摘要
Objective： The standard treatment for patients with locally advanced gastric cancer has relied on perioperativeradio-chemotherapy or chemotherapy and surgery. The aim of this study was to investigate the wealth of radiomicsfor pre-treatment computed tomography （CT） in the prediction of the pathological response of locally advancedgastric cancer with preoperative chemotherapy.Methods： Thirty consecutive patients with CT-staged Ⅱ/Ⅲ gastric cancer receiving neoadjuvant chemotherapywere enrolled in this study between December 2014 and March 2017. All patients underwent upper abdominal CTduring the unenhanced, late arterial phase （AP） and portal venous phase （PP） before the administration ofneoadjuvant chemotherapy. In total, 19,985 radiomics features were extracted in the AP and PP for each patient.Four methods were adopted during feature selection and eight methods were used in the process of building theclassifier model. Thirty-two combinations of feature selection and classification methods were examined. Receiveroperating characteristic （ROC） curves were used to evaluate the capability of each combination of feature selectionand classification method to predict a non-good response （non-GR） based on tumor regression grade （TRG）.Results： The mean area under the curve （AUC） ranged from 0.194 to 0.621 in the AP, and from 0.455 to 0.722in the PP, according to different combinations of feature selection and the classification methods. There was onlyone cross-combination machine-learning method indicating a relatively higher AUC （〉0.600） in the AP, while 12cross-combination machine-learning methods presented relatively higher AUCs （all 〉0.600） in the PP. The featureselection method adopted by a filter based on linear discriminant analysis ＋ classifier of random forest achieved asignificantly prognostic performance in the PP （AUC, 0.722~0.108; accuracy, 0.793; sensitivity, 0.636; specificity,0.889; Z=2.039; P=0.041）.Conclusions： It is possible to predict non-GR after neoadiuvant chemotherapy in locally advanced gastriccancers based on the radiomics of CT.
Objective： The standard treatment for patients with locally advanced gastric cancer has relied on perioperativeradio-chemotherapy or chemotherapy and surgery. The aim of this study was to investigate the wealth of radiomicsfor pre-treatment computed tomography （CT） in the prediction of the pathological response of locally advancedgastric cancer with preoperative chemotherapy.Methods： Thirty consecutive patients with CT-staged Ⅱ/Ⅲ gastric cancer receiving neoadjuvant chemotherapywere enrolled in this study between December 2014 and March 2017. All patients underwent upper abdominal CTduring the unenhanced, late arterial phase （AP） and portal venous phase （PP） before the administration ofneoadjuvant chemotherapy. In total, 19,985 radiomics features were extracted in the AP and PP for each patient.Four methods were adopted during feature selection and eight methods were used in the process of building theclassifier model. Thirty-two combinations of feature selection and classification methods were examined. Receiveroperating characteristic （ROC） curves were used to evaluate the capability of each combination of feature selectionand classification method to predict a non-good response （non-GR） based on tumor regression grade （TRG）.Results： The mean area under the curve （AUC） ranged from 0.194 to 0.621 in the AP, and from 0.455 to 0.722in the PP, according to different combinations of feature selection and the classification methods. There was onlyone cross-combination machine-learning method indicating a relatively higher AUC （〉0.600） in the AP, while 12cross-combination machine-learning methods presented relatively higher AUCs （all 〉0.600） in the PP. The featureselection method adopted by a filter based on linear discriminant analysis ＋ classifier of random forest achieved asignificantly prognostic performance in the PP （AUC, 0.722~0.108; accuracy, 0.793; sensitivity, 0.636; specificity,0.889; Z=2.039; P=0.041）.Conclusions： It is possible to predict non-GR after neoadiuvant chemotherapy in locally advanced gastriccancers based on the radiomics of CT.
基金
supported by the National Key Research and Development Program of China (No.2017YFC1309100)
the National Natural Scientific Foundation of China (No. 81771912)
the Applied Basic Research Projects of Yunnan Province, China [No. 2015FB071 and No. 2017FE467-084]
