Background
The accurate assessment of lateral pelvic lymph node (LPLN) metastasis (LPLNM) in preoperative examination data of rectal cancer patients is vital to identify those who would benefit from LPLN dissection (LPLD). Our objective was to develop an MRI-based radiomics model for individual preoperative prediction of LPLNM in patients with locally advanced rectal cancer.
Methods
We retrospectively enrolled 263 patients with rectal cancer who underwent total mesorectal excision and LPLD at our center between April 2015 and September 2022. Radiomics features from the primary lesion and LPLNs on baseline MRI images were utilized to construct a radiomics model with feature selection based on the minimal-redundancy-maximal-relevance criterion. The radiomics scores of the primary tumor and LPLNs were then combined to develop a radiomics scoring system. A clinical prediction model was developed using logistic regression. A hybrid predicting model was created through multivariable logistic regression analysis, integrating the radiomics score with significant clinical risk factors (baseline CEA, clinical circumferential resection margin status, and the short axis diameter of LPLN). This hybrid model was presented with a hybrid clinical-radiomics nomogram, and its calibration, discrimination, and clinical usefulness were assessed. The study protocol was registered on clinicaltrials.gov (NCT04850027).
Results
A total of 148 patients were included in the analysis and randomly divided into a training cohort (n=104) and an independent internal testing cohort (n=44). The hybrid clinical-radiomics model exhibited the highest discrimination, with an AUC of 0.843 (95% confidence interval, 0.706-0.968) in the testing cohort compared with the clinical model and radiomics model. The hybrid prediction model also demonstrated good calibration, and decision curve analysis confirmed its clinical usefulness .
Conclusion
This study developed a hybrid MRI-based radiomics model that incorporates a combination of radiomics score and significant clinical risk factors. The proposed model holds promise for individualized preoperative prediction of LPLNM in patients with locally advanced rectal cancer.