J. Lichtenberg, Guanjue Xiang, Elisabeth F. Heuston, B. Giardine, C. Keller, R. Hardison, D. Bodine, Yu Zhang
Motivation: Systems biology integrates expression, methylation, transcription factor binding and histone modification profiles with other physiological characteristics of a specific organ. Repositories that provide the required data, like ENCODE, generally work on a high level and do not take the heterogeneity of cell types within an organ into consideration. The hematopoietic system allows the characterization and study of each cell type involved in the generation of blood cells from bone marrow stem cells and thus provides a good foundation for systems biology studies. Here we compare RNA expression, DNA methylation, chromatin accessibility, DNA binding proteins and histone modification profiles in seven different hematopoietic populations using a Bayesian non-parametric hierarchical latent-class mixed-effect model known as IDEAS to characterize epigenetic changes associated with hematopoietic differentiation. Unlike other existing approaches IDEAS considers various cell types of a biological systems in concert instead of disjointly. Results: Using the VISION database and the IDEAS toolkit we provide insights into the transcriptional, epigenetic and regulatory programs governing the hematopoietic differentiation process. The characterization of the different hematopoietic components and their interactions provide the foundations for a systems biology model of hematopoiesis. Previous hematopoietic epigenome segmentation studies have focused on histone modifications, chromatin accessibility and DNA binding protein profiles. DNA methylation has been shown to vary markedly in hematopoietic populations. Inclusion of DNA methylation in these segmentation studies increased the original 36-state model of regulatory interactions to 41 states. These new DNA methylation-related states were associated with repressive marks, active RNA transcription, and a novel state regulated by DNA methylation alone. Imputing epigenetic models on inputs systematically perturbed for hematopoietic populations resulted in models of varying degrees of overlap, which were quantified and set in context with underlying biological processes. Conclusion: Our data show that methylation has a strong impact on functional genomic modeling and can be used to discern cell type specific epigenetic regulatory behavior by leveraging imputation for missing cell type data.
{"title":"Systems Biology in Heterogenous Tissues: Integrating Multiple *Omics Datasets to Understand Hematopoietic Differentiation","authors":"J. Lichtenberg, Guanjue Xiang, Elisabeth F. Heuston, B. Giardine, C. Keller, R. Hardison, D. Bodine, Yu Zhang","doi":"10.1109/BIBE.2019.00050","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00050","url":null,"abstract":"Motivation: Systems biology integrates expression, methylation, transcription factor binding and histone modification profiles with other physiological characteristics of a specific organ. Repositories that provide the required data, like ENCODE, generally work on a high level and do not take the heterogeneity of cell types within an organ into consideration. The hematopoietic system allows the characterization and study of each cell type involved in the generation of blood cells from bone marrow stem cells and thus provides a good foundation for systems biology studies. Here we compare RNA expression, DNA methylation, chromatin accessibility, DNA binding proteins and histone modification profiles in seven different hematopoietic populations using a Bayesian non-parametric hierarchical latent-class mixed-effect model known as IDEAS to characterize epigenetic changes associated with hematopoietic differentiation. Unlike other existing approaches IDEAS considers various cell types of a biological systems in concert instead of disjointly. Results: Using the VISION database and the IDEAS toolkit we provide insights into the transcriptional, epigenetic and regulatory programs governing the hematopoietic differentiation process. The characterization of the different hematopoietic components and their interactions provide the foundations for a systems biology model of hematopoiesis. Previous hematopoietic epigenome segmentation studies have focused on histone modifications, chromatin accessibility and DNA binding protein profiles. DNA methylation has been shown to vary markedly in hematopoietic populations. Inclusion of DNA methylation in these segmentation studies increased the original 36-state model of regulatory interactions to 41 states. These new DNA methylation-related states were associated with repressive marks, active RNA transcription, and a novel state regulated by DNA methylation alone. Imputing epigenetic models on inputs systematically perturbed for hematopoietic populations resulted in models of varying degrees of overlap, which were quantified and set in context with underlying biological processes. Conclusion: Our data show that methylation has a strong impact on functional genomic modeling and can be used to discern cell type specific epigenetic regulatory behavior by leveraging imputation for missing cell type data.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130544708","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}
M. B. Moran, G. H. Apostolo, A. S. Araújo, Eduardo de O. Andrade, J. V. Filho, A. Conci
Most studies analyzing medical images at some stage require the demarcation of boundaries of biological structures. This process is called segmentation. In some contexts, current techniques present satisfactory results, but in others, like breast segmentation in thermographies, it remains an open problem. Several studies have investigated the use of automated solutions for this problem. However, the automatic process does not always present a satisfactory result, requiring the active involvement of a specialist for validating it and re-segmenting images when necessary. As such task can be expensive and take too long to be completed, this scenario drives the exploration of alternative approaches for the segmentation process. Hence, in this work we propose an alternative that combines traditional techniques of image processing with techniques of collective intelligence, which is based on the wisdom of crowds to solve problems in a faster and less expensive way. We present SegMedBC, a prototype in which the methods previously mentioned are applied to improve the segmentation process. Furthermore, an experimental study is carried out to validate the involvement of lay users in this activity.
