Submit Manuscript  

Article Details


Cervical Cancer Metastasis and Recurrence Risk Prediction Based on Deep Convolutional Neural Network

Author(s):

Zixuan Ye, Yunxiang Zhang, Yuebin Liang, Jidong Lang, Xiaoli Zhang, Guoliang Zang, Dawei Yuan, Geng Tian, Mansheng Xiao* and Jialiang Yang *  

Abstract:


Background: Evaluating the risk of metastasis and recurrence of a cervical cancer patient is critical for appropriate adjuvant therapy. However, current risk assessment models usually involve the testing of tens to thousands of genes from patients’ tissue samples, which is expensive and time-consuming. Therefore, computer-aided diagnosis and prognosis prediction based on hematoxylin and eosin (H&E) pathological images have received much attention recently.

Objective: The prognosis of whether patients will have metastasis and recurrence can support accurate treatment for patients in advance and help reduce patient loss. It is also important for guiding treatment after surgery to be able to quickly and accurately predict the risk of metastasis and recurrence of a cervical cancer patient.

Method: To address this problem, we propose a hybrid method. Transfer learning is used to extract features, and it is combined with traditional machine learning in order to analyze and determine whether or not patients have the risks of metastasis and recurrence. First, the proposed model retrieved relevant patches using a color-based method from H&E pathological images, which were then subjected to image preprocessing steps such as image normalization and color homogenization. Based on the labeled patched images, the Xception model with good classification performance was selected, and deep features of patched pathological images were automatically extracted with transfer learning. After that, the extracted features were combined to train a random forest model to predict the label of a new patched image. Finally, a majority voting method was developed to predict the metastasis and recurrence risk of a patient based on the predictions of patched images from the whole-slide H&E image.

Results and Conclusion: In our experiment, the proposed model yielded an area under the receiver operating characteristic curve of 0.82 for the whole-slide image. The experimental results showed that the high-level features extracted by the deep convolutional neural network from the whole-slide image could be used to predict the risk of recurrence and metastasis after surgical resection and help identify patients who might receive additional benefit from adjuvant therapy.

Keywords:

cervical cancer, recurrence and metastasis, H&E pathological images, convolutional neural network, random forest, transfer learning

Affiliation:

School of Computer, Hunan University of Technology, Zhuzhou Hunan 412007, Weifang People’s Hospital, Shandong, 261000, Geneis (Beijing) Co. Ltd., Beijing 100102, Geneis (Beijing) Co. Ltd., Beijing 100102, School of Computer, Hunan University of Technology, Zhuzhou Hunan 412007, Geneis (Beijing) Co. Ltd., Beijing 100102, Geneis (Beijing) Co. Ltd., Beijing 100102, School of Computer, Hunan University of Technology, Zhuzhou Hunan 412007, School of Computer, Hunan University of Technology, Zhuzhou Hunan 412007, School of Computer, Hunan University of Technology, Zhuzhou Hunan 412007



Full Text Inquiry