Juan He, Qianyin Li, Zhiyong Tao, Kai Zhang, Yunpeng Cai
Microbial network analysis help with discovering microbe groups that covariate with environmental factors. However, microbial communities are highly diversified and localized, which poses challenges to existing correlation-based network construction methods in terms of stability and functional significance. In this paper, we propose to explore the high-level relationships in the microbial network structure with the aid of network embedding methods. Microbial function modules are then extracted by spectrum clustering on the embedded networks, rather than the original ones. By investigating the correlation between the obtained modules and the environmental factors on several real-world microbial datasets, we demonstrate that the embedded modules provide feature information of the microbial community that are distinct to traditional correlation-based network modules. Furthermore, we show that the introduction of high-order modules helps with improving the performance of prediction models comparing with using OTU features or traditional correlation-based modules alone. Our study demonstrated that high-order network modules created by network embedding can be served as a potential new biomarker for feature extraction of microbial communities.
{"title":"Finding High-Order Homologous Microbe Community Modules via Network Embedding","authors":"Juan He, Qianyin Li, Zhiyong Tao, Kai Zhang, Yunpeng Cai","doi":"10.1109/BIBE.2019.00023","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00023","url":null,"abstract":"Microbial network analysis help with discovering microbe groups that covariate with environmental factors. However, microbial communities are highly diversified and localized, which poses challenges to existing correlation-based network construction methods in terms of stability and functional significance. In this paper, we propose to explore the high-level relationships in the microbial network structure with the aid of network embedding methods. Microbial function modules are then extracted by spectrum clustering on the embedded networks, rather than the original ones. By investigating the correlation between the obtained modules and the environmental factors on several real-world microbial datasets, we demonstrate that the embedded modules provide feature information of the microbial community that are distinct to traditional correlation-based network modules. Furthermore, we show that the introduction of high-order modules helps with improving the performance of prediction models comparing with using OTU features or traditional correlation-based modules alone. Our study demonstrated that high-order network modules created by network embedding can be served as a potential new biomarker for feature extraction of microbial communities.","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":"129073203","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}
Nicoletta Prentzas, A. Nicolaides, E. Kyriacou, A. Kakas, C. Pattichis
Despite the recent recognition of the value of Artificial Intelligence and Machine Learning in healthcare, barriers to further adoption remain, mainly due to their "black box" nature and the algorithm's inability to explain its results. In this paper we present and propose a methodology of applying argumentation on top of machine learning to build explainable AI (XAI) models. We compare our results with Random Forests and an SVM classifier that was considered best for the same dataset in [1].
{"title":"Integrating Machine Learning with Symbolic Reasoning to Build an Explainable AI Model for Stroke Prediction","authors":"Nicoletta Prentzas, A. Nicolaides, E. Kyriacou, A. Kakas, C. Pattichis","doi":"10.1109/BIBE.2019.00152","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00152","url":null,"abstract":"Despite the recent recognition of the value of Artificial Intelligence and Machine Learning in healthcare, barriers to further adoption remain, mainly due to their \"black box\" nature and the algorithm's inability to explain its results. In this paper we present and propose a methodology of applying argumentation on top of machine learning to build explainable AI (XAI) models. We compare our results with Random Forests and an SVM classifier that was considered best for the same dataset in [1].","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"8 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":"128456609","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}
C. M. M. Mojica, N. Tsekos, J. D. V. Garcia, Haoran Zhao, I. Seimenis, E. Leiss, D. Shah, A. Webb, Aaron T. Becker, P. Tsiamyrtzis
The emerging potential of augmented reality (AR) to improve 3D medical image visualization for diagnosis, by immersing the user into 3D morphology is further enhanced with the advent of wireless head-mounted displays (HMD). Such information-immersive capabilities may also enhance planning and visualization of interventional procedures. To this end, we introduce a computational platform to generate an augmented reality holographic scene that fuses pre-operative magnetic resonance imaging (MRI) sets, segmented anatomical structures, and an actuated model of an interventional robot for performing MRI-guided and robot-assisted interventions. The interface enables the operator to manipulate the presented images and rendered structures using voice and gestures, as well as to robot control. The software uses forbidden-region virtual fixtures that alerts the operator of collisions with vital structures. The platform was tested with a HoloLens HMD in silico. To address the limited computational power of the HMD, we deployed the platform on a desktop PC with two-way communication to the HMD. Operation studies demonstrated the functionality and underscored the importance of interface customization to fit a particular operator and/or procedure, as well as the need for on-site studies to assess its merit in the clinical realm.
