Golpaighani, Hashemi M R; Fallah, A; Mousavi, P
Control of a Cybernetic Forearm by Artificial Neural Networks Conference
proc of the International Conference on Electrical Engineering of Iran proc of the International Conference on Electrical Engineering of Iran, Tehran, Iran, 1993.
@conference{436,
title = {Control of a Cybernetic Forearm by Artificial Neural Networks},
author = {Hashemi M R Golpaighani and A Fallah and P Mousavi},
year = {1993},
date = {1993-01-01},
publisher = {proc of the International Conference on Electrical Engineering of Iran},
address = {Tehran, Iran},
organization = {proc of the International Conference on Electrical Engineering of Iran},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Golpaighani, Hashemi M R; Fallah, A; Mousavi, P
Control of a Cybernetic Forearm by Artificial Neural Networks Journal Article
In: Pajoohesh Journal, vol. 13(27), 1993.
@article{445,
title = {Control of a Cybernetic Forearm by Artificial Neural Networks},
author = {Hashemi M R Golpaighani and A Fallah and P Mousavi},
year = {1993},
date = {1993-01-01},
journal = {Pajoohesh Journal},
volume = {13(27)},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
Lucas, C; Fallah, A; Mousavi, P
Effects of Learning, Fast Propagation and Momentum Coefficients on the Learning Process of Neural Networks Conference
proc of the Iranian Congress on Applied Computer Science proc of the Iranian Congress on Applied Computer Science, 1992.
@conference{437,
title = {Effects of Learning, Fast Propagation and Momentum Coefficients on the Learning Process of Neural Networks},
author = {C Lucas and A Fallah and P Mousavi},
year = {1992},
date = {1992-01-01},
publisher = {proc of the Iranian Congress on Applied Computer Science},
organization = {proc of the Iranian Congress on Applied Computer Science},
keywords = {},
pubstate = {published},
tppubtype = {conference}
}
Anas, Emran Mohammad Abu; Mousavi, Parvin; Abolmaesumi, Purang
A deep learning approach for real time prostate segmentation in freehand ultrasound guided biopsy. Journal Article
In: Med Image Anal, vol. 48, pp. 107-116, 0000, ISSN: 1361-8423.
@article{519,
title = {A deep learning approach for real time prostate segmentation in freehand ultrasound guided biopsy.},
author = {Emran Mohammad Abu Anas and Parvin Mousavi and Purang Abolmaesumi},
doi = {10.1016/j.media.2018.05.010},
issn = {1361-8423},
journal = {Med Image Anal},
volume = {48},
pages = {107-116},
abstract = {<p>Targeted prostate biopsy, incorporating multi-parametric magnetic resonance imaging (mp-MRI) and its registration with ultrasound, is currently the state-of-the-art in prostate cancer diagnosis. The registration process in most targeted biopsy systems today relies heavily on accurate segmentation of ultrasound images. Automatic or semi-automatic segmentation is typically performed offline prior to the start of the biopsy procedure. In this paper, we present a deep neural network based real-time prostate segmentation technique during the biopsy procedure, hence paving the way for dynamic registration of mp-MRI and ultrasound data. In addition to using convolutional networks for extracting spatial features, the proposed approach employs recurrent networks to exploit the temporal information among a series of ultrasound images. One of the key contributions in the architecture is to use residual convolution in the recurrent networks to improve optimization. We also exploit recurrent connections within and across different layers of the deep networks to maximize the utilization of the temporal information. Furthermore, we perform dense and sparse sampling of the input ultrasound sequence to make the network robust to ultrasound artifacts. Our architecture is trained on 2,238 labeled transrectal ultrasound images, with an additional 637 and 1,017 unseen images used for validation and testing, respectively. We obtain a mean Dice similarity coefficient of 93%, a mean surface distance error of 1.10~mm and a mean Hausdorff distance error of 3.0~mm. A comparison of the reported results with those of a state-of-the-art technique indicates statistically significant improvement achieved by the proposed approach.