The objective of this study is to develop, test and validate a fully automatic, deep learning-based segmentation method for the wrist joint cartilage in magnetic resonance images. The study was conducted in 8 healthy volunteers and 3 patients with wrist joint diseases. 3D MRI datasets (20 in total) were acquired at 1.5T using a VIBE sequence. Wrist cartilage was segmented on coronal slices by a clinician and the convolutional neural network (CNN) was trained, developed and tested using the corresponding segmented masks. For an inter and intra observer study wrist cartilage was segmented by three observers once and twice by one observer on a dataset of 20 central coronal slices. Performance of the CNN was compared quantitatively to the manual segmentations using the concordance and the Sørensen-Dice similarity coefficients (DSC). Cartilage segmentations obtained with the CNN showed a substantial agreement with the manual segmentations for the whole wrist joint (DSC = 0.73) and a good agreement (DSC = 0.81) for the central coronal slices. The inter-and intra-observer concordance indices for manual segmentations were 0.55 and 0.85, respectively. The concordance index of the CNN-based segmentation was 0.69 when compared to the manual segmentations. The fully automatic deep-learning based segmentation of the wrist cartilage showed a high concordance with the manual measurements. It could be applied to determine an automatic, quantitative metric in clinical wrist cartilage studies.