{"title":"Interactive and Immersive Image-Guided Control of Interventional Manipulators with a Prototype Holographic Interface","authors":"C. M. M. Mojica, N. Tsekos, J. D. V. Garcia, Haoran Zhao, I. Seimenis, E. Leiss, D. Shah, A. Webb, Aaron T. Becker, P. Tsiamyrtzis","doi":"10.1109/BIBE.2019.00186","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00186","url":null,"abstract":"The emerging potential of augmented reality (AR) to improve 3D medical image visualization for diagnosis, by immersing the user into 3D morphology is further enhanced with the advent of wireless head-mounted displays (HMD). Such information-immersive capabilities may also enhance planning and visualization of interventional procedures. To this end, we introduce a computational platform to generate an augmented reality holographic scene that fuses pre-operative magnetic resonance imaging (MRI) sets, segmented anatomical structures, and an actuated model of an interventional robot for performing MRI-guided and robot-assisted interventions. The interface enables the operator to manipulate the presented images and rendered structures using voice and gestures, as well as to robot control. The software uses forbidden-region virtual fixtures that alerts the operator of collisions with vital structures. The platform was tested with a HoloLens HMD in silico. To address the limited computational power of the HMD, we deployed the platform on a desktop PC with two-way communication to the HMD. Operation studies demonstrated the functionality and underscored the importance of interface customization to fit a particular operator and/or procedure, as well as the need for on-site studies to assess its merit in the clinical realm.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"31 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":"117196300","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}
Thomais Asvestopoulou, Victoria Manousaki, A. Psistakis, Erjona Nikolli, Vassilios Andreadakis, I. Aslanides, Yannis Pantazis, Ioannis Smyrnakis, M. Papadopouli
Eye movements during text reading can provide insights about reading disorders. We developed the DysLexML, a screening tool for developmental dyslexia, based on various ML algorithms that analyze gaze points recorded via eye-tracking during silent reading of children. We comparatively evaluated its performance using measurements collected from two systematic field studies with 221 participants in total. This work presents DysLexML and its performance. It identifies the features with prominent predictive power and performs dimensionality reduction. Specifically, it achieves its best performance using linear SVM, with an accuracy of 97% and 84% respectively, using a small feature set. We show that DysLexML is also robust in the presence of noise. These encouraging results set the basis for developing screening tools in less controlled, larger-scale environments, with inexpensive eye-trackers, potentially reaching a larger population for early intervention. Unlike other related studies, DysLexML achieves the aforementioned performance by employing only a small number of selected features, that have been identified with prominent predictive power. Finally, we developed a new data augmentation/substitution technique based on GANs for generating synthetic data similar to the original distributions.
