Cascaded hybrid residual U-Net for glioma segmentation
- PDF / 1,325,511 Bytes
- 19 Pages / 439.37 x 666.142 pts Page_size
- 29 Downloads / 175 Views
Cascaded hybrid residual U-Net for glioma segmentation Jiaosong Long, et al. [full author details at the end of the article] Received: 16 July 2019 / Revised: 26 April 2020 / Accepted: 11 June 2020 # Springer Science+Business Media, LLC, part of Springer Nature 2020
Abstract
Glioma segmentation is critical for making surgical plans. Recently, the traditional glioma segmentation method is less competitive with two deep learning segmentation strategies: the patch-based method which focuses more on the local feature for each pixel, and the image-based method which fully leverages the global feature and captures the overall shape, size and other characteristics of the lesion in a neighborhood of a pixel. In this study, we investigate and integrate the advantages of 2-D and 3-D image-based architectures, and propose a new convolutional neural network called the Cascaded Hybrid Residual U-Net (CHR-U-Net) for MRI glioma segmentation. The CHR-U-Net exploits both the 2D local features as well as the 3D global spatial contextual information simultaneously. In the first-level of CHR-U-Net, the R-2D-U-Net combines the 2D-U-Net and the residual unit for quick lesion area detecting without any miss. To prevent from missing false-positive pixels, the output of R-2D-U-Net is resampled by using the hard-mining to collect more possible falsepositive samples. In the second-level of CHR-U-Net, the axial, coronal, and sagittal 3D-U-Nets are trained to predict whether pixels belong to the area of glioma. The results of three 3D-U-Nets are fused to improve the accuracy and reduce false positives. The database of 2017 BRATS challenge were used in our experiments for the verification. The Dices and Sensitivities of Enhancing, Whole, and Core areas were calculated. The Dices are 0.73, 0.90, and 0.83 and the Sensitivities are 0.83, 0.90, and 0.82, respectively, for the axial, coronal, and sagittal 3D-U-Nets. Experimental results show that the proposed model significantly improves the performance of glioma segmentation. Keywords Glioma segmentation . Deep learning . Hybrid . U-Net . BRATS
1 Introduction Glioma is a common and highly lethal form of brain cancer. According to the national institute in the study of brain cancer [40], it is estimated that more than 13,000 patients died and 29,000 patients suffer from the glioma each year. In UK [23], more than 4200 new patients are diagnosed to have the disease annually. Clinical result illustrates that the survival rate is very
Multimedia Tools and Applications
low especially for glioblastomas. In addition, glioblastomas is commonly found among the children between 5 and 10 years old, and the adults between 30 and 40. Moreover, malignant gliomas is more common than other types of brain cancer in children [11]. Brain tissues consist of cerebrospinal fluid, white matter, and gray matter. As an obscure and too complex cancer, glioma is attached to white matter fiber and is very hard to be distinguished from normal tissues. MRI is commonly used for examining glioma, which is composed of multim
Data Loading...
