Introduction: Imaging studies are used to guide patient selection for acute stroke treatment. Perfusion CT (pCT) is widely used to identify the acute ischemic core and penumbra, but the prediction of the final infarct remains challenging. With the advent of machine learning, algorithms learning the prediction of the final lesion from imaging data collected in the acute phase have been proposed. We aimed to investigate whether machine learning methods that integrate prior ischemic core segmentation improve the prediction of the final infarct after stroke. Methodology: We retrospectively included all stroke patients admitted to the Geneva University Hospital for intravenous and/or endovascular treatment from 01.2016 to 12.2017. All patients had acute pCT and follow-up MRI. An Attention-Gated 3D Unet was used as the baseline model on which the effect of access to a threshold-based ischemic core segmentation was tested. To ensure the efficient integration of information contained in voxels from the ischemic core, we extended the baseline model with a bayesian skip connection allowing only the prior to bypass most of the network. This modifies the model’s task to predict divergence from the prior representation. All models were evaluated for the prediction of the final infarct on follow-up MRI, given acute pCT maps as input. The output of each model was compared to finals lesions manually delineated by expert neurologists. Dice score was used to assess performance. Results: A total of 144 patients were included. Median hypoperfused tissue volume (Tmax > 6s) was 60 ml [17-134], median ischemic core (relative CBF < 38%) volume was 23 ml [17-33] and median final infarct volume was 13 ml [3-38]. Dice score for the threshold based ischemic core segmentation was 0.1. The baseline model with and without prior segmentation as input achieved a Dice score of 0.19. Adding the proposed bayesian skip connection lead to a more efficient integration of the prior segmentation ensuring faster convergence and better performance with a final Dice score of 0.21. Conclusion: The evaluated deep learning model can effectively leverage the information contained in a prior segmentation of the ischemic core to enhance the learning process and improve the prediction of the final infarct after stroke.