{"title":"Towards a Robust and Accurate Screening Tool for Dyslexia with Data Augmentation using GANs","authors":"Thomais Asvestopoulou, Victoria Manousaki, A. Psistakis, Erjona Nikolli, Vassilios Andreadakis, I. Aslanides, Yannis Pantazis, Ioannis Smyrnakis, M. Papadopouli","doi":"10.1109/BIBE.2019.00145","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00145","url":null,"abstract":"Eye movements during text reading can provide insights about reading disorders. We developed the DysLexML, a screening tool for developmental dyslexia, based on various ML algorithms that analyze gaze points recorded via eye-tracking during silent reading of children. We comparatively evaluated its performance using measurements collected from two systematic field studies with 221 participants in total. This work presents DysLexML and its performance. It identifies the features with prominent predictive power and performs dimensionality reduction. Specifically, it achieves its best performance using linear SVM, with an accuracy of 97% and 84% respectively, using a small feature set. We show that DysLexML is also robust in the presence of noise. These encouraging results set the basis for developing screening tools in less controlled, larger-scale environments, with inexpensive eye-trackers, potentially reaching a larger population for early intervention. Unlike other related studies, DysLexML achieves the aforementioned performance by employing only a small number of selected features, that have been identified with prominent predictive power. Finally, we developed a new data augmentation/substitution technique based on GANs for generating synthetic data similar to the original distributions.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"23 3 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":"114396017","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. F. D. Cruz, Benjamin Bergner, Orhan Konak, F. Schneider, Philipp Bode, Conrad Lempert, M. Schapranow
Machine learning is rapidly becoming a mainstay in research and industry. Particularly for clinical predictive modeling, these approaches are being increasingly applied, as evidenced by the growth in the number of related publications. While different computer tools exist that support rapid prototyping, we observe that the state of the art is lacking in the extent to which the needs of research clinicians are addressed. This leads to an increase in the time needed for development and validation of such models. In this paper, we outline the requirements and challenges inherent to this domain and present a platform for rapid prototyping tailored to the specific needs of clinical modeling for outcome and risk prediction. We argue that a move towards hybrid solutions, i.e., a mix of cloud and on-premise infrastructure, constitutes a viable way to reduce the time needed to develop and validate clinical predictive models in a standardized, reproducible fashion.
{"title":"MORPHER - A Platform to Support Modeling of Outcome and Risk Prediction in Health Research","authors":"H. F. D. Cruz, Benjamin Bergner, Orhan Konak, F. Schneider, Philipp Bode, Conrad Lempert, M. Schapranow","doi":"10.1109/BIBE.2019.00090","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00090","url":null,"abstract":"Machine learning is rapidly becoming a mainstay in research and industry. Particularly for clinical predictive modeling, these approaches are being increasingly applied, as evidenced by the growth in the number of related publications. While different computer tools exist that support rapid prototyping, we observe that the state of the art is lacking in the extent to which the needs of research clinicians are addressed. This leads to an increase in the time needed for development and validation of such models. In this paper, we outline the requirements and challenges inherent to this domain and present a platform for rapid prototyping tailored to the specific needs of clinical modeling for outcome and risk prediction. We argue that a move towards hybrid solutions, i.e., a mix of cloud and on-premise infrastructure, constitutes a viable way to reduce the time needed to develop and validate clinical predictive models in a standardized, reproducible fashion.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"55 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":"115761615","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}
Understanding and predicting the pattern formation in groups of pluripotent stem cells has the potential to improve efficiency and efficacy of stem cell therapies. However, the underlying molecular mechanisms of pluripotent stem cell behaviors are highly complex and are currently still not fully understood. A key practical question is whether deep biological modelling of the cells is essential to predict their pattern formation, or whether there is sufficient predictive power in simply modelling their behaviors and interactions at a higher level. This study focuses on the social interactions and behaviors of pluripotent stem cells at a high-level to predict aggregate crowd behaviors within a level of uncertainty. Agent-based modelling was applied to study the pattern formation in pluripotent stem cells. Five models were established to test four biologically plausible rules of cell motility in terms of: a) velocity, b) directional persistence time, c) directional movements, and d) border effect. We found that it is possible that cells' directional movements based on local density play an important role of the pattern formation, and pattern formation in pluripotent stem cells is governed by a complex combination of rules in our agent-based model simulations, which account for much of the variability observed in experimental findings.
