Pub Date : 2013-10-10DOI: 10.1109/CBMS.2013.6627793
F. Isgrò, F. Pane, G. Porzio, R. Pennarola, E. Pennarola
Nailfold capillary microscopy examination has been used for long time as a non invasive technique for the diagnosis of connective tissue diseases. Computer systems helping the physician during the examination have been developed, but they still require a certain level of manual intervention. A first problem that need yet to be solved is the segmentation of the capillaries in the video sequence. In this paper we propose a software pipeline for the segmentation of the capillaries from video sequences of the nailfold. The core of the segmentation proposed is the combination into a single segmentation map of the output of a battery of simple segmentation algorithms, based only on the grey levels. The system has been tested on a set of data, for which a ground truth segmentation was obtained manually, reporting satisfactory results. We advocate that the inclusion in the battery of classifiers of ad-hoc segmentation algorithms present in the literature will produce a reliable system, that can be used by physicians.
{"title":"Segmentation of nailfold capillaries from microscopy video sequences","authors":"F. Isgrò, F. Pane, G. Porzio, R. Pennarola, E. Pennarola","doi":"10.1109/CBMS.2013.6627793","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627793","url":null,"abstract":"Nailfold capillary microscopy examination has been used for long time as a non invasive technique for the diagnosis of connective tissue diseases. Computer systems helping the physician during the examination have been developed, but they still require a certain level of manual intervention. A first problem that need yet to be solved is the segmentation of the capillaries in the video sequence. In this paper we propose a software pipeline for the segmentation of the capillaries from video sequences of the nailfold. The core of the segmentation proposed is the combination into a single segmentation map of the output of a battery of simple segmentation algorithms, based only on the grey levels. The system has been tested on a set of data, for which a ground truth segmentation was obtained manually, reporting satisfactory results. We advocate that the inclusion in the battery of classifiers of ad-hoc segmentation algorithms present in the literature will produce a reliable system, that can be used by physicians.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75366063","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 : 2013-10-10DOI: 10.1109/CBMS.2013.6627859
M. Haindl, Václav Remes
An efficient method for X-ray digital mammogram multi-view enhancement based on the underlying two-dimensional adaptive causal autoregressive texture model is presented. The method locally predicts breast tissue texture from multi-view mammograms and enhances breast tissue abnormalities, such as the sign of a developing cancer, using the estimated model prediction error. The mammo-gram enhancement is based on the cross-prediction error of mutually registered left and right breasts mammograms or on the single-view model prediction error if both breasts' mammograms are not available.
{"title":"Efficient textural model-based mammogram enhancement","authors":"M. Haindl, Václav Remes","doi":"10.1109/CBMS.2013.6627859","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627859","url":null,"abstract":"An efficient method for X-ray digital mammogram multi-view enhancement based on the underlying two-dimensional adaptive causal autoregressive texture model is presented. The method locally predicts breast tissue texture from multi-view mammograms and enhances breast tissue abnormalities, such as the sign of a developing cancer, using the estimated model prediction error. The mammo-gram enhancement is based on the cross-prediction error of mutually registered left and right breasts mammograms or on the single-view model prediction error if both breasts' mammograms are not available.","PeriodicalId":20519,"journal":{"name":"Proceedings of the 26th IEEE International Symposium on Computer-Based Medical Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2013-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78465082","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.2013.6627880
Márcia Ito, L. R. D. Silva, Eduardo Rodrigues de Camargo, Tarcio Roberto Carvalho de Lima
In this paper, we present an application design that enables the exchange of information between two databases located in different environments, seeking interoperability between the systems of health care using these bases. The application is based on agent technology using the JADE platform. The application's agents can establish a communication, request data, send and receive records database for XML, read this code and make updates to the database.