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>Targeted prostate biopsy, incorporating multi-parametric magnetic resonance imaging (mp-MRI) and its registration with ultrasound, is currently the state-of-the-art in prostate cancer diagnosis. The registration process in most targeted biopsy systems today relies heavily on accurate segmentation of ultrasound images. Automatic or semi-automatic segmentation is typically performed offline prior to the start of the biopsy procedure. In this paper, we present a deep neural network based real-time prostate segmentation technique during the biopsy procedure, hence paving the way for dynamic registration of mp-MRI and ultrasound data. In addition to using convolutional networks for extracting spatial features, the proposed approach employs recurrent networks to exploit the temporal information among a series of ultrasound images. One of the key contributions in the architecture is to use residual convolution in the recurrent networks to improve optimization. We also exploit recurrent connections within and across different layers of the deep networks to maximize the utilization of the temporal information. Furthermore, we perform dense and sparse sampling of the input ultrasound sequence to make the network robust to ultrasound artifacts. Our architecture is trained on 2,238 labeled transrectal ultrasound images, with an additional 637 and 1,017 unseen images used for validation and testing, respectively. We obtain a mean Dice similarity coefficient of 93%, a mean surface distance error of 1.10~mm and a mean Hausdorff distance error of 3.0~mm. A comparison of the reported results with those of a state-of-the-art technique indicates statistically significant improvement achieved by the proposed approach.</p>
Azizi, Shekoofeh; Bayat, Sharareh; Yan, Pingkun; Tahmasebi, Amir; Kwak, Jin Tae; Xu, Sheng; Turkbey, Baris; Choyke, Peter; Pinto, Peter; Wood, Bradford; Mousavi, Parvin; Abolmaesumi, Purang
Deep Recurrent Neural Networks for Prostate Cancer Detection: Analysis of Temporal Enhanced Ultrasound. Journal Article
In: IEEE Trans Med Imaging, vol. 37, pp. 2695-2703, 0000, ISSN: 1558-254X.
@article{524,
title = {Deep Recurrent Neural Networks for Prostate Cancer Detection: Analysis of Temporal Enhanced Ultrasound.},
author = {Shekoofeh Azizi and Sharareh Bayat and Pingkun Yan and Amir Tahmasebi and Jin Tae Kwak and Sheng Xu and Baris Turkbey and Peter Choyke and Peter Pinto and Bradford Wood and Parvin Mousavi and Purang Abolmaesumi},
doi = {10.1109/TMI.2018.2849959},
issn = {1558-254X},
journal = {IEEE Trans Med Imaging},
volume = {37},
pages = {2695-2703},
abstract = {<p>Temporal enhanced ultrasound (TeUS), comprising the analysis of variations in backscattered signals from a tissue over a sequence of ultrasound frames, has been previously proposed as a new paradigm for tissue characterization. In this paper, we propose to use deep recurrent neural networks (RNN) to explicitly model the temporal information in TeUS. By investigating several RNN models, we demonstrate that long short-term memory (LSTM) networks achieve the highest accuracy in separating cancer from benign tissue in the prostate. We also present algorithms for in-depth analysis of LSTM networks. Our in vivo study includes data from 255 prostate biopsy cores of 157 patients. We achieve area under the curve, sensitivity, specificity, and accuracy of 0.96, 0.76, 0.98, and 0.93, respectively. Our result suggests that temporal modeling of TeUS using RNN can significantly improve cancer detection accuracy over previously presented works.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>Temporal enhanced ultrasound (TeUS), comprising the analysis of variations in backscattered signals from a tissue over a sequence of ultrasound frames, has been previously proposed as a new paradigm for tissue characterization. In this paper, we propose to use deep recurrent neural networks (RNN) to explicitly model the temporal information in TeUS. By investigating several RNN models, we demonstrate that long short-term memory (LSTM) networks achieve the highest accuracy in separating cancer from benign tissue in the prostate. We also present algorithms for in-depth analysis of LSTM networks. Our in vivo study includes data from 255 prostate biopsy cores of 157 patients. We achieve area under the curve, sensitivity, specificity, and accuracy of 0.96, 0.76, 0.98, and 0.93, respectively. Our result suggests that temporal modeling of TeUS using RNN can significantly improve cancer detection accuracy over previously presented works.</p>
Nahlawi, Layan; Goncalves, Caroline; Imani, Farhad; Gaed, Mena; Gomez, Jose A; Moussa, Madeleine; Gibson, Eli; Fenster, Aaron; Ward, Aaron; Abolmaesumi, Purang; Shatkay, Hagit; Mousavi, Parvin
Stochastic Modeling of Temporal Enhanced Ultrasound: Impact of Temporal Properties on Prostate Cancer Characterization. Journal Article
In: IEEE Trans Biomed Eng, vol. 65, pp. 1798-1809, 0000, ISSN: 1558-2531.
