Pub Date : 2017-04-01DOI: 10.1109/ISBI.2017.7950573
Jagath Rajapakse, Sukrit Gupta, Xiuchao Sui
Functional connectivity of the human brain and the hierarchical modular architecture of functional networks can be investigated using functional magnetic resonance imaging (fMRI). Various network models, such as power-law networks and modular networks have been explored before to study brain networks. In order to investigate the plausibility of modeling functional brain networks with network models based on distribution of node degree and connection weights, we will compute the goodness-of-fit of several network models on resting-state fMRI scans gathered in the Human Connectome Project. Our experiments suggest that the power-law networks and stochastic block models aptly fit functional connectivity of the subjects and the stochastic block models have the potential to detect functional modules of the brain.
{"title":"Fitting networks models for functional brain connectivity","authors":"Jagath Rajapakse, Sukrit Gupta, Xiuchao Sui","doi":"10.1109/ISBI.2017.7950573","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950573","url":null,"abstract":"Functional connectivity of the human brain and the hierarchical modular architecture of functional networks can be investigated using functional magnetic resonance imaging (fMRI). Various network models, such as power-law networks and modular networks have been explored before to study brain networks. In order to investigate the plausibility of modeling functional brain networks with network models based on distribution of node degree and connection weights, we will compute the goodness-of-fit of several network models on resting-state fMRI scans gathered in the Human Connectome Project. Our experiments suggest that the power-law networks and stochastic block models aptly fit functional connectivity of the subjects and the stochastic block models have the potential to detect functional modules of the brain.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"128 1","pages":"515-519"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"73950555","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950584
Afaf Tareef, Yang Song, D. Feng, Mei Chen, Weidong (Tom) Cai
Segmentation of white blood cells (i.e. leukocytes) is a crucial step toward the development of haematological images analysis of peripheral blood smears. This step, however, is complicated by the complex nature of the different types of white blood cells and their large variations in shape, texture, color, and density. This study addresses this issue and presents a single fully automatic segmentation framework for both nuclei and cytoplasm of the five classes of leukocytes in a microscope blood smear. The proposed framework integrates a priori information of enhanced nuclei color with Gram-Schmidt orthogonalization, and multi-scale morphological enhancement to localize the nuclei, whereas clustering-based seed extraction and watershed are utilized to segment the cytoplasm. The experimental results on two different datasets show that the proposed method works successfully for both nuclei and cytoplasm segmentation, and achieves more accurate segmentation results compared to six leukocytes segmentation methods in the literature.
{"title":"Automated multi-stage segmentation of white blood cells via optimizing color processing","authors":"Afaf Tareef, Yang Song, D. Feng, Mei Chen, Weidong (Tom) Cai","doi":"10.1109/ISBI.2017.7950584","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950584","url":null,"abstract":"Segmentation of white blood cells (i.e. leukocytes) is a crucial step toward the development of haematological images analysis of peripheral blood smears. This step, however, is complicated by the complex nature of the different types of white blood cells and their large variations in shape, texture, color, and density. This study addresses this issue and presents a single fully automatic segmentation framework for both nuclei and cytoplasm of the five classes of leukocytes in a microscope blood smear. The proposed framework integrates a priori information of enhanced nuclei color with Gram-Schmidt orthogonalization, and multi-scale morphological enhancement to localize the nuclei, whereas clustering-based seed extraction and watershed are utilized to segment the cytoplasm. The experimental results on two different datasets show that the proposed method works successfully for both nuclei and cytoplasm segmentation, and achieves more accurate segmentation results compared to six leukocytes segmentation methods in the literature.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"469 3","pages":"565-568"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"72585690","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950575
Amanmeet Garg, Donghuan Lu, K. Popuri, M. Beg
The geometry of the human brain changes due to age and neurodegeneration. The brain geometry is expected to undergo a similar change in shape with a normal aging, however such change may differ in patients suffering from neurodegenerative disorders. In the novel framework proposed in this work, we model the brain geometry as a 3D point cloud and study the algebraic topology features of this point cloud. Specifically, we compute the persistence timelines of a simplicial complex in a multiscale simplicial homology of the underlying topology space. Further, persistence landscape summary features are obtained from the timelines and studied for their difference between the two groups. The statistical significance obtained in a permutation testing experiments highlights the ability of the persistence landscape features to differentiate between the PD and healthy control brain geometry.
