Pub Date : 2014-07-31DOI: 10.1109/ISBI.2014.6868015
K. Ghane
Advances in medical imaging have resulted in rapid growth in the amount and also the size of medical images that are stored in the medical imaging information systems. As a result of such rapid growth in storage requirements, public and private storage clouds have special appeal to medical imaging storage applications. Another factor that makes cloud storage attractive to medical imaging is that the time span of data retention has been increasing and in many cases it is now for the life of patient and many years beyond. In addition, Cloud solutions facilitate accessing data from any device and anywhere. Wide variety of cloud based solutions that are currently available cannot be effectively applied to medical imaging applications because of inefficient support for specific characteristics of the medical imaging data access. For many practical reasons including access speed requirements, off premise public/private clouds cannot be an optimum solution for medical imaging and hybrid cloud solutions are preferred and primarily used. However the existing hybrid cloud solutions primarily use public cloud as the backup for on-premise storage or as an archive for old/inactive records or as a copy for Healthcare Information Exchange with other healthcare entities. This paper provides a solution for optimizing total cost of ownership associated with volume, growth and scalability of medical imaging storage systems. It models medical imaging storage as a three level cache. It introduces a cache algorithm and policy that is devised based on the characteristics of medical imaging applications such as the inherent association of cache entries through patient attribute and the recognizable data usage patterns such as cancer treatment plans. Healthcare Information Exchange is an easy extension to this solution where images in public clouds can be shared and exposed to the other healthcare providers or entities of interest.
{"title":"Associative algorithm and policy with advance loading and self-tuning for medical imaging storage in hybrid cloud","authors":"K. Ghane","doi":"10.1109/ISBI.2014.6868015","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6868015","url":null,"abstract":"Advances in medical imaging have resulted in rapid growth in the amount and also the size of medical images that are stored in the medical imaging information systems. As a result of such rapid growth in storage requirements, public and private storage clouds have special appeal to medical imaging storage applications. Another factor that makes cloud storage attractive to medical imaging is that the time span of data retention has been increasing and in many cases it is now for the life of patient and many years beyond. In addition, Cloud solutions facilitate accessing data from any device and anywhere. Wide variety of cloud based solutions that are currently available cannot be effectively applied to medical imaging applications because of inefficient support for specific characteristics of the medical imaging data access. For many practical reasons including access speed requirements, off premise public/private clouds cannot be an optimum solution for medical imaging and hybrid cloud solutions are preferred and primarily used. However the existing hybrid cloud solutions primarily use public cloud as the backup for on-premise storage or as an archive for old/inactive records or as a copy for Healthcare Information Exchange with other healthcare entities. This paper provides a solution for optimizing total cost of ownership associated with volume, growth and scalability of medical imaging storage systems. It models medical imaging storage as a three level cache. It introduces a cache algorithm and policy that is devised based on the characteristics of medical imaging applications such as the inherent association of cache entries through patient attribute and the recognizable data usage patterns such as cancer treatment plans. Healthcare Information Exchange is an easy extension to this solution where images in public clouds can be shared and exposed to the other healthcare providers or entities of interest.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"26 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":"123469970","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.2014.6867997
Jia Qu, H. Nosato, H. Sakanashi, E. Takahashi, Kensuke Terai, N. Hiruta
Aiming to lessen the burdens of the pathologist with efficient diagnosis assistance, this paper proposes a cancer detection method for pathological images utilizing color features based on color-index local auto-correlations (CILAC), applied to color-indexed images to utilize co-occurrence information about indexed pixels. Moreover, a method for the automatic optimization of feature extraction is also proposed. Based on a database including both benign and cancerous pathological images, experimental results show enhanced performance compared to prior research, which demonstrate the effectiveness of the proposed cancer detection method.
{"title":"Computational cancer detection of pathological images based on an optimization method for color-index local auto-correlation feature extraction","authors":"Jia Qu, H. Nosato, H. Sakanashi, E. Takahashi, Kensuke Terai, N. Hiruta","doi":"10.1109/ISBI.2014.6867997","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867997","url":null,"abstract":"Aiming to lessen the burdens of the pathologist with efficient diagnosis assistance, this paper proposes a cancer detection method for pathological images utilizing color features based on color-index local auto-correlations (CILAC), applied to color-indexed images to utilize co-occurrence information about indexed pixels. Moreover, a method for the automatic optimization of feature extraction is also proposed. Based on a database including both benign and cancerous pathological images, experimental results show enhanced performance compared to prior research, which demonstrate the effectiveness of the proposed cancer detection method.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"10 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":"123628079","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.2014.6868002
Jaza Gul-Mohammed, T. Boudier
Automated 3D image segmentation and classification of biological structures is a critical task in modern cellular and developmental biology. Furthermore new emerging acquisition systems, like light-sheet microscopy, permit to observe whole embryo or developing cells in 4D, allowing us to better understand the spatial organization of tissues and cells. Numerous algorithms have been developed for 3D segmentation of cell nuclei, however when the cells are packed, classical methods usually fail. We present a new alternative for segmentation and classification by merging them into one classified region-growing algorithm. The combination of region growing and machine learning enabled us to both segment touching nuclei, and also classify them, even if their shape is changing in a dynamic context.
