D. Bastola, Scott P. McGrath, S. Bhowmick, I. Thapa
Molecular based identification of pathogenic organism is becoming a routine procedure in many diagnostic laboratories. Ribosomal RNA is particularly the most popular choice for this purpose. Although, other targets such as `cytochrome b', `rpoB' and `actin' are highly effective, they have not been extensively used. This could be due to the lack of effective data collection method. We used sequence based exhaustive search of public sequence database to obtain all target sequences. This approach is currently being extended to collect such molecular targets for Nocardia and other slow growing medically important organisms.
{"title":"A Comparison of Computational Approaches in the Molecular Identification of Pathogenic Organisms","authors":"D. Bastola, Scott P. McGrath, S. Bhowmick, I. Thapa","doi":"10.1109/HISB.2012.23","DOIUrl":"https://doi.org/10.1109/HISB.2012.23","url":null,"abstract":"Molecular based identification of pathogenic organism is becoming a routine procedure in many diagnostic laboratories. Ribosomal RNA is particularly the most popular choice for this purpose. Although, other targets such as `cytochrome b', `rpoB' and `actin' are highly effective, they have not been extensively used. This could be due to the lack of effective data collection method. We used sequence based exhaustive search of public sequence database to obtain all target sequences. This approach is currently being extended to collect such molecular targets for Nocardia and other slow growing medically important organisms.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"156 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127209453","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}
J. E. Kroll, J. E. Souza, B. Stransky, G. D. Souza, S. J. Souza
Summary form only given. Alternative splicing events (AS) are among the most significant factors determining the complexity of multi-cellular organisms. Most, if not all, multi-exonic human genes undergo AS. Many AS events are involved in the etiology of cancer, among many other common human disorders. The emergence of next-generation sequencing offers a unique opportunity to explore the variability generated by AS in an exhaustive way. Furthermore, recent developments in new mass-spectometry platforms have allowed a deeper survey of the human proteome. Here, an analysis of intron retention, the most rare type of AS, was performed integrating transcriptome and proteome data. Intron retention events were evaluated in relation to several features, focusing on whether they had biological significance or whether they were just spurious products from the splicing machinery. For the transcriptome analysis, the following dataset was used: 30,678 RefSeqs, 258,444 mRNAs, 6,987,423 ESTs and 9,565,439 sequences derived from NGS. For the proteome analysis, data from Geiger et al., MCP, 2012 were used. We were able to detect an intron retention event for 48% of all human genes. Confirming a previous publication from our group [1], these events are enriched at the 3'and 5'untranslated regions (UTRs). Retained introns were significantly enriched with coding potential, which supports a biological role for these events. Furthermore, they were enriched for targets of microRNAs, suggesting a role of this type of AS in the regulation of expression induced by these non-coding RNAs. A significant number of events were detected at the proteome level. This information was integrated together with transcriptome data to further explore the role of intron retention in many biological phenomena.
只提供摘要形式。选择性剪接事件(AS)是决定多细胞生物复杂性的最重要因素之一。大多数(如果不是全部的话)多外显子的人类基因都会经历AS。在许多其他常见的人类疾病中，许多AS事件与癌症的病因有关。下一代测序的出现提供了一个独特的机会，以详尽的方式探索由AS产生的变异性。此外，新的质谱平台的最新发展已经允许对人类蛋白质组进行更深入的调查。在这里，对最罕见的AS类型内含子保留进行分析，整合转录组和蛋白质组数据。内含子保留事件与几个特征有关，重点是它们是否具有生物学意义，或者它们是否只是剪接机制的虚假产物。转录组分析使用了以下数据集:30,678个RefSeqs, 258,444个mrna, 6,987,423个ESTs和9,565,439个来自NGS的序列。蛋白质组分析使用Geiger et al.， MCP, 2012年的数据。我们能够检测到48%的人类基因的内含子保留事件。证实了我们小组[1]先前发表的一篇文章，这些事件在3'和5'非翻译区(utr)富集。保留的内含子显著富集了编码潜能，这支持了这些事件的生物学作用。此外，它们富含microrna的靶标，这表明这种类型的AS在这些非编码rna诱导的表达调控中起作用。在蛋白质组水平上检测到大量事件。这些信息与转录组数据相结合，进一步探索内含子保留在许多生物现象中的作用。
