AUTHOR=Wu Zhijun , Wang Lin , Li Churong , Cai Yongcong , Liang Yuebin , Mo Xiaofei , Lu Qingqing , Dong Lixin , Liu Yonggang 

TITLE=DeepLRHE: A Deep Convolutional Neural Network Framework to Evaluate the Risk of Lung Cancer Recurrence and Metastasis From Histopathology Images

JOURNAL=Frontiers in Genetics

VOLUME=Volume 11 - 2020

YEAR=2020

URL=https://www.frontiersin.org/journals/genetics/articles/10.3389/fgene.2020.00768

DOI=10.3389/fgene.2020.00768

ISSN=1664-8021

ABSTRACT=Predicting the recurrence risk of lung cancer is critical for appropriate adjuvant therapy of lung cancer patients after surgical resection. However, traditional circulating tumor cell (CTC) detection or next generation sequencing-based methods are usually expensive and time-inefficient, which urges the need for more efficient computational models. In this study, we have established a convolutional neural network (CNN) framework called DeepLRHE to predict the recurrence risk of lung cancer through analyzing histopathology images. DeepLRHE consists of a few steps including automatic tumor region identification, image normalization, biomarker identification, and sample classification. In practice, we used 110 lung cancer samples downloaded from the TCGA database to train and validate our CNN model. The area under curve (AUC) for the 2-fold cross-validation is 0.85, suggesting a relative good prediction performance. Our study demonstrates that the features extracted from histopathology images could be well used to predict lung cancer recurrence after surgical resection, and help classify patients who should receive additional adjuvant therapy.