@article{518,
title = {Stochastic Modeling of Temporal Enhanced Ultrasound: Impact of Temporal Properties on Prostate Cancer Characterization.},
author = {Layan Nahlawi and Caroline Goncalves and Farhad Imani and Mena Gaed and Jose A Gomez and Madeleine Moussa and Eli Gibson and Aaron Fenster and Aaron Ward and Purang Abolmaesumi and Hagit Shatkay and Parvin Mousavi},
doi = {10.1109/TBME.2017.2778007},
issn = {1558-2531},
journal = {IEEE Trans Biomed Eng},
volume = {65},
pages = {1798-1809},
abstract = {<p>textbfOBJECTIVES: Temporal enhanced ultrasound (TeUS) is a new ultrasound-based imaging technique that provides tissue-specific information. Recent studies have shown the potential of TeUS for improving tissue characterization in prostate cancer diagnosis. We study the temporal properties of TeUS-temporal order and length-and present a new framework to assess their impact on tissue information.</p><p>textbfMETHODS: We utilize a probabilistic modeling approach using hidden Markov models (HMMs) to capture the temporal signatures of malignant and benign tissues from TeUS signals of nine patients. We model signals of benign and malignant tissues (284 and 286 signals, respectively) in their original temporal order as well as under order permutations. We then compare the resulting models using the Kullback-Liebler divergence and assess their performance differences in characterization. Moreover, we train HMMs using TeUS signals of different durations and compare their model performance when differentiating tissue types.</p><p>textbfRESULTS: Our findings demonstrate that models of order-preserved signals perform statistically significantly better (85% accuracy) in tissue characterization compared to models of order-altered signals (62% accuracy). The performance degrades as more changes in signal order are introduced. Additionally, models trained on shorter sequences perform as accurately as models of longer sequences.</p><p>textbfCONCLUSION: The work presented here strongly indicates that temporal order has substantial impact on TeUS performance; thus, it plays a significant role in conveying tissue-specific information. Furthermore, shorter TeUS signals can relay sufficient information to accurately distinguish between tissue types.</p><p>textbfSIGNIFICANCE: Understanding the impact of TeUS properties facilitates the process of its adopting in diagnostic procedures and provides insights on improving its acquisition.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>textbfOBJECTIVES: Temporal enhanced ultrasound (TeUS) is a new ultrasound-based imaging technique that provides tissue-specific information. Recent studies have shown the potential of TeUS for improving tissue characterization in prostate cancer diagnosis. We study the temporal properties of TeUS-temporal order and length-and present a new framework to assess their impact on tissue information.</p><p>textbfMETHODS: We utilize a probabilistic modeling approach using hidden Markov models (HMMs) to capture the temporal signatures of malignant and benign tissues from TeUS signals of nine patients. We model signals of benign and malignant tissues (284 and 286 signals, respectively) in their original temporal order as well as under order permutations. We then compare the resulting models using the Kullback-Liebler divergence and assess their performance differences in characterization. Moreover, we train HMMs using TeUS signals of different durations and compare their model performance when differentiating tissue types.</p><p>textbfRESULTS: Our findings demonstrate that models of order-preserved signals perform statistically significantly better (85% accuracy) in tissue characterization compared to models of order-altered signals (62% accuracy). The performance degrades as more changes in signal order are introduced. Additionally, models trained on shorter sequences perform as accurately as models of longer sequences.</p><p>textbfCONCLUSION: The work presented here strongly indicates that temporal order has substantial impact on TeUS performance; thus, it plays a significant role in conveying tissue-specific information. Furthermore, shorter TeUS signals can relay sufficient information to accurately distinguish between tissue types.</p><p>textbfSIGNIFICANCE: Understanding the impact of TeUS properties facilitates the process of its adopting in diagnostic procedures and provides insights on improving its acquisition.</p>
Imani, Farhad; Abolmaesumi, Purang; Gibson, Eli; Galesh-Khale, Amir Khojaste; Gaed, Mena; Moussa, Madeleine; Gomez, Jose A; Romagnoli, Cesare; Siemens, Robert D; Leviridge, Michael; Chang, Silvia; Fenster, Aaron; Ward, Aaron D; Mousavi, Parvin
Ultrasound-based characterization of prostate cancer: an in vivo clinical feasibility study. Journal Article
In: Med Image Comput Comput Assist Interv, vol. 16, pp. 279-86, 0000.
