Related Experiment Video
Updated: Sep 3, 2025
08:12
Detection of a Circulating MicroRNA Custom Panel in Patients with Metastatic Colorectal Cancer
Published on: March 14, 2019
5.6K
Radiomic Cancer Hallmarks to Identify High-Risk Patients in Non-Metastatic Colon Cancer
Damiano Caruso1, Michela Polici1, Marta Zerunian1
1Radiology Unit, Department of Medical Surgical Sciences and Translational Medicine, Sapienza University of Rome-Sant'Andrea University Hospital, Via di Grottarossa, 1035-1039, 00189 Rome, Italy.
Cancers
|July 27, 2022
Summary
This study developed a radiomic model using CT scans to identify high-risk colon cancer. The non-invasive model accurately stratified patients, offering a promising tool for clinical decision-making.
Area of Science:
- Radiology and Medical Imaging
- Oncology
- Artificial Intelligence in Medicine
Background:
- Colon cancer risk stratification is crucial for treatment planning.
- Pre-operative imaging can provide valuable prognostic information.
- Developing non-invasive tools for risk assessment is an ongoing need.
Purpose of the Study:
- To develop and validate a radiomic model for identifying high-risk colon cancer.
- To utilize pre-operative CT scans for non-invasive risk stratification.
- To assess the model's performance in both internal and external validation cohorts.
Main Methods:
- Retrospective analysis of 148 colon cancer patients (108 internal, 40 external validation).
- 3D segmentation of tumors on portal phase CT scans.
- Extraction and selection of stable radiomic features (ICC > 0.8).
- Development of a predictive model using logistic regression.
- Validation of the model using an external cohort.
Main Results:
- A radiomic model was built using 9 significant features.
- The model achieved an Area Under the Curve (AUC) of 0.73 in the internal cohort.
- The model demonstrated an AUC of 0.75 in the external validation cohort.
- The model successfully stratified patients into high-risk and no-risk groups.
Conclusions:
- A radiomic model derived from CT scans can effectively identify high-risk colon cancer.
- This non-invasive imaging tool aids in stratifying colon cancer patients.
- The model shows potential as a valuable tool in clinical practice for personalized treatment strategies.
