Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867905
Chuqing Cao, Ying Sun
The sparsity of MR images has been utilized to significantly undersample k-space measurements for accelerated MRI. In dynamic MRI, besides the spatiotemporal structures of images, the motion information should be considered to improve the reconstruction performance. Motivated by this, we propose a new method to recover dynamic MR images using partial k-space data based on the estimation of inter-frame motion. Our method consists of three main steps: single frame reconstruction, inter-frame motion estimation, and image sequence recovery. In contrast to algorithms which use a single reference frame for motion estimation, the motion information of each image in a dynamic MRI sequence is estimated according to adjacent frames. Since motion is estimated from the reconstructed images, the recovery process is robust against both noise and artifacts. The proposed method was evaluated on two dynamic MRI datasets, and compared with several state-of-the-art reconstruction methods. Experimental results demonstrate the effectiveness and robustness of the proposed method.
{"title":"Accelerated dynamic MRI via inter-frame motion estimation","authors":"Chuqing Cao, Ying Sun","doi":"10.1109/ISBI.2014.6867905","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867905","url":null,"abstract":"The sparsity of MR images has been utilized to significantly undersample k-space measurements for accelerated MRI. In dynamic MRI, besides the spatiotemporal structures of images, the motion information should be considered to improve the reconstruction performance. Motivated by this, we propose a new method to recover dynamic MR images using partial k-space data based on the estimation of inter-frame motion. Our method consists of three main steps: single frame reconstruction, inter-frame motion estimation, and image sequence recovery. In contrast to algorithms which use a single reference frame for motion estimation, the motion information of each image in a dynamic MRI sequence is estimated according to adjacent frames. Since motion is estimated from the reconstructed images, the recovery process is robust against both noise and artifacts. The proposed method was evaluated on two dynamic MRI datasets, and compared with several state-of-the-art reconstruction methods. Experimental results demonstrate the effectiveness and robustness of the proposed method.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129467634","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6868089
Chen-Ping Yu, Guilherme C. S. Ruppert, R. Collins, D. Nguyen, A. Falcão, Yanxi Liu
Automatic detection and segmentation of brain tumors in 3D MR neuroimages can significantly aid early diagnosis, surgical planning, and follow-up assessment. However, due to diverse location and varying size, primary and metastatic tumors present substantial challenges for detection. We present a fully automatic, unsupervised algorithm that can detect single and multiple tumors from 3 to 28,079 mm3 in volume. Using 20 clinical 3D MR scans containing from 1 to 15 tumors per scan, the proposed approach achieves between 87.84% and 95.30% detection rate and an average end-to-end running time of under 3 minutes. In addition, 5 normal clinical 3D MR scans are evaluated quantitatively to demonstrate that the approach has the potential to discriminate between abnormal and normal brains.
{"title":"3D blob based brain tumor detection and segmentation in MR images","authors":"Chen-Ping Yu, Guilherme C. S. Ruppert, R. Collins, D. Nguyen, A. Falcão, Yanxi Liu","doi":"10.1109/ISBI.2014.6868089","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6868089","url":null,"abstract":"Automatic detection and segmentation of brain tumors in 3D MR neuroimages can significantly aid early diagnosis, surgical planning, and follow-up assessment. However, due to diverse location and varying size, primary and metastatic tumors present substantial challenges for detection. We present a fully automatic, unsupervised algorithm that can detect single and multiple tumors from 3 to 28,079 mm3 in volume. Using 20 clinical 3D MR scans containing from 1 to 15 tumors per scan, the proposed approach achieves between 87.84% and 95.30% detection rate and an average end-to-end running time of under 3 minutes. In addition, 5 normal clinical 3D MR scans are evaluated quantitatively to demonstrate that the approach has the potential to discriminate between abnormal and normal brains.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128501183","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867808
Fang Cao, O. Commowick, Camille Maumet, C. Barillot
The development of brain Magentic Resonance Imaging (MRI) is driving increasing demand for quantitative measurements. Quantitative MRI (qMRI) templates of relaxation times and proton density can be of particular interest for dedicated clinical applications such as characterizing brain tissue abnormalities, as well as general research purposes. In this paper, we have developed 3D qMRI statistical templates consisting of T1, T2, T2* and ρ* maps from the human brain at 3T. The qMRI templates were built from a population of 20 normal controls, for which individual maps were estimated in a robust manner, accounting for acquisition artifacts and expected relationships between the relaxometry parameters. For validation, we fed the qMRI templates into a realistic MRI simulator to synthesize MR-weighted images, and compared these images with the real MR acquisitions. High correlation coefficients (>0.80) show that the developed qMRI templates can be used as input dataset for MRI simulation community, which may be of great interest to clinical neuroscience field.