{"title":"Integrating Transcriptome and Proteome Information for the Analysis of Alternative Splicing","authors":"J. E. Kroll, J. E. Souza, B. Stransky, G. D. Souza, S. J. Souza","doi":"10.1109/HISB.2012.44","DOIUrl":"https://doi.org/10.1109/HISB.2012.44","url":null,"abstract":"Summary form only given. Alternative splicing events (AS) are among the most significant factors determining the complexity of multi-cellular organisms. Most, if not all, multi-exonic human genes undergo AS. Many AS events are involved in the etiology of cancer, among many other common human disorders. The emergence of next-generation sequencing offers a unique opportunity to explore the variability generated by AS in an exhaustive way. Furthermore, recent developments in new mass-spectometry platforms have allowed a deeper survey of the human proteome. Here, an analysis of intron retention, the most rare type of AS, was performed integrating transcriptome and proteome data. Intron retention events were evaluated in relation to several features, focusing on whether they had biological significance or whether they were just spurious products from the splicing machinery. For the transcriptome analysis, the following dataset was used: 30,678 RefSeqs, 258,444 mRNAs, 6,987,423 ESTs and 9,565,439 sequences derived from NGS. For the proteome analysis, data from Geiger et al., MCP, 2012 were used. We were able to detect an intron retention event for 48% of all human genes. Confirming a previous publication from our group [1], these events are enriched at the 3'and 5'untranslated regions (UTRs). Retained introns were significantly enriched with coding potential, which supports a biological role for these events. Furthermore, they were enriched for targets of microRNAs, suggesting a role of this type of AS in the regulation of expression induced by these non-coding RNAs. A significant number of events were detected at the proteome level. This information was integrated together with transcriptome data to further explore the role of intron retention in many biological phenomena.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125528555","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}
Chromatin Immunoprecipitation followed by high-content sequencing (ChIP-seq) is a powerful approach for identifying bonafide transcription factor (TF) binding sites, however these studies can be difficult, time-consuming and costly. They require ChIP-validated antibodies and a priori knowledge of which TF to pull down. Moreover, to gain further mechanistic insights, transcriptomic data is required to determine if TF binding alters proximal gene expression. Determining regulatory pathways from expression data is not an easy task. The typical result of a gene expression experiment, a set of co-regulated genes, may not include the relevant TF at all. Many such factors become active through mechanisms other than a change in their level of expression. To understand how such a set of genes is co-regulated, it is necessary to find evidence of shared TF binding sites (TFBS). This approach presents its own set of problems. TFBS are identified by short sequences that can exist by chance without being biologically functional. An evolutionary perspective is required to consider only those functionally important sites that are conserved between the promoters of the genes in question and those of their orthologs in related species. Furthermore, the common occurrence of short TFBS makes it necessary to consider only those TFs that are significantly more common in the co-regulated genes than in the genome (or microarray) as a whole. InSilico-ChIP is a precomputed database of evolutionarily conserved TFBS for various species, which accepts a set of genes and quickly returns the conserved TFs that are statistically over-represented in the proximal promoter regions of those genes. It allows new species data to be created using only a whole genome alignment with a related species and gene locations. Several methods of identifying TF binding sites can be used, varying in alignment type, location, conservation restrictions, and TFBS matrices used to analyze the promoter regions.