{"title":"Investigating Motility and Pattern Formation in Pluripotent Stem Cells Through Agent-Based Modeling","authors":"Minhong Wang, A. Tsanas, G. Blin, D. Robertson","doi":"10.1109/BIBE.2019.00170","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00170","url":null,"abstract":"Understanding and predicting the pattern formation in groups of pluripotent stem cells has the potential to improve efficiency and efficacy of stem cell therapies. However, the underlying molecular mechanisms of pluripotent stem cell behaviors are highly complex and are currently still not fully understood. A key practical question is whether deep biological modelling of the cells is essential to predict their pattern formation, or whether there is sufficient predictive power in simply modelling their behaviors and interactions at a higher level. This study focuses on the social interactions and behaviors of pluripotent stem cells at a high-level to predict aggregate crowd behaviors within a level of uncertainty. Agent-based modelling was applied to study the pattern formation in pluripotent stem cells. Five models were established to test four biologically plausible rules of cell motility in terms of: a) velocity, b) directional persistence time, c) directional movements, and d) border effect. We found that it is possible that cells' directional movements based on local density play an important role of the pattern formation, and pattern formation in pluripotent stem cells is governed by a complex combination of rules in our agent-based model simulations, which account for much of the variability observed in experimental findings.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"244 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":"116148424","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The aim of this study was to propose a standard test battery consisting of necessary tools for measuring and comparing the various aspects of cognitive outcomes. The battery was used to determine whether adolescent women performing regular elite-level strength training differed from their sedentary peers in terms of cognition, and also to determine how a single session of strength training affects cognition in highly trained adolescents. Motor functions, ability of sustaining attention and executive functions of 25 elite female weightlifters and 22 sedentary females were evaluated through finger tapping performance, visual reaction time (VRT) and recognition visual reaction time (R-VRT) data. Weightlifters were tested before and after a training session, sedentary controls were tested only during resting. There was a significant increase in mean complex R-VRT of weightlifters after training (p<0.01). In R-VRT tests, rate of false answers increased significantly after training (p<0.05). Mean VRT of weightlifters (during rest) and sedentary peers were not different in any of the tests (p>0.05). Total number of taps and mean inter-tap intervals did not show any difference in the weightlifter group before and after training, also between weightlifters and sedentary controls (p>0.05). Elite level strength training does not improve cognition in adolescence. Adolescent weightlifters' executive functions are deteriorated following a single training session however, this effect is temporary.
{"title":"The Use of Computer Based Test Battery for the Assessment of Cognitive Functions in Elite-Level Strength Training","authors":"M. Yargic, Leyla Aydin, Kenan Erdağı, E. Kiziltan","doi":"10.1109/BIBE.2019.00066","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00066","url":null,"abstract":"The aim of this study was to propose a standard test battery consisting of necessary tools for measuring and comparing the various aspects of cognitive outcomes. The battery was used to determine whether adolescent women performing regular elite-level strength training differed from their sedentary peers in terms of cognition, and also to determine how a single session of strength training affects cognition in highly trained adolescents. Motor functions, ability of sustaining attention and executive functions of 25 elite female weightlifters and 22 sedentary females were evaluated through finger tapping performance, visual reaction time (VRT) and recognition visual reaction time (R-VRT) data. Weightlifters were tested before and after a training session, sedentary controls were tested only during resting. There was a significant increase in mean complex R-VRT of weightlifters after training (p<0.01). In R-VRT tests, rate of false answers increased significantly after training (p<0.05). Mean VRT of weightlifters (during rest) and sedentary peers were not different in any of the tests (p>0.05). Total number of taps and mean inter-tap intervals did not show any difference in the weightlifter group before and after training, also between weightlifters and sedentary controls (p>0.05). Elite level strength training does not improve cognition in adolescence. Adolescent weightlifters' executive functions are deteriorated following a single training session however, this effect is temporary.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"75 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":"127076232","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}
Wenhui Chu, Giovanni Molina, N. Navkar, C. Eick, Aaron T. Becker, P. Tsiamyrtzis, N. Tsekos
This work presents a novel deep learning architecture called BNU-Net for the purpose of cardiac segmentation based on short-axis MRI images. Its name is derived from the Batch Normalized (BN) U-Net architecture for medical image segmentation. New generations of deep neural networks (NN) are called convolutional NN (CNN). CNNs like U-Net have been widely used for image classification tasks. CNNs are supervised training models which are trained to learn hierarchies of features automatically and robustly perform classification. Our architecture consists of an encoding path for feature extraction and a decoding path that enables precise localization. We compare this approach with a parallel approach named U-Net. Both BNU-Net and U-Net are cardiac segmentation approaches: while BNU-Net employs batch normalization to the results of each convolutional layer and applies an exponential linear unit (ELU) approach that operates as activation function, U-Net does not apply batch normalization and is based on Rectified Linear Units (ReLU). The presented work (i) facilitates various image preprocessing techniques, which includes affine transformations and elastic deformations, and (ii) segments the preprocessed images using the new deep learning architecture. We evaluate our approach on a dataset containing 805 MRI images from 45 patients. The experimental results reveal that our approach accomplishes comparable or better performance than other state-of-the-art approaches in terms of the Dice coefficient and the average perpendicular distance.
