AUTHOR=Zhang Dongying , Li Peiheng , Wei Yong , Xue Mingmei , Guo Fangfang , Li Chenguang 

TITLE=Predicting the recurrence risk of liver metastasis from colorectal cancer: a study based on preoperative CT intratumoral and peritumoral radiomics features

JOURNAL=Frontiers in Oncology

VOLUME=Volume 15 - 2025

YEAR=2025

URL=https://www.frontiersin.org/journals/oncology/articles/10.3389/fonc.2025.1662354

DOI=10.3389/fonc.2025.1662354

ISSN=2234-943X

ABSTRACT=ObjectiveThis study aims to explore the value of predicting the recurrence risk of colorectal cancer liver metastasis (CRLM) based on preoperative CT intratumoral and peritumoral radiomics features.MethodsThis study utilized retrospectively collected preoperative CT data of 201 CRLM patients, comprising 145 cases from the hospital one and 56 cases from an external hospital two. Liver metastases were precisely segmented via manual annotation. Subsequently, the intratumoral region of interest (ROIIntra) was isotropically dilated to radii of 2 mm, 4 mm, and 6 mm, resulting in peri-tumoral ROIs (ROIPeri2mm, ROIPeri4mm and ROIPeri6mm). We established the prediction models based on support vector machine (SVM), random forest (RF), and multilayer perceptron (MLP) algorithms. The area under the subject operating characteristic curve (AUC) was used to evaluate the predictive performance.ResultsCompared with SVM and RF, MLP demonstrated superior predictive performance for estimating the recurrence risk of CRLM patients. The best radiomics signatures for predicting the recurrence risk of CRLM were ROIIntra+Peri4mm model, and the AUCs of the ROIIntra model, ROIIntra+Peri2mm model, ROIIntra+Peri4mm model, and ROIIntra+Peri6mm model constructed by MLP are 0.758 (95% confidence interval (CI), 0.621 - 0.865), 0.815 (95% CI, 0.684 - 0.908), 0.855 (95% CI, 0.731 - 0.936), and 0.825 (95% CI, 0.696 - 0.915), respectively, in the external test set.ConclusionPreoperative CT-based radiomics features extracted from intra-tumoral (ROIIntra) and peritumoral (ROIIntra+Peri2mm, ROIIntra+Peri4mm, and ROIIntra+Peri6mm) regions can effectively predict recurrence risk in CRLM patients.