Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627857
K. Drechsler, S. Meixner, C. O. Laura, S. Wesarg
Validation methods used in literature to evaluate vessel segmentation algorithms suffer to a great extent from objectiveness, reliability and reproducibility. This is because almost each group has its own way to evaluate an algorithms. In this paper, an extendable standardized evaluation framework for quantitative validation of vessel segmentation algorithms is presented. As ground-truth, it uses a physical vascular model to simulate the growth of vessels within organ masks extracted from clinical CT datasets. A set of image- and graph- based evaluation metrics are calculated to analyze various aspects of the algorithms under study. Using the proposed framework helps to meet the aforementioned quality criteria.
{"title":"A framework for validation of vessel segmentation algorithms","authors":"K. Drechsler, S. Meixner, C. O. Laura, S. Wesarg","doi":"10.1109/CBMS.2013.6627857","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627857","url":null,"abstract":"Validation methods used in literature to evaluate vessel segmentation algorithms suffer to a great extent from objectiveness, reliability and reproducibility. This is because almost each group has its own way to evaluate an algorithms. In this paper, an extendable standardized evaluation framework for quantitative validation of vessel segmentation algorithms is presented. As ground-truth, it uses a physical vascular model to simulate the growth of vessels within organ masks extracted from clinical CT datasets. A set of image- and graph- based evaluation metrics are calculated to analyze various aspects of the algorithms under study. Using the proposed framework helps to meet the aforementioned quality criteria.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"77215438","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627858
Gonçalo Monteiro, A. Correia, Joao Leite-Moreira
The purpose of this research was to assess the quality of information related to oral cancer available on the WWW for the Portuguese speaking population. A web search was done using Google. Structure and content of the websites were assessed with different informatic tools. 27 websites were selected according to defined criteria. Results showed that it seems to exist a lack of quantity and quality information available in Portuguese language.
{"title":"Quality evaluation of websites with information on oral cancer in Portuguese language","authors":"Gonçalo Monteiro, A. Correia, Joao Leite-Moreira","doi":"10.1109/CBMS.2013.6627858","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627858","url":null,"abstract":"The purpose of this research was to assess the quality of information related to oral cancer available on the WWW for the Portuguese speaking population. A web search was done using Google. Structure and content of the websites were assessed with different informatic tools. 27 websites were selected according to defined criteria. Results showed that it seems to exist a lack of quantity and quality information available in Portuguese language.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91407073","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627876
R. Bahati, F. Gwadry-Sridhar
This paper describes an approach utilizing both data analysis and visualization to help diabetes patients improve medication compliance. Through information visualization tools, we aim to provide feedback to patients to encourage behavior change. The system has two core building blocks: (1) Data analysis combining several statistical and machine learning models, founded under different principles and assumptions, into a single meta-model for predicting compliance behavior. The aim is to create superior models for behavior prediction - knowledge that can then be translated into patient-centered decision-support tools. (2) Incorporating data analysis and visualization enabling datasets to be turned into knowledge utilities that can intelligently interact with participants by alerting them to any interesting correlations within the data. Such tools could provide feedback indicating, for example, a high-risk to medication non-compliance behavior in which case appropriate resources could be directed to those who need help the most.