@article{75,
title = {Ultrasound-based characterization of prostate cancer: an in vivo clinical feasibility study.},
author = {Farhad Imani and Purang Abolmaesumi and Eli Gibson and Amir Khojaste Galesh-Khale and Mena Gaed and Madeleine Moussa and Jose A Gomez and Cesare Romagnoli and Robert D Siemens and Michael Leviridge and Silvia Chang and Aaron Fenster and Aaron D Ward and Parvin Mousavi},
journal = {Med Image Comput Comput Assist Interv},
volume = {16},
pages = {279-86},
abstract = {<p>textbfUNLABELLED: This paper presents the results of an in vivo clinical study to accurately characterize prostate cancer using new features of ultrasound RF time series.</p><p>textbfMETHODS: The mean central frequency and wavelet features of ultrasound RF time series from seven patients are used along with an elaborate framework of ultrasound to histology registration to identify and verify cancer in prostate tissue regions as small as 1.7 mm x 1.7 mm.</p><p>textbfRESULTS: In a leave-one-patient-out cross-validation strategy, an average classification accuracy of 76% and the area under ROC curve of 0.83 are achieved using two proposed RF time series features. The results statistically significantly outperform those achieved by previously reported features in the literature. The proposed features show the clinical relevance of RF time series for in vivo characterization of cancer.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>textbfUNLABELLED: This paper presents the results of an in vivo clinical study to accurately characterize prostate cancer using new features of ultrasound RF time series.</p><p>textbfMETHODS: The mean central frequency and wavelet features of ultrasound RF time series from seven patients are used along with an elaborate framework of ultrasound to histology registration to identify and verify cancer in prostate tissue regions as small as 1.7 mm x 1.7 mm.</p><p>textbfRESULTS: In a leave-one-patient-out cross-validation strategy, an average classification accuracy of 76% and the area under ROC curve of 0.83 are achieved using two proposed RF time series features. The results statistically significantly outperform those achieved by previously reported features in the literature. The proposed features show the clinical relevance of RF time series for in vivo characterization of cancer.</p>
Hashemi, Javad; Morin, Evelyn; Mousavi, Parvin; Hashtrudi-Zaad, Keyvan
Enhanced multi-site EMG-force estimation using contact pressure. Journal Article
In: Conf Proc IEEE Eng Med Biol Soc, vol. 2012, pp. 3098-101, 0000, ISSN: 1557-170X.
@article{30,
title = {Enhanced multi-site EMG-force estimation using contact pressure.},
author = {Javad Hashemi and Evelyn Morin and Parvin Mousavi and Keyvan Hashtrudi-Zaad},
doi = {10.1109/EMBC.2012.6346619},
issn = {1557-170X},
journal = {Conf Proc IEEE Eng Med Biol Soc},
volume = {2012},
pages = {3098-101},
abstract = {<p>A modification method based on integrated contact pressure and surface electromyogram (SEMG) recordings over the biceps brachii muscle is presented. Multi-site sEMGs are modified by pressure signals recorded at the same locations for isometric contractions. The resulting pressure times SEMG signals are significantly more correlated to the force induced at the wrist (FW), yielding SEMG-force models with superior performance in force estimation. A sensor patch, combining six SEMG and six contact pressure sensors was designed and built. SEMG, and contact pressure data over the biceps brachii and induced wrist force data were collected from 5 subjects. Polynomial fitting was used to find a mapping between biceps SEMG and wrist force. Comparison between evaluation values from models trained with modified and non-modified SEMG signals revealed a statistically significant superiority of models trained with the modified SEMG.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>A modification method based on integrated contact pressure and surface electromyogram (SEMG) recordings over the biceps brachii muscle is presented. Multi-site sEMGs are modified by pressure signals recorded at the same locations for isometric contractions. The resulting pressure times SEMG signals are significantly more correlated to the force induced at the wrist (FW), yielding SEMG-force models with superior performance in force estimation. A sensor patch, combining six SEMG and six contact pressure sensors was designed and built. SEMG, and contact pressure data over the biceps brachii and induced wrist force data were collected from 5 subjects. Polynomial fitting was used to find a mapping between biceps SEMG and wrist force. Comparison between evaluation values from models trained with modified and non-modified SEMG signals revealed a statistically significant superiority of models trained with the modified SEMG.</p>
Wang, Lili; Khankhanian, Pouya; Baranzini, Sergio E; Mousavi, Parvin
iCTNet: a Cytoscape plugin to produce and analyze integrative complex traits networks. Journal Article
In: BMC Bioinformatics, vol. 12, pp. 380, 0000, ISSN: 1471-2105.
