1. Second-order ResU-Net for automatic MRI brain tumor segmentation
- Author
-
Dongwei Liu, Jianxia Zhang, Jianxin Zhang, Chao Che, and Ning Sheng
- Subjects
Computer science ,Brain tumor ,Neuroimaging ,02 engineering and technology ,Field (computer science) ,Second order statistics ,0502 economics and business ,QA1-939 ,Image Processing, Computer-Assisted ,0202 electrical engineering, electronic engineering, information engineering ,medicine ,Humans ,Segmentation ,Mri brain ,medicine.diagnostic_test ,Brain Neoplasms ,business.industry ,Applied Mathematics ,05 social sciences ,u-net ,Magnetic resonance imaging ,Pattern recognition ,General Medicine ,brain tumor segmentation ,medicine.disease ,second-order statistics ,Magnetic Resonance Imaging ,Computational Mathematics ,Modeling and Simulation ,020201 artificial intelligence & image processing ,Neural Networks, Computer ,Artificial intelligence ,residual module ,General Agricultural and Biological Sciences ,business ,Brain tumor segmentation ,TP248.13-248.65 ,Mathematics ,050203 business & management ,Biotechnology ,Tumor segmentation - Abstract
Tumor segmentation using magnetic resonance imaging (MRI) plays a significant role in assisting brain tumor diagnosis and treatment. Recently, U-Net architecture with its variants have become prevalent in the field of brain tumor segmentation. However, the existing U-Net models mainly exploit coarse first-order features for tumor segmentation, and they seldom consider the more powerful second-order statistics of deep features. Therefore, in this work, we aim to explore the effectiveness of second-order statistical features for brain tumor segmentation application, and further propose a novel second-order residual brain tumor segmentation network, i.e., SoResU-Net. SoResU-Net utilizes a number of second-order modules to replace the original skip connection operations, thus augmenting the series of transformation operations and increasing the non-linearity of the segmentation network. Extensive experimental results on the BraTS 2018 and BraTS 2019 datasets demonstrate that SoResU-Net outperforms its baseline, especially on core tumor and enhancing tumor segmentation, illuminating the effectiveness of second-order statistical features for the brain tumor segmentation application.
- Published
- 2021