{"title":"InSilico-ChIP: A Coregulation and Evolutionary Conservation Based Transcription Factor and Target Gene Predictor","authors":"M. Munoz, A. Zambon","doi":"10.1109/HISB.2012.47","DOIUrl":"https://doi.org/10.1109/HISB.2012.47","url":null,"abstract":"Chromatin Immunoprecipitation followed by high-content sequencing (ChIP-seq) is a powerful approach for identifying bonafide transcription factor (TF) binding sites, however these studies can be difficult, time-consuming and costly. They require ChIP-validated antibodies and a priori knowledge of which TF to pull down. Moreover, to gain further mechanistic insights, transcriptomic data is required to determine if TF binding alters proximal gene expression. Determining regulatory pathways from expression data is not an easy task. The typical result of a gene expression experiment, a set of co-regulated genes, may not include the relevant TF at all. Many such factors become active through mechanisms other than a change in their level of expression. To understand how such a set of genes is co-regulated, it is necessary to find evidence of shared TF binding sites (TFBS). This approach presents its own set of problems. TFBS are identified by short sequences that can exist by chance without being biologically functional. An evolutionary perspective is required to consider only those functionally important sites that are conserved between the promoters of the genes in question and those of their orthologs in related species. Furthermore, the common occurrence of short TFBS makes it necessary to consider only those TFs that are significantly more common in the co-regulated genes than in the genome (or microarray) as a whole. InSilico-ChIP is a precomputed database of evolutionarily conserved TFBS for various species, which accepts a set of genes and quickly returns the conserved TFs that are statistically over-represented in the proximal promoter regions of those genes. It allows new species data to be created using only a whole genome alignment with a related species and gene locations. Several methods of identifying TF binding sites can be used, varying in alignment type, location, conservation restrictions, and TFBS matrices used to analyze the promoter regions.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129366209","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}
Computational drug repositioning offers promise for discovering new uses of existing drugs, as drug related molecular, chemical, and clinical information has increased over the past decade and become broadly accessible. In this study, we present a new computational approach for identifying potential new indications of an existing drug through its relation to similar drugs in disease-drug-target network. When measuring drug pairwise similarly, we used a bipartite-graph based method which combined similarity of drug compound structures, similarity of target protein profiles, and interaction between target proteins. In evaluation, our method compared favorably to the state of the art, achieving AUC of 0.888. The results indicated that our method is able to identify drug repositioning opportunities by exploring complex relationships in disease-drug-target network.
{"title":"A Network Approach for Computational Drug Repositioning","authors":"Jiao Li, Zhiyong Lu","doi":"10.1109/HISB.2012.26","DOIUrl":"https://doi.org/10.1109/HISB.2012.26","url":null,"abstract":"Computational drug repositioning offers promise for discovering new uses of existing drugs, as drug related molecular, chemical, and clinical information has increased over the past decade and become broadly accessible. In this study, we present a new computational approach for identifying potential new indications of an existing drug through its relation to similar drugs in disease-drug-target network. When measuring drug pairwise similarly, we used a bipartite-graph based method which combined similarity of drug compound structures, similarity of target protein profiles, and interaction between target proteins. In evaluation, our method compared favorably to the state of the art, achieving AUC of 0.888. The results indicated that our method is able to identify drug repositioning opportunities by exploring complex relationships in disease-drug-target network.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127630821","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}
Dimitrios Markonis, Roger Schaer, Ivan Eggel, H. Müller, A. Depeursinge
In this paper, MapReduce is used to speed up and make possible three large-scale medical image processing use-cases: (i) parameter optimization for lung texture classification using support vector machines (SVM), (ii) content-based medical image indexing, and (iii) three-dimensional directional wavelet analysis for solid texture classification.
{"title":"Using MapReduce for Large-Scale Medical Image Analysis","authors":"Dimitrios Markonis, Roger Schaer, Ivan Eggel, H. Müller, A. Depeursinge","doi":"10.1109/HISB.2012.8","DOIUrl":"https://doi.org/10.1109/HISB.2012.8","url":null,"abstract":"In this paper, MapReduce is used to speed up and make possible three large-scale medical image processing use-cases: (i) parameter optimization for lung texture classification using support vector machines (SVM), (ii) content-based medical image indexing, and (iii) three-dimensional directional wavelet analysis for solid texture classification.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127648410","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}
Vanderson Silva, F. Santana, B. Stransky, S. J. Souza
Tumours can be considered a set of cells that accumulate genetic and epigenetic alterations. According to the Multi-stage Hit theory, the transformation of a normal into a tumour cell involves a number of limiting events that occur in a number of discrete stages (driver mutations). However, not all mutations that occur in the cell are directly involved in the development of cancer and some probably do not contribute in any way (passenger mutations). Moreover, the process of tumour evolution is punctuated by selection of advantageous mutations and clonal expansions. Actually, it is not known how many limiting-events, i.e., how many driver mutations are necessary or sufficient to promote a carcinogenic process. This conjecture should be explored and tested - mathematically and statistically, with the availability of genomic data on databanks. In this work, we explore the model proposed by Bozic and collaborators (2010) that describes the evolution of the tumour according to a Galton-Watson process. Besides, the model gives the relation between the numbers of passenger mutations giving a specific number of driver mutations. We intend to explore some of the model parameters and test some premises about the number of drive mutations and selective advantage, comparing the simulation results with genomic data from colorectal cancer patients. The genomic data was obtained from the DBMutation (http://www.bioinformatics-brazil.org/dbmutation/), a comprehensive database for genomic mutations in cancer. We expect that correlations between driver mutations and the time evolution of tumour process will facilitate the interpretation of genomic information, to make them useful and applicable to clinical oncology.
