Abstract Objectives Chronic kidney disease (CKD) is a common disease and it is related to a higher risk of cardiovascular disease and end-stage renal disease that can be prevented by the earlier recognition and diagnosis of individuals at risk. Even though risk factors for CKD have been recognized, the effectiveness of CKD risk classification via prediction models remains uncertain. This paper intends to introduce a new predictive model for CKD using US image. Methods The proposed model includes three main phases “(1) preprocessing, (2) feature extraction, (3) and classification.” In the first phase, the input image is subjected to preprocessing, which deploys image inpainting and median filtering processes. After preprocessing, feature extraction takes place under four cases; (a) texture analysis to detect the characteristics of texture, (b) proposed high-level feature enabled local binary pattern (LBP) extraction, (c) area based feature extraction, and (d) mean intensity based feature extraction. These extracted features are then subjected for classification, where “optimized deep convolutional neural network (DCNN)” is used. In order to make the prediction more accurate, the weight and the activation function of DCNN are optimally chosen by a new hybrid model termed as diversity maintained hybrid whale moth flame optimization (DM-HWM) model. Results The accuracy of adopted model at 40th training percentage was 44.72, 11.02, 5.59, 3.92, 3.92, 3.57, 2.59, 1.71, 1.68, and 0.42% superior to traditional artificial neural networks (ANN), support vector machine (SVM), NB, J48, NB-tree, LR, composite hypercube on iterated random projection (CHIRP), CNN, moth flame optimization (MFO), and whale optimization algorithm (WOA) models. Conclusions Finally, the superiority of the adopted scheme is validated over other conventional models in terms of various measures.
{"title":"Deep convolutional neural network for chronic kidney disease prediction using ultrasound imaging","authors":"Smitha Patil, Savita Choudhary","doi":"10.1515/bams-2020-0068","DOIUrl":"https://doi.org/10.1515/bams-2020-0068","url":null,"abstract":"Abstract Objectives Chronic kidney disease (CKD) is a common disease and it is related to a higher risk of cardiovascular disease and end-stage renal disease that can be prevented by the earlier recognition and diagnosis of individuals at risk. Even though risk factors for CKD have been recognized, the effectiveness of CKD risk classification via prediction models remains uncertain. This paper intends to introduce a new predictive model for CKD using US image. Methods The proposed model includes three main phases “(1) preprocessing, (2) feature extraction, (3) and classification.” In the first phase, the input image is subjected to preprocessing, which deploys image inpainting and median filtering processes. After preprocessing, feature extraction takes place under four cases; (a) texture analysis to detect the characteristics of texture, (b) proposed high-level feature enabled local binary pattern (LBP) extraction, (c) area based feature extraction, and (d) mean intensity based feature extraction. These extracted features are then subjected for classification, where “optimized deep convolutional neural network (DCNN)” is used. In order to make the prediction more accurate, the weight and the activation function of DCNN are optimally chosen by a new hybrid model termed as diversity maintained hybrid whale moth flame optimization (DM-HWM) model. Results The accuracy of adopted model at 40th training percentage was 44.72, 11.02, 5.59, 3.92, 3.92, 3.57, 2.59, 1.71, 1.68, and 0.42% superior to traditional artificial neural networks (ANN), support vector machine (SVM), NB, J48, NB-tree, LR, composite hypercube on iterated random projection (CHIRP), CNN, moth flame optimization (MFO), and whale optimization algorithm (WOA) models. Conclusions Finally, the superiority of the adopted scheme is validated over other conventional models in terms of various measures.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"137 - 163"},"PeriodicalIF":1.2,"publicationDate":"2021-04-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0068","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41785768","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}
Abstract Objectives Autism Spectrum Disorders (ASD) represent developmental conditions with deficits in the cognitive, motor, communication and social domains. It is thought that imitative behaviour may be impaired in children with ASD. The Mirror Neural System (MNS) concept plays an important role in theories explaining the link between action perception, imitation and social decision-making in ASD. Methods In this study, Emergent 7.0.1 software was used to build a computational model of the phenomenon of MNS influence on motion imitation. Seven point populations of Hodgkin–Huxley artificial neurons were used to create a simplified model. Results The model shows pathologically altered processing in the neural network, which may reflect processes observed in ASD due to reduced stimulus attenuation. The model is considered preliminary—further research should test for a minimally significant difference between the states: normal processing and pathological processing. Conclusions The study shows that even a simple computational model can provide insight into the mechanisms underlying the phenomena observed in experimental studies, including in children with ASD.