{"title":"Quantitative relaxation templates for the human brain at 3T","authors":"Fang Cao, O. Commowick, Camille Maumet, C. Barillot","doi":"10.1109/ISBI.2014.6867808","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867808","url":null,"abstract":"The development of brain Magentic Resonance Imaging (MRI) is driving increasing demand for quantitative measurements. Quantitative MRI (qMRI) templates of relaxation times and proton density can be of particular interest for dedicated clinical applications such as characterizing brain tissue abnormalities, as well as general research purposes. In this paper, we have developed 3D qMRI statistical templates consisting of T1, T2, T2* and ρ* maps from the human brain at 3T. The qMRI templates were built from a population of 20 normal controls, for which individual maps were estimated in a robust manner, accounting for acquisition artifacts and expected relationships between the relaxometry parameters. For validation, we fed the qMRI templates into a realistic MRI simulator to synthesize MR-weighted images, and compared these images with the real MR acquisitions. High correlation coefficients (>0.80) show that the developed qMRI templates can be used as input dataset for MRI simulation community, which may be of great interest to clinical neuroscience field.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129075438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867845
Hao-Chih Lee, Ge Yang
Background fluorescence is a frequently encountered problem in biological fluorescence microscopy. It often significantly lowers the image signal-to-noise ratio and poses substantial challenges to subsequent computational image analysis. Here we propose a general computational method for separating and removing background fluorescence from a single fluorescence microscopy image. The method is formulated as solving a constrained convex optimization problem and assumes that the background signal is low-rank and additive to the sparse foreground signal. Solution of the optimization problem is found using a forward-backward algorithm. Our method only requires a single image and can be used in a broad range of biological fluorescence applications. We first validate performance of our method using synthetic image data. We then demonstrate applications of the method to actual biological image data.
{"title":"Computational removal ofbackground fluorescence for biological fluorescence microscopy","authors":"Hao-Chih Lee, Ge Yang","doi":"10.1109/ISBI.2014.6867845","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867845","url":null,"abstract":"Background fluorescence is a frequently encountered problem in biological fluorescence microscopy. It often significantly lowers the image signal-to-noise ratio and poses substantial challenges to subsequent computational image analysis. Here we propose a general computational method for separating and removing background fluorescence from a single fluorescence microscopy image. The method is formulated as solving a constrained convex optimization problem and assumes that the background signal is low-rank and additive to the sparse foreground signal. Solution of the optimization problem is found using a forward-backward algorithm. Our method only requires a single image and can be used in a broad range of biological fluorescence applications. We first validate performance of our method using synthetic image data. We then demonstrate applications of the method to actual biological image data.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130594048","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867796
M. Preti, Nora Leonardi, F. I. Karahanoğlu, F. Grouiller, M. Genetti, M. Seeck, S. Vulliémoz, D. Ville
Recent findings highlighted the non-stationarity of brain functional connectivity (FC) during resting-state functional magnetic resonance imaging (fMRI), encouraging the development of methods allowing to explore brain network dynamics. This appears particularly relevant when dealing with brain diseases involving dynamic neuronal processes, like epilepsy. In this study, we introduce a new method to pinpoint connectivity changes related to epileptic activity by integrating EEG and dynamic FC information. To our knowledge, no previous work has attempted to integrate dFC with the epileptic activity from EEG. The detailed results obtained from the analysis of two patients successfully detected specific patterns of connections/disconnections related to the epileptic activity and highlighted the potential of a dynamic analysis for a better understanding of network organisation in epilepsy.