{"title":"Brain geometry persistent homology marker for Parkinson's disease","authors":"Amanmeet Garg, Donghuan Lu, K. Popuri, M. Beg","doi":"10.1109/ISBI.2017.7950575","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950575","url":null,"abstract":"The geometry of the human brain changes due to age and neurodegeneration. The brain geometry is expected to undergo a similar change in shape with a normal aging, however such change may differ in patients suffering from neurodegenerative disorders. In the novel framework proposed in this work, we model the brain geometry as a 3D point cloud and study the algebraic topology features of this point cloud. Specifically, we compute the persistence timelines of a simplicial complex in a multiscale simplicial homology of the underlying topology space. Further, persistence landscape summary features are obtained from the timelines and studied for their difference between the two groups. The statistical significance obtained in a permutation testing experiments highlights the ability of the persistence landscape features to differentiate between the PD and healthy control brain geometry.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"45 1","pages":"525-528"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74555219","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950727
Bao Yang, L. Ying, Jing Tang
The performance of smoothness-enforced Bayesian PET image reconstruction is strongly affected by the weight on regularization. Compromises need to be made between variance and spatial resolution. In this work, we propose to use an artificial neural network (ANN) to fuse the image versions reconstructed from a maximum a posteriori (MAP) algorithm with different regularizing weights for quantitative improvement. Using the BrainWeb phantoms, we simulated PET data at different count levels for different subjects with and without lesions. We designed an ANN and trained it using MAP reconstructions with different regularization parameters for one normal subject at a specific count level. Reconstructed images from the simulations with lesions, of other count levels, and of other subjects were fused using the trained ANN. In all of the testing experiments, the designed ANN fusion keeps the noise level as low as what the MAP algorithm achieves at heavy regularization while significantly reduces the bias or improves the lesion contrast. We conclude that the proposed ANN fusion method removes the need for tuning the regularization of the MAP algorithm.
{"title":"Enhancing Bayesian PET image reconstruction using neural networks","authors":"Bao Yang, L. Ying, Jing Tang","doi":"10.1109/ISBI.2017.7950727","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950727","url":null,"abstract":"The performance of smoothness-enforced Bayesian PET image reconstruction is strongly affected by the weight on regularization. Compromises need to be made between variance and spatial resolution. In this work, we propose to use an artificial neural network (ANN) to fuse the image versions reconstructed from a maximum a posteriori (MAP) algorithm with different regularizing weights for quantitative improvement. Using the BrainWeb phantoms, we simulated PET data at different count levels for different subjects with and without lesions. We designed an ANN and trained it using MAP reconstructions with different regularization parameters for one normal subject at a specific count level. Reconstructed images from the simulations with lesions, of other count levels, and of other subjects were fused using the trained ANN. In all of the testing experiments, the designed ANN fusion keeps the noise level as low as what the MAP algorithm achieves at heavy regularization while significantly reduces the bias or improves the lesion contrast. We conclude that the proposed ANN fusion method removes the need for tuning the regularization of the MAP algorithm.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"9 1","pages":"1181-1184"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77626514","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950615
Alper Gungor, E. Kopanoglu, T. Çukur, H. Guven
In this study, we deal with the problem of image reconstruction from compressive measurements of multi-contrast magnetic resonance imaging (MRI). We propose a synthesis based approach for image reconstruction to better exploit mutual information across contrasts, while retaining individual features of each contrast image. For fast recovery, we propose an augmented Lagrangian based algorithm, using Alternating Direction Method of Multipliers (ADMM). We then compare the proposed algorithm to the state-of-the-art Compressive Sensing-MRI algorithms, and show that the proposed method results in better quality images in shorter computation time.
{"title":"A synthesis-based approach to compressive multi-contrast magnetic resonance imaging","authors":"Alper Gungor, E. Kopanoglu, T. Çukur, H. Guven","doi":"10.1109/ISBI.2017.7950615","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950615","url":null,"abstract":"In this study, we deal with the problem of image reconstruction from compressive measurements of multi-contrast magnetic resonance imaging (MRI). We propose a synthesis based approach for image reconstruction to better exploit mutual information across contrasts, while retaining individual features of each contrast image. For fast recovery, we propose an augmented Lagrangian based algorithm, using Alternating Direction Method of Multipliers (ADMM). We then compare the proposed algorithm to the state-of-the-art Compressive Sensing-MRI algorithms, and show that the proposed method results in better quality images in shorter computation time.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"402 1","pages":"696-699"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79810943","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950591
Erwan Zerhouni, B. Prisacari, Qing Zhong, P. Wild, M. Gabrani
One of the main challenges of histological image analysis is the high dimensionality of the images. This can be addressed via summarizing techniques or feature engineering. However, such approaches can limit the performance of subsequent machine learning models, particularly when dealing with highly heterogeneous tissue samples. One possible alternative is to employ unsupervised learning to determine the most relevant features automatically. In this paper, we propose a method of generating representative image signatures that are robust to tissue heterogeneity. At the core of our approach lies a novel deep-learning based mechanism to simultaneously produce representative image features as well as perform dictionary learning to further reduce dimensionality. By integrating this mechanism in a broader framework for disease grading, we show significant improvement in terms of grading accuracy compared to alternative local feature extraction methods.