{"title":"Computational model of decreased suppression of mu rhythms in patients with Autism Spectrum Disorders during movement observation—preliminary findings","authors":"Dariusz Zapała, D. Mikołajewski","doi":"10.1515/bams-2020-0064","DOIUrl":"https://doi.org/10.1515/bams-2020-0064","url":null,"abstract":"Abstract Objectives Autism Spectrum Disorders (ASD) represent developmental conditions with deficits in the cognitive, motor, communication and social domains. It is thought that imitative behaviour may be impaired in children with ASD. The Mirror Neural System (MNS) concept plays an important role in theories explaining the link between action perception, imitation and social decision-making in ASD. Methods In this study, Emergent 7.0.1 software was used to build a computational model of the phenomenon of MNS influence on motion imitation. Seven point populations of Hodgkin–Huxley artificial neurons were used to create a simplified model. Results The model shows pathologically altered processing in the neural network, which may reflect processes observed in ASD due to reduced stimulus attenuation. The model is considered preliminary—further research should test for a minimally significant difference between the states: normal processing and pathological processing. Conclusions The study shows that even a simple computational model can provide insight into the mechanisms underlying the phenomena observed in experimental studies, including in children with ASD.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"95 - 102"},"PeriodicalIF":1.2,"publicationDate":"2021-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0064","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44373745","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}
K. Kocemba-Pilarczyk, P. Dudzik, Katarzyna Leśkiewicz
Abstract Objectives CD146 is an adhesive molecule that was originally reported on malignant melanoma cells as a protein crucial for cell adhesion. It is now known that high expression of the CD146 protein is not only characteristic of melanoma, but it occurs on a number of cancers, contributing to worse prognosis and increased aggressiveness. Independent in vitro studies in breast cancer have shown that CD146 protein alone can induce a change in epithelial to mesenchymal transcriptional profile, which is the basis of the tumor aggressiveness and metastasis. Methods In the following work, the correlation coefficients were analyzed between the genes of the mesenchymal profile and the CD146 gene in 10 independent transcriptomic data of breast cancer patients. Results The analysis confirmed the relationship between CD146 expression and mesenchymal profile genes, pointing VIMENTIN as the gene which expression is most strongly correlated with the CD146, suggesting that both genes, CD146 and VIM may be directly controlled by the same mechanism or regulate one another. Conclusions The analysis points a potential route for research on the CD146 gene expression, which may lead to understanding of its regulation in breast cancer, contributing to the development of new therapeutic strategies targeting highly metastatic breast cancer cells.
{"title":"The relationship between expression of VIMENTIN and CD146 genes in breast cancer","authors":"K. Kocemba-Pilarczyk, P. Dudzik, Katarzyna Leśkiewicz","doi":"10.1515/bams-2020-0058","DOIUrl":"https://doi.org/10.1515/bams-2020-0058","url":null,"abstract":"Abstract Objectives CD146 is an adhesive molecule that was originally reported on malignant melanoma cells as a protein crucial for cell adhesion. It is now known that high expression of the CD146 protein is not only characteristic of melanoma, but it occurs on a number of cancers, contributing to worse prognosis and increased aggressiveness. Independent in vitro studies in breast cancer have shown that CD146 protein alone can induce a change in epithelial to mesenchymal transcriptional profile, which is the basis of the tumor aggressiveness and metastasis. Methods In the following work, the correlation coefficients were analyzed between the genes of the mesenchymal profile and the CD146 gene in 10 independent transcriptomic data of breast cancer patients. Results The analysis confirmed the relationship between CD146 expression and mesenchymal profile genes, pointing VIMENTIN as the gene which expression is most strongly correlated with the CD146, suggesting that both genes, CD146 and VIM may be directly controlled by the same mechanism or regulate one another. Conclusions The analysis points a potential route for research on the CD146 gene expression, which may lead to understanding of its regulation in breast cancer, contributing to the development of new therapeutic strategies targeting highly metastatic breast cancer cells.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"1 - 7"},"PeriodicalIF":1.2,"publicationDate":"2021-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0058","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49204472","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}
Abstract There have been significant developments in clinical, experimental, and theoretical approaches to understand the biomechanics of tumor cells and immune cells. Cytotoxic T lymphocytes (CTLs) are regarded as a major antitumor mechanism of immune cells. Mathematical modeling of tumor growth is an important and useful tool to observe and understand clinical phenomena analytically. This work develops a novel two-variable mathematical model to describe the interaction of tumor cells and CTLs. The designed model is providing an integrated framework to investigate the complexity of tumor progression and answer clinical questions that cannot always be reached with experimental tools. The parameters of the model are estimated from experimental study and stability analysis of the model is performed through nullclines. A global sensitivity analysis is also performed to check the uncertainty of the parameters. The results of numerical simulations of the model support the importance of the CTLs and demonstrate that CTLs can eliminate small tumors. The proposed model provides efficacious information to study and demonstrate the complex dynamics of breast cancer.
