A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancer

PurposeTo evaluate the potential of radiomics approach for predicting No. 14v station lymph node metastasis (14vM) in gastric cancer (GC).MethodsThe contrast enhanced CT (CECT) images with corresponding clinical information of 288 GC patients were retrospectively collected. Patients were separated i...

Full description

Saved in:
Bibliographic Details
Main Authors: Tingting Ma, Mengran Zhao, Xiangli Li, Xiangchao Song, Lingwei Wang, Zhaoxiang Ye
Format: Article
Language:English
Published: Frontiers Media S.A. 2024-10-01
Series:Frontiers in Medicine
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fmed.2024.1464632/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850283096016945152
author Tingting Ma
Tingting Ma
Tingting Ma
Tingting Ma
Tingting Ma
Mengran Zhao
Mengran Zhao
Mengran Zhao
Mengran Zhao
Mengran Zhao
Xiangli Li
Xiangchao Song
Xiangchao Song
Xiangchao Song
Xiangchao Song
Lingwei Wang
Lingwei Wang
Lingwei Wang
Lingwei Wang
Zhaoxiang Ye
Zhaoxiang Ye
Zhaoxiang Ye
Zhaoxiang Ye
author_facet Tingting Ma
Tingting Ma
Tingting Ma
Tingting Ma
Tingting Ma
Mengran Zhao
Mengran Zhao
Mengran Zhao
Mengran Zhao
Mengran Zhao
Xiangli Li
Xiangchao Song
Xiangchao Song
Xiangchao Song
Xiangchao Song
Lingwei Wang
Lingwei Wang
Lingwei Wang
Lingwei Wang
Zhaoxiang Ye
Zhaoxiang Ye
Zhaoxiang Ye
Zhaoxiang Ye
author_sort Tingting Ma
collection DOAJ
description PurposeTo evaluate the potential of radiomics approach for predicting No. 14v station lymph node metastasis (14vM) in gastric cancer (GC).MethodsThe contrast enhanced CT (CECT) images with corresponding clinical information of 288 GC patients were retrospectively collected. Patients were separated into training set (n = 202) and testing set (n = 86). A total of 1,316 radiomics feature were extracted from portal venous phase images of CECT. Seven machine learning (ML) algorithms including naïve Bayes (NB), k-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), random forest (RF), eXtreme gradient boosting (XGBoost) and support vector machine (SVM) were trained for development of optimal radiomics signature. A combined model was established by combining radiomics with important clinicopathological factors. The diagnostic ability of the signature and model were evaluated.ResultsLR algorithm was chosen for signature construction. The radiomics signature exhibited good discrimination accuracy of 14vM with AUCs of 0.83 in the training and 0.77 in the testing set. The risk of 14vM showed significant association with higher radiomics score. A combined model exhibited increased predictive ability and good agreement in the training (AUC = 0.87) and testing (AUC = 0.85) sets.ConclusionThe ML-based radiomics model provided a promising image biomarker for preoperative detection of 14vM and may help the surgeon to decide whether to add 14v dissection to lymphadenectomy.
format Article
id doaj-art-394a0ccd92a94d77a7fdb86ca3071045
institution OA Journals
issn 2296-858X
language English
publishDate 2024-10-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Medicine
spelling doaj-art-394a0ccd92a94d77a7fdb86ca30710452025-08-20T01:47:50ZengFrontiers Media S.A.Frontiers in Medicine2296-858X2024-10-011110.3389/fmed.2024.14646321464632A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancerTingting Ma0Tingting Ma1Tingting Ma2Tingting Ma3Tingting Ma4Mengran Zhao5Mengran Zhao6Mengran Zhao7Mengran Zhao8Mengran Zhao9Xiangli Li10Xiangchao Song11Xiangchao Song12Xiangchao Song13Xiangchao Song14Lingwei Wang15Lingwei Wang16Lingwei Wang17Lingwei Wang18Zhaoxiang Ye19Zhaoxiang Ye20Zhaoxiang Ye21Zhaoxiang Ye22Department of Radiology, Tianjin Cancer Hospital Airport Hospital, Tianjin, ChinaDepartment of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, ChinaNational Clinical Research Center for Cancer, Tianjin, ChinaTianjin’s Clinical Research Center for Cancer, Tianjin, ChinaThe Key Laboratory of Cancer Prevention and Therapy, Tianjin, ChinaDepartment of Radiology, Tianjin Cancer Hospital Airport Hospital, Tianjin, ChinaDepartment of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, ChinaNational Clinical Research Center for Cancer, Tianjin, ChinaTianjin’s Clinical Research Center for Cancer, Tianjin, ChinaThe Key Laboratory of Cancer Prevention and Therapy, Tianjin, ChinaHealth Management