{"title":"BNU-Net: A Novel Deep Learning Approach for LV MRI Analysis in Short-Axis MRI","authors":"Wenhui Chu, Giovanni Molina, N. Navkar, C. Eick, Aaron T. Becker, P. Tsiamyrtzis, N. Tsekos","doi":"10.1109/BIBE.2019.00137","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00137","url":null,"abstract":"This work presents a novel deep learning architecture called BNU-Net for the purpose of cardiac segmentation based on short-axis MRI images. Its name is derived from the Batch Normalized (BN) U-Net architecture for medical image segmentation. New generations of deep neural networks (NN) are called convolutional NN (CNN). CNNs like U-Net have been widely used for image classification tasks. CNNs are supervised training models which are trained to learn hierarchies of features automatically and robustly perform classification. Our architecture consists of an encoding path for feature extraction and a decoding path that enables precise localization. We compare this approach with a parallel approach named U-Net. Both BNU-Net and U-Net are cardiac segmentation approaches: while BNU-Net employs batch normalization to the results of each convolutional layer and applies an exponential linear unit (ELU) approach that operates as activation function, U-Net does not apply batch normalization and is based on Rectified Linear Units (ReLU). The presented work (i) facilitates various image preprocessing techniques, which includes affine transformations and elastic deformations, and (ii) segments the preprocessed images using the new deep learning architecture. We evaluate our approach on a dataset containing 805 MRI images from 45 patients. The experimental results reveal that our approach accomplishes comparable or better performance than other state-of-the-art approaches in terms of the Dice coefficient and the average perpendicular distance.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"38 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":"126865360","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}
Katerina Giannakaki, Giorgos Giannakakis, P. Vorgia, M. Klados, M. Zervakis
This paper evaluates the usage of matching pursuit (MP) features of electroencephalographic (EEG) signals and classification techniques on automatic absence seizure detection. Absence epileptic seizures are neurological disorders which are manifested as abnormal EEG patterns. Matching pursuit algorithm is able to decompose a signal into components with specific time-frequency characteristics. It is a robust technique especially when there is complex, multicomponent signal. In the present study, a clinical dataset containing 40 annotated absence seizures in long-term EEG recordings from pediatric epileptic patients (with age 6.0±2.9 years) was analyzed. The extracted MP features fed an automatic classification schema which achieved a time window based discrimination accuracy of 98.5%. As indicated by the study's results, the proposed features and analysis methods can be a promising addition to the area of automatic absence seizures detection.
