Retrospective Study
Copyright ©The Author(s) 2020. Published by Baishideng Publishing Group Inc. All rights reserved.
World J Gastroenterol. Sep 14, 2020; 26(34): 5156-5168
Published online Sep 14, 2020. doi: 10.3748/wjg.v26.i34.5156
Construction of a convolutional neural network classifier developed by computed tomography images for pancreatic cancer diagnosis
Han Ma, Zhong-Xin Liu, Jing-Jing Zhang, Feng-Tian Wu, Cheng-Fu Xu, Zhe Shen, Chao-Hui Yu, You-Ming Li
Han Ma, Jing-Jing Zhang, Cheng-Fu Xu, Zhe Shen, You-Ming Li, Department of Gastroenterology, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, Zhejiang Province, China
Zhong-Xin Liu, College of Computer Science and Technology, Zhejiang University, Hangzhou 310058, Zhejiang Province, China
Feng-Tian Wu, State Key Laboratory for Diagnosis and Treatment of Infectious Disease, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, Zhejiang Province, China
Chao-Hui Yu, Department of Gastroenterology, Zhejiang Provincial Key Laboratory of Pancreatic Disease, The First Affiliated Hospital, Zhejiang University School of Medicine, Hangzhou 310003, Zhejiang Province, China
Author contributions: Yu CH and Li YM conceived this project, and acted as guarantors; Ma H managed the data acquisition, data labeling, and contributed to the data analysis and manuscript drafting and editing, and experiments; Liu ZX developed the technology, implemented the deep-learning architectures, conducted the main experiments, and contributed to the data analysis and manuscript drafting and editing; Wu FT and Zhang JJ collected the data; Xu CF and Shen Z reviewed CT images and data labeling; Yu CH supervised the experiments, analyzed the results; all authors approved the final version of the manuscript.
Supported by the National Natural Science Foundation of China, No. 81900509; Fundamental Research Funds for the Central Universities, No. 2018XZZX002-10; and High-Level Talents Special Support Plan of Zhejiang Province (known as the Ten Thousand Talents Plan), No. ZJWR0108008.
Institutional review board statement: The study was reviewed and approved by the review board of Zhejiang University School of Medicine, Zhejiang Province, China.
Informed consent statement: Patients were not required to give written informed consent to the study because the analysis used anonymous clinical data that were obtained after each patient agreed to treatment by written consent.
Conflict-of-interest statement: We have no financial relationships to disclose.
Data sharing statement: Consent was not obtained, but the presented data are anonymized and risk of identification is low.
Open-Access: This article is an open-access article that was selected by an in-house editor and fully peer-reviewed by external reviewers. It is distributed in accordance with the Creative Commons Attribution NonCommercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/
Corresponding author: Chao-Hui Yu, MD, PhD, Chief Doctor, Professor, Department of Gastroenterology, Zhejiang Provincial Key Laboratory of Pancreatic Disease, The First Affiliated Hospital, Zhejiang University School of Medicine, No. 79 Qingchun Road, Hangzhou 310003, Zhejiang Province, China. zyyyych@zju.edu.cn
Received: April 20, 2020
Peer-review started: April 20, 2020
First decision: May 1, 2020
Revised: May 19, 2020
Accepted: August 26, 2020
Article in press: August 26, 2020
Published online: September 14, 2020
Processing time: 142 Days and 0.5 Hours
Core Tip

Core Tip: We developed a deep learning-based, computer-aided pancreatic ductal adenocarcinoma model trained on computed tomography images with pathologically confirmed pancreatic cancer in this retrospective study. We evaluated the approach used on the datasets in terms of both binary and ternary classifier, with the purposes of detecting and localizing masses, respectively. In the binary classifier, the performance of plain, arterial and venous phase had no difference. Its accuracy on plain scan was 95.47%, sensitivity was 91.58%, and specificity was 98.27%. In the ternary classifier, the arterial phase had the highest sensitivity in detecting cancer in the head of the pancreas among the three phases. Our model is suitable for screening purposes in pancreatic cancer detection.