Moradi, M; Mousavi, P; Abolmaesumi, P; Isotalo, P; Siemens, R; Sauerbrei, E
A New Approach for Detection of Prostate Cancer based on Fractal Analysis of RF Ultrasound Echo Signals Journal Article
In: 2006.
@article{431,
title = {A New Approach for Detection of Prostate Cancer based on Fractal Analysis of RF Ultrasound Echo Signals},
author = {M Moradi and P Mousavi and P Abolmaesumi and P Isotalo and R Siemens and E Sauerbrei},
year = {2006},
date = {2006-01-01},
publisher = {IRIS/Precarn ISConference},
address = {Victoria, BC},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Pichora, D R; Abolmaesumi, P; Tyryshkin, K; Beek, M; Chen, T K; Mousavi, P
A Novel Interface for Ultrasound-guided Shoulder Arthroscopy Journal Article
In: 2006.
@article{432,
title = {A Novel Interface for Ultrasound-guided Shoulder Arthroscopy},
author = {D R Pichora and P Abolmaesumi and K Tyryshkin and M Beek and T K Chen and P Mousavi},
year = {2006},
date = {2006-01-01},
publisher = {Transactions of Orthopaedic Research Society, pp. 1974},
address = {Chicago, IL},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Tyryshkin, K; Mousavi, P; Abolmaesumi, P; Pichora, D
A Novel Ultrasound-guided Computer System for Arthroscopic Surgery of the Shoulder Joint Journal Article
In: 2006.
@article{427,
title = {A Novel Ultrasound-guided Computer System for Arthroscopic Surgery of the Shoulder Joint},
author = {K Tyryshkin and P Mousavi and P Abolmaesumi and D Pichora},
year = {2006},
date = {2006-01-01},
publisher = {IRIS Workshop on Medical Technologies, Canadian Surgical Technologies and Advanced Robotics},
address = {London, ON},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Moradi, M; Mousavi, P; Abolmaesumi, P
Pathological Distinction of Prostate Cancer Tumors based on DNA Microarray Data Journal Article
In: 2006.
@article{428,
title = {Pathological Distinction of Prostate Cancer Tumors based on DNA Microarray Data},
author = {M Moradi and P Mousavi and P Abolmaesumi},
year = {2006},
date = {2006-01-01},
publisher = {proceedings of 1st Canadian Student Conference on Biomedical Computing},
address = {Kingston, ON},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Tyryshkin, K; Mousavi, P; Abolmaesumi, P; Pichora, D
Shoulder Arthroscopy using Ultrasound Guidance Journal Article
In: 2006.
@article{430,
title = {Shoulder Arthroscopy using Ultrasound Guidance},
author = {K Tyryshkin and P Mousavi and P Abolmaesumi and D Pichora},
year = {2006},
date = {2006-01-01},
publisher = {5th Annual Imaging Ontario Symposium},
address = {Toronto, Canada},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Knott, Simon; Mousavi, Parvin; Baranzini, Sergio
IEEE, 2006, ISBN: 1-4244-0623-4.
@proceedings{90,
title = {A Systematic Approach for Identifying Regulatory Interactions in Large Temporal Gene Expression Datasets from Peripheral Blood},
author = {Simon Knott and Parvin Mousavi and Sergio Baranzini},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=4133197},
doi = {10.1109/CIBCB.2006.330961},
isbn = {1-4244-0623-4},
year = {2006},
date = {2006-01-01},
journal = {CIBCB},
publisher = {IEEE},
abstract = {High throughput genomic techniques produce datasets involving thousands of gene expression profiles. In order to infer biologically meaningful regulatory interactions, a dimensionality reduction must take place to identify genes or groups of genes that are important to the biological system being analyzed. Here we provide a systematic approach to remove dispersible genes from consideration based on their gene expression profiles, and to identify a smaller set of coordinately expressed genes, or metagenes that are biologically related to one and other based on previous biological knowledge. We then apply neural network based reverse engineering techniques to demonstrate that through these dimensionality reduction techniques novel genetic interactions can be identified},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
High throughput genomic techniques produce datasets involving thousands of gene expression profiles. In order to infer biologically meaningful regulatory interactions, a dimensionality reduction must take place to identify genes or groups of genes that are important to the biological system being analyzed. Here we provide a systematic approach to remove dispersible genes from consideration based on their gene expression profiles, and to identify a smaller set of coordinately expressed genes, or metagenes that are biologically related to one and other based on previous biological knowledge. We then apply neural network based reverse engineering techniques to demonstrate that through these dimensionality reduction techniques novel genetic interactions can be identified
Knott, S; Mostafavi, S; Mousavi, P; Glasgow, J
Genetic network inference via gene set stochastic sampling and sensitivity analysis Proceedings
2005.
