Elhoussine Talab, Omar Mohamed, Labeeba Begum, F. Aloul, A. Sagahyroon
One out of four deaths is caused by heart related issues. Acting upon early signs of heart disease can, thus, drastically increase probability of saving lives. This paper discusses a cost-effective and reliable method of diagnosing heart abnormalities by using mobile phones that are nowadays typically available to an average user. A mobile application is developed to detect heart abnormal activities using either a digital stethoscope measurement as input, or a mobile recording of the heart beat using the mobile's microphone. To process the raw heart sound data, we first denoise the signal using wavelet transforms, and then apply machine learning techniques, namely, Convolutional Neural Networks for the classification of the stored heart sounds. A database consisting of recorded human heart sounds and their corresponding diagnosis is used to train the neural network. Moreover, neural network fine-tuning techniques such as ADAM Regularization is used to smoothen the prediction process. The proposed approach is tested on heart sound signals, that are 5 to 8 seconds long, and is shown to perform with an accuracy of 94.2% on the validation set.
{"title":"Detecting Heart Anomalies Using Mobile Phones and Machine Learning","authors":"Elhoussine Talab, Omar Mohamed, Labeeba Begum, F. Aloul, A. Sagahyroon","doi":"10.1109/BIBE.2019.00083","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00083","url":null,"abstract":"One out of four deaths is caused by heart related issues. Acting upon early signs of heart disease can, thus, drastically increase probability of saving lives. This paper discusses a cost-effective and reliable method of diagnosing heart abnormalities by using mobile phones that are nowadays typically available to an average user. A mobile application is developed to detect heart abnormal activities using either a digital stethoscope measurement as input, or a mobile recording of the heart beat using the mobile's microphone. To process the raw heart sound data, we first denoise the signal using wavelet transforms, and then apply machine learning techniques, namely, Convolutional Neural Networks for the classification of the stored heart sounds. A database consisting of recorded human heart sounds and their corresponding diagnosis is used to train the neural network. Moreover, neural network fine-tuning techniques such as ADAM Regularization is used to smoothen the prediction process. The proposed approach is tested on heart sound signals, that are 5 to 8 seconds long, and is shown to perform with an accuracy of 94.2% on the validation set.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"103 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":"133050380","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}
E. Mylona, Clement Lebreton, P. Fontaine, S. Supiot, N. Magné, G. Créhange, R. Crevoisier, O. Acosta
Prostate cancer radiotherapy unavoidably involves the irradiation not only of the target volume, but also of healthy organs-at-risk, neighboring the prostate, likely causing adverse, toxicity-related side-effects. Specifically, in the case of urinary toxicity, these side effects might be associated with a variety of dosimetric, clinical and genetic factors, making its prediction particularly challenging. Given the inconsistency of available data concerning radiation-induced toxicity, it is crucial to develop robust models with superior predictive performance in order to perform tailored treatments. Machine Learning techniques emerge as appealing in this context, nevertheless without any consensus on the best algorithms to be used. This work proposes a comparison of several machine-learning strategies together with different minority class oversampling techniques for prediction of urinary toxicity following prostate cancer radiotherapy using dosimetric and clinical data. The performance of these classifiers was evaluated on the original dataset and using four different synthetic oversampling techniques. The area under the ROC curve (AUC) and the F-measure were employed to evaluate their performance. Results suggest that, regardless of the technique, oversampling always increases the prediction performance of the models (p=0.004). Overall, oversampling with Synthetic Minority Oversampling Technique (SMOTE) followed by Edited Nearest Neighbour algorithm (ENN) together with Regularized Discriminant Analysis (RDA) classifier provide the best performance (AUC=0.71).
