A Generative Model for Brain Tumor Segmentation in Multi-Modal Images

摘要：

We introduce a generative probabilistic model for segmentation of tumors in multi-dimensional images. The model allows for different tumor boundaries in each channel, reflecting difference in tumor appearance across modalities.We augment a probabilistic atlas of healthy tissue priors with a latent atlas of the lesion and derive the estimation algorithm to extract tumor boundaries and the latent atlas from the image data. We present experiments on 25 glioma patient data sets, demonstrating significant improvement over the traditional multivariate tumor segmentation.

作者: Bjoern H.Menze Koen Van Leemput Danial Lashkari Marc-Andre Weber Nicholas Ayache Polina Golland

作者单位: Computer Science and Artificial Intelligence Laboratory,Massachusetts Institute of Technology, USAAs Computer Science and Artificial Intelligence Laboratory,Massachusetts Institute of Technology, USA R Computer Science and Artificial Intelligence Laboratory,Massachusetts Institute of Technology, USA Diagnostic Radiology, Heidelberg University Hospital, Germany Asclepios Research Project, INRIA Sophia-Antipolis, France Computer Science and Artificial Intelligence Laboratory, Massachusetts Institute of Technology, USA

会议类型: 国际会议

会议名称: The 13th International Conference on Medical Image Computing and Computer-Assisted Intervention(第13届医学影像计算与计算机辅助介入国际会议 MICCAI 2010)

会议地点: 北京

会议语种:英文

页码: 151-159

在线出版日期: 2010-09-01（万方平台首次上网日期，不代表论文的发表时间）