{"title":"A Novel Approach for the Segmentation of Breast Thermal Images Combining Image Processing and Collective Intelligence","authors":"M. B. Moran, G. H. Apostolo, A. S. Araújo, Eduardo de O. Andrade, J. V. Filho, A. Conci","doi":"10.1109/BIBE.2019.00099","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00099","url":null,"abstract":"Most studies analyzing medical images at some stage require the demarcation of boundaries of biological structures. This process is called segmentation. In some contexts, current techniques present satisfactory results, but in others, like breast segmentation in thermographies, it remains an open problem. Several studies have investigated the use of automated solutions for this problem. However, the automatic process does not always present a satisfactory result, requiring the active involvement of a specialist for validating it and re-segmenting images when necessary. As such task can be expensive and take too long to be completed, this scenario drives the exploration of alternative approaches for the segmentation process. Hence, in this work we propose an alternative that combines traditional techniques of image processing with techniques of collective intelligence, which is based on the wisdom of crowds to solve problems in a faster and less expensive way. We present SegMedBC, a prototype in which the methods previously mentioned are applied to improve the segmentation process. Furthermore, an experimental study is carried out to validate the involvement of lay users in this activity.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132973852","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}
Improving knowledge of RNA-binding protein targets is focusing the attention towards non-coding RNAs (ncRNAs), i.e., transcripts not translated into a protein; they are associated with a wide range of biological functions through different molecular mechanisms, usually concerning the interaction with one or more protein partners. Recent studies confirmed that the alteration of ncRNA-protein interactions (ncRPIs) may be linked to various pathologies, including autoimmune and metabolic diseases, neurological and muscular disorders and cancer. Unfortunately, the limited number of structurally characterized RNA-protein complexes available does not allow to accurately establish their role in cellular processes and diseases. Experimental analyses to identify ncRNA-protein interactions are providing a large amount of valuable data, but these experiments are expensive and time-consuming. For these reasons, computational approaches based on machine learning techniques appear very useful to predict ncRPIs. Yet, there are still few studies regarding the prediction of ncRPIs, especially including the use of higher-order structures, which are of vital importance for the ncRPI functions. In this work, a new computational method for non-coding RNA-protein interaction prediction is developed; from sequence data, it derives more accurate information about the secondary structure of the molecules involved in such interactions, which it then uses in the prediction. Obtained results suggest that the use of machine learning techniques, together with considering also information on higher-order structures of ncRNAs and proteins, can be useful to better predict ncRPIs.