@article{39e,
title = {iCTNet: a Cytoscape plugin to produce and analyze integrative complex traits networks.},
author = {Lili Wang and Pouya Khankhanian and Sergio E Baranzini and Parvin Mousavi},
doi = {10.1186/1471-2105-12-380},
issn = {1471-2105},
journal = {BMC Bioinformatics},
volume = {12},
pages = {380},
abstract = {<p>textbfBACKGROUND: The speed at which biological datasets are being accumulated stands in contrast to our ability to integrate them meaningfully. Large-scale biological databases containing datasets of genes, proteins, cells, organs, and diseases are being created but they are not connected. Integration of these vast but heterogeneous sources of information will allow the systematic and comprehensive analysis of molecular and clinical datasets, spanning hundreds of dimensions and thousands of individuals. This integration is essential to capitalize on the value of current and future molecular- and cellular-level data on humans to gain novel insights about health and disease.</p><p>textbfRESULTS: We describe a new open-source Cytoscape plugin named iCTNet (integrated Complex Traits Networks). iCTNet integrates several data sources to allow automated and systematic creation of networks with up to five layers of omics information: phenotype-SNP association, protein-protein interaction, disease-tissue, tissue-gene, and drug-gene relationships. It facilitates the generation of general or specific network views with diverse options for more than 200 diseases. Built-in tools are provided to prioritize candidate genes and create modules of specific phenotypes.</p><p>textbfCONCLUSIONS: iCTNet provides a user-friendly interface to search, integrate, visualize, and analyze genome-scale biological networks for human complex traits. We argue this tool is a key instrument that facilitates systematic integration of disparate large-scale data through network visualization, ultimately allowing the identification of disease similarities and the design of novel therapeutic approaches.The online database and Cytoscape plugin are freely available for academic use at: http://www.cs.queensu.ca/ictnet.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>textbfBACKGROUND: The speed at which biological datasets are being accumulated stands in contrast to our ability to integrate them meaningfully. Large-scale biological databases containing datasets of genes, proteins, cells, organs, and diseases are being created but they are not connected. Integration of these vast but heterogeneous sources of information will allow the systematic and comprehensive analysis of molecular and clinical datasets, spanning hundreds of dimensions and thousands of individuals. This integration is essential to capitalize on the value of current and future molecular- and cellular-level data on humans to gain novel insights about health and disease.</p><p>textbfRESULTS: We describe a new open-source Cytoscape plugin named iCTNet (integrated Complex Traits Networks). iCTNet integrates several data sources to allow automated and systematic creation of networks with up to five layers of omics information: phenotype-SNP association, protein-protein interaction, disease-tissue, tissue-gene, and drug-gene relationships. It facilitates the generation of general or specific network views with diverse options for more than 200 diseases. Built-in tools are provided to prioritize candidate genes and create modules of specific phenotypes.</p><p>textbfCONCLUSIONS: iCTNet provides a user-friendly interface to search, integrate, visualize, and analyze genome-scale biological networks for human complex traits. We argue this tool is a key instrument that facilitates systematic integration of disparate large-scale data through network visualization, ultimately allowing the identification of disease similarities and the design of novel therapeutic approaches.The online database and Cytoscape plugin are freely available for academic use at: http://www.cs.queensu.ca/ictnet.</p>
Sutherland, Colin; Hashtrudi-Zaad, Keyvan; Abolmaesumi, Purang; Mousavi, Parvin
Towards an augmented ultrasound guided spinal needle insertion system. Journal Article
In: Conf Proc IEEE Eng Med Biol Soc, vol. 2011, pp. 3459-62, 0000, ISSN: 1557-170X.
@article{22b,
title = {Towards an augmented ultrasound guided spinal needle insertion system.},
author = {Colin Sutherland and Keyvan Hashtrudi-Zaad and Purang Abolmaesumi and Parvin Mousavi},
doi = {10.1109/IEMBS.2011.6090935},
issn = {1557-170X},
journal = {Conf Proc IEEE Eng Med Biol Soc},
volume = {2011},
pages = {3459-62},
abstract = {<p>We propose a haptic-based simulator for ultrasound-guided percutaneous spinal interventions. The system is composed of a haptic device to provide force feedback, a camera system to display video and augmented computed tomography (CT) overlay, a finite element model for tissue deformation and US simulation from a CT volume. The proposed system is able to run a large finite element model at the required haptic rate for smooth force feedback, and uses haptic device position measurements for a steady response. The simulated US images from CT closely resemble the vertebrae images captured in vivo. This is the first report of a system that provides a training environment to couple haptic feedback with a tracked mannequin, and a CT volume overlaid on a visual feed of the mannequin.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>We propose a haptic-based simulator for ultrasound-guided percutaneous spinal interventions. The system is composed of a haptic device to provide force feedback, a camera system to display video and augmented computed tomography (CT) overlay, a finite element model for tissue deformation and US simulation from a CT volume. The proposed system is able to run a large finite element model at the required haptic rate for smooth force feedback, and uses haptic device position measurements for a steady response. The simulated US images from CT closely resemble the vertebrae images captured in vivo. This is the first report of a system that provides a training environment to couple haptic feedback with a tracked mannequin, and a CT volume overlaid on a visual feed of the mannequin.</p>
Hashemi, Javad; Hashtrudi-Zaad, Keyvan; Morin, Evelyn; Mousavi, Parvin
Dynamic modeling of EMG-force relationship using parallel cascade identification. Proceedings
vol. 2010, 0000, ISSN: 1557-170X.
