What question did this study set out to answer?

The aim is to develop and validate a machine learning model to predict intrahepatic recurrence in colorectal cancer liver metastases after surgery.

March 18, 2026Insights into ImagingOpen Access

Predicting intrahepatic recurrence of colorectal cancer liver metastases after curative hepatectomy using a machine learning model with data integration of ultrasound radiomics and clinicopathological parameters

View Full Paper

Ask AI

Bookmark

The aim is to develop and validate a machine learning model to predict intrahepatic recurrence in colorectal cancer liver metastases after surgery.
Retrospective analysis of 278 colorectal cancer liver metastases patients.
Integration of preoperative ultrasound images and clinical parameters to extract radiomics features.
Development of three predictive models: clinical, radiomics, and combined (cRadiomics).
Model performance evaluated using ROC curve analysis and cross-validation.
Assessment of accuracy, sensitivity, and specificity on both main and external cohorts.
cRadiomics model achieved AUC values of 0.811 and 0.784 in main and external cohorts, respectively.
Identified six clinical parameters and seven radiomics features as strong predictors of recurrence.
cRadiomics model significantly outperformed clinical and radiomics-only models in predictive accuracy.

Authors

No takes yet. Share an insight, caveat, or question.

Retrospective study develops a machine learning model to predict recurrence in colorectal cancer patients, suggesting enhanced clinical management.

Hu et al. (2026) studied this question.

View Full Paper

Ask AI

Bookmark

Retrospective study develops a machine learning model to predict recurrence in colorectal cancer patients, suggesting enhanced clinical management.