{"title":"Comparison of Machine Learning Algorithms and Oversampling Techniques for Urinary Toxicity Prediction After Prostate Cancer Radiotherapy","authors":"E. Mylona, Clement Lebreton, P. Fontaine, S. Supiot, N. Magné, G. Créhange, R. Crevoisier, O. Acosta","doi":"10.1109/BIBE.2019.00180","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00180","url":null,"abstract":"Prostate cancer radiotherapy unavoidably involves the irradiation not only of the target volume, but also of healthy organs-at-risk, neighboring the prostate, likely causing adverse, toxicity-related side-effects. Specifically, in the case of urinary toxicity, these side effects might be associated with a variety of dosimetric, clinical and genetic factors, making its prediction particularly challenging. Given the inconsistency of available data concerning radiation-induced toxicity, it is crucial to develop robust models with superior predictive performance in order to perform tailored treatments. Machine Learning techniques emerge as appealing in this context, nevertheless without any consensus on the best algorithms to be used. This work proposes a comparison of several machine-learning strategies together with different minority class oversampling techniques for prediction of urinary toxicity following prostate cancer radiotherapy using dosimetric and clinical data. The performance of these classifiers was evaluated on the original dataset and using four different synthetic oversampling techniques. The area under the ROC curve (AUC) and the F-measure were employed to evaluate their performance. Results suggest that, regardless of the technique, oversampling always increases the prediction performance of the models (p=0.004). Overall, oversampling with Synthetic Minority Oversampling Technique (SMOTE) followed by Edited Nearest Neighbour algorithm (ENN) together with Regularized Discriminant Analysis (RDA) classifier provide the best performance (AUC=0.71).","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"26 2 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":"130347046","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}
Electrical bioimpedance is a promising in vivo tissue characterization method. To develop optimized electronic instrumentation, knowledge of the electrical characteristics of the bioimpedance sensor and the targeted tissue are essential. This paper presents novel results from the characterization of a tetrapolar bioimpedance sensor for intestinal intraluminal mucosal ischemia assessment fabricated using flexible printed circuit (FPC) technology. The electrode impedance is measured individually and in pairs in saline solutions and equivalent circuits are proposed. The sensor is subsequently assessed in tetrapolar impedance measurements in saline solutions to extract experimentally the geometrical cell constant of the device. Finally, in vitro tetrapolar measurements from porcine intraluminal intestinal tissue are presented. The electrode impedance was found to be 145 ± 42 kΩ, while the tissue between 1.77 and 2.06 kΩ at 20 Hz. This work allows the design of next generation optimized CMOS instrumentation for implantable bioimpedance measurements for the particular application and sensor.
{"title":"Characterization and Modeling of a Flexible Tetrapolar Bioimpedance Sensor and Measurements of Intestinal Tissues","authors":"P. Kassanos, F. Seichepine, Guang-Zhong Yang","doi":"10.1109/BIBE.2019.00129","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00129","url":null,"abstract":"Electrical bioimpedance is a promising in vivo tissue characterization method. To develop optimized electronic instrumentation, knowledge of the electrical characteristics of the bioimpedance sensor and the targeted tissue are essential. This paper presents novel results from the characterization of a tetrapolar bioimpedance sensor for intestinal intraluminal mucosal ischemia assessment fabricated using flexible printed circuit (FPC) technology. The electrode impedance is measured individually and in pairs in saline solutions and equivalent circuits are proposed. The sensor is subsequently assessed in tetrapolar impedance measurements in saline solutions to extract experimentally the geometrical cell constant of the device. Finally, in vitro tetrapolar measurements from porcine intraluminal intestinal tissue are presented. The electrode impedance was found to be 145 ± 42 kΩ, while the tissue between 1.77 and 2.06 kΩ at 20 Hz. This work allows the design of next generation optimized CMOS instrumentation for implantable bioimpedance measurements for the particular application and sensor.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"59 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":"134084982","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}
H. Tibble, A. Chan, E. Mitchell, R. Horne, M. Mizani, A. Sheikh, A. Tsanas
Medication non-adherence is strongly associated with poor asthma control and outcomes. Many studies use an aggregate measure of adherence, such as the percentage of prescribed doses that were taken, however this conceals variation between patients' medication-taking routines. Electronic monitoring devices, which precisely record the date and time of a dose being actuated from an inhaler, provide the means to objectively and remotely monitor adherence behavior patterns. This secondary analysis of a New Zealand audio-visual medication reminder intervention study visually explored the relationships, variation, and heterogeneity between multiple measures of adherence, in 211 children aged 6-15 years old who presented to an emergency department with an asthma attack. Our findings highlight the weakness of statistical relationships between measures of adherence, and the irregularity in patient medication-taking behavior. This demonstrates that a single aggregate adherence measure fails to detect asthma patients for whom their day-to-day medication taking (implementation) is inconsistent with their longitudinal medication taking (persistence).
