Memory Network-Based Quality Normalization of Magnetic Resonance Images for Brain Segmentation
Medical images of the same modality but acquired at different centers, with different machines, using different protocols, and by different operators may have highly variable quality. Due to its limited generalization ability, a deep learning model usually cannot achieve the same performance on another database as it has done on the database with which it was trained. In this paper, we use the segmentation of brain magnetic resonance (MR) images as a case study to investigate the possibility of improving the performance of medical image analysis via normalizing the quality of images. Specifically, we propose a memory network (MemNet)-based algorithm to normalize the quality of brain MR images and adopt the widely used 3D U-Net to segment the images before and after quality normalization. We evaluated the proposed algorithm on the benchmark IBSR V2.0 database. Our results suggest that the MemNet-based algorithm can not only normalize and improve the quality of brain MR images, but also enable the same 3D U-Net to produce substantially more accurate segmentation of major brain tissues.
KeywordsMedical image quality normalization Deep learning Magnetic resonance image Brain tissue segmentation
This work was supported in part by the Science and Technology Innovation Committee of Shenzhen Municipality, China, under Grants JCYJ20180306171334997, and in part by the National Natural Science Foundation of China under Grants 61771397, in part by the Northwestern Polytechnical University Graduate School and Enterprise Cooperative Innovation Fund under Grant XQ201911, and in part by the Project for Graduate Innovation team of Northwestern Polytechnical University.
- 10.Tai, Y., Yang, J., Liu, X.M., Xu, C.Y.: MemNet: a persistent memory network for image restoration. In: IEEE International Conference on Computer Vision, pp. 4539–4547 (2017)Google Scholar
- 11.Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Brox, T., Rooneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 234–241 (2015)Google Scholar
- 12.School, M.G.H.H.M.: The Internet Brain Segmentation Repository (IBSR). http://www.cma.mgh.harvard.edu/ibsr/index.html
- 16.Glorot, X., Bengio, Y.: Understanding the difficulty of training deep feedforward neural networks. In: 13th International Conference on Artificial Intelligence and Statistics (2010)Google Scholar
- 17.Mao, X., Shen, C., Yang, Y.: Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. In: Neural Information Processing Systems (2016)Google Scholar