{"title":"Epileptic network activity revealed by dynamic functional connectivity in simultaneous EEG-fMRI","authors":"M. Preti, Nora Leonardi, F. I. Karahanoğlu, F. Grouiller, M. Genetti, M. Seeck, S. Vulliémoz, D. Ville","doi":"10.1109/ISBI.2014.6867796","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867796","url":null,"abstract":"Recent findings highlighted the non-stationarity of brain functional connectivity (FC) during resting-state functional magnetic resonance imaging (fMRI), encouraging the development of methods allowing to explore brain network dynamics. This appears particularly relevant when dealing with brain diseases involving dynamic neuronal processes, like epilepsy. In this study, we introduce a new method to pinpoint connectivity changes related to epileptic activity by integrating EEG and dynamic FC information. To our knowledge, no previous work has attempted to integrate dFC with the epileptic activity from EEG. The detailed results obtained from the analysis of two patients successfully detected specific patterns of connections/disconnections related to the epileptic activity and highlighted the potential of a dynamic analysis for a better understanding of network organisation in epilepsy.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"11 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128845363","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867844
Hengyong Yu, Chuang Miao
Inspired by the Compressive sensing (CS) theory, the Lp regularization methods have attracted a great attention. The Lp regularization is a generalized version of the well-known L1 regularization for sparser solution. In this paper, we derive a general thresholding representation for the Lp (0 <; p <; 1) regularization problem in term of a recursive function, which can be well approximated by few steps. This representation can be simplified to the well-known soft-threshold filtering for L1 regularization, the hard-threshold filtering for L0 regularization, and the recently reported half-threshold filtering for L1/2 regularization. This general threshold representation can be easily incorporated into the iterative thresholding framework to provide a tool for sparsity problems.
{"title":"General thresholding representation for the Lp regularization problem","authors":"Hengyong Yu, Chuang Miao","doi":"10.1109/ISBI.2014.6867844","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867844","url":null,"abstract":"Inspired by the Compressive sensing (CS) theory, the Lp regularization methods have attracted a great attention. The Lp regularization is a generalized version of the well-known L1 regularization for sparser solution. In this paper, we derive a general thresholding representation for the Lp (0 <; p <; 1) regularization problem in term of a recursive function, which can be well approximated by few steps. This representation can be simplified to the well-known soft-threshold filtering for L1 regularization, the hard-threshold filtering for L0 regularization, and the recently reported half-threshold filtering for L1/2 regularization. This general threshold representation can be easily incorporated into the iterative thresholding framework to provide a tool for sparsity problems.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126344628","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6868121
H. Morales, O. Bonnefous
In this work, we propose a novel approach for modeling hemodynamics after flow diverter (FD) stent in cerebral aneurysms. One image-based aneurysm model was used. The stented portion at the parent artery was modeled as a porous medium. Cell size, porous medium thickness and FD porosity were evaluated. Velocity magnitude and wall shear stress (WSS) inside the aneurysm were reduced after FD placement. Bigger cells compared to the stent strut diameter can be used. Thicker porous medium (which is equivalent of inserting multiple FDs) induces lower intra-aneurysmal velocity and WSS. Lower FD porosities produce higher reductions of intra-aneurysmal velocities, which diminish the contrast concentration inside the aneurysm and increase its residence time. Device design and multiple FD placements can be evaluated without remeshing the fluid domain.
{"title":"Modeling hemodynamics after flow diverter with a porous medium","authors":"H. Morales, O. Bonnefous","doi":"10.1109/ISBI.2014.6868121","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6868121","url":null,"abstract":"In this work, we propose a novel approach for modeling hemodynamics after flow diverter (FD) stent in cerebral aneurysms. One image-based aneurysm model was used. The stented portion at the parent artery was modeled as a porous medium. Cell size, porous medium thickness and FD porosity were evaluated. Velocity magnitude and wall shear stress (WSS) inside the aneurysm were reduced after FD placement. Bigger cells compared to the stent strut diameter can be used. Thicker porous medium (which is equivalent of inserting multiple FDs) induces lower intra-aneurysmal velocity and WSS. Lower FD porosities produce higher reductions of intra-aneurysmal velocities, which diminish the contrast concentration inside the aneurysm and increase its residence time. Device design and multiple FD placements can be evaluated without remeshing the fluid domain.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121389025","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867941
A. Seghouane, L. Johnston
Non-parametric Hemodynamic Response Function (HRF) estimation in noisy functional Magnetic Resonance Imaging (fMRI) plays an important role when investigating the temporal dynamics of regional brain responses during activation. Making use of a semiparametric model to characterize the fMRI time series and a sparsity assumption on the HRF, a new method for voxelwise non-parametric HRF estimation is derived in this paper. The proposed method consistently estimates the HRF by applying first order differencing to the fMRI time series samples and introducing a regularization penalty in the minimization problem to promote sparsity of the HRF coefficients. Based on the likelihood ratio test (LRT) principle, a new statistical test for detecting activated pixels is proposed using the estimated HRF. The effectiveness of the HRF estimation method is illustrated on both simulated and experimental fMRI data from a visual experiment.
