AUTHOR=Chen Hao , Zhao Na , Tan Tao , Kang Yan , Sun Chuanqi , Xie Guoxi , Verdonschot Nico , Sprengers André TITLE=Knee Bone and Cartilage Segmentation Based on a 3D Deep Neural Network Using Adversarial Loss for Prior Shape Constraint JOURNAL=Frontiers in Medicine VOLUME=Volume 9 - 2022 YEAR=2022 URL=https://www.frontiersin.org/journals/medicine/articles/10.3389/fmed.2022.792900 DOI=10.3389/fmed.2022.792900 ISSN=2296-858X ABSTRACT=Fast and accurate segmentation of knee bone and cartilage on MRI images is becoming increasingly important in the orthopaedic area, as the segmentation is an essential prerequisite step to a patient-specific diagnosis, optimising implant design, and pre- and intra- operative planning. However, manual segmentation is time-intensive and subject to inter- and intra- observer variation. Hence, in this study, a 3D deep neural network using adversarial loss was proposed to automatically segment the knee bone in a resampled image volume in order to enlarging the contextual information and incorporating prior shape constraint. A restoration network was proposed to further improve the bone segmentation accuracy by restoring the bone segmentation back to the original resolution. A conventional U-Net like network was used to segment the cartilage. The ultimate results were the combination of the bone and cartilage outcomes through post-processing. The quality of the proposed method was thoroughly assessed using various measures for the dataset from Grand Challenge SKI10, together with a comparison with a baseline network U-Net. A fined tuned U-Net like network can achieve state-of-the-art results without any post-processing operations. Our method achieved a total score higher than 76 in terms of SKI10 validation dataset. Our method showed to be robust to extract bone and cartilage mask from MRI dataset, even for the pathological case.