@proceedings{35e,
title = {Dynamic modeling of EMG-force relationship using parallel cascade identification.},
author = {Javad Hashemi and Keyvan Hashtrudi-Zaad and Evelyn Morin and Parvin Mousavi},
doi = {10.1109/IEMBS.2010.5626382},
issn = {1557-170X},
journal = {Conf Proc IEEE Eng Med Biol Soc},
volume = {2010},
pages = {1328-31},
abstract = {<p>Parallel cascade identification (PCI) is used as a dynamic estimation tool to map surface electromyography recordings from upper-arm muscles to the elbow-induced force at the wrist. PCI mapping is composed of parallel connection of a cascade of linear dynamic and nonlinear static blocks. Experimental comparison between PCI and previously published orthogonalization scheme has shown superior force prediction by PCI. The improved performance is attributed to the structural capability of PCI in capturing nonlinear dynamic effects in the generated force.</p>},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
<p>Parallel cascade identification (PCI) is used as a dynamic estimation tool to map surface electromyography recordings from upper-arm muscles to the elbow-induced force at the wrist. PCI mapping is composed of parallel connection of a cascade of linear dynamic and nonlinear static blocks. Experimental comparison between PCI and previously published orthogonalization scheme has shown superior force prediction by PCI. The improved performance is attributed to the structural capability of PCI in capturing nonlinear dynamic effects in the generated force.</p>
Nahlawi, Layan Imad; Mousavi, Parvin
Fast orthogonal search for genetic feature selection. Proceedings
vol. 2010, 0000, ISSN: 1557-170X.
@proceedings{27b,
title = {Fast orthogonal search for genetic feature selection.},
author = {Layan Imad Nahlawi and Parvin Mousavi},
doi = {10.1109/IEMBS.2010.5627300},
issn = {1557-170X},
journal = {Conf Proc IEEE Eng Med Biol Soc},
volume = {2010},
pages = {1077-80},
abstract = {<p>In this paper, we present the application of a multivariate regression approach, fast orthogonal search, to select the most informative features in Single Nucleotide Polymorphism data, and to use these features to accurately model the entire data. Our results on two published datasets show very high accuracies in capturing the hidden information in the sequence of studied SNPs. The execution time for our developed methodology is very short and paves the way for its application to large-scale genome wide datasets.</p>},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
<p>In this paper, we present the application of a multivariate regression approach, fast orthogonal search, to select the most informative features in Single Nucleotide Polymorphism data, and to use these features to accurately model the entire data. Our results on two published datasets show very high accuracies in capturing the hidden information in the sequence of studied SNPs. The execution time for our developed methodology is very short and paves the way for its application to large-scale genome wide datasets.</p>
Aboofazeli, Mohammad; Abolmaesumi, Purang; Fichtinger, Gabor; Mousavi, Parvin
Tissue characterization using multiscale products of wavelet transform of ultrasound radio frequency echoes. Proceedings
vol. 2009, 0000, ISSN: 1557-170X.