{"title":"Classified region growing for 3D segmentation of packed nuclei","authors":"Jaza Gul-Mohammed, T. Boudier","doi":"10.1109/ISBI.2014.6868002","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6868002","url":null,"abstract":"Automated 3D image segmentation and classification of biological structures is a critical task in modern cellular and developmental biology. Furthermore new emerging acquisition systems, like light-sheet microscopy, permit to observe whole embryo or developing cells in 4D, allowing us to better understand the spatial organization of tissues and cells. Numerous algorithms have been developed for 3D segmentation of cell nuclei, however when the cells are packed, classical methods usually fail. We present a new alternative for segmentation and classification by merging them into one classified region-growing algorithm. The combination of region growing and machine learning enabled us to both segment touching nuclei, and also classify them, even if their shape is changing in a dynamic context.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"186 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":"122053050","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.2014.6867896
Guanyu Yang, Yang Chen, L. Tang, H. Shu, C. Toumoulin
Cardiac CT angiography (CCTA) is widely used in the diagnosis of coronary heart disease. It can provide 4D (3D + t) sequence with high spatial and temporal resolution. Segmentation of left ventricle (LV) in 4D CCTA sequence can provide useful information for clinical practice. In this paper, we present an automatic method for LV segmentation in 4D CCTA sequence in this paper. This method mainly relies on an accurate multi-atlas registration method. Thus, we first improve the multi-atlas registration method presented by Kirişli et al. by adding an extra registration step with an estimated heart mask. Then, we use a two-stage framework based on multi-atlas registration to segment the LV in the 4D sequence. Quantitative evaluation results show that our proposed multi-atlas registration method outperforms the Kirişli's method. Finally, experimental results using two 4D CCTA sequences indicate that our method can segment LV accurately.
{"title":"Automatic left ventricle segmentation based on multiatlas registration in 4D CT images","authors":"Guanyu Yang, Yang Chen, L. Tang, H. Shu, C. Toumoulin","doi":"10.1109/ISBI.2014.6867896","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867896","url":null,"abstract":"Cardiac CT angiography (CCTA) is widely used in the diagnosis of coronary heart disease. It can provide 4D (3D + t) sequence with high spatial and temporal resolution. Segmentation of left ventricle (LV) in 4D CCTA sequence can provide useful information for clinical practice. In this paper, we present an automatic method for LV segmentation in 4D CCTA sequence in this paper. This method mainly relies on an accurate multi-atlas registration method. Thus, we first improve the multi-atlas registration method presented by Kirişli et al. by adding an extra registration step with an estimated heart mask. Then, we use a two-stage framework based on multi-atlas registration to segment the LV in the 4D sequence. Quantitative evaluation results show that our proposed multi-atlas registration method outperforms the Kirişli's method. Finally, experimental results using two 4D CCTA sequences indicate that our method can segment LV accurately.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"102 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":"122516901","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.2014.6867993
V. Uhlmann, R. Delgado-Gonzalo, M. Unser
We propose a novel active contour for the analysis of filament-like structures and boundaries - features that traditional snakes based on closed curves have difficulties to delineate. Our method relies on a parametric representation of an open curve involving Hermite-spline basis functions. This allows us to impose constraints both on the contour and on its derivatives. The proposed parameterization enables tangential controls and facilitates the design of an energy term that considers oriented features. In this way, our technique can be used to detect edges as well as ridges. The use of the Hermite-spline basis is well suited to a semi-interactive implementation. We developed an ImageJ plugin, and present experimental results on real biological data.
