HECTOR: prediction of recurrence risk in endometrial cancer with multimodal deep learning

Predicting distant recurrence of endometrial cancer (EC) is crucial for personalized adjuvant treatment. The current gold standard of combined pathological and molecular profiling is costly, hampering implementation. HECTOR (‘histopathology-based endometrial cancer tailored outcome risk’) is a multimodal deep learning prognostic model using hematoxylin and eosin-stained, whole-slide images and tumor stage of 2,072 EC patients as input. HECTOR demonstrated C-indices in internal (n=353) and two external (n=160 and n=151) test sets of 0.789, 0.828, and 0.815, respectively, outperforming the current gold standard. In HECTOR low-, intermediate-, and high risk groups the 10-year distant recurrence-free probabilities were 97.0%, 77.7%, and 58.1%, respectively. HECTOR also predicted adjuvant chemotherapy benefit better than current methods. The authors conclude that HECTOR improves on the current gold standard and may help delivery of personalizes treatment in EC.