{"title":"Communication between agents for interoperability in area health service platform using JADE","authors":"Márcia Ito, L. R. D. Silva, Eduardo Rodrigues de Camargo, Tarcio Roberto Carvalho de Lima","doi":"10.1109/CBMS.2013.6627880","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627880","url":null,"abstract":"In this paper, we present an application design that enables the exchange of information between two databases located in different environments, seeking interoperability between the systems of health care using these bases. The application is based on agent technology using the JADE platform. The application's agents can establish a communication, request data, send and receive records database for XML, read this code and make updates to the database.","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":"73062723","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.2013.6627865
Bernd Münzer, Klaus Schöffmann, L. Böszörményi
The actual content of endoscopic videos is typically limited to a circular area in the image center. This area has a dynamic position and size and is surrounded by a dark, but noisy border. In this paper we present a novel algorithm that (1) classifies which frames of an endoscopic video feature the circular content area and (2) determines its exact position and size, if present. This information is very useful for improving the performance of subsequent analysis techniques. It can also be used for more efficient video encoding and economic printing of still images in findings and reports. The evaluation shows that the proposed method is very accurate, robust and efficient in terms of runtime.
{"title":"Detection of circular content area in endoscopic videos","authors":"Bernd Münzer, Klaus Schöffmann, L. Böszörményi","doi":"10.1109/CBMS.2013.6627865","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627865","url":null,"abstract":"The actual content of endoscopic videos is typically limited to a circular area in the image center. This area has a dynamic position and size and is surrounded by a dark, but noisy border. In this paper we present a novel algorithm that (1) classifies which frames of an endoscopic video feature the circular content area and (2) determines its exact position and size, if present. This information is very useful for improving the performance of subsequent analysis techniques. It can also be used for more efficient video encoding and economic printing of still images in findings and reports. The evaluation shows that the proposed method is very accurate, robust and efficient in terms of runtime.","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":"77587282","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.2013.6627821
P. Leijdekkers, V. Gay, F. Wong
Autism Spectrum Disorder (ASD) is estimated to affect one in eighty-eight children and many mobile apps are available from Google Play or Apple store to help these children and their carer. Our research into apps for autistic children identified that none of the apps use the full potential offered by mobile technology and sensors to overcome one of autistic children's main difficulty: the identification and expression of emotions. This paper describes a mobile app called CaptureMyEmotion that enables autistic children to take photos, videos or sounds, and at the same time senses their arousal level using a wireless sensor. It also allows the child to comment on their emotion at the time of capture. The app has the potential to help autistic children improve their emotions learning based on their own pictures, videos or sounds. It gives the carer a means to discuss the identification and expression of emotions.
{"title":"CaptureMyEmotion: A mobile app to improve emotion learning for autistic children using sensors","authors":"P. Leijdekkers, V. Gay, F. Wong","doi":"10.1109/CBMS.2013.6627821","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627821","url":null,"abstract":"Autism Spectrum Disorder (ASD) is estimated to affect one in eighty-eight children and many mobile apps are available from Google Play or Apple store to help these children and their carer. Our research into apps for autistic children identified that none of the apps use the full potential offered by mobile technology and sensors to overcome one of autistic children's main difficulty: the identification and expression of emotions. This paper describes a mobile app called CaptureMyEmotion that enables autistic children to take photos, videos or sounds, and at the same time senses their arousal level using a wireless sensor. It also allows the child to comment on their emotion at the time of capture. The app has the potential to help autistic children improve their emotions learning based on their own pictures, videos or sounds. It gives the carer a means to discuss the identification and expression of emotions.","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":"85624891","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.2013.6627839
C. Lupascu, D. Tegolo, F. Bellavia, Cesare Valenti
Accurate retinal image registration is essential to track the evolution of eye-related diseases. We propose a semiautomatic method based on features relying upon retinal graphs for temporal registration of retinal images. The features represent straight lines connecting vascular landmarks on the retina vascular tree: bifurcations, branchings, crossings, end points. In the built retinal graph, one straight line between two vascular landmarks indicates that they are connected by a vascular segment in the original retinal image. The locations of the landmarks are manually extracted to avoid the information loss due to errors in a retinal vessels segmentation algorithms. A straight line model is designed to compute a similarity measure to quantify the line matching between images. From the set of matching lines, corresponding points are extracted and a global transformation is computed. The performance of the registration method is evaluated in the absence of ground truth using the cumulative inverse consistency error (CICE).