{"title":"Turning datasets into patient-centered knowledge utilities","authors":"R. Bahati, F. Gwadry-Sridhar","doi":"10.1109/CBMS.2013.6627876","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627876","url":null,"abstract":"This paper describes an approach utilizing both data analysis and visualization to help diabetes patients improve medication compliance. Through information visualization tools, we aim to provide feedback to patients to encourage behavior change. The system has two core building blocks: (1) Data analysis combining several statistical and machine learning models, founded under different principles and assumptions, into a single meta-model for predicting compliance behavior. The aim is to create superior models for behavior prediction - knowledge that can then be translated into patient-centered decision-support tools. (2) Incorporating data analysis and visualization enabling datasets to be turned into knowledge utilities that can intelligently interact with participants by alerting them to any interesting correlations within the data. Such tools could provide feedback indicating, for example, a high-risk to medication non-compliance behavior in which case appropriate resources could be directed to those who need help the most.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86978697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627822
Mohammad H. Keyhani, Wissam El Hakimi, S. Wesarg
CT or MR image data is typically anisotropic. But, it is desirable to base image processing as well as diagnosis on isotropic image data. In this work, we propose a novel method for correcting anisotropy of 3D image data sets by employing the recurrence of small 2D patches across different scales. We base our method on previous work dealing with super-resolution of single natural 2D images, show the applicability of that approach also to medical images, and extend it to a 3D solution for anisotropy correction. Our results show that the image quality can be significantly improved. For clinical CT and MRI data, we present feedback from the clinical end user.
{"title":"Anisotropy correction of medical image data employing patch similarity","authors":"Mohammad H. Keyhani, Wissam El Hakimi, S. Wesarg","doi":"10.1109/CBMS.2013.6627822","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627822","url":null,"abstract":"CT or MR image data is typically anisotropic. But, it is desirable to base image processing as well as diagnosis on isotropic image data. In this work, we propose a novel method for correcting anisotropy of 3D image data sets by employing the recurrence of small 2D patches across different scales. We base our method on previous work dealing with super-resolution of single natural 2D images, show the applicability of that approach also to medical images, and extend it to a 3D solution for anisotropy correction. Our results show that the image quality can be significantly improved. For clinical CT and MRI data, we present feedback from the clinical end user.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85115658","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627867
V. Nováček, A. Naseer
We introduce KI2NA-LHC (Linked Health Care) a system for data and knowledge integration in life sciences. In particular, we focus on linking clinical resources (electronic patient records) with scientific documents and data (research articles, biomedical ontologies and databases). Our motivation is two-fold. Firstly, we aim to instantly provide scientific context of particular patient cases for clinicians in order for them to propose treatments in a more informed way. Secondly, we want to build a technical infrastructure for researchers that will allow them to semi-automatically formulate and evaluate their hypothesis against longitudinal patient data. This paper outlines the proposed system and its services in a broader context of KI2NA, an ongoing collaboration between the DERI research institute and Fujitsu Laboratories.
{"title":"Linking the scientific and clinical data with KI2NA-LHC — An outline","authors":"V. Nováček, A. Naseer","doi":"10.1109/CBMS.2013.6627867","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627867","url":null,"abstract":"We introduce KI2NA-LHC (Linked Health Care) a system for data and knowledge integration in life sciences. In particular, we focus on linking clinical resources (electronic patient records) with scientific documents and data (research articles, biomedical ontologies and databases). Our motivation is two-fold. Firstly, we aim to instantly provide scientific context of particular patient cases for clinicians in order for them to propose treatments in a more informed way. Secondly, we want to build a technical infrastructure for researchers that will allow them to semi-automatically formulate and evaluate their hypothesis against longitudinal patient data. This paper outlines the proposed system and its services in a broader context of KI2NA, an ongoing collaboration between the DERI research institute and Fujitsu Laboratories.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79726622","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627762
Marcelo Ponciano-Silva, Juliana P. Souza, P. Bugatti, M. Bedo, D. S. Kaster, R. Braga, A. Bellucci, P. M. A. Marques, C. Traina, A. Traina
Content-based image retrieval systems are employed in several areas. One of the most prominent area is the medical field, due to the huge volume of digital images daily generated in healthcare institutions employed for decision making. There are several works applying CBIR techniques over medical images. However, the great majority of them do not verify whether the systems are actually considered by the specialists as a pontential aid in a real environment. In order to fill this research void in the literature, this work explores user experiments in a CBIR system involving resident physicians and radiologists. To do so, we developed a CBIR system according to requirements provided by the specialists and employed a methodology to analyze the effectiveness of the system for supporting them in clinical routine. The methodology aims at evaluating the system's impact in the user's decision, inquiring the specialists about the image classification and their degree of certainty in different situations using the system. By analyzing the obtained results we can argue that the proposed methodology joined with our medical CBIR system presented a high acceptance and viability rate regarding the radiologists interests in the clinical practice domain, providing a novel approach to analyze CBIR systems under realistic conditions.