@proceedings{13b,
title = {Tissue characterization using multiscale products of wavelet transform of ultrasound radio frequency echoes.},
author = {Mohammad Aboofazeli and Purang Abolmaesumi and Gabor Fichtinger and Parvin Mousavi},
doi = {10.1109/IEMBS.2009.5335160},
issn = {1557-170X},
journal = {Conf Proc IEEE Eng Med Biol Soc},
volume = {2009},
pages = {479-82},
abstract = {<p>This paper presents a novel method for tissue characterization using wavelet transform of ultrasound radio frequency (RF) echo signals. We propose the use of multiscale products of wavelet transform sequences of RF echoes to estimate the scatterer distribution in the tissue. The proposed method is based on the fact that when emitted ultrasound beams interact with scatterers in the tissue, backscattered beams contain singularities corresponding to the location of the scatterers. The singularities will exist in multiple scales of wavelet sequences of the echo signals. Therefore, peaks of wavelet transform multiscale products correspond to the location of scatterers. Estimation of scatterer spacing can be used for tissue characterization. The efficacy of the proposed method was validated in RF echo signals of in-vitro human prostate to characterize normal and cancerous tissue. The results confirm that wavelet transform multiscale products of RF echo signals contain tissue typing information that can be used as an effective tool to differentiate normal and cancerous prostate tissue.</p>},
keywords = {},
pubstate = {published},
tppubtype = {proceedings}
}
<p>This paper presents a novel method for tissue characterization using wavelet transform of ultrasound radio frequency (RF) echo signals. We propose the use of multiscale products of wavelet transform sequences of RF echoes to estimate the scatterer distribution in the tissue. The proposed method is based on the fact that when emitted ultrasound beams interact with scatterers in the tissue, backscattered beams contain singularities corresponding to the location of the scatterers. The singularities will exist in multiple scales of wavelet sequences of the echo signals. Therefore, peaks of wavelet transform multiscale products correspond to the location of scatterers. Estimation of scatterer spacing can be used for tissue characterization. The efficacy of the proposed method was validated in RF echo signals of in-vitro human prostate to characterize normal and cancerous tissue. The results confirm that wavelet transform multiscale products of RF echo signals contain tissue typing information that can be used as an effective tool to differentiate normal and cancerous prostate tissue.</p>
Moradi, M; Mousavi, P; Siemens, D R; Sauerbrei, E E; Isotalo, P; Boag, A; Abolmaesumi, P
Discrete Fourier analysis of ultrasound RF time series for detection of prostate cancer. Journal Article
In: Conf Proc IEEE Eng Med Biol Soc, vol. 2007, pp. 1339-42, 0000, ISSN: 1557-170X.
@article{7_38,
title = {Discrete Fourier analysis of ultrasound RF time series for detection of prostate cancer.},
author = {M Moradi and P Mousavi and D R Siemens and E E Sauerbrei and P Isotalo and A Boag and P Abolmaesumi},
doi = {10.1109/IEMBS.2007.4352545},
issn = {1557-170X},
journal = {Conf Proc IEEE Eng Med Biol Soc},
volume = {2007},
pages = {1339-42},
abstract = {<p>In this paper, we demonstrate that a set of six features extracted from the discrete Fourier transform of ultrasound Radio-Frequency (RF) time series can be used to detect prostate cancer with high sensitivity and specificity. Ultrasound RF time series refer to a series of echoes received from one spatial location of tissue while the imaging probe and the tissue are fixed in position. Our previous investigations have shown that at least one feature, fractal dimension, of these signals demonstrates strong correlation with the tissue microstructure. In the current paper, six new features that represent the frequency spectrum of the RF time series have been used, in conjunction with a neural network classification approach, to detect prostate cancer in regions of tissue as small as 0.03 cm2. Based on pathology results used as gold standard, we have acquired mean accuracy of 91%, mean sensitivity of 92% and mean specificity of 90% on seven human prostates.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>In this paper, we demonstrate that a set of six features extracted from the discrete Fourier transform of ultrasound Radio-Frequency (RF) time series can be used to detect prostate cancer with high sensitivity and specificity. Ultrasound RF time series refer to a series of echoes received from one spatial location of tissue while the imaging probe and the tissue are fixed in position. Our previous investigations have shown that at least one feature, fractal dimension, of these signals demonstrates strong correlation with the tissue microstructure. In the current paper, six new features that represent the frequency spectrum of the RF time series have been used, in conjunction with a neural network classification approach, to detect prostate cancer in regions of tissue as small as 0.03 cm2. Based on pathology results used as gold standard, we have acquired mean accuracy of 91%, mean sensitivity of 92% and mean specificity of 90% on seven human prostates.</p>
Moradi, Mehdi; Mousavi, Parvin; Abolmaesumi, Purang
Tissue characterization using fractal dimension of high frequency ultrasound RF time series. Journal Article
In: Med Image Comput Comput Assist Interv, vol. 10, pp. 900-8, 0000.
