The feasibility of CT-based radiomic nomogram for predicting histological classification of gastric cancer with different prognosis" />
CT影像组学预测胃癌不同预后组织学分型的可行性
The feasibility of CT-based radiomic nomogram for predicting histological classification of gastric cancer with different prognosis
CHEN Jian1,2, HUANG Hai-xia2, LU Chao3, WANG Xiao-xiao3, DING Yi1, SHAN Xiu-hong3#br#
(1. School of Medicine， Jiangsu University, Zhenjiang Jiangsu 212013; 2. Department of Radiology, the Fifth People′s Hospital of Zhenjiang, Zhenjiang Jiangsu 212004; 3. Department of Radiology, the Affiliated People′s Hospital of Jiangsu University, Zhenjiang Jiangsu 212002, China)
Abstract：Objective: To explore the application value of CTbased radiomic nomogram in predicting histological classification of gastric cancer with different prognosis. Methods: A total of 570 patients with gastric cancer were analyzed retrospectively，and divided into poor prognosis group and good prognosis group. All the samples were randomly divided into training cohort and validation cohort in the proportion of 2 ∶1. Standardized CT images were segmented by radiologists with ITKSNAP software manually.The clinical features with the greatest correlation with histological classification of gastric cancer were screened by univariate analysis, and used as parameters to construct the clinical feature model. Features are extracted from all segmented images, and minimum Redundancy Maximum Relevance (mRMR), Least Absolute Shrinkage and Selection Operator (LASSO) regression and stepwise regression were used to screen the redundant radiomic features. The effective characteristics were used to establish radiomic signature.Finally, the clinical features closely related to histological classification were fitted, and radiomic nomogram was constructed.The performance of each model was evaluated by the area under ROC curve (AUC). Results: A total of 985 features were extracted from all the segmentation region, which included first order statistics , shape features, texture features, wavelet features and other filtering feature. After the screening of redundant features, five key features were obtained, which were used as the parameters of radiomic signature. Three clinical characteristics (age, sex, CTM) were selected as the parameters of the clinical feature model. Compared with other two models (clinical feature model and radiomic signature), the classification performance of radiomic nomogram is the best.The AUC of radiomic nomogram in training cohort and validation cohort was 0.726 2 (95%CI:0.676-0.776) and 0.707 0(95%CI:0.632-0.781). Conclusion: CT-based radiomic nomogram has certain potentiality in noninvasive predicting different prognostis related to histological classification of gastric cancer before operation.
［1］Gao JP, Xu W, Liu WT,et al.Tumor heterogeneity of gastric cancer: From the perspective of tumorinitiating cell\[J\].World J Gastroenterol,2018,24(24): 2567-2581.
［2］Kang WM，Meng QB，Yu JC，et al．Factors associated with early recurrence after curative surgery for gastric cancer\[J\]．World J Gastroenterol，2015，21(19)：5934-5940.
［3］Degiuli M，Calvo F.Survival of early gastric cancer in specialized European center.Which lymphadenectomy is necessary? \[J\].World J Surg,2006,30(12):2193-2203.
［4］Liu L,Wang ZW, Ji J,et al.A cohort study and metaanalysis between histopathological classification and prognosis of gastric carcinoma\[J\]. Anticancer Agents Med Chem, 2013，13(2):27-34.
［5］Lai JF,Xu WN,Noh SH,et al.Effect of World Health Organization (WHO) histological classification on predicting lymph node metastasis and recurrence in early gastric cancer\[J\]. Med Sci Monit, 2016, 22: 3147-3153.
［7］Kumar V, Gu Y, Basu S, et al. Radiomics:the process and the challenges\[J\]. Magn Reson Imaging, 2012,30(8):1234-1248.
［8］Gillies RJ, Kinahan PE, Hricak H. Radiomics: images are more than pictures,they are data\[J\]. Radiology,2016, 278(2):563-577.
［9］Peng H, Dong D, Fang MJ, et al. Prognostic value of deep learning PET/CTbased radiomics: potential role for future individual induction chemotherapy in advanced nasopharyngeal carcinoma\[J\].Clin Cancer Res, 2019,25(14):4271-4279.
［10］Song JD, Shi JY, Dong D, et al. A new approach to predict progressionfree survival in stage Ⅳ EGFRmutant NSCLC patients with EGFRTKI therapy\[J\]. Clin Cancer Res, 2018,24(15): 3583-3592.
［11］Ma Z, Fang M, Huang Y, et al. CTbased radiomics signature for differentiating Borrmann typeⅣ gastric cancer from primary gastric lymphoma\[J\]. Eur J Radiol, 2017, 91(23): 142-147.
［12］BaSsalamah A, Muin D, Schernthaner R, et al. Texturebased classification of different gastric tumors at contrastenhanced CT\[J\].Radiology, 2013, 82(10): 537-543.
［13］Dong D, Tang L,Li ZY, et al. Development and validation of an individualized nomogram to identify occult peritoneal metastasis in patients with advanced gastric cancer\[J\].Ann Oncol，2019，30（3）：431-438.
［20］Liu S, Liu S, Ji C, et al. Application of CT texture analysis in predicting histopathological characteristics of gastric cancers\[J\]. Eur Radiol, 2017, 27(12): 4951-4959.
［21］Lin X, Yang F, Zhou L,et al. A support vector machinerecursive feature elimination feature selection method based on artificial contrast variables and mutual information\[ J\]. J Chromatogr B, 2012, 910: 149-155.