{"title":"Bio-algorithms for the modeling and simulation of cancer cells and the immune response","authors":"M. Idrees, A. Sohail","doi":"10.1515/bams-2020-0054","DOIUrl":"https://doi.org/10.1515/bams-2020-0054","url":null,"abstract":"Abstract There have been significant developments in clinical, experimental, and theoretical approaches to understand the biomechanics of tumor cells and immune cells. Cytotoxic T lymphocytes (CTLs) are regarded as a major antitumor mechanism of immune cells. Mathematical modeling of tumor growth is an important and useful tool to observe and understand clinical phenomena analytically. This work develops a novel two-variable mathematical model to describe the interaction of tumor cells and CTLs. The designed model is providing an integrated framework to investigate the complexity of tumor progression and answer clinical questions that cannot always be reached with experimental tools. The parameters of the model are estimated from experimental study and stability analysis of the model is performed through nullclines. A global sensitivity analysis is also performed to check the uncertainty of the parameters. The results of numerical simulations of the model support the importance of the CTLs and demonstrate that CTLs can eliminate small tumors. The proposed model provides efficacious information to study and demonstrate the complex dynamics of breast cancer.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"55 - 63"},"PeriodicalIF":1.2,"publicationDate":"2021-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0054","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48607485","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}
Pub Date : 2020-12-25DOI: 10.20944/preprints202012.0657.v1
S. Farias, M. José, F. Prosdocimi
Cells occupy a prominent place in the history of life in Earth. The central role of cellular organization can be understood by the fact that "cellular life" is often used as a synonym for life itself. Thus, most characteristics used to define cell overlap with those ones used to define life. However, innovative scenarios for the origin of life are bringing alternative views to describe how cells may have evolved from the open biological systems named progenotes. Here, using a logical and conceptual analysis, we re-evaluate the characteristics used to infer a single origin for cells. We argue that some evidences used to support cell monophyly, such as the presence of elements from the translation mechanism together with the universality of the genetic code, actually indicate a unique origin for all "biological systems", a term used to define not only cells, but also viruses and progenotes. Besides, we present evidence that at least two biochemical pathways as important as (i) DNA replication and (ii) lipid biosynthesis are not homologous between Bacteria and Archaea. The identities observed between the proteins involved in those pathways along representatives of these two ancestral domains of life are too low to indicate common genic ancestry. Altogether these facts can be seen as an indication that cellular organization has possibly evolved two or more times and that LUCA (the Last Universal Common Ancestor) may not have existed as a cellular entity. Thus, we aim to consider the possibility that different strategies acquired by biological systems to exist, such as viral, bacterial and archaeal were most likely originated independently from the evolution of different progenote populations.
