Automatic Semantic Segmentation of Brain Gliomas from MRI Images Using a Deep Cascaded Neural Network.

Shaoguo Cui,Chang Liu,Shuyu Xiong,Lei Mao,Jingfeng Jiang

doi:10.1155/2018/4940593

Abstract

Brain tumors can appear anywhere in the brain and have vastly different sizes and morphology. Additionally, these tumors are often diffused and poorly contrasted. Consequently, the segmentation of brain tumor and intratumor subregions using magnetic resonance imaging (MRI) data with minimal human interventions remains a challenging task. In this paper, we present a novel fully automatic segmentation method from MRI data containing in vivo brain gliomas. This approach can not only localize the entire tumor region but can also accurately segment the intratumor structure. The proposed work was based on a cascaded deep learning convolutional neural network consisting of two subnetworks: (1) a tumor localization network (TLN) and (2) an intratumor classification network (ITCN). The TLN, a fully convolutional network (FCN) in conjunction with the transfer learning technology, was used to first process MRI data. The goal of the first subnetwork was to define the tumor region from an MRI slice. Then, the ITCN was used to label the defined tumor region into multiple subregions. Particularly, ITCN exploited a convolutional neural network (CNN) with deeper architecture and smaller kernel. The proposed approach was validated on multimodal brain tumor segmentation (BRATS 2015) datasets, which contain 220 high-grade glioma (HGG) and 54 low-grade glioma (LGG) cases. Dice similarity coefficient (DSC), positive predictive value (PPV), and sensitivity were used as evaluation metrics. Our experimental results indicated that our method could obtain the promising segmentation results and had a faster segmentation speed. More specifically, the proposed method obtained comparable and overall better DSC values (0.89, 0.77, and 0.80) on the combined (HGG + LGG) testing set, as compared to other methods reported in the literature. Additionally, the proposed approach was able to complete a segmentation task at a rate of 1.54 seconds per slice.

Highlights

Brain cancers are less prevalent, they are very lethal
In the training phase of the Intratumor classification network (ITCN) subnet, we randomly selected 4,700,000 image patches (33 × 33) from the training set, which correspond to 1,175,000 patches for each label (4 different classes)
Visual inspections were conducted for testing data to validate the segmentation results of our proposed method

Summary

Introduction

Gliomas are the most common brain tumors. Some systems were tested and showed good performance, the fully automatic detection and subsequent diagnosis of brain tumors have not been massively used in the clinical settings, thereby indicating that some major developments are still needed [21]. Based on MRI data, our primary goal of this paper was to propose a new fast and accurate computer system that could first localize complete tumor region and segment the more detailed intratumor structure. The performance of the proposed algorithm was assessed in a public database containing 274 cases of in vivo gliomas. The paper is structured as follows: Section 2 presents the related works in the automated brain cancer segmentation.

Relevant Work and Our Contributions

Methods

A CNN with two pathways of both local and global information

Results

Method

Discussions and Conclusions