期刊
IEEE TRANSACTIONS ON NUCLEAR SCIENCE
卷 61, 期 1, 页码 218-224出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TNS.2013.2295975
关键词
Lung cancer; NSCLC; PET-CT; segmentation; tumor delineation
资金
- ARC
- PolyU grants
Accurate parenchymal lung tumor delineation with PET-CT can be problematic given the inherent tumor heterogeneity and proximity / involvement of extra-parenchymal tissue. In this paper, we propose a tumor delineation approach that is based on new tumor-background likelihood models in PET and CT. By incorporating the intensity downhill feature in PET as a distance cost into the background likelihood function of CT, our delineation method avoids leakage to structures with similar intensities on PET and CT, but at the same time follows the boundary definition in CT when it is distinct. We validated our method on 40 NSCLC patient datasets with manual delineation by three clinical experts. Our method achieved an average Dice's similarity coefficient (DSC) of 0.80 +/- 0.08 in the simple group, and 0.77 +/- 0.06 in the complex group. The t-test demonstrated that our method statistically outperformed the four other methods. Our method was able to delineate complex tumors that were located in close proximity to other structures with similar intensities.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据