Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6868106
Ajad Chhatkuli, A. Bartoli, Abed C. Malti, T. Collins
Augmented Reality (AR) can improve the information delivery to surgeons. In laparosurgery, the primary goal of AR is to provide multimodal information overlaid in live laparoscopic videos. For gynecologic laparoscopy, the 3D reconstruction of uterus and its deformable registration to preoperative data form the major problems in AR. Shape-from-Shading (SfS) and inter-frame registration require an accurate identification of the uterus region, the occlusions due to surgical tools, specularities, and other tissues. We propose a cascaded patient-specific real-time segmentation method to identify these four important regions. We use a color based Gaussian Mixture Model (GMM) to segment the tools and a more elaborate color and texture model to segment the uterus. The specularities are obtained by a saturation test. We show that our segmentation improves SfS and inter-frame registration of the uterus.
增强现实(AR)可以改善外科医生的信息传递。在腹腔镜手术中，AR的主要目标是在现场腹腔镜视频中提供多模态信息。对于妇科腹腔镜，子宫的三维重建及其与术前数据的可变形配准是AR的主要问题。shape - of - shading (SfS)和帧间配准需要准确识别子宫区域、手术工具造成的闭塞、镜面和其他组织。我们提出了一种级联的患者特异性实时分割方法来识别这四个重要区域。我们使用基于颜色的高斯混合模型(GMM)来分割工具，并使用更精细的颜色和纹理模型来分割子宫。通过饱和度测试获得了镜面率。我们发现我们的分割改善了SfS和子宫的帧间配准。
{"title":"Live image parsing in uterine laparoscopy","authors":"Ajad Chhatkuli, A. Bartoli, Abed C. Malti, T. Collins","doi":"10.1109/ISBI.2014.6868106","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6868106","url":null,"abstract":"Augmented Reality (AR) can improve the information delivery to surgeons. In laparosurgery, the primary goal of AR is to provide multimodal information overlaid in live laparoscopic videos. For gynecologic laparoscopy, the 3D reconstruction of uterus and its deformable registration to preoperative data form the major problems in AR. Shape-from-Shading (SfS) and inter-frame registration require an accurate identification of the uterus region, the occlusions due to surgical tools, specularities, and other tissues. We propose a cascaded patient-specific real-time segmentation method to identify these four important regions. We use a color based Gaussian Mixture Model (GMM) to segment the tools and a more elaborate color and texture model to segment the uterus. The specularities are obtained by a saturation test. We show that our segmentation improves SfS and inter-frame registration of the uterus.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"64 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":"127619941","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.2014.6867880
Cheng Lv, Xintao Hu, Junwei Han, Gong Cheng, Xiang Li, Lei Guo, Tianming Liu
Functional brain mapping under naturalistic stimuli such as video watching has been receiving greater interest in recent years. We presented a sparse representation based data-driven strategy to explore consistent functional brain networks during free viewing of continuous video streams. Compared with the traditional independent component analysis (ICA) based method, the novelty of our method is taking the intrinsic sparsity of whole-brain fMRI data into consideration and identify those highly descriptive dictionary atoms for sparse representation of fMRI signals. Our experimental results demonstrate that meaningful consistent functional brain networks can be mapped during free viewing of video stream by our method. We also compared the proposed method with ICA-based method.