{"title":"Snakes with tangent-based control and energies for bioimage analysis","authors":"V. Uhlmann, R. Delgado-Gonzalo, M. Unser","doi":"10.1109/ISBI.2014.6867993","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867993","url":null,"abstract":"We propose a novel active contour for the analysis of filament-like structures and boundaries - features that traditional snakes based on closed curves have difficulties to delineate. Our method relies on a parametric representation of an open curve involving Hermite-spline basis functions. This allows us to impose constraints both on the contour and on its derivatives. The proposed parameterization enables tangential controls and facilitates the design of an energy term that considers oriented features. In this way, our technique can be used to detect edges as well as ridges. The use of the Hermite-spline basis is well suited to a semi-interactive implementation. We developed an ImageJ plugin, and present experimental results on real biological data.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"358 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":"122811385","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.2014.6867906
T. Pécot, J. Boulanger, C. Kervrann, P. Bouthemy, J. Salamero
Automatic analysis of the dynamic content in fluorescence video-microscopy is crucial for understanding molecular mechanisms involved in cell functions. In this paper, we propose an original approach for analyzing particle trafficking in these sequences. Instead of individually tracking every particle, we estimate the particle flows between predefined regions. This approach allows us to process image sequences with a high number of particles and a low frame rate. We investigate several ways to estimate the particle flow at the cellular level and evaluate their performance in synthetic and real image sequences.
{"title":"Estimation of the flow of particles within a partition of the image domain in fluorescence video-microscopy","authors":"T. Pécot, J. Boulanger, C. Kervrann, P. Bouthemy, J. Salamero","doi":"10.1109/ISBI.2014.6867906","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867906","url":null,"abstract":"Automatic analysis of the dynamic content in fluorescence video-microscopy is crucial for understanding molecular mechanisms involved in cell functions. In this paper, we propose an original approach for analyzing particle trafficking in these sequences. Instead of individually tracking every particle, we estimate the particle flows between predefined regions. This approach allows us to process image sequences with a high number of particles and a low frame rate. We investigate several ways to estimate the particle flow at the cellular level and evaluate their performance in synthetic and real image sequences.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"110 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":"125111825","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.2014.6867895
Qian Zhao, Nabile M. Safdar, Glenna Yu, Emmarie Myers, A. Koroulakis, C. Duan, A. Sandler, M. Linguraru
Pectus excavatum (PE) is the most common major congenital deformity that involves the lower sternum and cartilages. Noncontrast CT is useful to assess the deformity of the bones and guide minimally invasive surgery. However, it has very poor visibility of cartilages even for the experienced clinicians who need to assess the 3D geometry of cartilages. In this study, we propose a novel method to estimate cartilages in noncontrast CT scans. The ribs and sternum are first segmented using region growing. The skeleton of the ribs is extracted and modeled by cosine series expansion. Then a statistical shape model is built with the cosine coefficients to estimate the cartilages as curves that connect the ribs and sternum. The results are refined by the cartilage surface that is approximated by contracting the skin surface to the bones. Leave-one-out validation was performed on 12 CT scans from healthy and PE subjects. The average distance between the estimated cartilages and ground truth is 1.53 mm. The promising results indicate that our method could estimate the costal cartilages in noncontrast CT effectively and assist to develop an image-based surgical planning system for PE correction.
{"title":"Cartilage estimation in noncontrast thoracic CT","authors":"Qian Zhao, Nabile M. Safdar, Glenna Yu, Emmarie Myers, A. Koroulakis, C. Duan, A. Sandler, M. Linguraru","doi":"10.1109/ISBI.2014.6867895","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867895","url":null,"abstract":"Pectus excavatum (PE) is the most common major congenital deformity that involves the lower sternum and cartilages. Noncontrast CT is useful to assess the deformity of the bones and guide minimally invasive surgery. However, it has very poor visibility of cartilages even for the experienced clinicians who need to assess the 3D geometry of cartilages. In this study, we propose a novel method to estimate cartilages in noncontrast CT scans. The ribs and sternum are first segmented using region growing. The skeleton of the ribs is extracted and modeled by cosine series expansion. Then a statistical shape model is built with the cosine coefficients to estimate the cartilages as curves that connect the ribs and sternum. The results are refined by the cartilage surface that is approximated by contracting the skin surface to the bones. Leave-one-out validation was performed on 12 CT scans from healthy and PE subjects. The average distance between the estimated cartilages and ground truth is 1.53 mm. The promising results indicate that our method could estimate the costal cartilages in noncontrast CT effectively and assist to develop an image-based surgical planning system for PE correction.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"4 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":"126164927","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.2014.6867811
F. Tek, Thorben Kröger, S. Mikula, F. Hamprecht
Volumetric electron microscopy techniques, such as serial block-face electron microscopy (SBEM), generate massive amounts of image data that are used for reconstructing neural circuits. Typically, this requires time-intensive manual annotation of cells and their connections. To facilitate this analysis, we study the problem of automated detection of cell nuclei in a new SBEM dataset that contains cerebral cortex, white matter, and striatum from an adult mouse brain. The dataset was manually annotated to identify the locations of all 3309 cell nuclei in the volume. We make both dataset and annotations available here. Using a hybrid approach that combines interactive learning, morphological processing, and object level feature classification, we demonstrate automated detection of cell nuclei at 92.4% recall and 95.1% precision. These algorithms are not RAM-limited and can scale to arbitrarily large datasets.
