|Table of Contents|

Predictive value of CT imaging in risk stratification of stage Ⅱ colon cancer

Journal Of Modern Oncology[ISSN:1672-4992/CN:61-1415/R]

Issue:
2024 01
Page:
120-125
Research Field:
Publishing date:

Info

Title:
Predictive value of CT imaging in risk stratification of stage Ⅱ colon cancer
Author(s):
ZHANG Xiaojin1; ZHANG Hu1; WU Shujian2; XU Jiajun1; HUANG Guoquan1; DONG Mingsong1; ZHU Xianfeng1; WANG Jiawei3
1.Medical Imaging Department;3.Urology Department,the Second People's Hospital of Wuhu,Anhui Wuhu 241000,China;2.Department of Radiology,the First Affiliated Hospital of Wannan Medical College,Anhui Wuhu 241000,China.
Keywords:
radiomics; stage Ⅱ; colon cancer; risk stratification
PACS:
R735.3
DOI:
10.3969/j.issn.1672-4992.2024.01.021
Abstract:
Objective:To explore the predictive value of CT radiomics models for risk stratification of stage Ⅱ colon cancer(CC).Methods:The data of 167 patients with stage Ⅱ CC confirmed by surgery from January 2015 to July 2023 were collected consecutively.According to the guidelines of the European Society of Medical Oncology(ESMO),the patients were divided into a low risk group of 77 cases,and a medium-high risk group of 90 cases.The samples were randomly divided into a training group(n=116) and an internal validation group(n=51) at 7∶3.Segmentation of tumors and extraction of radiomics features were performed on preoperative venous CT images.After dimensionality reduction and screening,independent influencing factors were selected with logistic regression analysis and predictive models were constructed to observe model calibration and clinical benefits.Results:Among the training group,64/116 cases were at medium-high risk.There were 26/51 medium-high risk cases in the internal validation group,and there was no statistically significant difference in observation indicators between the two groups(all P>0.05).A total of 6 radiomics features were selected to construct prediction models for low risk and medium-high risk of stage Ⅱ CC,with the AUC of 0.822,sensitivity of 84.4%,and specificity of 71.2% in the training group.The AUC of the internal validation group was 0.802,with sensitivity of 96.2% and specificity of 60.0%.The model showed high calibration.The decision curve analysis(DCA) threshold probability range was 0.04~0.85,which was clinically beneficial.Conclusion:The radiomics model constructed on venous phase CT images has achieved accurate classification of low risk and medium-high risk stage Ⅱ CC,which is expected to improve the hierarchical management of this type of patient in clinical practice.

References:

