Marek Wodzinski, A. Skalski, P. Kedzierawski, T. Kuszewski
{"title":"Application of B-splines FFD image registration in breast cancer radiotherapy planning","authors":"Marek Wodzinski, A. Skalski, P. Kedzierawski, T. Kuszewski","doi":"10.1109/IWSSIP.2017.7965578","DOIUrl":null,"url":null,"abstract":"Localization of a resected tumor lodge after a breast cancer surgery is a challenging task for the radiotherapy planning. Currently, the problem is handled by creating radiation dose margins, which take into account the lack of information about lodge localization. We propose an alternative approach based on the image registration techniques, that aims to align computed tomography 3D images before and after surgery and to estimate the resected tumor lodge localization. The rigid registration and free-form deformations based on B-Splines are evaluated with additional 3D images preprocessing and analytical gradient calculation to speed-up the registration process. The correctness and usefulness are evaluated using target registration error, visual inspection, and physician opinion. The results demonstrate that the usage of image registration techniques can improve the quality of the radiotherapy planning.","PeriodicalId":302860,"journal":{"name":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","volume":"275 ","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2017-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2017 International Conference on Systems, Signals and Image Processing (IWSSIP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/IWSSIP.2017.7965578","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 5
Abstract
Localization of a resected tumor lodge after a breast cancer surgery is a challenging task for the radiotherapy planning. Currently, the problem is handled by creating radiation dose margins, which take into account the lack of information about lodge localization. We propose an alternative approach based on the image registration techniques, that aims to align computed tomography 3D images before and after surgery and to estimate the resected tumor lodge localization. The rigid registration and free-form deformations based on B-Splines are evaluated with additional 3D images preprocessing and analytical gradient calculation to speed-up the registration process. The correctness and usefulness are evaluated using target registration error, visual inspection, and physician opinion. The results demonstrate that the usage of image registration techniques can improve the quality of the radiotherapy planning.