N. Ferreira, F. Caramelo, A. Liborio, M. Botelho, S. Carvalho, L. Mendes, R. Faustino, M. Ribeiro, A. Rodrigues
{"title":"迈向核医学中详细的全身群分析","authors":"N. Ferreira, F. Caramelo, A. Liborio, M. Botelho, S. Carvalho, L. Mendes, R. Faustino, M. Ribeiro, A. Rodrigues","doi":"10.1109/ENBENG.2011.6026069","DOIUrl":null,"url":null,"abstract":"In this work we describe a project that is currently in progress. We point out the key ideas of the project explaining the pros and cons of the chosen approach. A clinic with image facilities produces a huge amount of information per year that, most of the times, is underused since exams are analyzed individually without the comparison between individuals or the exploration of features of a certain population. Data mining would be recommendable in these cases, however image databases are difficult to analyze because they depend on robust and automatic methods of segmentation and classification. We propose a method for segmenting nuclear medicine images (whole body PET scans) based on a classification method. The segmented regions are also labeled and used as additional features for a structured database.","PeriodicalId":206538,"journal":{"name":"1st Portuguese Biomedical Engineering Meeting","volume":"1 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2011-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"3","resultStr":"{\"title\":\"Towards detailed whole body group analysis in nuclear medicine\",\"authors\":\"N. Ferreira, F. Caramelo, A. Liborio, M. Botelho, S. Carvalho, L. Mendes, R. Faustino, M. Ribeiro, A. Rodrigues\",\"doi\":\"10.1109/ENBENG.2011.6026069\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In this work we describe a project that is currently in progress. We point out the key ideas of the project explaining the pros and cons of the chosen approach. A clinic with image facilities produces a huge amount of information per year that, most of the times, is underused since exams are analyzed individually without the comparison between individuals or the exploration of features of a certain population. Data mining would be recommendable in these cases, however image databases are difficult to analyze because they depend on robust and automatic methods of segmentation and classification. We propose a method for segmenting nuclear medicine images (whole body PET scans) based on a classification method. The segmented regions are also labeled and used as additional features for a structured database.\",\"PeriodicalId\":206538,\"journal\":{\"name\":\"1st Portuguese Biomedical Engineering Meeting\",\"volume\":\"1 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2011-03-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"3\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"1st Portuguese Biomedical Engineering Meeting\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/ENBENG.2011.6026069\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"1st Portuguese Biomedical Engineering Meeting","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ENBENG.2011.6026069","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Towards detailed whole body group analysis in nuclear medicine
In this work we describe a project that is currently in progress. We point out the key ideas of the project explaining the pros and cons of the chosen approach. A clinic with image facilities produces a huge amount of information per year that, most of the times, is underused since exams are analyzed individually without the comparison between individuals or the exploration of features of a certain population. Data mining would be recommendable in these cases, however image databases are difficult to analyze because they depend on robust and automatic methods of segmentation and classification. We propose a method for segmenting nuclear medicine images (whole body PET scans) based on a classification method. The segmented regions are also labeled and used as additional features for a structured database.