The study objective was to investigate the performance of a dedicated convolutional neural network (CNN) optimized for wrist cartilage segmentation from 2D MR images. CNN utilized a planar architecture and patch-based (PB) training approach that ensured optimal performance in the presence of a limited amount of training data. The CNN was trained and validated in twenty multi-slice MRI datasets acquired with two different coils in eleven subjects (healthy volunteers and patients). The validation included a comparison with the alternative state-of-the-art CNN methods for the segmentation of joints from MR images and the ground-truth manual segmentation. When trained on the limited training data, the CNN outperformed significantly image-based and patch-based U-Net networks. Our PB-CNN also demonstrated a good agreement with manual segmentation (Sorensen-Dice similarity coefficient (DSC) = 0.81) in the representative (central coronal) slices with large amount of cartilage tissue. Reduced performance of the network for slices with a very limited amount of cartilage tissue suggests the need for fully 3D convolutional networks to provide uniform performance across the joint. The study also assessed inter- and intra-observer variability of the manual wrist cartilage segmentation (DSC=0.78-0.88 and 0.9, respectively). The proposed deep-learning-based segmentation of the wrist cartilage from MRI could facilitate research of novel imaging markers of wrist osteoarthritis to characterize its progression and response to therapy.
@article{arxiv.1811.01123,
title = {Deep learning-based fully automatic segmentation of wrist cartilage in MR images},
author = {Ekaterina Brui and Aleksandr Y. Efimtcev and Vladimir A. Fokin and Remi Fernandez and Anatoliy G. Levchuk and Augustin C. Ogier and Alexey A. Samsonov and Jean. P. Mattei and Irina V. Melchakova and David Bendahan and Anna Andreychenko},
journal= {arXiv preprint arXiv:1811.01123},
year = {2020}
}