{"title":"Exploring consistent functional brain networks during free viewing of videos via sparse representation","authors":"Cheng Lv, Xintao Hu, Junwei Han, Gong Cheng, Xiang Li, Lei Guo, Tianming Liu","doi":"10.1109/ISBI.2014.6867880","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867880","url":null,"abstract":"Functional brain mapping under naturalistic stimuli such as video watching has been receiving greater interest in recent years. We presented a sparse representation based data-driven strategy to explore consistent functional brain networks during free viewing of continuous video streams. Compared with the traditional independent component analysis (ICA) based method, the novelty of our method is taking the intrinsic sparsity of whole-brain fMRI data into consideration and identify those highly descriptive dictionary atoms for sparse representation of fMRI signals. Our experimental results demonstrate that meaningful consistent functional brain networks can be mapped during free viewing of video stream by our method. We also compared the proposed method with ICA-based method.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"71 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":"129188330","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}
Accurately delineating the myocardium from cardiac T2 and delayed enhanced (DE) MRI is a prerequisite to identifying and quantifying the edema and infarcts. The automatic delineation is however challenging due to the heterogeneous intensity distribution of the myocardium. In this paper, we propose a fully automatic method, which combines the complementary information from the two sequences using the newly proposed Multi-Component Bivariate Gaussian (MCBG) mixture model. The expectation maximization (EM) framework is adopted to estimate the segmentation and model parameters, where a probabilistic atlas is also used. This method performs the segmentation on the two MRI sequences simultaneously, and hence improves the robustness and accuracy. The results on six clinical cases showed that the proposed method significantly improved the performance compared to the atlas-based methods: myocardium Dice scores 0.643±0.084 versus 0.576±0.103 (P=0.002) on DE MRI, and 0.623±0.129 versus 0.484±0.106 (P=0.002) on T2 MRI.
{"title":"Myocardium segmentation combining T2 and DE MRI using Multi-Component Bivariate Gaussian mixture model","authors":"Jie Liu, X. Zhuang, Jing Liu, Shaoting Zhang, Guotai Wang, Lianming Wu, Jianrong Xu, Lixu Gu","doi":"10.1109/ISBI.2014.6868013","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6868013","url":null,"abstract":"Accurately delineating the myocardium from cardiac T2 and delayed enhanced (DE) MRI is a prerequisite to identifying and quantifying the edema and infarcts. The automatic delineation is however challenging due to the heterogeneous intensity distribution of the myocardium. In this paper, we propose a fully automatic method, which combines the complementary information from the two sequences using the newly proposed Multi-Component Bivariate Gaussian (MCBG) mixture model. The expectation maximization (EM) framework is adopted to estimate the segmentation and model parameters, where a probabilistic atlas is also used. This method performs the segmentation on the two MRI sequences simultaneously, and hence improves the robustness and accuracy. The results on six clinical cases showed that the proposed method significantly improved the performance compared to the atlas-based methods: myocardium Dice scores 0.643±0.084 versus 0.576±0.103 (P=0.002) on DE MRI, and 0.623±0.129 versus 0.484±0.106 (P=0.002) on T2 MRI.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"43 6 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":"116311178","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.2014.6867795
Hewei Cheng, Yong Fan
In this study, we propose a semi-supervised clustering method for parcellating the hippocampus into functionally homogeneous subregions based on resting state fMRI data. Particularly, the semi-supervised clustering is implemented as a graph partition problem by modeling each voxel as one node of the graph and connecting each pair of voxels with an edge weighted by a similarity measure between their functional signals. A geometric parcellation result of the hippocampus is adopted as prior information and a spatial consistent constraint is adopted as a regularization term to achieve spatially contiguous clustering. The graph partition problem is solved using an efficient algorithm similar to the well-known weighted kernel k-means algorithm. Our method has been validated based on resting state fMRI data of 28 subjects for the hippocampus parcellation with three subregions. The experiment results have demonstrated that the proposed method could parcellate the hippocampus into its head, body and tail parts. The distinctive functional and structural connectivity patterns of these subregions, derived from resting state fMRI and dMRI data respectively, have further demonstrated the validity of the parcellation results.
