Deep learning model based on multiparametric MRI for prediction of synchronous liver metastasis from rectal cancer: a two-center study.

Motivation: Accurate synchronous liver metastasis (SLM) risk stratification is important for treatment planning and prognosis improvement. Goal(s): Our goal is to establish a non-invasive and quantitative prediction model of synchronous liver metastases (SLM) in rectal cancer (RC) to help with accurate staging. Approach: The deep learning (DL) model was fitted based on multi-parameter MRI of primary cancer combined with Clinical features (CF) features, and 5-fold cross-validation and external validation were performed. Results: We demonstrated that the combination of CF and DL features achieved a satisfactory predictive performance for SLM, and also confirmed the generalizability of this model by external validation. Impact: The discovery of the DL model would change treatment strategies. For patients with high-risk metastasis, a more aggressive systemic examination and shorter follow-up should be considered and may contribute to improved outcomes.