{"title":"个性化椎体模型开发","authors":"Sándor Bazsó, Á. Viola, B. Benyó","doi":"10.1109/INES52918.2021.9512908","DOIUrl":null,"url":null,"abstract":"Elderly people frequently suffer from osteoporosis, increasing the risk of vertebral injuries, especially compression vertebral fracture. Geometric modelling can help identifying the parameters of the vertebral body and can be used to analyse and improve the vertebral fracture correction interventions.In this study we will suggest a customisable geometrical model of the vertebral body able to describe all the segments of the spinal column. Beside the customizable model, several optimisation methods are introduced to make easy the definition of the patient specific geometric model.The accuracy of the suggested modelling methodology is evaluated on a public dataset of 20 vertebrae. The Dice coefficient was in average 91.9 ± 2.56%, the Hausdorff distance was 2.28±0.67 mm on the 95% of the model which is considered to be very accurate compared to results published in papers dealing with similar problems. The applicability of the proposed model for clinical studies has been also validated.","PeriodicalId":427652,"journal":{"name":"2021 IEEE 25th International Conference on Intelligent Engineering Systems (INES)","volume":"94 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2021-07-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":"{\"title\":\"Personalisable vertebral body model development\",\"authors\":\"Sándor Bazsó, Á. Viola, B. Benyó\",\"doi\":\"10.1109/INES52918.2021.9512908\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Elderly people frequently suffer from osteoporosis, increasing the risk of vertebral injuries, especially compression vertebral fracture. Geometric modelling can help identifying the parameters of the vertebral body and can be used to analyse and improve the vertebral fracture correction interventions.In this study we will suggest a customisable geometrical model of the vertebral body able to describe all the segments of the spinal column. Beside the customizable model, several optimisation methods are introduced to make easy the definition of the patient specific geometric model.The accuracy of the suggested modelling methodology is evaluated on a public dataset of 20 vertebrae. The Dice coefficient was in average 91.9 ± 2.56%, the Hausdorff distance was 2.28±0.67 mm on the 95% of the model which is considered to be very accurate compared to results published in papers dealing with similar problems. The applicability of the proposed model for clinical studies has been also validated.\",\"PeriodicalId\":427652,\"journal\":{\"name\":\"2021 IEEE 25th International Conference on Intelligent Engineering Systems (INES)\",\"volume\":\"94 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2021-07-07\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"1\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"2021 IEEE 25th International Conference on Intelligent Engineering Systems (INES)\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1109/INES52918.2021.9512908\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"2021 IEEE 25th International Conference on Intelligent Engineering Systems (INES)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/INES52918.2021.9512908","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
Elderly people frequently suffer from osteoporosis, increasing the risk of vertebral injuries, especially compression vertebral fracture. Geometric modelling can help identifying the parameters of the vertebral body and can be used to analyse and improve the vertebral fracture correction interventions.In this study we will suggest a customisable geometrical model of the vertebral body able to describe all the segments of the spinal column. Beside the customizable model, several optimisation methods are introduced to make easy the definition of the patient specific geometric model.The accuracy of the suggested modelling methodology is evaluated on a public dataset of 20 vertebrae. The Dice coefficient was in average 91.9 ± 2.56%, the Hausdorff distance was 2.28±0.67 mm on the 95% of the model which is considered to be very accurate compared to results published in papers dealing with similar problems. The applicability of the proposed model for clinical studies has been also validated.