{"title":"Breast Delineation using Active Contours to Facilitate Coregistration of Serial MRI Studies for Therapy Response Evaluation","authors":"R. Chittineni, M. Su, O. Nalcioglu","doi":"10.1109/ICIP.2007.4379571","DOIUrl":null,"url":null,"abstract":"MRI is the most accurate imaging modality to monitor response of breast cancer undergoing neoadjuvant chemotherapy, by comparing the tumor volume measured in follow up MRI, taken during the course of therapy, to its baseline value. Due to the deformable nature of the breast, its' shape in MR acquisitions taken in different studies varies significantly. If these images can be co-registered, the location of lesion in each study can be matched. Breast MR images collected often include large areas outside the breast, such as the thoracic region and surrounding air, which may pose a hindrance to registration algorithms. In this paper, we describe a segmentation algorithm to delineate the breast region from the chest by using the invariant, rigid structure such as the chest, as opposed to the use of varying breast outlines employed in currently available solutions. This ensures robustness and reproducibility of our algorithm.","PeriodicalId":131177,"journal":{"name":"2007 IEEE International Conference on Image Processing","volume":"17 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2007-11-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"5","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2007 IEEE International Conference on Image Processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICIP.2007.4379571","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
MRI is the most accurate imaging modality to monitor response of breast cancer undergoing neoadjuvant chemotherapy, by comparing the tumor volume measured in follow up MRI, taken during the course of therapy, to its baseline value. Due to the deformable nature of the breast, its' shape in MR acquisitions taken in different studies varies significantly. If these images can be co-registered, the location of lesion in each study can be matched. Breast MR images collected often include large areas outside the breast, such as the thoracic region and surrounding air, which may pose a hindrance to registration algorithms. In this paper, we describe a segmentation algorithm to delineate the breast region from the chest by using the invariant, rigid structure such as the chest, as opposed to the use of varying breast outlines employed in currently available solutions. This ensures robustness and reproducibility of our algorithm.