{"title":"Heterogeneity in Asthma Medication Adherence Measurement","authors":"H. Tibble, A. Chan, E. Mitchell, R. Horne, M. Mizani, A. Sheikh, A. Tsanas","doi":"10.1109/BIBE.2019.00168","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00168","url":null,"abstract":"Medication non-adherence is strongly associated with poor asthma control and outcomes. Many studies use an aggregate measure of adherence, such as the percentage of prescribed doses that were taken, however this conceals variation between patients' medication-taking routines. Electronic monitoring devices, which precisely record the date and time of a dose being actuated from an inhaler, provide the means to objectively and remotely monitor adherence behavior patterns. This secondary analysis of a New Zealand audio-visual medication reminder intervention study visually explored the relationships, variation, and heterogeneity between multiple measures of adherence, in 211 children aged 6-15 years old who presented to an emergency department with an asthma attack. Our findings highlight the weakness of statistical relationships between measures of adherence, and the irregularity in patient medication-taking behavior. This demonstrates that a single aggregate adherence measure fails to detect asthma patients for whom their day-to-day medication taking (implementation) is inconsistent with their longitudinal medication taking (persistence).","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"211 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134094164","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. Zanti, M. Loizidou, M. Zachariou, K. Michailidou, K. Kyriacou, A. Hadjisavvas, G. Spyrou
The evolution of Next Generation Sequencing (NGS) technologies represents a significant advancement in the field of molecular genetics and has set the ground, for the discovery of novel variants which cannot be easily classified as deleterious or neutral. In-vitro and in-vivo characterization of these variants of uncertain clinical significance (VUS) should be followed; however, it is often not feasible to carry out the experimental interpretation for every single VUS. In silico tools have been crucial for the prediction of the impact of VUS on protein structure, stability and function. Our aim was to combine computational approaches to investigate the impact of VUS identified in a cohort of Cypriot Triple-Negative Breast Cancer (TNBC) patients by NGS. Using a combination of structural, functional and network-based bioinformatics approaches for the classification of a nonsense PRF1 mutation in association with BC susceptibility, we propose a possible triggered interaction of the mutant PRF1 protein with the CDKN2A protein, a product of a BC susceptibility gene. Additionally, our results support that the increased probability of interaction of the mutant counterpart of perforin with its top 10 predicted interactors, could play an important role in the obstruction of cellular processes related to carcinogenesis such as cell death, necrosis, DNA damage, immortality, UV stress, DNA repair and cell cycle control. We conclude that probably the nonsense PRF1 mutation could be associated with BC predisposition. However, although in silico tools provide an important tool for the interpretation of VUS, functional studies, co-segregation analyses and/or case-control association studies are needed to draw conclusions on variant classification.
{"title":"In Silico Assessment of the Structural, Functional and Stability Impact of a Nonsense PRF1 Mutation with Uncertain Clinical Significance; Identified in 2 Unrelated Cypriot Triple-Negative Breast Cancer Patients.","authors":"M. Zanti, M. Loizidou, M. Zachariou, K. Michailidou, K. Kyriacou, A. Hadjisavvas, G. Spyrou","doi":"10.1109/BIBE.2019.00040","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00040","url":null,"abstract":"The evolution of Next Generation Sequencing (NGS) technologies represents a significant advancement in the field of molecular genetics and has set the ground, for the discovery of novel variants which cannot be easily classified as deleterious or neutral. In-vitro and in-vivo characterization of these variants of uncertain clinical significance (VUS) should be followed; however, it is often not feasible to carry out the experimental interpretation for every single VUS. In silico tools have been crucial for the prediction of the impact of VUS on protein structure, stability and function. Our aim was to combine computational approaches to investigate the impact of VUS identified in a cohort of Cypriot Triple-Negative Breast Cancer (TNBC) patients by NGS. Using a combination of structural, functional and network-based bioinformatics approaches for the classification of a nonsense PRF1 mutation in association with BC susceptibility, we propose a possible triggered interaction of the mutant PRF1 protein with the CDKN2A protein, a product of a BC susceptibility gene. Additionally, our results support that the increased probability of interaction of the mutant counterpart of perforin with its top 10 predicted interactors, could play an important role in the obstruction of cellular processes related to carcinogenesis such as cell death, necrosis, DNA damage, immortality, UV stress, DNA repair and cell cycle control. We conclude that probably the nonsense PRF1 mutation could be associated with BC predisposition. However, although in silico tools provide an important tool for the interpretation of VUS, functional studies, co-segregation analyses and/or case-control association studies are needed to draw conclusions on variant classification.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"19 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":"133191108","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}
Shaikh Farhad Hossain, Ming Huang, N. Ono, S. Kanaya, M. Altaf-Ul-Amin
A biomarker (short for biological marker) is a medical sign of a disease or condition which indicates a normal or abnormal state of a body. The biomarker is a key factor in the analysis of diseases and also for analyzing inter disease relations. In the previous study, we designed and developed a human biomarker (metabolites and proteins) database and the database is currently available online. This work was supported by the Ministry of Education, Japan and NAIST Big Data Project. We have used our previously developed database and collected 486 human biomarkers and their respective diseases. We determined the similarity among NCBI disease classes based on associated biomarker fingerprints. For this purpose, we collected biomarker PubChem IDs and using them downloaded the SDF files in a batch, then with those molecular description files determined their atom pair fingerprints using ChemmineR package. We constructed a network of biomarkers based on Tanimoto similarity between their fingerprints and applied DPclusO algorithm to find clusters consisting of biomarkers with similar chemical structures. We also conducted hierarchical clustering of the biomarkers. We categorized all the diseases in our data into 18 NCBI disease classes. Combining all information, we finally determined inter disease relations based on structural similarity between biomarkers.