{"title":"De Novo Sequence-Based Method for ncRPI Prediction using Structural Information","authors":"M. Leone, Marta Galvani, M. Masseroli","doi":"10.1109/BIBE.2019.00034","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00034","url":null,"abstract":"Improving knowledge of RNA-binding protein targets is focusing the attention towards non-coding RNAs (ncRNAs), i.e., transcripts not translated into a protein; they are associated with a wide range of biological functions through different molecular mechanisms, usually concerning the interaction with one or more protein partners. Recent studies confirmed that the alteration of ncRNA-protein interactions (ncRPIs) may be linked to various pathologies, including autoimmune and metabolic diseases, neurological and muscular disorders and cancer. Unfortunately, the limited number of structurally characterized RNA-protein complexes available does not allow to accurately establish their role in cellular processes and diseases. Experimental analyses to identify ncRNA-protein interactions are providing a large amount of valuable data, but these experiments are expensive and time-consuming. For these reasons, computational approaches based on machine learning techniques appear very useful to predict ncRPIs. Yet, there are still few studies regarding the prediction of ncRPIs, especially including the use of higher-order structures, which are of vital importance for the ncRPI functions. In this work, a new computational method for non-coding RNA-protein interaction prediction is developed; from sequence data, it derives more accurate information about the secondary structure of the molecules involved in such interactions, which it then uses in the prediction. Obtained results suggest that the use of machine learning techniques, together with considering also information on higher-order structures of ncRNAs and proteins, can be useful to better predict ncRPIs.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"63 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131938121","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}
Branko Arsić, Mihailo Obrenović, Miloš Anić, A. Tsuda, N. Filipovic
Pulmonary acinus represents the gas exchange unit which includes branches of the terminal bronchiole, alveolar ducts, alveolar sacs, alveoli and associated blood vessels. Over the past few decades, many results related to the fluid mechanics characterizing pulmonary acinus of the lungs have been reported. In order to describe a micromechanics in 3D acinar micro-architecture and airflow through it, 3D reconstruction of parenchyma with computational fluid dynamics plays an important role. For the reliable 3D model, precise image segmentation of the stacked 2D images is a necessary pre-step. However, in most cases this step is neglected and the classic threshold segmentation is applied. Convolutional neural networks proved to be very successful in image classification and object detection, and in the field of medical image segmentation U-Net architecture showed very good performance. In this paper, automatic pulmonary acinus lung field segmentation has been performed using U-Net based deep convolutional network. Our proposed model has been evaluated on the images of rat lungs imaged by synchrotron radiation-based X-ray tomographic microscopy (SRXTM). The experimental results show that our model outperforms the baseline models.
{"title":"Image Segmentation of the Pulmonary Acinus Imaged by Synchrotron X-Ray Tomography","authors":"Branko Arsić, Mihailo Obrenović, Miloš Anić, A. Tsuda, N. Filipovic","doi":"10.1109/BIBE.2019.00101","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00101","url":null,"abstract":"Pulmonary acinus represents the gas exchange unit which includes branches of the terminal bronchiole, alveolar ducts, alveolar sacs, alveoli and associated blood vessels. Over the past few decades, many results related to the fluid mechanics characterizing pulmonary acinus of the lungs have been reported. In order to describe a micromechanics in 3D acinar micro-architecture and airflow through it, 3D reconstruction of parenchyma with computational fluid dynamics plays an important role. For the reliable 3D model, precise image segmentation of the stacked 2D images is a necessary pre-step. However, in most cases this step is neglected and the classic threshold segmentation is applied. Convolutional neural networks proved to be very successful in image classification and object detection, and in the field of medical image segmentation U-Net architecture showed very good performance. In this paper, automatic pulmonary acinus lung field segmentation has been performed using U-Net based deep convolutional network. Our proposed model has been evaluated on the images of rat lungs imaged by synchrotron radiation-based X-ray tomographic microscopy (SRXTM). The experimental results show that our model outperforms the baseline models.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131319630","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}
Fotis Konstantakopoulos, Eleni I. Georga, Kostas Klampanas, Dimitris Rouvalis, Nikolaos Ioannou, D. Fotiadis
The daily care of type 1 diabetes has been considerably improved through the increased adoption of continuous glucose monitoring, continuous subcutaneous insulin infusion, and precise behavioral monitoring (diet, physical activity) mHealth solutions. In this study, we present the food recognition and nutrient estimation components of the GlucoseML system; a type 1 diabetes self-management system relying on short-term predictive analytics of the glucose trajectory. A computer-vision-based approach is outlined combining image processing and machine learning to plate detection, food segmentation, food recognition and volume estimation of a plate's content. The systematic collection of an annotated Greek food images dataset allows the evaluation of the proposed methodology.
