The authors of this study developed a deep learning model used for segmenting fat metaplasia (FM) on sacroiliac joint (SIJ) MRI with the additional aim of utilizing the deep learning model to classify axial spondyloarthritis (axSpA) and non-axSpA. They were able to conclude that the deep learning model could automatically and accurately segment FM on SIJ MRI, helping to increase the radiologist’s performance, with applications in improving diagnosis and progression of axSpA.
Key points:
- Deep learning was used for automatic segmentation of fat metaplasia on MRI.
- UNet-based models achieved automatic and accurate segmentation of fat metaplasia.
- Automatic segmentation facilitates quantitative analysis of fat metaplasia to improve diagnosis and prognosis of axial spondyloarthritis.
Article: Automatic segmentation of fat metaplasia on sacroiliac joint MRI using deep learning
Authors: Xin Li, Yi Lin, Zhuoyao Xie, Zixiao Lu, Liwen Song, Qiang Ye, Menghong Wang, Xiao Fang, Yi He, Hao Chen & Yinghua Zhao