{"title":"Does a CBIR system really impact decisions of physicians in a clinical environment?","authors":"Marcelo Ponciano-Silva, Juliana P. Souza, P. Bugatti, M. Bedo, D. S. Kaster, R. Braga, A. Bellucci, P. M. A. Marques, C. Traina, A. Traina","doi":"10.1109/CBMS.2013.6627762","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627762","url":null,"abstract":"Content-based image retrieval systems are employed in several areas. One of the most prominent area is the medical field, due to the huge volume of digital images daily generated in healthcare institutions employed for decision making. There are several works applying CBIR techniques over medical images. However, the great majority of them do not verify whether the systems are actually considered by the specialists as a pontential aid in a real environment. In order to fill this research void in the literature, this work explores user experiments in a CBIR system involving resident physicians and radiologists. To do so, we developed a CBIR system according to requirements provided by the specialists and employed a methodology to analyze the effectiveness of the system for supporting them in clinical routine. The methodology aims at evaluating the system's impact in the user's decision, inquiring the specialists about the image classification and their degree of certainty in different situations using the system. By analyzing the obtained results we can argue that the proposed methodology joined with our medical CBIR system presented a high acceptance and viability rate regarding the radiologists interests in the clinical practice domain, providing a novel approach to analyze CBIR systems under realistic conditions.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82732860","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627825
Ana González, Beatriz Remeseiro, M. Ortega, M. G. Penedo, Pablo Charlón
In this work Optical Coherence Tomography (OCT) retinal images are automatically processed to detect the presence of cysts. The methodology is composed by three phases: region of interest where cysts will be searched is delimited; a watershed algorithm is applied to find all the possible regions in the image which might conform cystic structures; finally, texture analysis is performed in each region from previous phase to final classification. Results show that accuracy achieved with this method is over 80%.
{"title":"Automatic cyst detection in OCT retinal images combining region flooding and texture analysis","authors":"Ana González, Beatriz Remeseiro, M. Ortega, M. G. Penedo, Pablo Charlón","doi":"10.1109/CBMS.2013.6627825","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627825","url":null,"abstract":"In this work Optical Coherence Tomography (OCT) retinal images are automatically processed to detect the presence of cysts. The methodology is composed by three phases: region of interest where cysts will be searched is delimited; a watershed algorithm is applied to find all the possible regions in the image which might conform cystic structures; finally, texture analysis is performed in each region from previous phase to final classification. Results show that accuracy achieved with this method is over 80%.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91065632","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627782
Romulo Bourget Novas, V. Fazan, J. C. Felipe
The morphometric analysis of myelinated fibers is known to produce relevant information for the evaluation of several phenomena, which range from nerve demyelization/remyelization to the aging process. This analysis can be achieved manually or using computer-based image analysis systems which vary to a certain degree of automation. However, systems which are manual or semi-automated are extremely laborious, highly tedious and time-consuming. Therefore, the aim of this paper is the proposal, implementation and evaluation of a computational tool capable of automatically performing the morphometry of myelinated fibers. We have implemented and tested various methods for the segmentation of images from different types of nerve, which present differences in form, color and size. Then, we implemented an algorithm capable of extracting the required morphometric features. The developed tool has shown maximum area overlap accuracy of 83.1% and sensitivity of 90.7% for our database. The tool has widespread potential in experimental and clinical applications eliminating many of the tedious and time-consuming tasks associated with nerve morphometry.