@proceedings{206,
title = {Genetic network inference via gene set stochastic sampling and sensitivity analysis},
author = {S Knott and S Mostafavi and P Mousavi and J Glasgow},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=1507116},
doi = {10.1109/CCA.2005.1507116},
year = {2005},
date = {2005-08-01},
journal = {Control Applications, 2005. CCA 2005. Proceedings of 2005 IEEE Conference on},
abstract = {In this paper, two approaches utilizing neural networks, intended to infer genetic regulatory networks from temporal gene expression measurements, are examined. These approaches aimed to find a minimal set of genes that were able to accurately predict the expression levels of a given gene, thus modeling the interactions in the underlying genetic regulatory networks. Two neural network architectures were employed in each approach to determine the robustness of the modeling procedure with respect to the network architecture. Two testing procedures were also devised to evaluate the trained neural networkstextquoteright performance and generalizability. The resulting neural networks predicted, with high accuracy, the target gene expression level at future times given the predicted minimal gene-set expression levels at previous time points},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
In this paper, two approaches utilizing neural networks, intended to infer genetic regulatory networks from temporal gene expression measurements, are examined. These approaches aimed to find a minimal set of genes that were able to accurately predict the expression levels of a given gene, thus modeling the interactions in the underlying genetic regulatory networks. Two neural network architectures were employed in each approach to determine the robustness of the modeling procedure with respect to the network architecture. Two testing procedures were also devised to evaluate the trained neural networkstextquoteright performance and generalizability. The resulting neural networks predicted, with high accuracy, the target gene expression level at future times given the predicted minimal gene-set expression levels at previous time points
Somogyi, R; McMichael, J; Baranzini, S E; Mousavi, P; Greller, L D
Advanced Data Mining and Predictive Modeling at the Core of Personalized Medicine Book Chapter
In: Multidisciplinary Approaches to Theory in Medicine, Elsevier, 2005.
@inbook{398,
title = {Advanced Data Mining and Predictive Modeling at the Core of Personalized Medicine},
author = {R Somogyi and J McMichael and S E Baranzini and P Mousavi and L D Greller},
year = {2005},
date = {2005-01-01},
booktitle = {Multidisciplinary Approaches to Theory in Medicine},
publisher = {Elsevier},
organization = {Elsevier},
keywords = {},
pubstate = {published},
tppubtype = {inbook}
}
Cho, C R; Mousavi, P; Baranzini, S; Oksenberg, J; Greller, L D; Somogyi, R
Advanced Data Mining and Predictive Modeling Increases the Value of Molecular Profiling Data in Drug Discovery Journal Article
In: 2005.
@article{434,
title = {Advanced Data Mining and Predictive Modeling Increases the Value of Molecular Profiling Data in Drug Discovery},
author = {C R Cho and P Mousavi and S Baranzini and J Oksenberg and L D Greller and R Somogyi},
year = {2005},
date = {2005-01-01},
publisher = {World Congress on Drug Discovery Technology},
address = {Boston, MA},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Chan, Cheryl; Mousavi, Parvin
Discovery of gene expression patterns across multiple cancer types Conference
Bioinformatics and Bioengineering, 2005. BIBE 2005. Fifth IEEE Symposium on, IEEE IEEE, 2005.