{"title":"Is it possible that cells have had more than one origin?","authors":"S. Farias, M. José, F. Prosdocimi","doi":"10.20944/preprints202012.0657.v1","DOIUrl":"https://doi.org/10.20944/preprints202012.0657.v1","url":null,"abstract":"Cells occupy a prominent place in the history of life in Earth. The central role of cellular organization can be understood by the fact that \"cellular life\" is often used as a synonym for life itself. Thus, most characteristics used to define cell overlap with those ones used to define life. However, innovative scenarios for the origin of life are bringing alternative views to describe how cells may have evolved from the open biological systems named progenotes. Here, using a logical and conceptual analysis, we re-evaluate the characteristics used to infer a single origin for cells. We argue that some evidences used to support cell monophyly, such as the presence of elements from the translation mechanism together with the universality of the genetic code, actually indicate a unique origin for all \"biological systems\", a term used to define not only cells, but also viruses and progenotes. Besides, we present evidence that at least two biochemical pathways as important as (i) DNA replication and (ii) lipid biosynthesis are not homologous between Bacteria and Archaea. The identities observed between the proteins involved in those pathways along representatives of these two ancestral domains of life are too low to indicate common genic ancestry. Altogether these facts can be seen as an indication that cellular organization has possibly evolved two or more times and that LUCA (the Last Universal Common Ancestor) may not have existed as a cellular entity. Thus, we aim to consider the possibility that different strategies acquired by biological systems to exist, such as viral, bacterial and archaeal were most likely originated independently from the evolution of different progenote populations.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"271 1","pages":"104371"},"PeriodicalIF":1.2,"publicationDate":"2020-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73013683","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}
Abstract Objectives The main aim of this work is to introduce a robust controller for controlling the drug dosage. Methods The presented work establishes a novel robust controller that controls the drug dosage and it also carried out parameters estimation. Along with this, a Regularized Error Function-based EKF (REF-EKF) is introduced for estimating the tumor cells that could be adapted for different conditions. It also assists in solving the overfitting problems, which occur during the drug dosage estimation. Moreover, the performance of the adopted controller is compared over other conventional schemes, and the attained outcomes reveal the appropriate impact of drug dosage injection on immune, normal, and tumor cells. It is also ensured that the presented controller does a robust performance on the parameter uncertainties. Moreover, to enhance the performance of the proposed system and for fast convergence, it is aimed to fine-tune the initial state of EKF optimally using a new Improved Gray Wolf Optimization (GWO) termed as Adaptive GWO (AGWO). Finally, analysis is held to validate the betterment of the presented model. Results The outcomes, the proposed method has accomplished a minimal value of error with an increase in time, when evaluated over the compared models. Conclusions Thus, the improvement of the proposed REF-EKF-AGWO model is proved from the attained results.
{"title":"Regularized error function-based extended Kalman filter for estimating the cancer chemotherapy dosage: impact of improved grey wolf optimization","authors":"U. L. Mohite, H. Patel","doi":"10.1515/bams-2020-0048","DOIUrl":"https://doi.org/10.1515/bams-2020-0048","url":null,"abstract":"Abstract Objectives The main aim of this work is to introduce a robust controller for controlling the drug dosage. Methods The presented work establishes a novel robust controller that controls the drug dosage and it also carried out parameters estimation. Along with this, a Regularized Error Function-based EKF (REF-EKF) is introduced for estimating the tumor cells that could be adapted for different conditions. It also assists in solving the overfitting problems, which occur during the drug dosage estimation. Moreover, the performance of the adopted controller is compared over other conventional schemes, and the attained outcomes reveal the appropriate impact of drug dosage injection on immune, normal, and tumor cells. It is also ensured that the presented controller does a robust performance on the parameter uncertainties. Moreover, to enhance the performance of the proposed system and for fast convergence, it is aimed to fine-tune the initial state of EKF optimally using a new Improved Gray Wolf Optimization (GWO) termed as Adaptive GWO (AGWO). Finally, analysis is held to validate the betterment of the presented model. Results The outcomes, the proposed method has accomplished a minimal value of error with an increase in time, when evaluated over the compared models. Conclusions Thus, the improvement of the proposed REF-EKF-AGWO model is proved from the attained results.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"41 - 54"},"PeriodicalIF":1.2,"publicationDate":"2020-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0048","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49539962","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}