{"title":"Automatic Estimation of the Nutritional Composition of Foods as Part of the GlucoseML Type 1 Diabetes Self-Management System","authors":"Fotis Konstantakopoulos, Eleni I. Georga, Kostas Klampanas, Dimitris Rouvalis, Nikolaos Ioannou, D. Fotiadis","doi":"10.1109/BIBE.2019.00091","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00091","url":null,"abstract":"The daily care of type 1 diabetes has been considerably improved through the increased adoption of continuous glucose monitoring, continuous subcutaneous insulin infusion, and precise behavioral monitoring (diet, physical activity) mHealth solutions. In this study, we present the food recognition and nutrient estimation components of the GlucoseML system; a type 1 diabetes self-management system relying on short-term predictive analytics of the glucose trajectory. A computer-vision-based approach is outlined combining image processing and machine learning to plate detection, food segmentation, food recognition and volume estimation of a plate's content. The systematic collection of an annotated Greek food images dataset allows the evaluation of the proposed methodology.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123176168","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}
Georgios C. Manikis, M. Venianaki, I. Skepasianos, G. Papadakis, T. Maris, S. Agelaki, A. Karantanas, K. Marias
Radiomics-based studies have created an unprecedented momentum in computational medical imaging over the last years by significantly advancing and empowering correlational and predictive quantitative studies in numerous clinical applications. An important element of this exciting field of research especially in oncology is multi-scale texture analysis since it can effectively describe tissue heterogeneity, which is highly informative for clinical diagnosis and prognosis. There are however, several concerns regarding the plethora of radiomics features used in the literature especially regarding their performance consistency across studies. Since many studies use software packages that yield multi-scale texture features it makes sense to investigate the scale-space performance of texture candidate biomarkers under the hypothesis that significant texture markers may have a more persistent scale-space performance. To this end, this study proposes a methodology for the extraction of Gabor multi-scale and orientation texture DCE-MRI radiomics for predicting breast cancer complete response to neoadjuvant therapy. More specifically, a Gabor filter bank was created using four different orientations and ten different scales and then firstorder and second-order texture features were extracted for each scale-orientation data representation. The performance of all these features was evaluated under a generalized repeated cross-validation framework in a scale-space fashion using extreme gradient boosting classifiers.
{"title":"Scale-Space DCE-MRI Radiomics Analysis Based on Gabor Filters for Predicting Breast Cancer Therapy Response","authors":"Georgios C. Manikis, M. Venianaki, I. Skepasianos, G. Papadakis, T. Maris, S. Agelaki, A. Karantanas, K. Marias","doi":"10.1109/BIBE.2019.00185","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00185","url":null,"abstract":"Radiomics-based studies have created an unprecedented momentum in computational medical imaging over the last years by significantly advancing and empowering correlational and predictive quantitative studies in numerous clinical applications. An important element of this exciting field of research especially in oncology is multi-scale texture analysis since it can effectively describe tissue heterogeneity, which is highly informative for clinical diagnosis and prognosis. There are however, several concerns regarding the plethora of radiomics features used in the literature especially regarding their performance consistency across studies. Since many studies use software packages that yield multi-scale texture features it makes sense to investigate the scale-space performance of texture candidate biomarkers under the hypothesis that significant texture markers may have a more persistent scale-space performance. To this end, this study proposes a methodology for the extraction of Gabor multi-scale and orientation texture DCE-MRI radiomics for predicting breast cancer complete response to neoadjuvant therapy. More specifically, a Gabor filter bank was created using four different orientations and ten different scales and then firstorder and second-order texture features were extracted for each scale-orientation data representation. The performance of all these features was evaluated under a generalized repeated cross-validation framework in a scale-space fashion using extreme gradient boosting classifiers.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126797917","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}
Thi Mai Phuong Nguyen, Xinzhe Li, Y. Hayashi, S. Yano, T. Kondo
Network studies of brain connectivity have demonstrated that the highly connected area, or hub, is a vital feature of human functional and structural brain organization. Hubs identify which region plays an important role in cognitive/sensorimotor tasks. In addition, a complex visuomotor learning skill causes specific changes of neuronal activation across brain regions. Accordingly, this study utilizes the hub as one of the features to map the visuomotor learning tasks and their dynamic functional connectivity (dFC). The electroencephalogram (EEG) data recorded under three different behavior conditions were investigated: motion only (MO), vision only (VO), and tracking (Tra) conditions. Here, we used the phase locking value (PLV) with a sliding window (50 ms) to calculate the dFC at four distinct frequency bands: 8-12 Hz (alpha), 18-22 Hz (low beta), 26-30 Hz (high beta) and 38-42 Hz (gamma), and the eigenvector centrality to evaluate the hub identification. The Gaussian Mixture Model (GMM) was applied to investigate the dFC patterns. The results showed that the dFC patterns with the hub feature represent the characteristic of neuronal activities under visuomotor coordination.