@conference{385,
title = {Discovery of gene expression patterns across multiple cancer types},
author = {Cheryl Chan and Parvin Mousavi},
year = {2005},
date = {2005-01-01},
booktitle = {Bioinformatics and Bioengineering, 2005. BIBE 2005. Fifth IEEE Symposium on},
publisher = {IEEE},
organization = {IEEE},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Baranzini, Sergio E; Mousavi, Parvin; Rio, Jordi; Caillier, Stacy J; Stillman, Althea; Villoslada, Pablo; Wyatt, Matthew M; Comabella, Manuel; Greller, Larry D; Somogyi, Roland; Montalban, Xavier; Oksenberg, Jorge R
Transcription-based prediction of response to IFNbeta using supervised computational methods. Journal Article
In: PLoS Biol, vol. 3, pp. e2, 2005, ISSN: 1545-7885.
@article{83d,
title = {Transcription-based prediction of response to IFNbeta using supervised computational methods.},
author = {Sergio E Baranzini and Parvin Mousavi and Jordi Rio and Stacy J Caillier and Althea Stillman and Pablo Villoslada and Matthew M Wyatt and Manuel Comabella and Larry D Greller and Roland Somogyi and Xavier Montalban and Jorge R Oksenberg},
doi = {10.1371/journal.pbio.0030002},
issn = {1545-7885},
year = {2005},
date = {2005-01-01},
journal = {PLoS Biol},
volume = {3},
pages = {e2},
abstract = {<p>Changes in cellular functions in response to drug therapy are mediated by specific transcriptional profiles resulting from the induction or repression in the activity of a number of genes, thereby modifying the preexisting gene activity pattern of the drug-targeted cell(s). Recombinant human interferon beta (rIFNbeta) is routinely used to control exacerbations in multiple sclerosis patients with only partial success, mainly because of adverse effects and a relatively large proportion of nonresponders. We applied advanced data-mining and predictive modeling tools to a longitudinal 70-gene expression dataset generated by kinetic reverse-transcription PCR from 52 multiple sclerosis patients treated with rIFNbeta to discover higher-order predictive patterns associated with treatment outcome and to define the molecular footprint that rIFNbeta engraves on peripheral blood mononuclear cells. We identified nine sets of gene triplets whose expression, when tested before the initiation of therapy, can predict the response to interferon beta with up to 86% accuracy. In addition, time-series analysis revealed potential key players involved in a good or poor response to interferon beta. Statistical testing of a random outcome class and tolerance to noise was carried out to establish the robustness of the predictive models. Large-scale kinetic reverse-transcription PCR, coupled with advanced data-mining efforts, can effectively reveal preexisting and drug-induced gene expression signatures associated with therapeutic effects.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>Changes in cellular functions in response to drug therapy are mediated by specific transcriptional profiles resulting from the induction or repression in the activity of a number of genes, thereby modifying the preexisting gene activity pattern of the drug-targeted cell(s). Recombinant human interferon beta (rIFNbeta) is routinely used to control exacerbations in multiple sclerosis patients with only partial success, mainly because of adverse effects and a relatively large proportion of nonresponders. We applied advanced data-mining and predictive modeling tools to a longitudinal 70-gene expression dataset generated by kinetic reverse-transcription PCR from 52 multiple sclerosis patients treated with rIFNbeta to discover higher-order predictive patterns associated with treatment outcome and to define the molecular footprint that rIFNbeta engraves on peripheral blood mononuclear cells. We identified nine sets of gene triplets whose expression, when tested before the initiation of therapy, can predict the response to interferon beta with up to 86% accuracy. In addition, time-series analysis revealed potential key players involved in a good or poor response to interferon beta. Statistical testing of a random outcome class and tolerance to noise was carried out to establish the robustness of the predictive models. Large-scale kinetic reverse-transcription PCR, coupled with advanced data-mining efforts, can effectively reveal preexisting and drug-induced gene expression signatures associated with therapeutic effects.</p>
Somogyi, R; Mousavi, P; Baranzini, S; Greller, L D
Data Mining and Predictive Modeling for Personalized Medicine: Practical Examples from Analysis of Image and Molecular Profiling Data Journal Article
In: 2004.
