For the prediction of deep myometrial invasion (DMI) in endometrial cancer (EC), this study proposes an ensemble learning method which combines deep learning (DL) and improved Bayesian extreme learning machine (BELM). Firstly, the MRI images of endometrial cancer are preprocessed to meet the requirements. Secondly, the deep features relevant to the task are extracted from the images by using convolutional kernels. Finally, the bootstrap resampling method is employed to repeatedly sample multiple training subsets from the training set. The improved Bayesian extreme learning machine is used as the base classifier to train multiple independent sub-models. An ensemble learning classifier is constructed using an ensemble strategy to improve the prediction accuracy and stability of the model. Experimental results show that the proposed method achieves an AUC of 0.758 on the internal validation set and 0.740 on the external validation set, which demonstrat good generalization ability and stability of the proposed method.