当前位置: X-MOL 学术Neurocomputing › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Brain Tumor Segmentation of Multi-Modality MR Images via Triple Intersecting U-Nets
Neurocomputing ( IF 6 ) Pub Date : 2021-01-01 , DOI: 10.1016/j.neucom.2020.09.016
Jinjing Zhang , Jianchao Zeng , Pinle Qin , Lijun Zhao

Abstract In this paper, we propose a triple intersecting U-Nets (TIU-Nets) for brain glioma segmentation. First, the proposed TIU-Nets is composed of binary-class segmentation U-Net (BU-Net) and multi-class segmentation U-Net (MU-Net), in which MU-Net reuses multi-resolution features from BU-Net. Second, we introduce a segmentation soft-mask predicted by BU-Net, that is, candidate glioma region is generated by removing most of non-glioma backgrounds, which guides multi-category segmentation of MU-Net in a weighted manner. Third, an edge branch in MU-Net is leveraged to enhance boundary information of glioma substructure, which facilitates to locate glioma true boundaries and improve segmentation accuracy. Finally, we propose a sigmoid-evolution based polarized cross-entropy loss (S-CE) to resolve class unbalance problem, and apply S-CE loss to soft-mask prediction loss in BU-Net, multi-class segmentation loss in MU-Net and edge prediction loss in edge branch. Experimental results have demonstrated that the proposed 2D/3D TIU-Nets achieves a higher segmentation accuracy than corresponding 2D/3D state-of-the-art segmentation methods including FCN, U-Net, SegNet, CRDN, IVD-Net, FCDenseNet, DeepMedic, DMFNet, etc, evaluating on publicly available brain tumor segmentation challenge 2015 (BRATS2015) datasets. To show the universality of the proposed method, we also give a comparison of segmentation performance on BrainWeb dataset.

中文翻译:

通过三重交叉 U-Nets 对多模态 MR 图像进行脑肿瘤分割

摘要 在本文中,我们提出了一种用于脑胶质瘤分割的三重交叉 U-Nets (TIU-Nets)。首先,提出的 TIU-Nets 由二元类分割 U-Net (BU-Net) 和多类分割 U-Net (MU-Net) 组成,其中 MU-Net 重用了 BU-Net 的多分辨率特征. 其次,我们引入了 BU-Net 预测的分割软掩码,即通过去除大部分非神经胶质瘤背景生成候选神经胶质瘤区域,以加权的方式指导 MU-Net 的多类别分割。第三,利用MU-Net中的边缘分支来增强胶质瘤亚结构的边界信息,有助于定位胶质瘤真实边界并提高分割精度。最后,我们提出了一种基于 sigmoid-evolution 的极化交叉熵损失 (S-CE) 来解决类不平衡问题,并将 S-CE 损失应用于 BU-Net 中的软掩码预测损失、MU-Net 中的多类分割损失和边缘分支中的边缘预测损失。实验结果表明,所提出的 2D/3D TIU-Nets 比相应的 2D/3D 最先进的分割方法(包括 FCN、U-Net、SegNet、CRDN、IVD-Net、FCDenseNet、DeepMedic)实现了更高的分割精度、DMFNet 等,评估公开可用的脑肿瘤分割挑战 2015 (BRATS2015) 数据集。为了显示所提出方法的通用性,我们还对 BrainWeb 数据集上的分割性能进行了比较。实验结果表明,所提出的 2D/3D TIU-Nets 比相应的 2D/3D 最先进的分割方法(包括 FCN、U-Net、SegNet、CRDN、IVD-Net、FCDenseNet、DeepMedic)实现了更高的分割精度、DMFNet 等,评估公开可用的脑肿瘤分割挑战 2015 (BRATS2015) 数据集。为了显示所提出方法的通用性,我们还对 BrainWeb 数据集上的分割性能进行了比较。实验结果表明,所提出的 2D/3D TIU-Nets 比相应的 2D/3D 最先进的分割方法(包括 FCN、U-Net、SegNet、CRDN、IVD-Net、FCDenseNet、DeepMedic)实现了更高的分割精度、DMFNet 等,评估公开可用的脑肿瘤分割挑战 2015 (BRATS2015) 数据集。为了显示所提出方法的通用性,我们还对 BrainWeb 数据集上的分割性能进行了比较。
更新日期:2021-01-01
down
wechat
bug