@article{10b,
title = {Tissue characterization using fractal dimension of high frequency ultrasound RF time series.},
author = {Mehdi Moradi and Parvin Mousavi and Purang Abolmaesumi},
journal = {Med Image Comput Comput Assist Interv},
volume = {10},
pages = {900-8},
abstract = {<p>This paper is the first report on the analysis of ultrasound RF echo time series acquired using high frequency ultrasound. We show that variations in the intensity of one sample of RF echo over time is correlated with tissue microstructure. To form the RF time series, a high frequency probe and a tissue sample were fixed in position and RF signals backscattered from the tissue were continuously recorded. The fractal dimension of RF time series was used as a feature for tissue classification. Feature values acquired from different areas of one tissue type were statistically similar. For animal tissues with different cellular microstructure, we successfully used the fractal dimension of RF time series to distinguish segments as small as 20 microns with accuracies as high as 98%. The results of this study demonstrate that the analysis of RF time series is a promising approach for distinguishing tissue types with different cellular microstructure.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>This paper is the first report on the analysis of ultrasound RF echo time series acquired using high frequency ultrasound. We show that variations in the intensity of one sample of RF echo over time is correlated with tissue microstructure. To form the RF time series, a high frequency probe and a tissue sample were fixed in position and RF signals backscattered from the tissue were continuously recorded. The fractal dimension of RF time series was used as a feature for tissue classification. Feature values acquired from different areas of one tissue type were statistically similar. For animal tissues with different cellular microstructure, we successfully used the fractal dimension of RF time series to distinguish segments as small as 20 microns with accuracies as high as 98%. The results of this study demonstrate that the analysis of RF time series is a promising approach for distinguishing tissue types with different cellular microstructure.</p>
Moradi, Mehdi; Abolmaesumi, Purang; Isotalo, Phillip A; Siemens, David R; Sauerbrei, Eric E; Mousavi, Parvin
Detection of prostate cancer from RF ultrasound echo signals using fractal analysis. Journal Article
In: Conf Proc IEEE Eng Med Biol Soc, vol. 1, pp. 2400-3, 0000, ISSN: 1557-170X.
@article{8_35,
title = {Detection of prostate cancer from RF ultrasound echo signals using fractal analysis.},
author = {Mehdi Moradi and Purang Abolmaesumi and Phillip A Isotalo and David R Siemens and Eric E Sauerbrei and Parvin Mousavi},
doi = {10.1109/IEMBS.2006.259325},
issn = {1557-170X},
journal = {Conf Proc IEEE Eng Med Biol Soc},
volume = {1},
pages = {2400-3},
abstract = {<p>In this paper we propose a new feature, average Higuchi dimension of RF time series (AHDRFT), for detection of prostate cancer using ultrasound data. The proposed feature is extracted from RF echo signals acquired from prostate tissue in an in vitro setting and is used in combination with texture features extracted from the corresponding B-scan images. In a novel approach towards RF data collection, we continuously recorded backscattered echoes from the prostate tissue to acquire time series of the RF signals. We also collected B-scan images and performed a detailed histopathologic analysis on the tissue. To compute AHDRFT, the Higuchi fractal dimensions of the RF time series were averaged over a region of interest. AHDRFT and texture features extracted from corresponding B-scan images were used to classify regions of interest, as small as 0.028 cm of the prostate tissue in cancerous and normal classes. We validated the results based on our histopathologic maps. A combination of image statistical moments and features extracted from co-occurrence matrices of the B-scan images resulted in classification accuracy of around 87%. When AHDRFT was added to the feature vectors, the classification accuracy was consistently over 95% with best results of over 99% accuracy. Our results show that the RF time series backscattered from prostate tissues contain information that can be used for detection of prostate cancer.</p>},
keywords = {},
pubstate = {published},
tppubtype = {article}
}
<p>In this paper we propose a new feature, average Higuchi dimension of RF time series (AHDRFT), for detection of prostate cancer using ultrasound data. The proposed feature is extracted from RF echo signals acquired from prostate tissue in an in vitro setting and is used in combination with texture features extracted from the corresponding B-scan images. In a novel approach towards RF data collection, we continuously recorded backscattered echoes from the prostate tissue to acquire time series of the RF signals. We also collected B-scan images and performed a detailed histopathologic analysis on the tissue. To compute AHDRFT, the Higuchi fractal dimensions of the RF time series were averaged over a region of interest. AHDRFT and texture features extracted from corresponding B-scan images were used to classify regions of interest, as small as 0.028 cm of the prostate tissue in cancerous and normal classes. We validated the results based on our histopathologic maps. A combination of image statistical moments and features extracted from co-occurrence matrices of the B-scan images resulted in classification accuracy of around 87%. When AHDRFT was added to the feature vectors, the classification accuracy was consistently over 95% with best results of over 99% accuracy. Our results show that the RF time series backscattered from prostate tissues contain information that can be used for detection of prostate cancer.</p>