EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

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

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

Frontiers in Oncology · 23.09.2025 · 15

DOI: 10.3389/fonc.2025.1662354 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Frontiers in Oncology, online erschienen am 23.09.2025. Verfasst von Dongying Zhang und 5 weiteren Autor:innen. Beteiligte Einrichtung: Department of Radiology, The First Affiliated Hospital of Xinxiang Medical University, Weihui, China. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Objective

This 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.

Methods

This 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 (ROI Intra ) was isotropically dilated to radii of 2 mm, 4 mm, and 6 mm, resulting in peri-tumoral ROIs (ROI Peri2mm , ROI Peri4mm and ROI Peri6mm ). 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.

Results

Compared 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 ROI Intra+Peri4mm model, and the AUCs of the ROI Intra model, ROI Intra+Peri2mm model, ROI Intra+Peri4mm model, and ROI Intra+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.

Conclusion

Preoperative CT-based radiomics features extracted from intra-tumoral (ROI Intra ) and peritumoral (ROI Intra+Peri2mm , ROI Intra+Peri4mm , and ROI Intra+Peri6mm ) regions can effectively predict recurrence risk in CRLM patients.

Schlagwörter

Stichwörter der Autor:innen

colorectal neoplasmscomputed tomographyliverneoplasm metastasisradiomics

Autor:innen und Institutionen

  • Department of Radiology, The First Affiliated Hospital of Xinxiang Medical University, Weihui, China.

Zitieren

APA

Zhang, D., Li, P., Wei, Y., Xue, M., Guo, F., & Li, C. (2025). Predicting the recurrence risk of liver metastasis from colorectal cancer: a study based on preoperative CT intratumoral and peritumoral radiomics features. Frontiers in Oncology, 15. https://doi.org/10.3389/fonc.2025.1662354

Vancouver

Zhang D, Li P, Wei Y, Xue M, Guo F, Li C. Predicting the recurrence risk of liver metastasis from colorectal cancer: a study based on preoperative CT intratumoral and peritumoral radiomics features. Frontiers in Oncology. 2025;15. doi:10.3389/fonc.2025.1662354

BibTeX
@article{Zhang2025,
  author = {Zhang, Dongying and Li, Peiheng and Wei, Yong and Xue, Mingmei and Guo, Fangfang and 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},
  year = {2025},
  volume = {15},
  doi = {10.3389/fonc.2025.1662354}
}
Kostenlos starten →