A novel multi-atlas segmentation approach under the semi-supervised learning framework: Application to knee cartilage segmentation

• Published in: Computer methods and programs in biomedicine 2022-12, Vol.227, p.107208-107208, Article 107208
• Main Authors: Chadoulos, Christos G., Tsaopoulos, Dimitrios E., Moustakidis, Serafeim, Tsakiridis, Nikolaos L., Theocharis, John B.
• Format: Article
• Language: English
• Subjects: Knee cartilage segmentation; Magnetic resonance imaging (MRI); Multi-Atlas patch-Based; Osteoarthritis (OA); Semi-Supervised learning (SSL); Sparse coding (SC)
• ISSN: 0169-2607; 1872-7565
• DOI: 10.1016/j.cmpb.2022.107208

•A multi-atlas semi-supervised framework for knee cartilage segmentation is proposed.•Both local and global information is incorporated through the construction of two sparse graphs.•3D-HOG features are used for better characterization of voxel patches.•A fast iterative sampling scheme is employed to speed-up the labeling process.•The framework was applied to the Osteoarthritis Initiative data repository Background and objective: Multi-atlas based segmentation techniques, which rely on an atlas library comprised of training images labeled by an expert, have proven their effectiveness in multiple automatic segmentation applications. However, the usage of exhaustive patch libraries combined with the voxel-wise labeling incur a large computational cost in terms of memory requirements and execution times. Methods: To confront this shortcoming, we propose a novel two-stage multi-atlas approach designed under the Semi-Supervised Learning (SSL) framework. The main properties of our method are as follows: First, instead of the voxel-wise labeling approach, the labeling of target voxels is accomplished here by exploiting the spectral content of globally sampled datasets from the target image, along with their spatially correspondent data collected from the atlases. Following SSL, voxels classification is boosted by incorporating unlabeled data from the target image, in addition to the labeled ones from atlas library. Our scheme integrates constructively fruitful concepts, including sparse reconstructions of voxels from linear neighborhoods, HOG feature descriptors of patches/regions, and label propagation via sparse graph constructions. Segmentation of the target image is carried out in two stages: stage-1 focuses on the sampling and labeling of global data, while stage-2 undertakes the above tasks for the out-of-sample data. Finally, we propose different graph-based methods for the labeling of global data, while these methods are extended to deal with the out-of-sample voxels. Results: A thorough experimental investigation is conducted on 76 subjects provided by the publicly accessible Osteoarthritis Initiative (OAI) repository. Comparative results and statistical analysis demonstrate that the suggested methodology exhibits superior segmentation performance compared to the existing patch-based methods, across all evaluation metrics (DSC:88.89%, Precision: 89.86%, Recall: 88.12%), while at the same time it requires a considerably reduced computational load (>70% re