{"title":"Fully-automatic tool for morphometric analysis of myelinated fibers","authors":"Romulo Bourget Novas, V. Fazan, J. C. Felipe","doi":"10.1109/CBMS.2013.6627782","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627782","url":null,"abstract":"The morphometric analysis of myelinated fibers is known to produce relevant information for the evaluation of several phenomena, which range from nerve demyelization/remyelization to the aging process. This analysis can be achieved manually or using computer-based image analysis systems which vary to a certain degree of automation. However, systems which are manual or semi-automated are extremely laborious, highly tedious and time-consuming. Therefore, the aim of this paper is the proposal, implementation and evaluation of a computational tool capable of automatically performing the morphometry of myelinated fibers. We have implemented and tested various methods for the segmentation of images from different types of nerve, which present differences in form, color and size. Then, we implemented an algorithm capable of extracting the required morphometric features. The developed tool has shown maximum area overlap accuracy of 83.1% and sensitivity of 90.7% for our database. The tool has widespread potential in experimental and clinical applications eliminating many of the tedious and time-consuming tasks associated with nerve morphometry.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82001954","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627773
D. Vieira, J. Linden, J. Hollmén, J. Suni
Many studies have been performed in predicting periodontal diseases based on genetic information, dental images or patients habits but few have yet used dental visits records. This paper proposes a methodology based on Random Forest to classify the periodontal disease condition of patients and a way to assess the most important features that lead to a successful classification. We investigate three problematic issues found in dental care records: noise, class imbalance and concept drift and propose solutions to overcome them by respectively detecting and removing noise, under-sampling and only considering recent data. Experiments performed on records from Finnish public hospitals of two cities had good classification results and feature importance was able to detect dentists with poor performance with respect to diagnosis and treatment application.
{"title":"Challenges in predicting community periodontal index from hospital dental care records","authors":"D. Vieira, J. Linden, J. Hollmén, J. Suni","doi":"10.1109/CBMS.2013.6627773","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627773","url":null,"abstract":"Many studies have been performed in predicting periodontal diseases based on genetic information, dental images or patients habits but few have yet used dental visits records. This paper proposes a methodology based on Random Forest to classify the periodontal disease condition of patients and a way to assess the most important features that lead to a successful classification. We investigate three problematic issues found in dental care records: noise, class imbalance and concept drift and propose solutions to overcome them by respectively detecting and removing noise, under-sampling and only considering recent data. Experiments performed on records from Finnish public hospitals of two cities had good classification results and feature importance was able to detect dentists with poor performance with respect to diagnosis and treatment application.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79601193","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2013-06-20DOI: 10.1109/CBMS.2013.6627805
F. Maiorana
Medical images are a key element in disease prevention, diagnosis, treatment and patient follow-up. The advent of 3D imaging equipment has increased the amount of medical images produced daily and software tools that are able to search and retrieve images are becoming popular, however improvements are still needed to close the gaps between the expert and the computer image representation. This article presents a software tool that integrates a Content Based Image Retrieval (CBIR) system with an implicit relevance feedback system that uses data gathered from an eye tracker. The gaze point can be used to infer regions of interest in the query image thus allowing for searches based on global or local features, and to steer the retrieval process of relevant images. A preliminary evaluation of the system is presented and discussed.
{"title":"A medical content based image retrieval system with eye tracking relevance feedback","authors":"F. Maiorana","doi":"10.1109/CBMS.2013.6627805","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627805","url":null,"abstract":"Medical images are a key element in disease prevention, diagnosis, treatment and patient follow-up. The advent of 3D imaging equipment has increased the amount of medical images produced daily and software tools that are able to search and retrieve images are becoming popular, however improvements are still needed to close the gaps between the expert and the computer image representation. This article presents a software tool that integrates a Content Based Image Retrieval (CBIR) system with an implicit relevance feedback system that uses data gathered from an eye tracker. The gaze point can be used to infer regions of interest in the query image thus allowing for searches based on global or local features, and to steer the retrieval process of relevant images. A preliminary evaluation of the system is presented and discussed.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75595358","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：