{"title":"Inter Disease Relations Based on Human Biomarkers by Network Analysis","authors":"Shaikh Farhad Hossain, Ming Huang, N. Ono, S. Kanaya, M. Altaf-Ul-Amin","doi":"10.1109/BIBE.2019.00027","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00027","url":null,"abstract":"A biomarker (short for biological marker) is a medical sign of a disease or condition which indicates a normal or abnormal state of a body. The biomarker is a key factor in the analysis of diseases and also for analyzing inter disease relations. In the previous study, we designed and developed a human biomarker (metabolites and proteins) database and the database is currently available online. This work was supported by the Ministry of Education, Japan and NAIST Big Data Project. We have used our previously developed database and collected 486 human biomarkers and their respective diseases. We determined the similarity among NCBI disease classes based on associated biomarker fingerprints. For this purpose, we collected biomarker PubChem IDs and using them downloaded the SDF files in a batch, then with those molecular description files determined their atom pair fingerprints using ChemmineR package. We constructed a network of biomarkers based on Tanimoto similarity between their fingerprints and applied DPclusO algorithm to find clusters consisting of biomarkers with similar chemical structures. We also conducted hierarchical clustering of the biomarkers. We categorized all the diseases in our data into 18 NCBI disease classes. Combining all information, we finally determined inter disease relations based on structural similarity between biomarkers.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"12 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":"121131131","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}
Oscar L. Mosquera, D. Guzman, Jhon Zamudio, J. García, Cristhian Rodriguez, Daniel Botero
considering the strategic direction of the Colombian National Army, the need to increase training effectiveness using technological developments in biomedical engineering is highlighted. This study evaluates brain electrical activity via complex networks in virtual reality situations which simulate military reactions. Results suggest that a high network degree may be related to an appropriate decision-making process, whereas a lower value may be associated with poor performances according to military doctrine. While not entirely significant, some difference is appreciated, mainly between the base period and the event related to subject elimination (p=0.058). The authors also noted the burst suppression pattern when the subject was eliminated. As this is a work in progress, more research subjects are being recruited and more complex networks descriptors are being explored.
{"title":"Complex Brain Networks and Simulated Military Reactions using a Virtual Reality System","authors":"Oscar L. Mosquera, D. Guzman, Jhon Zamudio, J. García, Cristhian Rodriguez, Daniel Botero","doi":"10.1109/BIBE.2019.00105","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00105","url":null,"abstract":"considering the strategic direction of the Colombian National Army, the need to increase training effectiveness using technological developments in biomedical engineering is highlighted. This study evaluates brain electrical activity via complex networks in virtual reality situations which simulate military reactions. Results suggest that a high network degree may be related to an appropriate decision-making process, whereas a lower value may be associated with poor performances according to military doctrine. While not entirely significant, some difference is appreciated, mainly between the base period and the event related to subject elimination (p=0.058). The authors also noted the burst suppression pattern when the subject was eliminated. As this is a work in progress, more research subjects are being recruited and more complex networks descriptors are being explored.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"37 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":"115968741","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}
In this paper, we present a new pain detection approach that analyzes the electroencephalography (EEG) signals using a quadratic time-frequency distribution (QTFD), namely the Wigner-Ville distribution (WVD). The use of the WVD enables to construct a time-frequency representation (TFR) of the EEG signals that characterizes the time-varying spectral components of the EEG signals. To reduce the dimensionality of the constructed WVD-based TFR of the EEG signals, we have extracted 12 time-frequency features that quantify the energy distribution of the EEG signals in the constructed WVD-based TFR. The extracted time-frequency features are used to train a support vector machine classifier to distinguish between EEG signals that are associated with the no-pain and pain classes. To assess the performance of our proposed pain detection approach, we have recorded the EEG signals for 24 participants under tonic cold pain stimulus. The experimental results show that our proposed approach achieved an average classification accuracy of 83.4% in distinguishing between the no-pain and pain classes.
