Back to articles
Regular Articles
Volume: 64 | Article ID: jist0846
Image
Integrating Improved U-Net and Continuous Maximum Flow Algorithm for 3D Brain Tumor Image Segmentation
  DOI :  10.2352/J.ImagingSci.Technol.2020.64.4.040412  Published OnlineJuly 2020
Abstract
Abstract

To address the issues of the relatively small size of brain tumor image datasets, severe class imbalance, and low precision in existing segmentation algorithms for brain tumor images, this study proposes a two-stage segmentation algorithm integrating convolutional neural networks (CNNs) and conventional methods. Four modalities of the original magnetic resonance images were first preprocessed separately. Next, preliminary segmentation was performed using an improved U-Net CNN containing deep monitoring, residual structures, dense connection structures, and dense skip connections. The authors adopted a multiclass Dice loss function to deal with class imbalance and successfully prevented overfitting using data augmentation. The preliminary segmentation results subsequently served as the a priori knowledge for a continuous maximum flow algorithm for fine segmentation of target edges. Experiments revealed that the mean Dice similarity coefficients of the proposed algorithm in whole tumor, tumor core, and enhancing tumor segmentation were 0.9072, 0.8578, and 0.7837, respectively. The proposed algorithm presents higher accuracy and better stability in comparison with some of the more advanced segmentation algorithms for brain tumor images.

Subject Areas :
Views 34
Downloads 5
 articleview.views 34
 articleview.downloads 5
  Cite this article 

Kexin Bai, Qiang Li, Ching-Hsin Wang, "Integrating Improved U-Net and Continuous Maximum Flow Algorithm for 3D Brain Tumor Image Segmentationin Journal of Imaging Science and Technology,  2020,  pp 040412-1 - 040412-11,  https://doi.org/10.2352/J.ImagingSci.Technol.2020.64.4.040412

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2020
  Article timeline 
  • received January 2020
  • accepted March 2020
  • PublishedJuly 2020

Preprint submitted to:
  Login or subscribe to view the content