期刊
2016 IEEE 13TH INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING (ISBI)
卷 -, 期 -, 页码 1173-1176出版社
IEEE
DOI: 10.1109/ISBI.2016.7493475
关键词
Lung cancer; Survival prediction; Integration Framework; Genetic Data; Pathological Image
In this paper, we have proposed a framework for lung cancer survival prediction by integrating genetic data and pathological images. Since molecular profiles and pathological images reveal complementary information on tumor characteristics, the integration will benefit the survival analysis. The gene expression signatures are processed using Model-Based Background Correction method. A robust cell detection and segmentation method is applied to segment each individual cell from pathological images to extract the image features. Based on the cell detection results, a set of extensive features are extracted using efficient geometry and texture descriptors. The supervised principal component regression model is fitted to evaluate the proposed framework. Experimental results demonstrate strong prediction power of the statistical model built from the integration of genetic data and pathological images compared with using only one of the two types of data alone.
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