{"title":"A Time-Frequency Distribution Based Approach for Detecting Tonic Cold Pain using EEG Signals","authors":"R. Alazrai, Saifaldeen Al-Rawi, M. Daoud","doi":"10.1109/BIBE.2019.00112","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00112","url":null,"abstract":"In this paper, we present a new pain detection approach that analyzes the electroencephalography (EEG) signals using a quadratic time-frequency distribution (QTFD), namely the Wigner-Ville distribution (WVD). The use of the WVD enables to construct a time-frequency representation (TFR) of the EEG signals that characterizes the time-varying spectral components of the EEG signals. To reduce the dimensionality of the constructed WVD-based TFR of the EEG signals, we have extracted 12 time-frequency features that quantify the energy distribution of the EEG signals in the constructed WVD-based TFR. The extracted time-frequency features are used to train a support vector machine classifier to distinguish between EEG signals that are associated with the no-pain and pain classes. To assess the performance of our proposed pain detection approach, we have recorded the EEG signals for 24 participants under tonic cold pain stimulus. The experimental results show that our proposed approach achieved an average classification accuracy of 83.4% in distinguishing between the no-pain and pain classes.","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":"116905069","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 S. Ioannidis, K. Nikiforaki, A. Karantanas
The aim of the present work is to correlate perfusion information obtained from semi-quantitative DCE data analysis with quantitative diffusion data analysis in patients with peripheral arterial disease. An in-house built software deploying linear and nonlinear least squares algorithms, was used for the quantification of the parameters based on intra-voxel incoherent motion (IVIM) model and exponentially modified Gaussian function. All numerical calculations were implemented in Python 3.5. Derived per-fusion parameters (micro-perfusion fraction f and Wash-In respectively) showed good correlation (>0.5). This constitutes a promising result for obtaining perfusion information from DWI sequences without the need for contrast agent in patients with vascular disease.
{"title":"Correlation of DWI and DCE MRI Markers for the Study of Perfusion of the Lower Limb in Patients with Peripheral Arterial Disease","authors":"Georgios S. Ioannidis, K. Nikiforaki, A. Karantanas","doi":"10.1109/BIBE.2019.00084","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00084","url":null,"abstract":"The aim of the present work is to correlate perfusion information obtained from semi-quantitative DCE data analysis with quantitative diffusion data analysis in patients with peripheral arterial disease. An in-house built software deploying linear and nonlinear least squares algorithms, was used for the quantification of the parameters based on intra-voxel incoherent motion (IVIM) model and exponentially modified Gaussian function. All numerical calculations were implemented in Python 3.5. Derived per-fusion parameters (micro-perfusion fraction f and Wash-In respectively) showed good correlation (>0.5). This constitutes a promising result for obtaining perfusion information from DWI sequences without the need for contrast agent in patients with vascular disease.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"30 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":"115912365","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}
P. Dimitrakopoulos, Giorgos Sfikas, Christophoros Nikou
Detection of cell nuclei in microscopy images is a challenging research topic due to limitations in acquired image quality as well as due to the diversity of nuclear morphology. This has been a topic of enduring interest with promising success shown by deep learning methods. Recently, attention gating methods have been proposed and employed successfully in a diverse array of pattern recognition tasks. In this work, we introduce a novel attention module and integrate it with feature pyramid networks and the state-of-the-art Mask R-CNN network. We show with numerical experiments that the proposed model outperforms the state-of-the-art baseline.
{"title":"Nuclei Detection Using Residual Attention Feature Pyramid Networks","authors":"P. Dimitrakopoulos, Giorgos Sfikas, Christophoros Nikou","doi":"10.1109/BIBE.2019.00028","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00028","url":null,"abstract":"Detection of cell nuclei in microscopy images is a challenging research topic due to limitations in acquired image quality as well as due to the diversity of nuclear morphology. This has been a topic of enduring interest with promising success shown by deep learning methods. Recently, attention gating methods have been proposed and employed successfully in a diverse array of pattern recognition tasks. In this work, we introduce a novel attention module and integrate it with feature pyramid networks and the state-of-the-art Mask R-CNN network. We show with numerical experiments that the proposed model outperforms the state-of-the-art baseline.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"20 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":"117019235","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：