Improving tumor co-segmentation on PET-CT images with 3D co-matting
Improving tumor co-segmentation on PET-CT images with 3D co-matting
复制标题
DOI：
10.1109/isbi.2018.8363560
复制
发表时间：
2018-04
期刊：
影响因子：
--
通讯作者：
Zisha Zhong;Yusung Kim;Leixin Zhou;K. Plichta;B. Allen;J. Buatti;Xiaodong Wu
中科院分区：
文献类型：
--
作者：
Zisha Zhong;Yusung Kim;Leixin Zhou;K. Plichta;B. Allen;J. Buatti;Xiaodong Wu
正电子发射断层扫描和计算机断层扫描（PET-CT）在现代癌症治疗中起着至关重要的作用。在本文中，我们专注于自动肿瘤描绘PET-CT图像对。受共分割模型的启发，本文提出了一种新的三维图像共抠图技术，利用PET和CT的内部模态信息进行抠图。然后将所获得的共抠图结果并入基于图切割的PET-CT共分割框架中。我们对32个肺癌患者的PET-CT扫描对的对比实验表明，所提出的3D图像共抠图技术可以显着提高成本图像的质量的共同分割，导致高精度的肿瘤分割的PET和CT扫描对。
Positron emission tomography and computed tomography (PET-CT) plays a critically important role in modern cancer therapy. In this paper, we focus on automated tumor delineation on PET-CT image pairs. Inspired by co-segmentation model, we develop a novel 3D image co-matting technique making use of the inner-modality information of PET and CT for matting. The obtained co-matting results are then incorporated in the graph-cut based PET-CT co-segmentation framework. Our comparative experiments on 32 PET-CT scan pairs of lung cancer patients demonstrate that the proposed 3D image co-matting technique can significantly improve the quality of cost images for the co-segmentation, resulting in highly accurate tumor segmentation on both PET and CT scan pairs.