Abstract
The manual brain tumor annotation process is time consuming and resource consuming, therefore, an automated and accurate brain tumor segmentation tool is greatly in demand. In this paper, we introduce a novel method to integrate location information with the state-of-the-art patch-based neural networks for brain tumor segmentation. This is motivated by the observation that lesions are not uniformly distributed across different brain parcellation regions and that a locality-sensitive segmentation is likely to obtain better segmentation accuracy. Toward this, we use an existing brain parcellation atlas in the Montreal Neurological Institute (MNI) space and map this atlas to the individual subject data. This mapped atlas in the subject data space is integrated with structural Magnetic Resonance (MR) imaging data, and patch-based neural networks, including 3D U-Net and DeepMedic, are trained to classify the different brain lesions. Multiple state-of-the-art neural networks are trained and integrated with XGBoost fusion in the proposed two-level ensemble method. The first level reduces the uncertainty of the same type of models with different seed initializations, and the second level leverages the advantages of different types of neural network models. The proposed location information fusion method improves the segmentation performance of state-of-the-art networks including 3D U-Net and DeepMedic. Our proposed ensemble also achieves better segmentation performance compared to the state-of-the-art networks in BraTS 2017 and rivals state-of-the-art networks in BraTS 2018. Detailed results are provided on the public multimodal brain tumor segmentation (BraTS) benchmarks.
Highlights
Glioma is a common type of brain tumor in adults originating in the glial cells that support neurons and help them function
We demonstrate the advantage of the proposed location information fusion method and the proposed twolevel ensemble learning method
In Experiment 3, we examine different ensemble methods that predict the final brain tumor lesions based on the output probability maps from DeepMedics and 3D U-Nets
Summary
Glioma is a common type of brain tumor in adults originating in the glial cells that support neurons and help them function. Patients with HGG had median survival time (MST) 18 months, and the MST of patients with Grade III and IV glioma were 26 and 13 months, respectively (Noiphithak and Veerasarn, 2017). Gliomas are further divided into four types of sub-regions, namely edema, non-enhancing core, necrotic core, and enhancing core based on the acuteness of the tumor cells that have different appearances in MR imaging data. Segmenting the different sub-regions of gliomas is a daunting task because of the intrinsic heterogeneity which affects their visual appearance as well as shape. The treatment depends on the type, size, shape, grade, and location of the tumor, which varies widely. This observation leads to the importance of an accurate brain tumor segmentation for better diagnosis of brain tumors. The manual annotation process is time consuming and resource consuming, an automated and accurate brain tumor segmentation tool is greatly in demand
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