{"title":"Modelling the Effects of Genetic Changes in Tumour Progression","authors":"Vanderson Silva, F. Santana, B. Stransky, S. J. Souza","doi":"10.1109/HISB.2012.62","DOIUrl":"https://doi.org/10.1109/HISB.2012.62","url":null,"abstract":"Tumours can be considered a set of cells that accumulate genetic and epigenetic alterations. According to the Multi-stage Hit theory, the transformation of a normal into a tumour cell involves a number of limiting events that occur in a number of discrete stages (driver mutations). However, not all mutations that occur in the cell are directly involved in the development of cancer and some probably do not contribute in any way (passenger mutations). Moreover, the process of tumour evolution is punctuated by selection of advantageous mutations and clonal expansions. Actually, it is not known how many limiting-events, i.e., how many driver mutations are necessary or sufficient to promote a carcinogenic process. This conjecture should be explored and tested - mathematically and statistically, with the availability of genomic data on databanks. In this work, we explore the model proposed by Bozic and collaborators (2010) that describes the evolution of the tumour according to a Galton-Watson process. Besides, the model gives the relation between the numbers of passenger mutations giving a specific number of driver mutations. We intend to explore some of the model parameters and test some premises about the number of drive mutations and selective advantage, comparing the simulation results with genomic data from colorectal cancer patients. The genomic data was obtained from the DBMutation (http://www.bioinformatics-brazil.org/dbmutation/), a comprehensive database for genomic mutations in cancer. We expect that correlations between driver mutations and the time evolution of tumour process will facilitate the interpretation of genomic information, to make them useful and applicable to clinical oncology.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"117 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124634396","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}
Siddhartha R. Jonnalagadda, G. Fiol, Richard Medlin, C. Weir, M. Fiszman, Javed Mostafa, Hongfang Liu
Online health knowledge resources contain answers to most of the information needs raised by clinicians in the course of care. However, significant barriers limit the use of these resources for decision-making, especially clinicians' lack of time. Existing solutions are less optimal when information needs cannot be met without substantial cognitive effort and time. Objectives: In this study, we assessed the feasibility of automatically generating knowledge summaries for a particular clinical topic composed of relevant sentences extracted from Medline citations. Methods: The proposed approach combines information retrieval and semantic information extraction techniques to identify relevant sentences from Medline abstracts. We assessed this approach in two case studies on the treatment alternatives for depression and Alzheimer's disease. Results: A total of 515 out of 564 (91.3%) sentences retrieved in the two case studies were relevant to the topic of interest. About one third of the relevant sentences described factual knowledge or a study conclusion that can be used for supporting information needs at the point of care. Conclusions: Our proposed technical approach to helping clinicians meet their information needs is promising. The approach can be extended for other knowledge resources and information need types.
{"title":"Automatically Extracting Sentences from Medline Citations to Support Clinicians' Information Needs","authors":"Siddhartha R. Jonnalagadda, G. Fiol, Richard Medlin, C. Weir, M. Fiszman, Javed Mostafa, Hongfang Liu","doi":"10.1109/HISB.2012.22","DOIUrl":"https://doi.org/10.1109/HISB.2012.22","url":null,"abstract":"Online health knowledge resources contain answers to most of the information needs raised by clinicians in the course of care. However, significant barriers limit the use of these resources for decision-making, especially clinicians' lack of time. Existing solutions are less optimal when information needs cannot be met without substantial cognitive effort and time. Objectives: In this study, we assessed the feasibility of automatically generating knowledge summaries for a particular clinical topic composed of relevant sentences extracted from Medline citations. Methods: The proposed approach combines information retrieval and semantic information extraction techniques to identify relevant sentences from Medline abstracts. We assessed this approach in two case studies on the treatment alternatives for depression and Alzheimer's disease. Results: A total of 515 out of 564 (91.3%) sentences retrieved in the two case studies were relevant to the topic of interest. About one third of the relevant sentences described factual knowledge or a study conclusion that can be used for supporting information needs at the point of care. Conclusions: Our proposed technical approach to helping clinicians meet their information needs is promising. The approach can be extended for other knowledge resources and information need types.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130007283","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}
T. Lingren, Louise Deléger, Katalin Molnár, Haijun Zhai, J. Meinzen-Derr, M. Kaiser, Laura Stoutenborough, Qi Li, I. Solti
In this study our aim was to present a series of experiments to evaluate the impact of pre-annotation: (1) on the speed of manual annotation of clinical notes and clinical trial announcements; and (2) test for potential bias if pre-annotation is utilized. The gold standard was 900 clinical trial announcements from clinicaltrials.gov website and 1655 clinical notes annotated for diagnoses, signs, symptoms, UMLS CUI and SNOMED CT codes. Two dictionary-based methods were used to pre-annotate the text. Annotation time savings ranged from 2.89% to 29.1% per entity. The pre-annotation did not reduce the IAA or annotator performance but reduced the time to annotate in every experiment. Dictionary-based pre-annotation is a feasible and practical method to reduce cost of annotation without introducing bias in the process.