{"title":"Disease grading of heterogeneous tissue using convolutional autoencoder","authors":"Erwan Zerhouni, B. Prisacari, Qing Zhong, P. Wild, M. Gabrani","doi":"10.1109/ISBI.2017.7950591","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950591","url":null,"abstract":"One of the main challenges of histological image analysis is the high dimensionality of the images. This can be addressed via summarizing techniques or feature engineering. However, such approaches can limit the performance of subsequent machine learning models, particularly when dealing with highly heterogeneous tissue samples. One possible alternative is to employ unsupervised learning to determine the most relevant features automatically. In this paper, we propose a method of generating representative image signatures that are robust to tissue heterogeneity. At the core of our approach lies a novel deep-learning based mechanism to simultaneously produce representative image features as well as perform dictionary learning to further reduce dimensionality. By integrating this mechanism in a broader framework for disease grading, we show significant improvement in terms of grading accuracy compared to alternative local feature extraction methods.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"5 1","pages":"596-599"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79432835","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950596
Shuhang Chen, P. Gyawali, Huafeng Liu, B. Horáček, J. Sapp, Linwei Wang
An automatic, real-time localization of ventricular tachycardia (VT) can improve the efficiency and efficacy of interventional therapies. Because the exit site of VT gives rise to its QRS morphology on electrocardiograms (ECG), it has been shown feasible to predict VT exits from 12-lead ECGs. However, existing work have reported limited resolution and accuracy due to a critical challenge: the significant inter-subject heterogeneity in ECG data. In this paper, we present a method to explicitly separate and represent the factors of variation in data throughout a deep network using denoising autoencoder with contrastive regularization. We demonstrate the performance of this method on an ECG dataset collected from 39 patients and 1012 distinct sites of ventricular origins. An improvement in the accuracy of localizing the origin of activation is obtained in comparison to a traditional approach that uses prescribed QRS features for prediction, as well as the use of a standard autoencoder network without separating the factors of variations in ECG data.
{"title":"Disentangling inter-subject variations: Automatic localization of ventricular tachycardia origin from 12-lead electrocardiograms","authors":"Shuhang Chen, P. Gyawali, Huafeng Liu, B. Horáček, J. Sapp, Linwei Wang","doi":"10.1109/ISBI.2017.7950596","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950596","url":null,"abstract":"An automatic, real-time localization of ventricular tachycardia (VT) can improve the efficiency and efficacy of interventional therapies. Because the exit site of VT gives rise to its QRS morphology on electrocardiograms (ECG), it has been shown feasible to predict VT exits from 12-lead ECGs. However, existing work have reported limited resolution and accuracy due to a critical challenge: the significant inter-subject heterogeneity in ECG data. In this paper, we present a method to explicitly separate and represent the factors of variation in data throughout a deep network using denoising autoencoder with contrastive regularization. We demonstrate the performance of this method on an ECG dataset collected from 39 patients and 1012 distinct sites of ventricular origins. An improvement in the accuracy of localizing the origin of activation is obtained in comparison to a traditional approach that uses prescribed QRS features for prediction, as well as the use of a standard autoencoder network without separating the factors of variations in ECG data.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"201 1","pages":"616-619"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77000639","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950739
Haijun Lei, Jian Zhang, Zhang Yang, Ee-Leng Tan, B. Lei, Qiuming Luo
In this study, a novel feature selection framework is proposed to simultaneously perform classification and clinical scores prediction of Parkinson's disease (PD) via multi-modal neuroimaging data. Specifically, a new feature selection model is devised to capture discriminative features to train support vector regression model for clinical scores (e.g., sleep scores and olfactory scores) prediction and support vector classification model for class label identification. Our method is evaluated on a public dataset of 208 subjects including 56 normal controls (NC), 123 PD and 29 scans without evidence of dopamine deficit (SWEDD) via a 10-fold cross-validation method. The experimental results demonstrate that multi-modal data can effectively improve the performance in disease status identification and clinical scores prediction compared to one single modality. Our proposed method also outperforms the related methods.
