Radiomics and Morphomics Predict Colorectal Cancer Recurrence Risk
Key Insights
Radiomic features from tumor imaging and morphomic features of body composition independently correlate with colorectal cancer (search) (CRC) recurrence risk.
Combining radiomics and morphomics provides valuable information for predicting recurrence risk in stage III CRC patients.
Elevated post-surgery CEA (search) levels and pathological stage are significantly associated with CRC recurrence.
Imaging biomarkers, specifically radiomics and morphomics, show promise in predicting cancer prognosis and clinical outcomes. A recent study published in PubMed explored the use of these biomarkers, extracted from baseline pre-treatment CT scans, to predict recurrence in patients with stage III colorectal cancer (search) (CRC).
The prospective observational study enrolled 101 patients with newly diagnosed stage III CRC. Radiomics analysis, focusing on tumor characteristics, was performed on 60 patients with visible tumors. Morphomics analysis, assessing muscle, fat, and bone composition, was conducted on all 101 patients. The primary outcome measured was time to recurrence.
The study revealed significant associations between morphomic and radiomic features and the risk of CRC recurrence. Patients suitable for radiomics analysis presented with lower ECOG scores (p < 0.05), greater muscle mass (p > 0.05), and reduced fat density (p > 0.05) compared to those not suitable for radiomics analysis. Multivariate analyses identified pathological stage (HR: 2.69; p = 0.03) and post-surgery CEA (search) level (HR: 1.11 per 1 ng/mL; p < 0.005) as significant predictors of recurrence. Bone mineral density (HR: 1.01 per 1 Hounsfield Unit; p < 0.01) and tumor skewness (HR: 0.33 per unit; p < 0.05) also demonstrated associations with recurrence.
Risk Stratification
A Cox regression model effectively stratified patients into low-, medium-, and high-risk groups for recurrence based on the combined radiomic and morphomic features. This suggests that integrating these imaging biomarkers could refine risk assessment and potentially guide personalized treatment strategies.
Clinical Implications
These findings underscore the potential of radiomics and morphomics as non-invasive tools for predicting CRC recurrence. By incorporating these biomarkers into clinical practice, healthcare professionals may be able to identify high-risk patients who could benefit from more aggressive adjuvant therapies or closer monitoring. The study highlights the importance of considering both tumor-specific and whole-body characteristics in assessing recurrence risk in CRC patients.