomography (CT) images were obtained at the initial\u0000 admission. The lesions on CT images were segmented using an artificial intelligent (AI) tool. Then, quantitative CT (QCT) parameters, including the volume, percentage, ground glass opacity (GGO) percentage and heterogeneity of the lesions were calculated. Correlations of blood test results\u0000 and QCT parameters were analyzed by the Pearson test first. Then, discriminative features for detecting severe cases were selected by both the independent samples t test and least absolute shrinkage and selection operator (LASSO) regression. Next, support vector machine (SVM),\u0000 Gaussian naïve Bayes (GNB), Knearest neighbor (KNN), decision tree (DT), random forest (RF) and multi-layer perceptron-neural net (MLP-NN) algorithms were used as classifiers, and their accuracies were assessed by 10-fold-cross-validation. Results:\u0000 Blood test indexes and CT parameters were moderately to medially correlated. Of all selected features, lesion percentage contributed mostly to the classification of the two groups, followed by lesion volume, patient age, lymphocyte count, neutrophil count, GGO percentage and tumor heterogeneity.\u0000 RF-assisted identification had the highest accuracy of 91.38%, followed by GNB (87.83%), KNN (87.93%), SVM (86.21%), MLP-NN (85.34%) and DT (84.48%). Conclusions: The RF-assisted model combining blood test and QCT parameters is\u0000 helpful in the identification of severe COVID-19 cases.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129619458","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Medical image processing typically deals with the exploration of several medical image datasets for attaining an effective solution in diagnosing the affected patients. Medical image of the patients are typically stored in digital form as Electronic patient’s record (EPR), which must be dealt with utmost security and confidentiality, as the patient’s data are linked with external open platforms for future diagnosis. Medical image watermarking and encryption schemes assist in meeting the above requirements in effectively securing the patient’s image data. The ultimate objective of this research inclines towards securing medical images so as to achieve maximum effectiveness over health related areas. In this paper, an enhanced hybrid medical image watermarking and equivalent encryption strategy is typically investigated for attaining an effective solution towards medical image processing. The proposed methodology works with the integration of image watermarking algorithm together with an encryption algorithm. Image watermarking is achieved by a system based on Redundant discrete wavelet transform and Singular value decomposition. Moreover, by utilizing the property of chaotic signals for improving the integrity, a hybrid medical image watermarking technique is proposed by upgrading the Arnold cat map (ACM) with Logistic map. For image encryption, Symmetric block encryption algorithm based on Feistel structure is proposed. The efficiency of the proposed strategy is estimated in terms of Peak signal to noise ratio (PSNR), Mean square error (MSE) and Correlation coefficient (CC).
{"title":"An Enhanced Hybrid Watermarking Method and Imaging System for Securing Medical Images","authors":"N. Kumar, C. Ramya","doi":"10.1166/jmihi.2021.3867","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3867","url":null,"abstract":"Medical image processing typically deals with the exploration of several medical image datasets for attaining an effective solution in diagnosing the affected patients. Medical image of the patients are typically stored in digital form as Electronic patient’s record (EPR), which\u0000 must be dealt with utmost security and confidentiality, as the patient’s data are linked with external open platforms for future diagnosis. Medical image watermarking and encryption schemes assist in meeting the above requirements in effectively securing the patient’s image data.\u0000 The ultimate objective of this research inclines towards securing medical images so as to achieve maximum effectiveness over health related areas. In this paper, an enhanced hybrid medical image watermarking and equivalent encryption strategy is typically investigated for attaining an effective\u0000 solution towards medical image processing. The proposed methodology works with the integration of image watermarking algorithm together with an encryption algorithm. Image watermarking is achieved by a system based on Redundant discrete wavelet transform and Singular value decomposition. Moreover,\u0000 by utilizing the property of chaotic signals for improving the integrity, a hybrid medical image watermarking technique is proposed by upgrading the Arnold cat map (ACM) with Logistic map. For image encryption, Symmetric block encryption algorithm based on Feistel structure is proposed. The\u0000 efficiency of the proposed strategy is estimated in terms of Peak signal to noise ratio (PSNR), Mean square error (MSE) and Correlation coefficient (CC).","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114406065","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
A MANET is a self-governing network for mobile devices in many crucial domains, including health care, for transmitting health data of the patients. The key challenge in MANETS is maintaining the links between devices under mobility; it creates limitless network disconnections and path loss frequently. Such issues, raises network delay and minimize packet delivery ratio (PDR) and entire set-up throughput brings reduced quality of services (QOS). To get better QoS, stable path selection and link disconnection count based nearby device selection carried out in this work. It’s on this basis that the thesis is exploring the design and the analysis of the FPC. The FPC is designed in network simulator with the support of optimized fuzzy logic (FL). It has obtained three inputs which is fallout to 27 set of laws. This law sets (LS) direct in the fortitude of the precedence to select best path set to transmit a packets from sender to destination. The analyses are with previous protocols of Distributed Admission Control Protocol (DACP) and Call Admission Protocol of MANET. The outcome results monitored with delay, Packet Delivery Ratio (PDR), throughput and overheads as the QOS metrics of network.
{"title":"PCCAMN - Path Constancy Based Channel Assignment in Mobile ADHOC Network for Healthcare Data Transmission","authors":"T. Sangeetha, M. Manikandan","doi":"10.1166/jmihi.2021.3879","DOIUrl":"https://doi.org/10.1166/jmihi.2021.3879","url":null,"abstract":"A MANET is a self-governing network for mobile devices in many crucial domains, including health care, for transmitting health data of the patients. The key challenge in MANETS is maintaining the links between devices under mobility; it creates limitless network disconnections and path\u0000 loss frequently. Such issues, raises network delay and minimize packet delivery ratio (PDR) and entire set-up throughput brings reduced quality of services (QOS). To get better QoS, stable path selection and link disconnection count based nearby device selection carried out in this work. It’s\u0000 on this basis that the thesis is exploring the design and the analysis of the FPC. The FPC is designed in network simulator with the support of optimized fuzzy logic (FL). It has obtained three inputs which is fallout to 27 set of laws. This law sets (LS) direct in the fortitude of the precedence\u0000 to select best path set to transmit a packets from sender to destination. The analyses are with previous protocols of Distributed Admission Control Protocol (DACP) and Call Admission Protocol of MANET. The outcome results monitored with delay, Packet Delivery Ratio (PDR), throughput and overheads\u0000 as the QOS metrics of network.","PeriodicalId":393031,"journal":{"name":"J. Medical Imaging Health Informatics","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129797299","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：