{"title":"Pre-annotating Clinical Notes and Clinical Trial Announcements for Gold Standard Corpus Development: Evaluating the Impact on Annotation Speed and Potential Bias","authors":"T. Lingren, Louise Deléger, Katalin Molnár, Haijun Zhai, J. Meinzen-Derr, M. Kaiser, Laura Stoutenborough, Qi Li, I. Solti","doi":"10.1109/HISB.2012.33","DOIUrl":"https://doi.org/10.1109/HISB.2012.33","url":null,"abstract":"In this study our aim was to present a series of experiments to evaluate the impact of pre-annotation: (1) on the speed of manual annotation of clinical notes and clinical trial announcements; and (2) test for potential bias if pre-annotation is utilized. The gold standard was 900 clinical trial announcements from clinicaltrials.gov website and 1655 clinical notes annotated for diagnoses, signs, symptoms, UMLS CUI and SNOMED CT codes. Two dictionary-based methods were used to pre-annotate the text. Annotation time savings ranged from 2.89% to 29.1% per entity. The pre-annotation did not reduce the IAA or annotator performance but reduced the time to annotate in every experiment. Dictionary-based pre-annotation is a feasible and practical method to reduce cost of annotation without introducing bias in the process.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125415417","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}
To help diagnose the early stage of lung cancer, this paper studies pulmonary nodule and blood vessel detection and segmentation. Owing to the fact that variation in the shape and number of pulmonary blood vessels would reveal the progress of lung cancer, automatic segmentation of pulmonary nodules and blood vessels is desirable for chest computer-aided diagnosis (CAD) systems. The proposed algorithm is composed of four steps: pre-segmentation, structure enhancement, active evolution, and refinement. Through the initial extraction of 3D region growing, the line structure of vessel and blob-like structure of nodule would be enhanced by multi-scale filtering. In particular, the active evolution is devoted to the maximum likelihood estimation with a vessel energy function (VEF) of intensity, gradient, and structure. The VEF aims to shape a precise extraction by adapting all the cue distribution along the vessel region from nodules. Furthermore, a radius-variable sphere model is adopted to refine the contour with the smoothness of radius alone the centerline of the blood vessel. Finally, the proposed scheme is sufficiently evaluated to exceed the existing techniques on lung image database consortium (LIDC) database and DICOM images.
