RT Journal Article
SR Electronic
T1 Comprehensive analysis of lung cancer pathology images to discover tumor shape features that predict survival outcome
JF bioRxiv
FD Cold Spring Harbor Laboratory
SP 274332
DO 10.1101/274332
A1 Shidan Wang
A1 Alyssa Chen
A1 Lin Yang
A1 Ling Cai
A1 Yang Xie
A1 Junya Fujimoto
A1 Adi Gazdar
A1 Guanghua Xiao
YR 2018
UL http://biorxiv.org/content/early/2018/03/02/274332.abstract
AB Pathology slide images capture tumor histomorphological details in high resolution. However, manual detection and characterization of tumor regions in pathology slides is labor intensive and subjective. Using a deep convolutional neural network (CNN), we developed an automated tumor region recognition system for lung cancer pathology slides. From the identified regions, we extracted 22 well-defined tumor shape features and found that 15 of them were significantly associated with patient survival outcome in lung adenocarcinoma patients from the National Lung Screening Trial. A tumor shape-based prognostic model was developed and validated in an independent patient cohort (n=389). The predicted high-risk group had significantly worse survival than the low-risk group (p value = 0.0029). Predicted risk group serves as an independent prognostic factor (high-risk vs. low-risk, hazard ratio = 2.25, 95% CI 1.34-3.77, p value = 0.0022) after adjusting for age, gender, smoking status, and stage. This study provides new insights into the relationship between tumor shape and patient prognosis.