{"title":"Functional parcellation of the hippocampus by clustering resting state fMRI signals","authors":"Hewei Cheng, Yong Fan","doi":"10.1109/ISBI.2014.6867795","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867795","url":null,"abstract":"In this study, we propose a semi-supervised clustering method for parcellating the hippocampus into functionally homogeneous subregions based on resting state fMRI data. Particularly, the semi-supervised clustering is implemented as a graph partition problem by modeling each voxel as one node of the graph and connecting each pair of voxels with an edge weighted by a similarity measure between their functional signals. A geometric parcellation result of the hippocampus is adopted as prior information and a spatial consistent constraint is adopted as a regularization term to achieve spatially contiguous clustering. The graph partition problem is solved using an efficient algorithm similar to the well-known weighted kernel k-means algorithm. Our method has been validated based on resting state fMRI data of 28 subjects for the hippocampus parcellation with three subregions. The experiment results have demonstrated that the proposed method could parcellate the hippocampus into its head, body and tail parts. The distinctive functional and structural connectivity patterns of these subregions, derived from resting state fMRI and dMRI data respectively, have further demonstrated the validity of the parcellation results.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"16 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":"114172281","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.2014.6867815
B. Lei, Liu Zhuo, Siping Chen, Shengli Li, Dong Ni, Tianfu Wang
Detection and recognition of standard plane automatically during the course of US examination is an effective method for diagnosis of fetal development. In this paper, an automatic algorithm is developed to address the issue of recognition of standard planes (i.e. axial, coronal and sagittal planes) in the fetal ultrasound (US) image. The dense sampling feature transform descriptor (DSIFT) with aggregating vector method (i.e. fish vector (FV)) is explored for feature extraction. The learning and recognition of the planes have been implemented by support vector machine (SVM) classifier. Experimental results on the collected data demonstrate that high recognition accuracy is obtained.
{"title":"Automatic recognition of fetal standard plane in ultrasound image","authors":"B. Lei, Liu Zhuo, Siping Chen, Shengli Li, Dong Ni, Tianfu Wang","doi":"10.1109/ISBI.2014.6867815","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867815","url":null,"abstract":"Detection and recognition of standard plane automatically during the course of US examination is an effective method for diagnosis of fetal development. In this paper, an automatic algorithm is developed to address the issue of recognition of standard planes (i.e. axial, coronal and sagittal planes) in the fetal ultrasound (US) image. The dense sampling feature transform descriptor (DSIFT) with aggregating vector method (i.e. fish vector (FV)) is explored for feature extraction. The learning and recognition of the planes have been implemented by support vector machine (SVM) classifier. Experimental results on the collected data demonstrate that high recognition accuracy is obtained.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"409 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":"116242769","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.2014.6867960
C. Ledig, W. Shi, A. Makropoulos, J. Koikkalainen, R. Heckemann, A. Hammers, J. Lötjönen, O. Tenovuo, D. Rueckert
We propose a consistent approach to automatically segmenting longitudinal magnetic resonance scans of pathological brains. Using symmetric intra-subject registration, we align corresponding scans. In an expectation-maximization framework we exploit the availability of probabilistic segmentation estimates to perform a symmetric intensity normalisation. We introduce a novel technique to perform symmetric differential bias correction for images in presence of pathologies. To achieve a consistent multi-time-point segmentation, we propose a patch-based coupling term using a spatially and temporally varying Markov random field. We demonstrate the superior consistency of our method by segmenting repeat scans into 134 regions. Furthermore, the approach has been applied to segment baseline and six month follow-up scans from 56 patients who have sustained traumatic brain injury (TBI). We find significant correlations between regional atrophy rates and clinical outcome: Patients with poor outcome showed a much higher thalamic atrophy rate (4.9 ± 3.4%) than patients with favourable outcome (0.6 ± 1.9%).