{"title":"Estimation of Brain Dynamics Under Visuomotor Task using Functional Connectivity Analysis Based on Graph Theory","authors":"Thi Mai Phuong Nguyen, Xinzhe Li, Y. Hayashi, S. Yano, T. Kondo","doi":"10.1109/BIBE.2019.00110","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00110","url":null,"abstract":"Network studies of brain connectivity have demonstrated that the highly connected area, or hub, is a vital feature of human functional and structural brain organization. Hubs identify which region plays an important role in cognitive/sensorimotor tasks. In addition, a complex visuomotor learning skill causes specific changes of neuronal activation across brain regions. Accordingly, this study utilizes the hub as one of the features to map the visuomotor learning tasks and their dynamic functional connectivity (dFC). The electroencephalogram (EEG) data recorded under three different behavior conditions were investigated: motion only (MO), vision only (VO), and tracking (Tra) conditions. Here, we used the phase locking value (PLV) with a sliding window (50 ms) to calculate the dFC at four distinct frequency bands: 8-12 Hz (alpha), 18-22 Hz (low beta), 26-30 Hz (high beta) and 38-42 Hz (gamma), and the eigenvector centrality to evaluate the hub identification. The Gaussian Mixture Model (GMM) was applied to investigate the dFC patterns. The results showed that the dFC patterns with the hub feature represent the characteristic of neuronal activities under visuomotor coordination.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"220 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122851955","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}
Michael D. Vasilakakis, V. Iosifidou, Panagiota Fragkaki, Dimitrios K. Iakovidis
The fracture detection process is difficult and requires specialized knowledge of the anatomical structures of the area under consideration. X-ray imaging provides images of the body's internal structures. Despite the rapid developments of medical imaging by adding newer imaging techniques such as CT and MRI, the exam of choice to detect bone fractures faster and cheaper is x-ray imaging (radiography). The objective of this study is the automatic detection of fractures in bone x-ray images using an image classification method. The dataset that was used in this study consists of 300 x-ray bone images of upper and lower extremity. In this study, we propose a novel feature extraction and classification methodology for the detection of bone fractures, named Wavelet Fuzzy Phrases (WFP). WFP extracts textural information from different bands of the 2D Discrete Wavelet Transform (DWT) images, which is expressed by a set of words. Each word is represented by a fuzzy set. The words form phrases, obtained from the aggregation of the fuzzy sets, representing the image contents. The classification accuracy achieved for bone fracture detection is 84%, which is higher than that obtained by other, state-of-the-art bone fracture detection methods. The results of this work show that this method can be used to draw the attention of the physicians in areas of the x-rays that are suspicious for fracture; therefore, it could contribute in the reduction of diagnostic errors as well as the increase of the radiologists' productivity.
{"title":"Bone Fracture Identification in X-Ray Images using Fuzzy Wavelet Features","authors":"Michael D. Vasilakakis, V. Iosifidou, Panagiota Fragkaki, Dimitrios K. Iakovidis","doi":"10.1109/BIBE.2019.00136","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00136","url":null,"abstract":"The fracture detection process is difficult and requires specialized knowledge of the anatomical structures of the area under consideration. X-ray imaging provides images of the body's internal structures. Despite the rapid developments of medical imaging by adding newer imaging techniques such as CT and MRI, the exam of choice to detect bone fractures faster and cheaper is x-ray imaging (radiography). The objective of this study is the automatic detection of fractures in bone x-ray images using an image classification method. The dataset that was used in this study consists of 300 x-ray bone images of upper and lower extremity. In this study, we propose a novel feature extraction and classification methodology for the detection of bone fractures, named Wavelet Fuzzy Phrases (WFP). WFP extracts textural information from different bands of the 2D Discrete Wavelet Transform (DWT) images, which is expressed by a set of words. Each word is represented by a fuzzy set. The words form phrases, obtained from the aggregation of the fuzzy sets, representing the image contents. The classification accuracy achieved for bone fracture detection is 84%, which is higher than that obtained by other, state-of-the-art bone fracture detection methods. The results of this work show that this method can be used to draw the attention of the physicians in areas of the x-rays that are suspicious for fracture; therefore, it could contribute in the reduction of diagnostic errors as well as the increase of the radiologists' productivity.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127719745","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}
This paper presents the implementation of a users' privacy protection approach in a health Internet of Things (IoT) system. It is composed of a set of security layers based on cryptography, pseudonymization and anonymization techniques applied to processed (Data-In-Use, DIU), stored (Data-At-Rest, DAR) and transmitted (Data-In-Motion, DIM) data. Regarding security and privacy in IoT systems, especially in digital health systems, it is necessary to guarantee that the user rights are respected. This requires a security-in-depth strategy established based on risk-based results, every interconnecting actors, their security and privacy requirements and the specific aspects of the entire ecosystem, including the applications and platform. The presented privacy protection approach was developed and applied in a digital health platform, OCARIoT.