{"title":"Semi-automatic registration of retinal images based on line matching approach","authors":"C. Lupascu, D. Tegolo, F. Bellavia, Cesare Valenti","doi":"10.1109/CBMS.2013.6627839","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627839","url":null,"abstract":"Accurate retinal image registration is essential to track the evolution of eye-related diseases. We propose a semiautomatic method based on features relying upon retinal graphs for temporal registration of retinal images. The features represent straight lines connecting vascular landmarks on the retina vascular tree: bifurcations, branchings, crossings, end points. In the built retinal graph, one straight line between two vascular landmarks indicates that they are connected by a vascular segment in the original retinal image. The locations of the landmarks are manually extracted to avoid the information loss due to errors in a retinal vessels segmentation algorithms. A straight line model is designed to compute a similarity measure to quantify the line matching between images. From the set of matching lines, corresponding points are extracted and a global transformation is computed. The performance of the registration method is evaluated in the absence of ground truth using the cumulative inverse consistency error (CICE).","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":"82567633","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.2013.6627852
M. Molinara, C. Marrocco, F. Tortorella
When mammograms are analyzed through a Computer Aided Diagnosis (CAD) system the presence of the pectoral muscle can affect the results of the automatic detection of breast lesions. This problem is particularly evident in mediolateral oblique (MLO) view where the pectoral muscle appears as a high intensity region across the margin of the mammogram. An automatic identification of the pectoral muscle is an essential step because of its similar characteristics with the abnormal tissue that can interfere with the detection of suspicious regions or bias the estimation of breast tissue density. This paper presents a new approach for the detection of pectoral muscle in MLO view of the mammo-graphic images. It is based on a preprocessing step useful to normalize the image and highlight the boundary between the muscle and the mammary tissue. A subsequent step including edge detection and regression via RANSAC provides the final contour of the muscle area. The experiments performed on a standard data set show very encouraging results.
{"title":"Automatic segmentation of the pectoral muscle in mediolateral oblique mammograms","authors":"M. Molinara, C. Marrocco, F. Tortorella","doi":"10.1109/CBMS.2013.6627852","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627852","url":null,"abstract":"When mammograms are analyzed through a Computer Aided Diagnosis (CAD) system the presence of the pectoral muscle can affect the results of the automatic detection of breast lesions. This problem is particularly evident in mediolateral oblique (MLO) view where the pectoral muscle appears as a high intensity region across the margin of the mammogram. An automatic identification of the pectoral muscle is an essential step because of its similar characteristics with the abnormal tissue that can interfere with the detection of suspicious regions or bias the estimation of breast tissue density. This paper presents a new approach for the detection of pectoral muscle in MLO view of the mammo-graphic images. It is based on a preprocessing step useful to normalize the image and highlight the boundary between the muscle and the mammary tissue. A subsequent step including edge detection and regression via RANSAC provides the final contour of the muscle area. The experiments performed on a standard data set show very encouraging results.","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":"81330491","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.2013.6627761
Mehnaz Adnan, J. Warren, Martin Orr
Discharge Summaries contains vocabulary that is difficult to understand for consumers. We used semantic annotation in SemLink to dynamically generate synonyms and hyperlinks to appropriate Internet resources for difficult terms in discharge summary text to make the text more comprehensible to consumers. This paper describes our semantic annotation approach and evaluates our automatic hyperlink generation algorithm in terms of success in locating web pages to hyperlink for difficult terms in the Clinical Management sections of a corpus of 200 discharge summary texts. The system achieved 95% success in hyperlinking topically relevant web resources to the difficult terms; 83% of the hyperlinks could be restricted to resources of reading grade-level 8 or less with no reduction in relevance. In the context of discharge summaries we find automated hyperlinking to provide a good level of performance in leveraging openly available resources to aid consumer interpretation of difficult terms.