Abstract Objectives Spinal cord damage is one of the traumatic situations in persons that may cause the loss of sensation and proper functioning of the muscles either temporarily or permanently. Hence, steps to assure the recovery through the early functioning and precaution could safe-guard a proper interceptive. To ensure the recovery of spinal cord damage through optimized recurrent neural network. Methods The research on the spinal cord injury classification and level detection is done using the CT images, which is initially given to the segmentation that is done using the adaptive thresholding methodology. Once the segments are formed, the disc is localized using the sparse fuzzy C-means clustering approach. In the next step, the features are extracted from the localized disc and the features include the connectivity features, statistical features, image-level features, grid-level features, Histogram of Oriented Gradients (HOG), and Linear Gradient Pattern (LGP). Then, the injury detection is done based on the Crow search Rider Optimization algorithm-based Deep Convolutional Neural Network (CS-ROA-based DCNN). Once the result regarding the presence of the injury is obtained, the injury-level classification is done based on the proposed Deep Recurrent Neural Network (Deep RNN), and in case of the absence of injury, the process is terminated. Therefore, the injury detection classifier derives the level of the injury, such as normal, wedge, biconcavity, and crush. Results The experimentation is carried out using an Osteoporotic vertebral fractures database. The performance of the injury level detection based on the proposed model is evaluated based on accuracy, sensitivity, and specificity. The proposed model achieves the maximal accuracy of 0.895, maximal sensitivity of 0.871, and the maximal specificity of 0.933 with respect to K-Fold. Conclusions The experimental results show that the proposed model is better than the existing models in terms of accuracy, sensitivity, and specificity.
{"title":"Injury classification and level detection of the spinal cord based on the optimized recurrent neural network","authors":"K. MunavarJasim, T. Brindha","doi":"10.1515/bams-2019-0065","DOIUrl":"https://doi.org/10.1515/bams-2019-0065","url":null,"abstract":"Abstract Objectives Spinal cord damage is one of the traumatic situations in persons that may cause the loss of sensation and proper functioning of the muscles either temporarily or permanently. Hence, steps to assure the recovery through the early functioning and precaution could safe-guard a proper interceptive. To ensure the recovery of spinal cord damage through optimized recurrent neural network. Methods The research on the spinal cord injury classification and level detection is done using the CT images, which is initially given to the segmentation that is done using the adaptive thresholding methodology. Once the segments are formed, the disc is localized using the sparse fuzzy C-means clustering approach. In the next step, the features are extracted from the localized disc and the features include the connectivity features, statistical features, image-level features, grid-level features, Histogram of Oriented Gradients (HOG), and Linear Gradient Pattern (LGP). Then, the injury detection is done based on the Crow search Rider Optimization algorithm-based Deep Convolutional Neural Network (CS-ROA-based DCNN). Once the result regarding the presence of the injury is obtained, the injury-level classification is done based on the proposed Deep Recurrent Neural Network (Deep RNN), and in case of the absence of injury, the process is terminated. Therefore, the injury detection classifier derives the level of the injury, such as normal, wedge, biconcavity, and crush. Results The experimentation is carried out using an Osteoporotic vertebral fractures database. The performance of the injury level detection based on the proposed model is evaluated based on accuracy, sensitivity, and specificity. The proposed model achieves the maximal accuracy of 0.895, maximal sensitivity of 0.871, and the maximal specificity of 0.933 with respect to K-Fold. Conclusions The experimental results show that the proposed model is better than the existing models in terms of accuracy, sensitivity, and specificity.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"25 - 40"},"PeriodicalIF":1.2,"publicationDate":"2020-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2019-0065","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41370125","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}
B. Narhari, Bakwad Kamlakar Murlidhar, A. Sayyad, G. Sable
Abstract Objectives The focus of this paper is to introduce an automated early Diabetic Retinopathy (DR) detection scheme from colour fundus images through enhanced segmentation and classification strategies by analyzing blood vessels. Methods The occurrence of DR is increasing from the past years, impacting the eyes due to a sudden rise in the glucose level of blood. All over the world, half of the people who are under age 70 are severely suffered from diabetes. The patients who are affected by DR will lose their vision during the absence of early recognition of DR and appropriate treatment. To decrease the growth and occurrence of loss of vision, the early detection and timely treatment of DR are desirable. At present, deep learning models have presented better performance using retinal images for DR detection. In this work, the input retinal fundus images are initially subjected to pre-processing that undergoes contrast enhancement by Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filtering. Further, the optimized binary thresholding-based segmentation is done for blood vessel segmentation. For the segmented image, Tri-level Discrete Level Decomposition (Tri-DWT) is performed to decompose it. In the feature extraction phase, Local Binary Pattern (LBP), and Gray-Level Co-occurrence Matrices (GLCMs) are extracted. Next, the classification of images is done through the combination of two algorithms, one is Neural Network (NN), and the other Convolutional Neural Network (CNN). The extracted features are subjected to NN, and the tri-DWT-based segmented image is subjected to CNN. Both the segmentation and classification phases are enhanced by the improved meta-heuristic algorithm called Fitness Rate-based Crow Search Algorithm (FR-CSA), in which few parameters are optimized for attaining maximum detection accuracy. Results The proposed DR detection model was implemented in MATLAB 2018a, and the analysis was done using three datasets, HRF, Messidor, and DIARETDB. Conclusions The developed FR-CSA algorithm has the best detection accuracy in diagnosing DR.