Center, Weifang People’s Hospital, Weifang, ChinaDepartment of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, ChinaNational Clinical Research Center for Cancer, Tianjin, ChinaTianjin’s Clinical Research Center for Cancer, Tianjin, ChinaThe Key Laboratory of Cancer Prevention and Therapy, Tianjin, ChinaDepartment of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, ChinaNational Clinical Research Center for Cancer, Tianjin, ChinaTianjin’s Clinical Research Center for Cancer, Tianjin, ChinaThe Key Laboratory of Cancer Prevention and Therapy, Tianjin, ChinaDepartment of Radiology, Tianjin Medical University Cancer Institute and Hospital, Tianjin, ChinaNational Clinical Research Center for Cancer, Tianjin, ChinaTianjin’s Clinical Research Center for Cancer, Tianjin, ChinaThe Key Laboratory of Cancer Prevention and Therapy, Tianjin, ChinaPurposeTo evaluate the potential of radiomics approach for predicting No. 14v station lymph node metastasis (14vM) in gastric cancer (GC).MethodsThe contrast enhanced CT (CECT) images with corresponding clinical information of 288 GC patients were retrospectively collected. Patients were separated into training set (n = 202) and testing set (n = 86). A total of 1,316 radiomics feature were extracted from portal venous phase images of CECT. Seven machine learning (ML) algorithms including naïve Bayes (NB), k-nearest neighbor (KNN), decision tree (DT), logistic regression (LR), random forest (RF), eXtreme gradient boosting (XGBoost) and support vector machine (SVM) were trained for development of optimal radiomics signature. A combined model was established by combining radiomics with important clinicopathological factors. The diagnostic ability of the signature and model were evaluated.ResultsLR algorithm was chosen for signature construction. The radiomics signature exhibited good discrimination accuracy of 14vM with AUCs of 0.83 in the training and 0.77 in the testing set. The risk of 14vM showed significant association with higher radiomics score. A combined model exhibited increased predictive ability and good agreement in the training (AUC = 0.87) and testing (AUC = 0.85) sets.ConclusionThe ML-based radiomics model provided a promising image biomarker for preoperative detection of 14vM and may help the surgeon to decide whether to add 14v dissection to lymphadenectomy.https://www.frontiersin.org/articles/10.3389/fmed.2024.1464632/fullradiomicscomputed tomographygastric cancerlymph node metastasis14v station
spellingShingle Tingting Ma
Tingting Ma
Tingting Ma
Tingting Ma
Tingting Ma
Mengran Zhao
Mengran Zhao
Mengran Zhao
Mengran Zhao
Mengran Zhao
Xiangli Li
Xiangchao Song
Xiangchao Song
Xiangchao Song
Xiangchao Song
Lingwei Wang
Lingwei Wang
Lingwei Wang
Lingwei Wang
Zhaoxiang Ye
Zhaoxiang Ye
Zhaoxiang Ye
Zhaoxiang Ye
A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancer
Frontiers in Medicine
radiomics
computed tomography
gastric cancer
lymph node metastasis
14v station
title A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancer
title_full A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancer
title_fullStr A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancer
title_full_unstemmed A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancer
title_short A machine learning based radiomics approach for predicting No. 14v station lymph node metastasis in gastric cancer
title_sort machine learning based radiomics approach for predicting no 14v station lymph node metastasis in gastric cancer
topic radiomics
computed tomography
gastric cancer
lymph node metastasis
14v station
url https://www.frontiersin.org/articles/10.3389/fmed.2024.1464632/full
work_keys_str_mv AT tingtingma amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xianglili amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye amachinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT tingtingma machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT mengranzhao machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xianglili machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT xiangchaosong machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT lingweiwang machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer
AT zhaoxiangye machinelearningbasedradiomicsapproachforpredictingno14vstationlymphnodemetastasisingastriccancer