{"title":"SemLink — Dynamic generation of hyperlinks to enhance patient readability of discharge summaries","authors":"Mehnaz Adnan, J. Warren, Martin Orr","doi":"10.1109/CBMS.2013.6627761","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627761","url":null,"abstract":"Discharge Summaries contains vocabulary that is difficult to understand for consumers. We used semantic annotation in SemLink to dynamically generate synonyms and hyperlinks to appropriate Internet resources for difficult terms in discharge summary text to make the text more comprehensible to consumers. This paper describes our semantic annotation approach and evaluates our automatic hyperlink generation algorithm in terms of success in locating web pages to hyperlink for difficult terms in the Clinical Management sections of a corpus of 200 discharge summary texts. The system achieved 95% success in hyperlinking topically relevant web resources to the difficult terms; 83% of the hyperlinks could be restricted to resources of reading grade-level 8 or less with no reduction in relevance. In the context of discharge summaries we find automated hyperlinking to provide a good level of performance in leveraging openly available resources to aid consumer interpretation of difficult terms.","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":"78875800","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.2013.6627837
Wissam El Hakimi, S. Wesarg
The resolution and accuracy of medical images play an important role for early medical diagnosis, since a wrong resolution may increase the risk of making a poor decision. In practice, magnetic resonance and computed tomography images often suffer from anisotropic resolution, so that the image quality is high only within the slices. In this paper we propose a further development of a previously presented super-resolution approach, to reconstruct isotropic high resolution images from only two orthogonal low resolution data sets. Thereby, voxel uncertainties, which arise during image acquisition and preprocessing, are considered. Furthermore, an adapted inpainting method is introduced to ensure a better initial estimation of missing data. Reconstruction quality is also improved, by combining regional and local information. Experiments on synthetic and clinical data sets reveal significant improvement of image quality and accuracy, yielding better results when compared with conventional reconstruction approaches.
{"title":"Accurate super-resolution reconstruction for CT and MR images","authors":"Wissam El Hakimi, S. Wesarg","doi":"10.1109/CBMS.2013.6627837","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627837","url":null,"abstract":"The resolution and accuracy of medical images play an important role for early medical diagnosis, since a wrong resolution may increase the risk of making a poor decision. In practice, magnetic resonance and computed tomography images often suffer from anisotropic resolution, so that the image quality is high only within the slices. In this paper we propose a further development of a previously presented super-resolution approach, to reconstruct isotropic high resolution images from only two orthogonal low resolution data sets. Thereby, voxel uncertainties, which arise during image acquisition and preprocessing, are considered. Furthermore, an adapted inpainting method is introduced to ensure a better initial estimation of missing data. Reconstruction quality is also improved, by combining regional and local information. Experiments on synthetic and clinical data sets reveal significant improvement of image quality and accuracy, yielding better results when compared with conventional reconstruction approaches.","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":"86456217","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.2013.6627774
K. Davis, R. C. Price, J. Facelli
Public health data could be used to assist with public health surveillance and decision support. However, in most cases data has to be transformed into a coded format to make it computable and amiable to quasi real time analytical processing. Natural language processing (NLP) systems, which aim to accurately extract and encode biomedical information in a standard format, have a great potential in surveillance. NLP methods are complex, difficult, and expensive to implement. Its implementation, in most cases, is well beyond the technical expertise and resources available in Public Health organizations. Making NLP systems available as a service can greatly improve access to this methodology by public health officials and potentially enhance disease surveillance. MetaMap is a comprehensive biomedical NLP system, and has been shown to perform well for numerous applications. We describe how we have implemented MetaMap as a grid service to make it available to the public health community.
{"title":"Implementing public health analytical services: Grid enabling of MetaMap","authors":"K. Davis, R. C. Price, J. Facelli","doi":"10.1109/CBMS.2013.6627774","DOIUrl":"https://doi.org/10.1109/CBMS.2013.6627774","url":null,"abstract":"Public health data could be used to assist with public health surveillance and decision support. However, in most cases data has to be transformed into a coded format to make it computable and amiable to quasi real time analytical processing. Natural language processing (NLP) systems, which aim to accurately extract and encode biomedical information in a standard format, have a great potential in surveillance. NLP methods are complex, difficult, and expensive to implement. Its implementation, in most cases, is well beyond the technical expertise and resources available in Public Health organizations. Making NLP systems available as a service can greatly improve access to this methodology by public health officials and potentially enhance disease surveillance. MetaMap is a comprehensive biomedical NLP system, and has been shown to perform well for numerous applications. We describe how we have implemented MetaMap as a grid service to make it available to the public health community.","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":"90163802","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：