CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma

PurposeTo develop and validate a machine learning classifier based on multidetector computed tomography (MDCT), for the preoperative prediction of tumor–stroma ratio (TSR) expression in patients with pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsIn this retrospective study, 227 patien...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Yinghao Meng, Hao Zhang, Qi Li, Fang Liu, Xu Fang, Jing Li, Jieyu Yu, Xiaochen Feng, Mengmeng Zhu, Na Li, Guodong Jing, Li Wang, Chao Ma, Jianping Lu, Yun Bian, Chengwei Shao
Formato:	article
Lenguaje:	EN
Publicado:	Frontiers Media S.A. 2021
Materias:	pancreatic neoplasm carcinoma prognosis tumor-stroma ratio multidetector computed tomography radiomics Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
Acceso en línea:	https://doaj.org/article/97a9274c27c04a598c8643a72ca74334
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:97a9274c27c04a598c8643a72ca74334
record_format	dspace
spelling	oai:doaj.org-article:97a9274c27c04a598c8643a72ca743342021-11-08T07:38:04ZCT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma2234-943X10.3389/fonc.2021.707288https://doaj.org/article/97a9274c27c04a598c8643a72ca743342021-11-01T00:00:00Zhttps://www.frontiersin.org/articles/10.3389/fonc.2021.707288/fullhttps://doaj.org/toc/2234-943XPurposeTo develop and validate a machine learning classifier based on multidetector computed tomography (MDCT), for the preoperative prediction of tumor–stroma ratio (TSR) expression in patients with pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsIn this retrospective study, 227 patients with PDAC underwent an MDCT scan and surgical resection. We quantified the TSR by using hematoxylin and eosin staining and extracted 1409 arterial and portal venous phase radiomics features for each patient, respectively. Moreover, we used the least absolute shrinkage and selection operator logistic regression algorithm to reduce the features. The extreme gradient boosting (XGBoost) was developed using a training set consisting of 167 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 60 consecutive patients, admitted between January 2018 and April 2018. We determined the XGBoost classifier performance based on its discriminative ability, calibration, and clinical utility.ResultsWe observed low and high TSR in 91 (40.09%) and 136 (59.91%) patients, respectively. A log-rank test revealed significantly longer survival for patients in the TSR-low group than those in the TSR-high group. The prediction model revealed good discrimination in the training (area under the curve [AUC]= 0.93) and moderate discrimination in the validation set (AUC= 0.63). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 94.06%, 81.82%, 0.89, 0.89, and 0.90, respectively, those for the validation set were 85.71%, 48.00%, 0.70, 0.70, and 0.71, respectively.ConclusionsThe CT radiomics-based XGBoost classifier provides a potentially valuable noninvasive tool to predict TSR in patients with PDAC and optimize risk stratification.Yinghao MengYinghao MengHao ZhangQi LiFang LiuXu FangJing LiJieyu YuXiaochen FengMengmeng ZhuNa LiGuodong JingLi WangChao MaJianping LuYun BianChengwei ShaoFrontiers Media S.A.articlepancreatic neoplasmcarcinomaprognosistumor-stroma ratiomultidetector computed tomographyradiomicsNeoplasms. Tumors. Oncology. Including cancer and carcinogensRC254-282ENFrontiers in Oncology, Vol 11 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	pancreatic neoplasm carcinoma prognosis tumor-stroma ratio multidetector computed tomography radiomics Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282
spellingShingle	pancreatic neoplasm carcinoma prognosis tumor-stroma ratio multidetector computed tomography radiomics Neoplasms. Tumors. Oncology. Including cancer and carcinogens RC254-282 Yinghao Meng Yinghao Meng Hao Zhang Qi Li Fang Liu Xu Fang Jing Li Jieyu Yu Xiaochen Feng Mengmeng Zhu Na Li Guodong Jing Li Wang Chao Ma Jianping Lu Yun Bian Chengwei Shao CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma
description	PurposeTo develop and validate a machine learning classifier based on multidetector computed tomography (MDCT), for the preoperative prediction of tumor–stroma ratio (TSR) expression in patients with pancreatic ductal adenocarcinoma (PDAC).Materials and MethodsIn this retrospective study, 227 patients with PDAC underwent an MDCT scan and surgical resection. We quantified the TSR by using hematoxylin and eosin staining and extracted 1409 arterial and portal venous phase radiomics features for each patient, respectively. Moreover, we used the least absolute shrinkage and selection operator logistic regression algorithm to reduce the features. The extreme gradient boosting (XGBoost) was developed using a training set consisting of 167 consecutive patients, admitted between December 2016 and December 2017. The model was validated in 60 consecutive patients, admitted between January 2018 and April 2018. We determined the XGBoost classifier performance based on its discriminative ability, calibration, and clinical utility.ResultsWe observed low and high TSR in 91 (40.09%) and 136 (59.91%) patients, respectively. A log-rank test revealed significantly longer survival for patients in the TSR-low group than those in the TSR-high group. The prediction model revealed good discrimination in the training (area under the curve [AUC]= 0.93) and moderate discrimination in the validation set (AUC= 0.63). While the sensitivity, specificity, accuracy, positive predictive value, and negative predictive value for the training set were 94.06%, 81.82%, 0.89, 0.89, and 0.90, respectively, those for the validation set were 85.71%, 48.00%, 0.70, 0.70, and 0.71, respectively.ConclusionsThe CT radiomics-based XGBoost classifier provides a potentially valuable noninvasive tool to predict TSR in patients with PDAC and optimize risk stratification.
format	article
author	Yinghao Meng Yinghao Meng Hao Zhang Qi Li Fang Liu Xu Fang Jing Li Jieyu Yu Xiaochen Feng Mengmeng Zhu Na Li Guodong Jing Li Wang Chao Ma Jianping Lu Yun Bian Chengwei Shao
author_facet	Yinghao Meng Yinghao Meng Hao Zhang Qi Li Fang Liu Xu Fang Jing Li Jieyu Yu Xiaochen Feng Mengmeng Zhu Na Li Guodong Jing Li Wang Chao Ma Jianping Lu Yun Bian Chengwei Shao
author_sort	Yinghao Meng
title	CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma
title_short	CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma
title_full	CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma
title_fullStr	CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma
title_full_unstemmed	CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma
title_sort	ct radiomics and machine-learning models for predicting tumor-stroma ratio in patients with pancreatic ductal adenocarcinoma
publisher	Frontiers Media S.A.
publishDate	2021
url	https://doaj.org/article/97a9274c27c04a598c8643a72ca74334
work_keys_str_mv	AT yinghaomeng ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT yinghaomeng ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT haozhang ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT qili ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT fangliu ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT xufang ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT jingli ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT jieyuyu ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT xiaochenfeng ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT mengmengzhu ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT nali ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT guodongjing ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT liwang ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT chaoma ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT jianpinglu ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT yunbian ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma AT chengweishao ctradiomicsandmachinelearningmodelsforpredictingtumorstromaratioinpatientswithpancreaticductaladenocarcinoma
_version_	1718442929697062912

CT Radiomics and Machine-Learning Models for Predicting Tumor-Stroma Ratio in Patients With Pancreatic Ductal Adenocarcinoma

Ejemplares similares