Related Experiment Video
Updated: May 28, 2026
Comparison of Predictive Performance of Three Lymph Node Staging Systems in Colorectal Signet Ring Cell Carcinoma Based on Machine Learning Model
Published on: April 18, 2025
Novel scoring system for the preoperative computed tomographic diagnosis of lymph node metastasis in colorectal
Chieko Hotta1, Tatsuya Manabe2, Tomokazu Tanaka1
1Department of Surgery, Faculty of Medicine, Saga University, Saga, Japan.
Purpose:
The diagnostic accuracy of conventional size-based evaluation on computed tomography (CT) is limited. We conducted this study to develop and validate a novel CT-based scoring system, integrating lymph node morphology, enhancement, size, and tumor laterality for the accurate preoperative assessment of lymph node metastasis in colorectal cancer patients.
Methods:
We analyzed a retrospective cohort of 145 patients who underwent curative colorectal cancer surgery with D3 lymph node dissection. Short-axis diameter, contrast enhancement, and margin irregularity of evaluable lymph nodes were assessed on preoperative CT images, and the largest lymph node in each patient was analyzed. Diameter-based and composite-based approaches were developed and validated using temporally separate cohorts. Diagnostic performance was evaluated using the area under the receiver operating characteristic curve and other accuracy measures.
Results:
In the derivation cohort, the composite-based approach showed superior performance to the diameter-based approach across all tumor locations (AUC 0.80 vs. 0.73), including right-sided (0.80 vs. 0.70) and left-sided colon cancers (0.84 vs. 0.77). Sensitivity and specificity further improved with laterality-adjusted scoring. These findings were confirmed in the validation cohort.
Conclusions:
A laterality-specific scoring system integrating lymph node morphology, enhancement, and size may improve the preoperative diagnostic accuracy for identifying lymph node metastasis in colorectal cancer patients.