{"title":"Automated diagnosis of diabetic retinopathy enabled by optimized thresholding-based blood vessel segmentation and hybrid classifier","authors":"B. Narhari, Bakwad Kamlakar Murlidhar, A. Sayyad, G. Sable","doi":"10.1515/bams-2020-0053","DOIUrl":"https://doi.org/10.1515/bams-2020-0053","url":null,"abstract":"Abstract Objectives The focus of this paper is to introduce an automated early Diabetic Retinopathy (DR) detection scheme from colour fundus images through enhanced segmentation and classification strategies by analyzing blood vessels. Methods The occurrence of DR is increasing from the past years, impacting the eyes due to a sudden rise in the glucose level of blood. All over the world, half of the people who are under age 70 are severely suffered from diabetes. The patients who are affected by DR will lose their vision during the absence of early recognition of DR and appropriate treatment. To decrease the growth and occurrence of loss of vision, the early detection and timely treatment of DR are desirable. At present, deep learning models have presented better performance using retinal images for DR detection. In this work, the input retinal fundus images are initially subjected to pre-processing that undergoes contrast enhancement by Contrast Limited Adaptive Histogram Equalization (CLAHE) and average filtering. Further, the optimized binary thresholding-based segmentation is done for blood vessel segmentation. For the segmented image, Tri-level Discrete Level Decomposition (Tri-DWT) is performed to decompose it. In the feature extraction phase, Local Binary Pattern (LBP), and Gray-Level Co-occurrence Matrices (GLCMs) are extracted. Next, the classification of images is done through the combination of two algorithms, one is Neural Network (NN), and the other Convolutional Neural Network (CNN). The extracted features are subjected to NN, and the tri-DWT-based segmented image is subjected to CNN. Both the segmentation and classification phases are enhanced by the improved meta-heuristic algorithm called Fitness Rate-based Crow Search Algorithm (FR-CSA), in which few parameters are optimized for attaining maximum detection accuracy. Results The proposed DR detection model was implemented in MATLAB 2018a, and the analysis was done using three datasets, HRF, Messidor, and DIARETDB. Conclusions The developed FR-CSA algorithm has the best detection accuracy in diagnosing DR.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"9 - 23"},"PeriodicalIF":1.2,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0053","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41319144","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. Krajka, Ireneusz Panasiuk, Adam Misiura, Grzegorz M. Wójcik
Abstract Objectives The most common technique of determining biological paternity or another relationship among people are the investigations of DNA polymorphism called Fingerprinting DNA. The key concept of these investigations is the statistical analysis, which leads to obtain the likelihood ratio (LR), sometimes called the paternity index. Methods Among the different assumptions stated in these computations is a mutation model (this model is used for all the computations). Results and conclusions Although its influence on LR is usually negligible, there are some situations (when the mother–child mutation arises) when it is crucial.
