There is provided a method for segmentation of an image of a target patient, comprising: providing a target 2D slice and nearest neighbor 2D slice(s) of a 3D anatomical image, and computing, by a trained multi-slice fully convolutional neural network (multi-slice FCN), a segmentation region including a defined intra-body anatomical feature that extends spatially across the target 2D slice and the nearest neighbor 2D slice(s), wherein the target 2D slice and each of the nearest neighbor 2D slice(s) are processed by a corresponding contracting component of sequential contracting components of the multi-slice FCN according to the order of the target 2D slice and the nearest neighbor 2D slice(s) based on the sequence of 2D slices extracted from the 3D anatomical image, wherein outputs of the sequential contracting components are combined and processed by a single expanding component that outputs a segmentation mask for the target 2D slice.