Automatic Segmentation of Non-Tumor Tissues in Glioma MR Brain Images Using Deformable Registration with Partial Convolutional Networks

TL;DR

This paper introduces a novel registration method combining tumor segmentation with partial convolutional networks to improve normal tissue segmentation in glioma MR images, addressing variability challenges.

Contribution

It presents a new approach that reduces pathological variability effects in deformable registration by simulating normal tissues within tumor regions before registration.

Findings

Significant improvement in Dice coefficient for gray matter segmentation.

Enhanced accuracy in normal tissue segmentation around tumors.

Effective handling of pathological variability in brain image registration.

Abstract

In brain tumor diagnosis and surgical planning, segmentation of tumor regions and accurate analysis of surrounding normal tissues are necessary for physicians. Pathological variability often renders difficulty to register a well-labeled normal atlas to such images and to automatic segment/label surrounding normal brain tissues. In this paper, we propose a new registration approach that first segments brain tumor using a U-Net and then simulates missed normal tissues within the tumor region using a partial convolutional network. Then, a standard normal brain atlas image is registered onto such tumor-removed images in order to segment/label the normal brain tissues. In this way, our new approach greatly reduces the effects of pathological variability in deformable registration and segments the normal tissues surrounding brain tumor well. In experiments, we used MICCAI BraTS2018 T1 tumor images to evaluate the proposed algorithm. By comparing direct registration with the proposed algorithm, the results showed that the Dice coefficient for gray matters was significantly improved for surrounding normal brain tissues.