{"title":"Consistent and robust 4D whole-brain segmentation: Application to traumatic brain injury","authors":"C. Ledig, W. Shi, A. Makropoulos, J. Koikkalainen, R. Heckemann, A. Hammers, J. Lötjönen, O. Tenovuo, D. Rueckert","doi":"10.1109/ISBI.2014.6867960","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867960","url":null,"abstract":"We propose a consistent approach to automatically segmenting longitudinal magnetic resonance scans of pathological brains. Using symmetric intra-subject registration, we align corresponding scans. In an expectation-maximization framework we exploit the availability of probabilistic segmentation estimates to perform a symmetric intensity normalisation. We introduce a novel technique to perform symmetric differential bias correction for images in presence of pathologies. To achieve a consistent multi-time-point segmentation, we propose a patch-based coupling term using a spatially and temporally varying Markov random field. We demonstrate the superior consistency of our method by segmenting repeat scans into 134 regions. Furthermore, the approach has been applied to segment baseline and six month follow-up scans from 56 patients who have sustained traumatic brain injury (TBI). We find significant correlations between regional atrophy rates and clinical outcome: Patients with poor outcome showed a much higher thalamic atrophy rate (4.9 ± 3.4%) than patients with favourable outcome (0.6 ± 1.9%).","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"7 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":"125442240","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.2014.6867794
Yuhui Du, J. Sui, Qingbao Yu, Hao He, V. Calhoun
Identification of subject-specific brain functional networks of interest is of great importance in fMRI based brain network analysis. In this study, a novel method is proposed to identify subject-specific brain functional networks using a graph theory based semi-supervised learning technique by incorporating not only prior information of the network to be identified as similarly used in seed region based correlation analysis (SCA) but also background information, which leads to robust performance for fMRI data with low signal noise ratio (SNR). Comparison experiments on both simulated and real fMRI data demonstrate that our method is more robust and accurate for identification of known brain functional networks than SCA, blind independent component analysis (ICA), and clustering based methods including Ncut and Kmeans.
{"title":"Semi-supervised learning of brain functional networks","authors":"Yuhui Du, J. Sui, Qingbao Yu, Hao He, V. Calhoun","doi":"10.1109/ISBI.2014.6867794","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867794","url":null,"abstract":"Identification of subject-specific brain functional networks of interest is of great importance in fMRI based brain network analysis. In this study, a novel method is proposed to identify subject-specific brain functional networks using a graph theory based semi-supervised learning technique by incorporating not only prior information of the network to be identified as similarly used in seed region based correlation analysis (SCA) but also background information, which leads to robust performance for fMRI data with low signal noise ratio (SNR). Comparison experiments on both simulated and real fMRI data demonstrate that our method is more robust and accurate for identification of known brain functional networks than SCA, blind independent component analysis (ICA), and clustering based methods including Ncut and Kmeans.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"19 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":"126976474","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.2014.6868007
S. Bauer, N. Porz, Raphael Meier, A. Pica, J. Slotboom, R. Wiest, M. Reyes
Medical doctors often do not trust the result of fully automatic segmentations because they have no possibility to make corrections if necessary. On the other hand, manual corrections can introduce a user bias. In this work, we propose to integrate the possibility for quick manual corrections into a fully automatic segmentation method for brain tumor images. This allows for necessary corrections while maintaining a high objectiveness. The underlying idea is similar to the well-known Grab-Cut algorithm, but here we combine decision forest classification with conditional random field regularization for interactive segmentation of 3D medical images. The approach has been evaluated by two different users on the BraTS2012 dataset. Accuracy and robustness improved compared to a fully automatic method and our interactive approach was ranked among the top performing methods. Time for computation including manual interaction was less than 10 minutes per patient, which makes it attractive for clinical use.
{"title":"Interactive segmentation of MR images from brain tumor patients","authors":"S. Bauer, N. Porz, Raphael Meier, A. Pica, J. Slotboom, R. Wiest, M. Reyes","doi":"10.1109/ISBI.2014.6868007","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6868007","url":null,"abstract":"Medical doctors often do not trust the result of fully automatic segmentations because they have no possibility to make corrections if necessary. On the other hand, manual corrections can introduce a user bias. In this work, we propose to integrate the possibility for quick manual corrections into a fully automatic segmentation method for brain tumor images. This allows for necessary corrections while maintaining a high objectiveness. The underlying idea is similar to the well-known Grab-Cut algorithm, but here we combine decision forest classification with conditional random field regularization for interactive segmentation of 3D medical images. The approach has been evaluated by two different users on the BraTS2012 dataset. Accuracy and robustness improved compared to a fully automatic method and our interactive approach was ranked among the top performing methods. Time for computation including manual interaction was less than 10 minutes per patient, which makes it attractive for clinical use.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"152 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":"127030176","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.2014.6867915
P. Irrera, I. Bloch, M. Delplanque
A multi-scale (MS) decomposition method for contrast enhancement of Micro Dose (MD) X-ray images is presented in this paper. First, we get a denoised version of the input exploiting a non-local means filter with adaptable parameters setting that we defined in a former approach. Then, the MS representations of the input and of its de-noised version are combined to obtain an optimal image in terms of preservation of details and noise attenuation. The efficiency of the algorithm is demonstrated by quantitative and qualitative assessments on both phantoms and clinical MD images.
