Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer

We aimed to develop a deep convolutional neural network (DCNN) model based on computed tomography (CT) images for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC). A total of 544 patients with AGC were retrospectively enrolled. Seventy-nine patients w...

Full description

Bibliographic Details
Main Authors: Zixing Huang, Dan Liu, Xinzu Chen, Du He, Pengxin Yu, Baiyun Liu, Bing Wu, Jiankun Hu, Bin Song
Format: Article
Language:English
Published: Frontiers Media S.A. 2020-11-01
Series:Frontiers in Oncology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fonc.2020.601869/full
_version_ 1818458157259685888
author Zixing Huang
Dan Liu
Xinzu Chen
Du He
Pengxin Yu
Baiyun Liu
Bing Wu
Jiankun Hu
Bin Song
author_facet Zixing Huang
Dan Liu
Xinzu Chen
Du He
Pengxin Yu
Baiyun Liu
Bing Wu
Jiankun Hu
Bin Song
author_sort Zixing Huang
collection DOAJ
description We aimed to develop a deep convolutional neural network (DCNN) model based on computed tomography (CT) images for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC). A total of 544 patients with AGC were retrospectively enrolled. Seventy-nine patients were confirmed with OPM during surgery or laparoscopy. CT images collected during the initial visit were randomly split into a training cohort and a testing cohort for DCNN model development and performance evaluation, respectively. A conventional clinical model using multivariable logistic regression was also developed to estimate the pretest probability of OPM in patients with gastric cancer. The DCNN model showed an AUC of 0.900 (95% CI: 0.851–0.953), outperforming the conventional clinical model (AUC = 0.670, 95% CI: 0.615–0.739; p < 0.001). The proposed DCNN model demonstrated the diagnostic detection of occult PM, with a sensitivity of 81.0% and specificity of 87.5% using the cutoff value according to the Youden index. Our study shows that the proposed deep learning algorithm, developed with CT images, may be used as an effective tool to preoperatively diagnose OPM in AGC.
first_indexed 2024-12-14T22:54:00Z
format Article
id doaj.art-e602d0a286644f80a3306d334b9baabf
institution Directory Open Access Journal
issn 2234-943X
language English
last_indexed 2024-12-14T22:54:00Z
publishDate 2020-11-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Oncology
spelling doaj.art-e602d0a286644f80a3306d334b9baabf2022-12-21T22:44:37ZengFrontiers Media S.A.Frontiers in Oncology2234-943X2020-11-011010.3389/fonc.2020.601869601869Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric CancerZixing Huang0Dan Liu1Xinzu Chen2Du He3Pengxin Yu4Baiyun Liu5Bing Wu6Jiankun Hu7Bin Song8Department of Radiology, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Radiology, West China Hospital, Sichuan University, Chengdu, ChinaState Key Laboratory of Biotherapy, Department of Gastrointestinal Surgery and Laboratory of Gastric Cancer, Collaborative Innovation Center for Biotherapy, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Pathology, West China Hospital, Sichuan University, Chengdu, ChinaInstitute of Advanced Research, Infervision, Beijing, ChinaInstitute of Advanced Research, Infervision, Beijing, ChinaDepartment of Radiology, West China Hospital, Sichuan University, Chengdu, ChinaState Key Laboratory of Biotherapy, Department of Gastrointestinal Surgery and Laboratory of Gastric Cancer, Collaborative Innovation Center for Biotherapy, West China Hospital, Sichuan University, Chengdu, ChinaDepartment of Radiology, West China Hospital, Sichuan University, Chengdu, ChinaWe aimed to develop a deep convolutional neural network (DCNN) model based on computed tomography (CT) images for the preoperative diagnosis of occult peritoneal metastasis (OPM) in advanced gastric cancer (AGC). A total of 544 patients with AGC were retrospectively enrolled. Seventy-nine patients were confirmed with OPM during surgery or laparoscopy. CT images collected during the initial visit were randomly split into a training cohort and a testing cohort for DCNN model development and performance evaluation, respectively. A conventional clinical model using multivariable logistic regression was also developed to estimate the pretest probability of OPM in patients with gastric cancer. The DCNN model showed an AUC of 0.900 (95% CI: 0.851–0.953), outperforming the conventional clinical model (AUC = 0.670, 95% CI: 0.615–0.739; p < 0.001). The proposed DCNN model demonstrated the diagnostic detection of occult PM, with a sensitivity of 81.0% and specificity of 87.5% using the cutoff value according to the Youden index. Our study shows that the proposed deep learning algorithm, developed with CT images, may be used as an effective tool to preoperatively diagnose OPM in AGC.https://www.frontiersin.org/articles/10.3389/fonc.2020.601869/fullstomach neoplasmsperitoneal neoplasmsdeep learningtomographyx-ray computedneural networks
spellingShingle Zixing Huang
Dan Liu
Xinzu Chen
Du He
Pengxin Yu
Baiyun Liu
Bing Wu
Jiankun Hu
Bin Song
Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer
Frontiers in Oncology
stomach neoplasms
peritoneal neoplasms
deep learning
tomography
x-ray computed
neural networks
title Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer
title_full Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer
title_fullStr Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer
title_full_unstemmed Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer
title_short Deep Convolutional Neural Network Based on Computed Tomography Images for the Preoperative Diagnosis of Occult Peritoneal Metastasis in Advanced Gastric Cancer
title_sort deep convolutional neural network based on computed tomography images for the preoperative diagnosis of occult peritoneal metastasis in advanced gastric cancer
topic stomach neoplasms
peritoneal neoplasms
deep learning
tomography
x-ray computed
neural networks
url https://www.frontiersin.org/articles/10.3389/fonc.2020.601869/full
work_keys_str_mv AT zixinghuang deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT danliu deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT xinzuchen deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT duhe deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT pengxinyu deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT baiyunliu deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT bingwu deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT jiankunhu deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer
AT binsong deepconvolutionalneuralnetworkbasedoncomputedtomographyimagesforthepreoperativediagnosisofoccultperitonealmetastasisinadvancedgastriccancer