{"title":"Pulmonary Blood Vessels and Nodules Segmentation via Vessel Energy Function and Radius-Variable Sphere Model","authors":"Qingxiang Zhu, H. Xiong, Xiaoqian Jiang","doi":"10.1109/HISB.2012.46","DOIUrl":"https://doi.org/10.1109/HISB.2012.46","url":null,"abstract":"To help diagnose the early stage of lung cancer, this paper studies pulmonary nodule and blood vessel detection and segmentation. Owing to the fact that variation in the shape and number of pulmonary blood vessels would reveal the progress of lung cancer, automatic segmentation of pulmonary nodules and blood vessels is desirable for chest computer-aided diagnosis (CAD) systems. The proposed algorithm is composed of four steps: pre-segmentation, structure enhancement, active evolution, and refinement. Through the initial extraction of 3D region growing, the line structure of vessel and blob-like structure of nodule would be enhanced by multi-scale filtering. In particular, the active evolution is devoted to the maximum likelihood estimation with a vessel energy function (VEF) of intensity, gradient, and structure. The VEF aims to shape a precise extraction by adapting all the cue distribution along the vessel region from nodules. Furthermore, a radius-variable sphere model is adopted to refine the contour with the smoothness of radius alone the centerline of the blood vessel. Finally, the proposed scheme is sufficiently evaluated to exceed the existing techniques on lung image database consortium (LIDC) database and DICOM images.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116213274","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}
In this post-genomic era it is clear that the sum of the cellular gene expression state determines the cellular phenotypes. The challenge we now face is to keep up the bioinformatics analysis and to understand the genome blueprint. In our lab we applied and developed bioinformatics and systems biology tools for deciphering cancer and stem cell transcriptome data. Cancer stem-like cells were isolated as colonospheres from primary colon cancer tissues and cell lines and characterized their gene expression patterns and genetic networks. Expanded colon cancer spheres had many features of cancer stem cells, including chemoresistance and radioresistance, the ability to initiate tumor formation, and activation of epithelial-mesenchymal transition (EMT). SNAIL, an activator of EMT, was expressed at high levels by CRC colonospheres. smRNA-Seq and genetic network analyses revealed that SNAIL activates genes and microRNAs, such as IL8 and miR-146a, in colonospheres. Blocking IL-8 or miR-146a expression/activity disrupted SNAIL-induced stem cell-like features of colonospheres. Strategies that disrupt the SNAIL-IL8 and SNAIL-miR146a pathways can be developed to block tumor formation by colon cancer stem-like cells. We also applied our systems on brain tumor research. Atypical teratoid/rhabdoid tumor (AT/RT) is a highly malignant pediatric brain tumor often misdiagnosed as other embryonal brain tumors such as medulloblastoma (MB). AT/RT prognosis is much worse than MB, but the underlying mechanisms are unclear. We deciphered the miRNome patterns of AT/RT and MB by sequencing their small RNA fractions. Novel as well as known miRNAs were found deregulated in tumor cells. miR-221 and miR-222 are oncomiRs that can target several tumor suppressors. Further challenge will be to integrate RNA-seq information with systems biology and cloud computing tools.
{"title":"Small RNA Sequencing in microRNA Research","authors":"Hsei-Wei Wang","doi":"10.1109/HISB.2012.34","DOIUrl":"https://doi.org/10.1109/HISB.2012.34","url":null,"abstract":"In this post-genomic era it is clear that the sum of the cellular gene expression state determines the cellular phenotypes. The challenge we now face is to keep up the bioinformatics analysis and to understand the genome blueprint. In our lab we applied and developed bioinformatics and systems biology tools for deciphering cancer and stem cell transcriptome data. Cancer stem-like cells were isolated as colonospheres from primary colon cancer tissues and cell lines and characterized their gene expression patterns and genetic networks. Expanded colon cancer spheres had many features of cancer stem cells, including chemoresistance and radioresistance, the ability to initiate tumor formation, and activation of epithelial-mesenchymal transition (EMT). SNAIL, an activator of EMT, was expressed at high levels by CRC colonospheres. smRNA-Seq and genetic network analyses revealed that SNAIL activates genes and microRNAs, such as IL8 and miR-146a, in colonospheres. Blocking IL-8 or miR-146a expression/activity disrupted SNAIL-induced stem cell-like features of colonospheres. Strategies that disrupt the SNAIL-IL8 and SNAIL-miR146a pathways can be developed to block tumor formation by colon cancer stem-like cells. We also applied our systems on brain tumor research. Atypical teratoid/rhabdoid tumor (AT/RT) is a highly malignant pediatric brain tumor often misdiagnosed as other embryonal brain tumors such as medulloblastoma (MB). AT/RT prognosis is much worse than MB, but the underlying mechanisms are unclear. We deciphered the miRNome patterns of AT/RT and MB by sequencing their small RNA fractions. Novel as well as known miRNAs were found deregulated in tumor cells. miR-221 and miR-222 are oncomiRs that can target several tumor suppressors. Further challenge will be to integrate RNA-seq information with systems biology and cloud computing tools.","PeriodicalId":375089,"journal":{"name":"2012 IEEE Second International Conference on Healthcare Informatics, Imaging and Systems Biology","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2012-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125607462","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：