Spatial analysis and pattern recognition with vector spatial data is particularly useful to enrich raw data. In road networks for instance, there are many patterns and structures that are implicit with only road line features, among which highway interchange appeared very complex to recognise with vector-based techniques. The goal is to find the roads that belong to an interchange, i.e. the slip roads and the highway roads connected to the slip roads. In order to go further than state-of-the-art vector-based techniques, this paper proposes to use raster-based deep learning techniques to recognise highway interchanges. The contribution of this work is to study how to optimally convert vector data into small images suitable for state-of-the-art deep learning models. Image classification with a convolutional neural network (i.e. is there an interchange in this image or not?) and image segmentation with a u-net (i.e. find the pixels that cover the interchange) are experimented and give results way better than existing vector-based techniques in this specific use case.