{"title":"On the mutation model used in the fingerprinting DNA","authors":"A. Krajka, Ireneusz Panasiuk, Adam Misiura, Grzegorz M. Wójcik","doi":"10.1515/bams-2020-0057","DOIUrl":"https://doi.org/10.1515/bams-2020-0057","url":null,"abstract":"Abstract Objectives The most common technique of determining biological paternity or another relationship among people are the investigations of DNA polymorphism called Fingerprinting DNA. The key concept of these investigations is the statistical analysis, which leads to obtain the likelihood ratio (LR), sometimes called the paternity index. Methods Among the different assumptions stated in these computations is a mutation model (this model is used for all the computations). Results and conclusions Although its influence on LR is usually negligible, there are some situations (when the mother–child mutation arises) when it is crucial.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":" ","pages":""},"PeriodicalIF":1.2,"publicationDate":"2020-12-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0057","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45538655","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}
Parvathaneni Rajendra Kumar, S. Ravichandran, S. Narayana
Abstract Objectives This research work exclusively aims to develop a novel heart disease prediction framework including three major phases, namely proposed feature extraction, dimensionality reduction, and proposed ensemble-based classification. Methods As the novelty, the training of NN is carried out by a new enhanced optimization algorithm referred to as Sea Lion with Canberra Distance (S-CDF) via tuning the optimal weights. The improved S-CDF algorithm is the extended version of the existing “Sea Lion Optimization (SLnO)”. Initially, the statistical and higher-order statistical features are extracted including central tendency, degree of dispersion, and qualitative variation, respectively. However, in this scenario, the “curse of dimensionality” seems to be the greatest issue, such that there is a necessity of dimensionality reduction in the extracted features. Hence, the principal component analysis (PCA)-based feature reduction approach is deployed here. Finally, the dimensional concentrated features are fed as the input to the proposed ensemble technique with “Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN)” with optimized Neural Network (NN) as the final classifier. Results An elaborative analyses as well as discussion have been provided by concerning the parameters, like evaluation metrics, year of publication, accuracy, implementation tool, and utilized datasets obtained by various techniques. Conclusions From the experiment outcomes, it is proved that the accuracy of the proposed work with the proposed feature set is 5, 42.85, and 10% superior to the performance with other feature sets like central tendency + dispersion feature, central tendency qualitative variation, and dispersion qualitative variation, respectively. Results Finally, the comparative evaluation shows that the presented work is appropriate for heart disease prediction as it has high accuracy than the traditional works.
{"title":"Ensemble classification technique for heart disease prediction with meta-heuristic-enabled training system","authors":"Parvathaneni Rajendra Kumar, S. Ravichandran, S. Narayana","doi":"10.1515/bams-2020-0033","DOIUrl":"https://doi.org/10.1515/bams-2020-0033","url":null,"abstract":"Abstract Objectives This research work exclusively aims to develop a novel heart disease prediction framework including three major phases, namely proposed feature extraction, dimensionality reduction, and proposed ensemble-based classification. Methods As the novelty, the training of NN is carried out by a new enhanced optimization algorithm referred to as Sea Lion with Canberra Distance (S-CDF) via tuning the optimal weights. The improved S-CDF algorithm is the extended version of the existing “Sea Lion Optimization (SLnO)”. Initially, the statistical and higher-order statistical features are extracted including central tendency, degree of dispersion, and qualitative variation, respectively. However, in this scenario, the “curse of dimensionality” seems to be the greatest issue, such that there is a necessity of dimensionality reduction in the extracted features. Hence, the principal component analysis (PCA)-based feature reduction approach is deployed here. Finally, the dimensional concentrated features are fed as the input to the proposed ensemble technique with “Support Vector Machine (SVM), Random Forest (RF), K-Nearest Neighbor (KNN)” with optimized Neural Network (NN) as the final classifier. Results An elaborative analyses as well as discussion have been provided by concerning the parameters, like evaluation metrics, year of publication, accuracy, implementation tool, and utilized datasets obtained by various techniques. Conclusions From the experiment outcomes, it is proved that the accuracy of the proposed work with the proposed feature set is 5, 42.85, and 10% superior to the performance with other feature sets like central tendency + dispersion feature, central tendency qualitative variation, and dispersion qualitative variation, respectively. Results Finally, the comparative evaluation shows that the presented work is appropriate for heart disease prediction as it has high accuracy than the traditional works.","PeriodicalId":42620,"journal":{"name":"Bio-Algorithms and Med-Systems","volume":"17 1","pages":"119 - 136"},"PeriodicalIF":1.2,"publicationDate":"2020-11-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1515/bams-2020-0033","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43689362","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：