Preoperative prediction of peritoneal metastasis in colorectal cancer using a clinical-radiomics model

• Published in: European journal of radiology 2020-11, Vol.132, p.109326-109326, Article 109326
• Main Authors: Li, Menglei, Sun, Kai, Dai, Weixing, Xiang, Wenqiang, Zhang, Zhaohe, Zhang, Rui, Wang, Renjie, Li, Qingguo, Mo, Shaobo, Han, Lingyu, Tong, Tong, Liu, Zhenyu, Tian, Jie, Cai, Guoxiang
• Format: Article
• Language: English
• Subjects: Adult; Aged; Aged, 80 and over; Algorithms; Colorectal cancer; Colorectal Neoplasms - diagnostic imaging; Colorectal Neoplasms - pathology; Female; Humans; Imaging, Three-Dimensional; Lymph node; Lymph Nodes - diagnostic imaging; Male; Middle Aged; Nomograms; Peritoneal Neoplasms - diagnostic imaging; Peritoneal Neoplasms - secondary; Preoperative Period; Preoperative prediction; Radiomics; Synchronous peritoneal metastasis; Tomography, Spiral Computed - methods; Young Adult
• ISSN: 0720-048X; 1872-7727
• DOI: 10.1016/j.ejrad.2020.109326

•Radiomics is a high-throughput extraction of large amounts of image information.•We first built a clinical-radiomics prediction model for PM in CRC patients.•The model showed good performance and may assist clinical decision-making. To establish and validate a combined clinical-radiomics model for preoperative prediction of synchronous peritoneal metastasis (PM) in patients with colorectal cancer (CRC). We enrolled 779 patients (585 in the training set: 553 with nonmetastasis (NM) and 32 with PM; 194 in the validation set: 184 with NM and 10 with PM) with clinicopathologically confirmed CRC. The significant clinical risk factors were used to build the clinical model; the least absolute shrinkage and selection operator (LASSO) algorithm was adopted to construct a radiomics signature, which included imaging features of the primary lesion and the largest peripheral lymph node, and stepwise logistic regression was applied to select the significant variables to develop the clinical-radiomics model. We used the Akaike information criterion (AIC) and receiver operating characteristic analysis to compare the goodness of fit and the prediction performance of the three models respectively. An independent validation cohort, containing 139 consecutive patients from February to September 2018, was used to evaluate the performance of the optimal model. Among the three models, the clinical-radiomics model (AUC = 0.855; AIC = 1043.2) was identified as the optimal model, with the maximum AUC value and the minimum AIC value (the clinical-only model: AUC = 0.771, AIC = 1277.7; the radiomics-only model: AUC = 0.764, AIC = 1280.5). The clinical-radiomics model also showed good discrimination in both the validation cohort (AUC = 0.793) and the independent validation cohort (AUC = 0.781). The present study proposes a clinical-radiomics model created with the CT-based radiomics signature and key clinical features that can potentially be applied in the individual preoperative prediction of synchronous PM for CRC patients.