{"title":"Privacy Protection with Pseudonymization and Anonymization In a Health IoT System: Results from OCARIoT","authors":"S. Ribeiro, E. Nakamura","doi":"10.1109/BIBE.2019.00169","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00169","url":null,"abstract":"This paper presents the implementation of a users' privacy protection approach in a health Internet of Things (IoT) system. It is composed of a set of security layers based on cryptography, pseudonymization and anonymization techniques applied to processed (Data-In-Use, DIU), stored (Data-At-Rest, DAR) and transmitted (Data-In-Motion, DIM) data. Regarding security and privacy in IoT systems, especially in digital health systems, it is necessary to guarantee that the user rights are respected. This requires a security-in-depth strategy established based on risk-based results, every interconnecting actors, their security and privacy requirements and the specific aspects of the entire ecosystem, including the applications and platform. The presented privacy protection approach was developed and applied in a digital health platform, OCARIoT.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132791577","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}
G. Kallergis, S. Sfakianakis, M. Zervakis, Marios Spanakis
Coxibs are a group of drugs with selective inhibition against cyclooxygenase-2 (COX-2) enzymes with increased interest from scientific community due to their side effects and potential other pharmacological mechanisms. The aim of this work is to utilize the chemical characteristics of coxibs in order to identify compounds with similar chemical structure. The approach is based on the assessment of the Simplified Molecular-Input Line-Entry System (SMILES) as adequate molecular structure representations for the identification of drug similarities. The similarity measurements are based on molecular fingerprints that were extracted from coxibs and the Maximum Consecutive Subsequence (MCS) algorithm. An ensemble of methods based on majority voting, weighting and equal weighting on the algorithms was further applied. Majority voting returned 200 similar compounds whereas weighting and equal weighting returned 53 and 27 compounds respectively. Interestingly, despite the independence of the methods, all three identified 20 common compounds. The identification of drugs with potential chemical similarity with coxibs, as revealed from similarity measurements of fingerprints and MCS scores could provide new insights for potential biological targets for coxibs or drugs that could interact with COX-2 or other biological targets of coxibs.
{"title":"Drugs with SMILES Similar to Coxibs","authors":"G. Kallergis, S. Sfakianakis, M. Zervakis, Marios Spanakis","doi":"10.1109/BIBE.2019.00153","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00153","url":null,"abstract":"Coxibs are a group of drugs with selective inhibition against cyclooxygenase-2 (COX-2) enzymes with increased interest from scientific community due to their side effects and potential other pharmacological mechanisms. The aim of this work is to utilize the chemical characteristics of coxibs in order to identify compounds with similar chemical structure. The approach is based on the assessment of the Simplified Molecular-Input Line-Entry System (SMILES) as adequate molecular structure representations for the identification of drug similarities. The similarity measurements are based on molecular fingerprints that were extracted from coxibs and the Maximum Consecutive Subsequence (MCS) algorithm. An ensemble of methods based on majority voting, weighting and equal weighting on the algorithms was further applied. Majority voting returned 200 similar compounds whereas weighting and equal weighting returned 53 and 27 compounds respectively. Interestingly, despite the independence of the methods, all three identified 20 common compounds. The identification of drugs with potential chemical similarity with coxibs, as revealed from similarity measurements of fingerprints and MCS scores could provide new insights for potential biological targets for coxibs or drugs that could interact with COX-2 or other biological targets of coxibs.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133506572","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：