Improving 3D Brain Tumor Segmentation With Predict-Refine Mechanism Using Saliency And Feature Maps

Improving 3D Brain Tumor Segmentation With Predict-Refine Mechanism Using Saliency And Feature Maps
Title:
Improving 3D Brain Tumor Segmentation With Predict-Refine Mechanism Using Saliency And Feature Maps
Other Titles:
IEEE International Conference on Image Processing (ICIP)
Publication Date:
01 October 2020
Citation:
Abstract:
This paper demonstrates the use of 3D Anisotropic Convolutional Neural Network (CNN) with predict-refine mechanism for 3D brain tumor segmentation. We propose two networks that utilize multi-scale feedback and saliency maps respectively to segment three critical regions involved in automated brain tumor segmentation. The proposed networks are formulated to predict feature maps at different resolutions during the prediction phase. These networks perform refinement process using the saliency or feature maps as feedback information for the refinement process. The recurrent architecture allows the network to automatically rectify errors in saliency map of the previous prediction phase resulting in more reliable final predictions. Our experimental results on the BraTS2017 dataset demonstrate the superior performance of our proposed predict-refine architecture than current state of the art approaches improving results by up to 8% without any additional increase in the 1.9M model parameters.
License type:
http://creativecommons.org/licenses/by-nc/4.0/
Funding Info:
This project is supported by the IAF-ICP Implementing Agency under its RIE 2020 Industry alignment Fund – Industry collaboration Projects (IAF-ICP) Grant No. - I1901E004
Description:
“© 2020 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.”
ISSN:
2381-8549
Files uploaded:
File Size Format Action
There are no attached files.