［1］SUNG H,FERLAY J,SIEGEL RL,et al.Global cancer statistics 2020:GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries［J］.CA Cancer J Clin,2021,71(3):209-249.
［2］ARGILS G,TABERNERO J,LABIANCA R,et al.Localised colon cancer:ESMO clinical practice guidelines for diagnosis,treatment and follow-up［J］.Ann Oncol,2020,31(10):1291-1305.
［3］KORNGOLD EK,MORENO C,KIM DH,et al.ACR appropriateness criteria staging of colorectal cancer:2021 update［J］.J Am Coll Radiol,2022,19(5S):S208-S222.
［4］李清扬,张晓燕,孙应实.影像组学与深度学习在评价直肠癌淋巴结状态中的应用［J］.中华放射学杂志,2023,57(2):231-234. LI QY,ZHANG XY,SUN YS.Application of radiomics and deep learning in evaluating lymph node status of rectal cancer［J］.Chin J Radiol,2023,57(2):231-234.
［5］刘俊忠,王琦,褚玉静,等.CT影像组学预测肺浸润性腺癌脉管癌栓的价值［J］.中国医学影像学杂志,2023,31(5):487-491. LIU JZ,WANG Q,CHU YJ,et al.CT radiomics model for predicting lymphovascular tumor embolus in lung invasive adenocarcinomas［J］.Chinese Journal of Medical Imaging,2023,31(5):487-491.
［6］贾济波,刘原庆,冯飞文,等.CT影像组学列线图模型预测胃肠道间质瘤Ki-67表达的临床研究［J］.临床放射学杂志,2023,42(5):783-788. JIA JB,LIU YQ,FENG FW,et al.Clinical study on predicting the expression of Ki-67 in gastrointestinal stromal tumors by radiomics nomogram model［J］.Journal of Clinical Radiology,2023,42(5):783-788.
［7］LAMBIN P,RIOS-VELAZQUEZ E,LEIJENAAR R,et al.Radiomics:Extracting more information from medical images using advanced feature analysis［J］.Eur J Cancer,2012,48(4):441-446.
［8］YOSHINO T,ARGILS G,OKI E,et al.Pan-Asian adapted ESMO clinical practice guidelines for the diagnosis treatment and follow-up of patients with localised colon cancer［J］.Ann Oncol,2021,32(12):1496-1510.
［9］MAYR P,AUMANN G,SCHALLER T,et al.Lymph node hypoplasia is associated with adverse outcomes in node-negative colon cancer using advanced lymph node dissection methods［J］.Langenbecks Arch Surg,2016,401(2):181-188.
［10］DAI WX,MO SB,HAN LY,et al.Prognostic and predictive value of radiomics signatures in stage Ⅰ-Ⅲ colon cancer［J］.Clin Transl Med,2020,10(1):288-293.
［11］陈松,李清楚,陈如潭,等.CT三维定量参数对纯磨玻璃结节中腺体前驱病变的预测价值［J］.临床放射学杂志,2023,42(4):575-580. CHEN S,LI QC,CHEN RT,et al.The predictive value of CT three-dimensional quantitative parameters for precursor glandular lesions in pure ground-glass nodules［J］.Journal of Clinical Radiology,2023,42(4):575-580.
［12］刘华,郑欢记,何泳聪,等.常规MRI定量检测对新生儿高胆红素血症诱导脑损伤的诊断价值［J］.临床放射学杂志,2023,42(4):660-665. LIU H,ZHENG HJ,HE YC,et al.Quantitative detection method of conventional MRI in the diagnostic value of neonatal hyperbilirubinemia induced brain injury［J］.Journal of Clinical Radiology,2023,42(4):660-665.
［13］雷岩,宋彬,刘恋恋,等.磁共振多参数定量分析在区分卵巢-附件O-RADS MRI 4分病变良恶性的价值［J］.中国医学计算机成像杂志,2023,29(1):50-57. LEI Y,SONG B,LIU LL,et al.Value of quantitative analysis of multiparameter MRI in differentiation of benign and malignant ovarian lesions with O-RADS MRI score 4［J］.Chinese Computed Medical Imaging,2023,29(1):50-57.
［14］CARUSO D,POLICI M,ZERUNIAN M,et al.Radiomics in oncology,Part 1:Technical principles and gastrointestinal application in CT and MRI［J］.Cancers(Basel),2021,13(11):2522.
［15］FILITTO G,COPPOLA F,CURTI N,et al.Automated prediction of the response to neoadjuvant chemoradiotherapy in patients affected by rectal cancer［J］.Cancers(Basel),2022,14(9):2231.
［16］CARUSO D,POLICI M,ZERUNIAN M,et al.Radiomic cancer hallmarks to identify high-risk patients in non-metastatic colon cancer［J］.Cancers(Basel),2022,14(14):3438.
［17］LI ML,ZHANG J,DAN YB,et al.A clinical-radiomics nomogram for the preoperative prediction of lymph node metastasis in colorectal cancer［J］.J Transl Med,2020,18(1):46.
［18］HONG EK,BODALAL Z,LANDOLFI F,et al.Identifying high-risk colon cancer on CT an a radiomics signature improve radiologist's performance for T staging［J］.Abdom Radiol(NY),2022,47(8):2739-2746.
［19］YAO X,SUN CX,XIONG F,et al.Radiomic signature-based nomogram to predict disease-free survival in stage Ⅱ and Ⅲ colon cancer［J］.Eur J Radiol,2020,131:109205.

Memo

Memo:
安徽省卫生健康科研项目（编号：AHWJ2022b100）
Last Update: 2023-11-30