Whole brain segmentation method from 2.5D brain MRI slice image based on Triple U-Net

作者：Chen, Xingyan; Jiang, Shaofeng^*; Guo, Lanting; Chen, Zhen; Zhang, Congxuan

来源：VISUAL COMPUTER, 2023, 39(1): 255-266.

DOI：10.1007/s00371-021-02326-9

• Triple U-Net
• 2
• 5D slice image
• Whole brain segmentation
• Inter-layer constraints

With the application of magnetic resonance imaging (MRI) in the diagnosis of brain diseases, MRI has become a powerful tool for clinical neuroimaging analysis, and whole brain segmentation is a very important step of neuroimaging analysis. In order to promote segmentation accuracy, this paper makes full use of the spatial constraint information between adjacent slice of MRI brain image sequence, and combines three consecutive images into one image named 2.5D slice image. Through 2.5D slice image, a triple U-Net-based whole brain segmentation method is proposed, which is composed of one main U-Net and two auxiliary U-Nets. Moreover, this network introduces three auxiliary outputs to provide inter-layer constraints for the final prediction, and uses a multi-auxiliary hybrid loss function based on binary cross-entropy loss and dice loss to optimize the training model. In this paper, a comprehensive comparative experiment is carried out on LPBA40 dataset and IBSR18 dataset. The experimental results show that the dice coefficient, specificity and sensitivity of this method are 98.23%, 99.62% and 98.54%, respectively, on LPBA40 dataset, and 97.01%, 99.45% and 98%, respectively, on IBSR18 dataset. The experiments show that the accuracy of whole brain segmentation is greatly improved by the proposed triple U-Net.

• 单位
  南昌航空大学