{"title":"Automatic Absence Seizure Detection Evaluating Matching Pursuit Features of EEG Signals","authors":"Katerina Giannakaki, Giorgos Giannakakis, P. Vorgia, M. Klados, M. Zervakis","doi":"10.1109/BIBE.2019.00165","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00165","url":null,"abstract":"This paper evaluates the usage of matching pursuit (MP) features of electroencephalographic (EEG) signals and classification techniques on automatic absence seizure detection. Absence epileptic seizures are neurological disorders which are manifested as abnormal EEG patterns. Matching pursuit algorithm is able to decompose a signal into components with specific time-frequency characteristics. It is a robust technique especially when there is complex, multicomponent signal. In the present study, a clinical dataset containing 40 annotated absence seizures in long-term EEG recordings from pediatric epileptic patients (with age 6.0±2.9 years) was analyzed. The extracted MP features fed an automatic classification schema which achieved a time window based discrimination accuracy of 98.5%. As indicated by the study's results, the proposed features and analysis methods can be a promising addition to the area of automatic absence seizures detection.","PeriodicalId":318819,"journal":{"name":"2019 IEEE 19th International Conference on Bioinformatics and Bioengineering (BIBE)","volume":"32 6 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":"124329808","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}
V. Dimakopoulos, M. Antonakakis, Gabriel Moeddel, J. Wellmer, S. Rampp, M. Zervakis, C. Wolters
In recent years, several approaches have been introduced for estimating the spike onset zone within the irritative zone in epilepsy diagnosis for presurgical planning. One important direction utilizes source analysis from combined electroencephalography (EEG) and magnetoencephalography (MEG), EMEG, leveraging the benefits from the complementary properties of the two modalities. For EMEG source reconstruction, an average across the annotated epileptic spikes is often used to improve the signal-to-noise-ratio (SNR). In this contribution, we propose a two-phase clustering of interictal spikes with unsupervised learning methods, namely Self Organizing Maps (SOM) and K-means. In addition, we investigate the accuracy of combined EMEG source analysis on the sorted activity, using an individualized (with regard to both geometry and conductivity) six-compartment finite element head model with calibrated skull conductivity and white matter conductivity anisotropy. The results indicate that SOM eliminates the random variations of K-means and stabilizes the clustering efficiency. In terms of source reconstruction accuracy, this study demonstrates that the combined use of modalities reveals activity around two focal cortical dysplasias (FCDs), of one epilepsy patient, one in the right frontal area and one smaller in the left premotor cortex. It is worth mentioning that only EMEG could localize the left premotor FCD, which was then also found in surgery to be the responsible for triggering the epilepsy.
{"title":"Combined EEG/MEG Source Reconstruction of Epileptic Activity using a Two-Phase Spike Clustering Approach","authors":"V. Dimakopoulos, M. Antonakakis, Gabriel Moeddel, J. Wellmer, S. Rampp, M. Zervakis, C. Wolters","doi":"10.1109/BIBE.2019.00163","DOIUrl":"https://doi.org/10.1109/BIBE.2019.00163","url":null,"abstract":"In recent years, several approaches have been introduced for estimating the spike onset zone within the irritative zone in epilepsy diagnosis for presurgical planning. One important direction utilizes source analysis from combined electroencephalography (EEG) and magnetoencephalography (MEG), EMEG, leveraging the benefits from the complementary properties of the two modalities. For EMEG source reconstruction, an average across the annotated epileptic spikes is often used to improve the signal-to-noise-ratio (SNR). In this contribution, we propose a two-phase clustering of interictal spikes with unsupervised learning methods, namely Self Organizing Maps (SOM) and K-means. In addition, we investigate the accuracy of combined EMEG source analysis on the sorted activity, using an individualized (with regard to both geometry and conductivity) six-compartment finite element head model with calibrated skull conductivity and white matter conductivity anisotropy. The results indicate that SOM eliminates the random variations of K-means and stabilizes the clustering efficiency. In terms of source reconstruction accuracy, this study demonstrates that the combined use of modalities reveals activity around two focal cortical dysplasias (FCDs), of one epilepsy patient, one in the right frontal area and one smaller in the left premotor cortex. It is worth mentioning that only EMEG could localize the left premotor FCD, which was then also found in surgery to be the responsible for triggering the epilepsy.","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":"123808589","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：