@article{435,
title = {Data Mining and Predictive Modeling for Personalized Medicine: Practical Examples from Analysis of Image and Molecular Profiling Data},
author = {R Somogyi and P Mousavi and S Baranzini and L D Greller},
year = {2004},
date = {2004-01-01},
publisher = {proceedings of National Institutes of Health (NIH) BECON/BISTIC 2004 Symposium on Biomedical Informatics for Clinical Decision Support: A Vision for the 21st Century,},
address = {Bethesda , MD},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Chan, C; Kuo, T; Mousavi, P
Discovery of Gene Expression Patterns Across Multiple Cancer Types Journal Article
In: 2004.
@article{439,
title = {Discovery of Gene Expression Patterns Across Multiple Cancer Types},
author = {C Chan and T Kuo and P Mousavi},
year = {2004},
date = {2004-01-01},
publisher = {IRIS/Precarn ISConference},
address = {Ottawa, ON},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Mousavi, P; Ward, Rabab Kreidieh; Fels, Sidney S; Sameti, Mohammad; Lansdorp, Peter M
Feature analysis and centromere segmentation of human chromosome images using an iterative fuzzy algorithm. Journal Article
In: IEEE Trans Biomed Eng, vol. 49, pp. 363-71, 2002, ISSN: 0018-9294.
@article{32b,
title = {Feature analysis and centromere segmentation of human chromosome images using an iterative fuzzy algorithm.},
author = {P Mousavi and Rabab Kreidieh Ward and Sidney S Fels and Mohammad Sameti and Peter M Lansdorp},
doi = {10.1109/10.991164},
issn = {0018-9294},
year = {2002},
date = {2002-04-01},
journal = {IEEE Trans Biomed Eng},
volume = {49},
pages = {363-71},
abstract = {<p>Classification of homologous chromosomes is essential to advanced studies of cancer genetics. Centromere intensities are believed to be an important differentiating feature between homologs. Therefore, segmentation of centromeres is a major step toward the realization of homolog classification. This paper describes an iterative fuzzy algorithm which successfully segments centromeres from images of human chromosomes prepared using fluorescence in-situ hybridization technique. The algorithm is based on assigning a fuzzy membership value to each pixel in the centromere image. An iterative algorithm then updates and minimizes a defined error function. Chromosome 22, a highly heteromorphic chromosome, is used to verify the centromere segmentation method. Homologs of this chromosome are classified based on their segmented centromere intensities as well as their morphological differences. The classification results of these two methods agree completely and are used to validate our developed algorithm.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>Classification of homologous chromosomes is essential to advanced studies of cancer genetics. Centromere intensities are believed to be an important differentiating feature between homologs. Therefore, segmentation of centromeres is a major step toward the realization of homolog classification. This paper describes an iterative fuzzy algorithm which successfully segments centromeres from images of human chromosomes prepared using fluorescence in-situ hybridization technique. The algorithm is based on assigning a fuzzy membership value to each pixel in the centromere image. An iterative algorithm then updates and minimizes a defined error function. Chromosome 22, a highly heteromorphic chromosome, is used to verify the centromere segmentation method. Homologs of this chromosome are classified based on their segmented centromere intensities as well as their morphological differences. The classification results of these two methods agree completely and are used to validate our developed algorithm.</p>
Mousavi, Parvin; Fels, Sidney; Ward, Rabab Kreidieh; Lansdorp, Peter M
Classification of homologous human chromosomes using mutual information maximization Proceedings
2001, ISBN: 0-7803-6725-1.
