The aim of this article is to introduce a novel approach to identifying flow regimes and void fractions in microchannel flow boiling, which is based on binary image segmentation using digital image processing and deep learning. The proposed image processing pipeline uses adaptive thresholding, blurring, gamma correction, contour detection and histogram comparison to separate vapour from liquid areas, while the deep learning method uses a customized version of a convolutional neural network (CNN) called Unet to extract meaningful features from video frames. Both approaches enabled automatic detection of flow boiling conditions, such as bubbly, slug, and annular flow, as well as automatic void fraction calculation. Especially the CNN has demonstrated its ability to deliver fast and dependable results, presenting an appealing substitute to manual feature extraction. The U-net-based CNN was able to segment flow boiling images with a Dice score of 99.1 % and classify the above flow regimes with an overall classification accuracy of 91 %. In addition, the neural network was able to predict resistance sensor readings from image data and assign them to a flow state with a mean squared error (MSE) < 10−6. This sensor signal prediction is a promising first step towards automated, imageless prediction of two-phase flow in microchannels using only the measurement data from resistance sensors. The approaches discussed in this paper were performed on an ordinary 6 GB NVIDIA laptop GPU using Python and are general enough to be applied to other similar applications. The deep learning model can be downloaded from: github.com/schepperlemark