{"title":"Joint detection and clinical score prediction in Parkinson's disease via multi-modal sparse learning","authors":"Haijun Lei, Jian Zhang, Zhang Yang, Ee-Leng Tan, B. Lei, Qiuming Luo","doi":"10.1109/ISBI.2017.7950739","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950739","url":null,"abstract":"In this study, a novel feature selection framework is proposed to simultaneously perform classification and clinical scores prediction of Parkinson's disease (PD) via multi-modal neuroimaging data. Specifically, a new feature selection model is devised to capture discriminative features to train support vector regression model for clinical scores (e.g., sleep scores and olfactory scores) prediction and support vector classification model for class label identification. Our method is evaluated on a public dataset of 208 subjects including 56 normal controls (NC), 123 PD and 29 scans without evidence of dopamine deficit (SWEDD) via a 10-fold cross-validation method. The experimental results demonstrate that multi-modal data can effectively improve the performance in disease status identification and clinical scores prediction compared to one single modality. Our proposed method also outperforms the related methods.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"3 1","pages":"1231-1234"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78363649","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950669
Peter Naylor, M. Laé, F. Reyal, Thomas Walter
Analysis and interpretation of stained tumor sections is one of the main tools in cancer diagnosis and prognosis, which is mainly carried out manually by pathologists. The avent of digital pathology provides us with the challenging opportunity to automatically analyze large amounts of these complex image data in order to draw biological conclusions from them and to study cellular and tissular phenotypes at a large scale. One of the bottlenecks for such approaches is the automatic segmentation of cell nuclei from this type of image data. Here, we present a fully automated workflow to segment nuclei from histopathology image data by using deep neural networks trained from a set of manually annotated images and by processing the posterior probability maps in order to split jointly segmented nuclei. Further, we provide the image data set that has been generated for this study as a benchmark set to the scientific community.
{"title":"Nuclei segmentation in histopathology images using deep neural networks","authors":"Peter Naylor, M. Laé, F. Reyal, Thomas Walter","doi":"10.1109/ISBI.2017.7950669","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950669","url":null,"abstract":"Analysis and interpretation of stained tumor sections is one of the main tools in cancer diagnosis and prognosis, which is mainly carried out manually by pathologists. The avent of digital pathology provides us with the challenging opportunity to automatically analyze large amounts of these complex image data in order to draw biological conclusions from them and to study cellular and tissular phenotypes at a large scale. One of the bottlenecks for such approaches is the automatic segmentation of cell nuclei from this type of image data. Here, we present a fully automated workflow to segment nuclei from histopathology image data by using deep neural networks trained from a set of manually annotated images and by processing the posterior probability maps in order to split jointly segmented nuclei. Further, we provide the image data set that has been generated for this study as a benchmark set to the scientific community.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"45 1","pages":"933-936"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77217803","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 : 2017-04-01DOI: 10.1109/ISBI.2017.7950630
Haozhe Jia, Yong Xia, Weidong (Tom) Cai, M. Fulham, D. Feng
The automated segmentation of the prostate gland from MR images is increasingly used for clinical diagnosis. Since deep learning demonstrates superior performance in computer vision applications, we propose a coarse-to-fine segmentation strategy using ensemble deep convolutional neural networks (DCNNs) to address prostate segmentation in MR images. First, we use registration-based coarse segmentation on pre-processed prostate MR images to define the potential boundary region. We then train four DCNNs as voxel-based classifiers and classify the voxel in the potential region is a prostate voxel when at least three DCNNs made that decision. Finally, we use boundary refinement to eliminate the outliers and smooth the boundary. We evaluated our approach on the MICCAI PROMIS12 challenge dataset and our experimental results verify the effectiveness of the proposed algorithms.
{"title":"Prostate segmentation in MR images using ensemble deep convolutional neural networks","authors":"Haozhe Jia, Yong Xia, Weidong (Tom) Cai, M. Fulham, D. Feng","doi":"10.1109/ISBI.2017.7950630","DOIUrl":"https://doi.org/10.1109/ISBI.2017.7950630","url":null,"abstract":"The automated segmentation of the prostate gland from MR images is increasingly used for clinical diagnosis. Since deep learning demonstrates superior performance in computer vision applications, we propose a coarse-to-fine segmentation strategy using ensemble deep convolutional neural networks (DCNNs) to address prostate segmentation in MR images. First, we use registration-based coarse segmentation on pre-processed prostate MR images to define the potential boundary region. We then train four DCNNs as voxel-based classifiers and classify the voxel in the potential region is a prostate voxel when at least three DCNNs made that decision. Finally, we use boundary refinement to eliminate the outliers and smooth the boundary. We evaluated our approach on the MICCAI PROMIS12 challenge dataset and our experimental results verify the effectiveness of the proposed algorithms.","PeriodicalId":6547,"journal":{"name":"2017 IEEE 14th International Symposium on Biomedical Imaging (ISBI 2017)","volume":"81 1","pages":"762-765"},"PeriodicalIF":0.0,"publicationDate":"2017-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76244862","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：