@proceedings{84c,
title = {Classification of homologous human chromosomes using mutual information maximization},
author = {Parvin Mousavi and Sidney Fels and Rabab Kreidieh Ward and Peter M Lansdorp},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?arnumber=00958626},
isbn = {0-7803-6725-1},
year = {2001},
date = {2001-01-01},
journal = {ICIP (2)},
abstract = {Multi-feature analysis of human chromosome images is a major step towards classification of homologous chromosomes. An automatic quantitative classification method is proposed for homolog differentiation using multiple features. This method is based on mutual information maximization applied to an unsupervised neural network architecture. The neural network consists of separate modules which are trained to classify homologs using independent features. Mutual information is then maximized between the outputs of the modules forcing them to produce the same classification results, for a given chromosome. The proposed method was successfully applied to classify homologs of chromosome 16 with 100% accuracy},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Multi-feature analysis of human chromosome images is a major step towards classification of homologous chromosomes. An automatic quantitative classification method is proposed for homolog differentiation using multiple features. This method is based on mutual information maximization applied to an unsupervised neural network architecture. The neural network consists of separate modules which are trained to classify homologs using independent features. Mutual information is then maximized between the outputs of the modules forcing them to produce the same classification results, for a given chromosome. The proposed method was successfully applied to classify homologs of chromosome 16 with 100% accuracy
Mousavi, P; Ward, R K; Sameti, M; Lansdorp, P M; Fels, S S
Homologue classification of human chromosome images using an iterative centromere segmentation algorithm Proceedings
2000.
@proceedings{86,
title = {Homologue classification of human chromosome images using an iterative centromere segmentation algorithm},
author = {P Mousavi and R K Ward and M Sameti and P M Lansdorp and S S Fels},
url = {http://dx.doi.org/10.1109/IEMBS.2000.900522},
doi = {10.1109/IEMBS.2000.900522},
year = {2000},
date = {2000-01-01},
journal = {Engineering in Medicine and Biology Society, 2000. Proceedings of the 22nd Annual International Conference of the IEEE},
abstract = {Segmentation of centromeres is a major step towards classification of homologous chromosomes, which in turn, is essential to advanced studies of cancer genetics. This paper describes an iterative fuzzy algorithm, which successfully segments the centromeres of human chromosome images. The algorithm is based on assigning a fuzzy membership value to each pixel and iteratively updating an error function, Chromosome 22 is then used to verify the centromere segmentation method},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Segmentation of centromeres is a major step towards classification of homologous chromosomes, which in turn, is essential to advanced studies of cancer genetics. This paper describes an iterative fuzzy algorithm, which successfully segments the centromeres of human chromosome images. The algorithm is based on assigning a fuzzy membership value to each pixel and iteratively updating an error function, Chromosome 22 is then used to verify the centromere segmentation method
Mousavi, Parvin; Ward, Rabab Kreidieh; Lansdorp, Peter M; Fels, Sidney
2000.
@proceedings{85c,
title = {Multi-Feature Analysis and Classification of Human Chromosome Images Using Centromere Segmentation Algorithms},
author = {Parvin Mousavi and Rabab Kreidieh Ward and Peter M Lansdorp and Sidney Fels},
url = {http://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=900917},
year = {2000},
date = {2000-01-01},
journal = {ICIP},
abstract = {Classification of homologous chromosomes is essential to advanced studies of cancer genetics. Centromere intensities are believed to be an important differentiating feature between homologs. Therefore, segmentation of centromeres is a major step toward the realization of homolog classification. This paper describes an iterative fuzzy algorithm which successfully segments centromeres from images of human chromosomes prepared using fluorescence in-situ hybridization technique. The algorithm is based on assigning a fuzzy membership value to each pixel in the centromere image. An iterative algorithm then updates and minimizes a defined error function. Chromosome 22, a highly heteromorphic chromosome, is used to verify the centromere segmentation method. Homologs of this chromosome are classified based on their segmented centromere intensities as well as their morphological differences. The classification results of these two methods agree completely and are used to validate our developed algorithm.},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Classification of homologous chromosomes is essential to advanced studies of cancer genetics. Centromere intensities are believed to be an important differentiating feature between homologs. Therefore, segmentation of centromeres is a major step toward the realization of homolog classification. This paper describes an iterative fuzzy algorithm which successfully segments centromeres from images of human chromosomes prepared using fluorescence in-situ hybridization technique. The algorithm is based on assigning a fuzzy membership value to each pixel in the centromere image. An iterative algorithm then updates and minimizes a defined error function. Chromosome 22, a highly heteromorphic chromosome, is used to verify the centromere segmentation method. Homologs of this chromosome are classified based on their segmented centromere intensities as well as their morphological differences. The classification results of these two methods agree completely and are used to validate our developed algorithm.