{"title":"Consistent hemodynamic response estimation function in fMRI using sparse prior information","authors":"A. Seghouane, L. Johnston","doi":"10.1109/ISBI.2014.6867941","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867941","url":null,"abstract":"Non-parametric Hemodynamic Response Function (HRF) estimation in noisy functional Magnetic Resonance Imaging (fMRI) plays an important role when investigating the temporal dynamics of regional brain responses during activation. Making use of a semiparametric model to characterize the fMRI time series and a sparsity assumption on the HRF, a new method for voxelwise non-parametric HRF estimation is derived in this paper. The proposed method consistently estimates the HRF by applying first order differencing to the fMRI time series samples and introducing a regularization penalty in the minimization problem to promote sparsity of the HRF coefficients. Based on the likelihood ratio test (LRT) principle, a new statistical test for detecting activated pixels is proposed using the estimated HRF. The effectiveness of the HRF estimation method is illustrated on both simulated and experimental fMRI data from a visual experiment.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121407849","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867947
Jasmine Song, Colin Davey, C. Poulsen, S. Turovets, P. Luu, D. Tucker
In research with electroencephalographic (EEG) measures, it is useful to identify the sources underlying the potentials recorded at the head surface in order to relate the EEG potentials to brain function. The EEG recorded at the head surface is a function of how current at specific brain (primarily cortical) locations propagates through the conducting volume of head tissues. The accuracy of source localization depends on a sufficient sampling of the surface potential field, an accurate estimation of the conducting volume (head model), and the inverse technique. The present paper reports the effect of spatial sampling of the potential field at the head surface, in terms of both sensor density and coverage of the inferior (lower) as well as superior (upper) head regions. Several inverse methods are examined, using the four shells spherical head model and the finite difference model. Consistent with previous research, greater sensor density improves source localization accuracy. In addition, across all sampling density and inverse methods, sampling across the whole head surface improves the accuracy of source estimates.
{"title":"Sensor density and head surface coverage in EEG source localization","authors":"Jasmine Song, Colin Davey, C. Poulsen, S. Turovets, P. Luu, D. Tucker","doi":"10.1109/ISBI.2014.6867947","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867947","url":null,"abstract":"In research with electroencephalographic (EEG) measures, it is useful to identify the sources underlying the potentials recorded at the head surface in order to relate the EEG potentials to brain function. The EEG recorded at the head surface is a function of how current at specific brain (primarily cortical) locations propagates through the conducting volume of head tissues. The accuracy of source localization depends on a sufficient sampling of the surface potential field, an accurate estimation of the conducting volume (head model), and the inverse technique. The present paper reports the effect of spatial sampling of the potential field at the head surface, in terms of both sensor density and coverage of the inferior (lower) as well as superior (upper) head regions. Several inverse methods are examined, using the four shells spherical head model and the finite difference model. Consistent with previous research, greater sensor density improves source localization accuracy. In addition, across all sampling density and inverse methods, sampling across the whole head surface improves the accuracy of source estimates.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126394805","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6867999
A. Basset, P. Bouthemy, J. Boulanger, J. Salamero, C. Kervrann
The detection of proteins and the classification of their temporal behaviors in live cell fluorescence microscopy are of utmost importance to understand cell mechanisms. In this paper, we aim at locating and recognizing temporal events in TIRF microscopy image sequences related to membrane dynamics. After segmenting the time-varying vesicles in the image, we exploit space-time information extracted from three successive images only to model, locate and recognize the two dynamic configurations of interest: translational motion or local fluorescence diffusion. A likelihood ratio test is defined to solve this issue. Results on synthetic and real TIRF sequences demonstrate the accuracy and efficiency of the proposed method.
{"title":"Localization and classification of membrane dynamics in TIRF microscopy image sequences","authors":"A. Basset, P. Bouthemy, J. Boulanger, J. Salamero, C. Kervrann","doi":"10.1109/ISBI.2014.6867999","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867999","url":null,"abstract":"The detection of proteins and the classification of their temporal behaviors in live cell fluorescence microscopy are of utmost importance to understand cell mechanisms. In this paper, we aim at locating and recognizing temporal events in TIRF microscopy image sequences related to membrane dynamics. After segmenting the time-varying vesicles in the image, we exploit space-time information extracted from three successive images only to model, locate and recognize the two dynamic configurations of interest: translational motion or local fluorescence diffusion. A likelihood ratio test is defined to solve this issue. Results on synthetic and real TIRF sequences demonstrate the accuracy and efficiency of the proposed method.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-07-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121705965","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：