{"title":"Automated cell nucleus detection for large-volume electron microscopy of neural tissue","authors":"F. Tek, Thorben Kröger, S. Mikula, F. Hamprecht","doi":"10.1109/ISBI.2014.6867811","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867811","url":null,"abstract":"Volumetric electron microscopy techniques, such as serial block-face electron microscopy (SBEM), generate massive amounts of image data that are used for reconstructing neural circuits. Typically, this requires time-intensive manual annotation of cells and their connections. To facilitate this analysis, we study the problem of automated detection of cell nuclei in a new SBEM dataset that contains cerebral cortex, white matter, and striatum from an adult mouse brain. The dataset was manually annotated to identify the locations of all 3309 cell nuclei in the volume. We make both dataset and annotations available here. Using a hybrid approach that combines interactive learning, morphological processing, and object level feature classification, we demonstrate automated detection of cell nuclei at 92.4% recall and 95.1% precision. These algorithms are not RAM-limited and can scale to arbitrarily large datasets.","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":"129425341","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.2014.6867988
A. Akselrod-Ballin, R. Avni, M. Neeman
In-utero 3D MRI analysis of embryos in mice is difficult due to the periodic and non-periodic motion, small tissues and multiple embryos involved. This paper presents an automated algorithm for serial alignment of fetal tissue in MRI of pregnant mice. The algorithm extends our former algorithm to allow follow up across time between 3D MR sequences in a difficult novel small animal application. The algorithm is based on features combining intensity and geometric information and the registration energy function is minimized by alternating optimization with regard to the feature correspondence and transformation model. Experimental validation on a set of MRI acquisition with fetal livers and placentas demonstrate the high accuracy and promise of the approach. The results confirm that measures of development can be automatically derived from multifetal pregnancy in mice.
{"title":"Sequence alignment of in-utero fetal tissue MRI in mice","authors":"A. Akselrod-Ballin, R. Avni, M. Neeman","doi":"10.1109/ISBI.2014.6867988","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867988","url":null,"abstract":"In-utero 3D MRI analysis of embryos in mice is difficult due to the periodic and non-periodic motion, small tissues and multiple embryos involved. This paper presents an automated algorithm for serial alignment of fetal tissue in MRI of pregnant mice. The algorithm extends our former algorithm to allow follow up across time between 3D MR sequences in a difficult novel small animal application. The algorithm is based on features combining intensity and geometric information and the registration energy function is minimized by alternating optimization with regard to the feature correspondence and transformation model. Experimental validation on a set of MRI acquisition with fetal livers and placentas demonstrate the high accuracy and promise of the approach. The results confirm that measures of development can be automatically derived from multifetal pregnancy in mice.","PeriodicalId":440405,"journal":{"name":"2014 IEEE 11th International Symposium on Biomedical Imaging (ISBI)","volume":"5 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":"129443162","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.2014.6867813
M. Maddah, K. Loewke
The increased use of stem cells to study disease states in vitro has created a need for tools that provide automated, non-invasive, and objective characterization of cell cultures. In this work, we address this need by developing a novel framework for stem cell assessment using time-lapse phase-contrast microscopy and automated texture-based analysis of images. We capture and quantify morphological changes during stem cell colony growth by segmenting each image of the time-lapse sequence into five distinct classes of cells. We apply our automated classification to enable non-invasive estimation of cell doubling time, and demonstrate applications of the presented framework for quantitative assessment of cell culture conditions.
{"title":"Dynamic morphology-based characterization of stem cells enabled by texture-based pattern recognition from phase-contrast images","authors":"M. Maddah, K. Loewke","doi":"10.1109/ISBI.2014.6867813","DOIUrl":"https://doi.org/10.1109/ISBI.2014.6867813","url":null,"abstract":"The increased use of stem cells to study disease states in vitro has created a need for tools that provide automated, non-invasive, and objective characterization of cell cultures. In this work, we address this need by developing a novel framework for stem cell assessment using time-lapse phase-contrast microscopy and automated texture-based analysis of images. We capture and quantify morphological changes during stem cell colony growth by segmenting each image of the time-lapse sequence into five distinct classes of cells. We apply our automated classification to enable non-invasive estimation of cell doubling time, and demonstrate applications of the presented framework for quantitative assessment of cell culture conditions.","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":"129452317","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：