Mousavi, P; Ward, R K; Chavez, E; Lansdorp, P M
1999.
@proceedings{87,
title = {Analysis of telomere intensities in human chromosomes with application to classification of chromosome 16 homologs},
author = {P Mousavi and R K Ward and E Chavez and P M Lansdorp},
url = {http://dx.doi.org/10.1109/PACRIM.1999.799513},
doi = {10.1109/PACRIM.1999.799513},
year = {1999},
date = {1999-01-01},
journal = {Communications, Computers and Signal Processing, 1999 IEEE Pacific Rim Conference on},
abstract = {Studies telomere lengths in human chromosome 16 and attempts to classify homologs of chromosome 16 into maternal and paternal classes. A fuzzy c-means clustering algorithm is used for classification. A gradient method developed previously is also used to classify chromosome 16 and the results of these two methods are compared. Our study takes advantage of novel PNA probes developed at the BC Cancer Research Centre},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Studies telomere lengths in human chromosome 16 and attempts to classify homologs of chromosome 16 into maternal and paternal classes. A fuzzy c-means clustering algorithm is used for classification. A gradient method developed previously is also used to classify chromosome 16 and the results of these two methods are compared. Our study takes advantage of novel PNA probes developed at the BC Cancer Research Centre
Mousavi, P; Ward, R K; Lansdorp, P
Classification of Chromosome 16 Homologues Using Centromere and Telomere Intensity Features Conference
proceedings of the IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, pp. 205-208 proceedings of the IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, pp. 205-208, Victoria, BC, 1999.
@conference{438,
title = {Classification of Chromosome 16 Homologues Using Centromere and Telomere Intensity Features},
author = {P Mousavi and R K Ward and P Lansdorp},
year = {1999},
date = {1999-01-01},
publisher = {proceedings of the IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, pp. 205-208},
address = {Victoria, BC},
organization = {proceedings of the IEEE Pacific Rim Conference on Communications, Computers and Signal Processing, pp. 205-208},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Mousavi, P; Ward, R K; Lansdorp, P M
Feature analysis and classification of chromosome 16 homologs using fluorescence microscopy images Proceedings
1999.
@proceedings{88,
title = {Feature analysis and classification of chromosome 16 homologs using fluorescence microscopy images},
author = {P Mousavi and R K Ward and P M Lansdorp},
url = {http://dx.doi.org/10.1109/CCECE.1999.808082},
doi = {10.1109/CCECE.1999.808082},
year = {1999},
date = {1999-01-01},
journal = {Electrical and Computer Engineering, 1999 IEEE Canadian Conference on},
abstract = {Image processing techniques used to classify human chromosome 16 into two classes of parental homologs are described. The classification is accomplished using DNA probes and detecting intensity differences in homologs of chromosome 16. The classification of homologous chromosomes into maternal and paternal classes is essential to advanced studies of cancer genetics},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
Image processing techniques used to classify human chromosome 16 into two classes of parental homologs are described. The classification is accomplished using DNA probes and detecting intensity differences in homologs of chromosome 16. The classification of homologous chromosomes into maternal and paternal classes is essential to advanced studies of cancer genetics