{"title":"Contrast enhancement of Micro Dose X-ray images","authors":"P. Irrera, I. Bloch, M. Delplanque","doi":"10.1109/ISBI.2014.6867915","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867915","url":null,"abstract":"A multi-scale (MS) decomposition method for contrast enhancement of Micro Dose (MD) X-ray images is presented in this paper. First, we get a denoised version of the input exploiting a non-local means filter with adaptable parameters setting that we defined in a former approach. Then, the MS representations of the input and of its de-noised version are combined to obtain an optimal image in terms of preservation of details and noise attenuation. The efficiency of the algorithm is demonstrated by quantitative and qualitative assessments on both phantoms and clinical MD images.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"75 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":"127344763","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.2014.6867962
Jinglei Lv, Tuo Zhang, Xintao Hu, Dajiang Zhu, Kaiming Li, Lei Guo, Tianming Liu
Task-based fMRI is widely used to locate activated cortical regions during task performance. In the community of fMRI analysis, the general linear model (GLM) is the most popular method to detect activated brain regions, based on the assumption that fMRI BOLD signals follow well the shape of external stimulus. In this paper, instead of analyzing the voxel-based BOLD signal, we examine the functional connection curves between pairs of brain regions. Specifically, we calculate the dynamic functional connection (DFC) between a pair of our recently developed and validated Dense Individualized and Common Connectivity-based Cortical Landmarks (DICCCOL), and use the GLM to estimate if DFC time series follow the shape of external stimulus. Since the DICCCOL landmarks possess structural and functional correspondence across subjects and these correspondences also apply to their connections, the mixed-effects model is thus performed to effect sizes estimated from GLM of each corresponding connection across subjects to detect group-wise activation. In other words, we assess the activation of cortical landmarks' dynamic interactions at the group-level. Our experimental results demonstrate that the proposed approach is able to detect reasonable activated connection patterns.
{"title":"Group-wise connection activation detection based on DICCCOL","authors":"Jinglei Lv, Tuo Zhang, Xintao Hu, Dajiang Zhu, Kaiming Li, Lei Guo, Tianming Liu","doi":"10.1109/ISBI.2014.6867962","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867962","url":null,"abstract":"Task-based fMRI is widely used to locate activated cortical regions during task performance. In the community of fMRI analysis, the general linear model (GLM) is the most popular method to detect activated brain regions, based on the assumption that fMRI BOLD signals follow well the shape of external stimulus. In this paper, instead of analyzing the voxel-based BOLD signal, we examine the functional connection curves between pairs of brain regions. Specifically, we calculate the dynamic functional connection (DFC) between a pair of our recently developed and validated Dense Individualized and Common Connectivity-based Cortical Landmarks (DICCCOL), and use the GLM to estimate if DFC time series follow the shape of external stimulus. Since the DICCCOL landmarks possess structural and functional correspondence across subjects and these correspondences also apply to their connections, the mixed-effects model is thus performed to effect sizes estimated from GLM of each corresponding connection across subjects to detect group-wise activation. In other words, we assess the activation of cortical landmarks' dynamic interactions at the group-level. Our experimental results demonstrate that the proposed approach is able to detect reasonable activated connection patterns.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"29 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":"126353149","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：