Objective To develop and validate a fusion model that integrates a multi-parametric MRI deep learning algorithm with clinicopathological factors to improve the accuracy of preoperative prediction for lymph node metastasis (LNM) in rectal cancer.

Methods A total of 191 rectal cancer patients who received treatment at Xiamen Hospital of Zhongshan Hospital affiliated with Fudan University (modeling group, n=141) from January 2022 to December 2024 and at Zhongshan Hospital affiliated with Fudan University (external validation group, n=50) from January to June 2021 were retrospectively included. Magnetic resonance imaging and clinical data of all patients were collected to compare the diagnostic performance of the previously developed algorithm with that of two radiologists. Logistic regression was further employed to identify independent risk factors for lymph node metastasis (LNM), and an integrated model combining "algorithm + clinical factors" was constructed. The clinical value of this model was evaluated using the area under the receiver operating characteristic curve (AUC) and decision curve analysis (DCA).

Results In the modeling group, the algorithm's predictive performance for LNM (AUC=0.763) was higher than that of two physicians (AUC=0.675, 0.655). Multivariate analysis results indicated that carcinoembryonic antigen ＞5 μg/L and low differentiation were independent risk factors for LNM. The fusion model improved predictive performance, with an AUC of 0.872 in the modeling group and 0.830 in the external validation group. DCA analysis showed that the fusion model provided higher net benefits across the clinically common threshold range. At the point of maximum sensitivity, the fusion model identified 93.1% of LNM-positive cases.

Conclusions The fusion model based on multi parameter magnetic resonance image deep learning algorithm and clinical features shows good predictive performance for lymph node metastasis (LNM) of rectal cancer, which is superior to simple algorithms and manual interpretation. It is expected to become an auxiliary tool for preoperative risk stratification and treatment strategy selection of rectal cancer.