A Longitudinal MRI-Based Artificial Intelligence System to Predict Pathological Complete Response After Neoadjuvant Therapy in Rectal Cancer: A Multicenter Validation Study

BACKGROUND: Accurate prediction of response to neoadjuvant chemoradiotherapy is critical for subsequent treatment decisions for patients with locally advanced rectal cancer. OBJECTIVE: To develop and validate a deep learning model that based on the comparison of paired magnetic resonance imaging before and after neoadjuvant chemoradiotherapy to predict pathological complete response. DESIGN: By capturing the changes from magnetic resonance images before and after neoadjuvant chemoradiotherapy in 638 patients, we trained a multitask deep learning model for response prediction (DeepRP-RC) that also allowed simultaneous segmentation. Its performance was independently tested in an internal and three external validation sets, and its prognostic value was also evaluated. SETTINGS: Multicenter study. PATIENTS: We retrospectively rerolled 1201 patients diagnosed with locally advanced rectal cancer and undergoing neoadjuvant chemoradiotherapy prior to total mesorectal excision. They were from four hospitals in China between January 2013 and December 2020. MAIN OUTCOME MEASURES: The main outcomes were accuracy of predicting pathological complete response, measured as the area under receiver operating curve for the training and validation data sets. RESULTS: DeepRP-RC achieved high performance in predicting pathological complete response after neoadjuvant chemoradiotherapy, with area under curve values of 0.969 (0.942-0.996), 0.946 (0.915-0.977), 0.943 (0.888-0.998), and 0.919 (0.840-0.997) for the internal and 3 external validation sets, respectively. DeepRP-RC performed similarly well in the subgroups defined by receipt of radiotherapy, tumor location, T/N stages before and after neoadjuvant chemoradiotherapy, and age. Compared with experienced radiologists, the model showed substantially higher performance in pathological complete response prediction. The model was also highly accurate in identifying the patients with poor response. Further, the model was significantly associated with disease-free survival independent of clinicopathologic variables. LIMITATIONS: This study was limited by retrospective design and absence of multi-ethnic data. CONCLUSIONS: DeepRP-RC could serve as an accurate preoperative tool for pathological complete response prediction in rectal cancer after neoadjuvant chemoradiotherapy.