当前位置: X-MOL 学术Int. J. Imaging Syst. Technol. › 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.)
Multi‐Scale 3D U‐Nets: An approach to automatic segmentation of brain tumor
International Journal of Imaging Systems and Technology ( IF 3.0 ) Pub Date : 2019-09-18 , DOI: 10.1002/ima.22368
Suting Peng 1 , Wei Chen 1 , Jiawei Sun 1 , Boqiang Liu 1
Affiliation  

Gliomas segmentation is a critical and challenging task in surgery and treatment, and it is also the basis for subsequent evaluation of gliomas. Magnetic resonance imaging is extensively employed in diagnosing brain and nervous system abnormalities. However, brain tumor segmentation remains a challenging task, because differentiating brain tumors from normal tissues is difficult, tumor boundaries are often ambiguous and there is a high degree of variability in the shape, location, and extent of the patient. It is therefore desired to devise effective image segmentation architectures. In the past few decades, many algorithms for automatic segmentation of brain tumors have been proposed. Methods based on deep learning have achieved favorable performance for brain tumor segmentation. In this article, we propose a Multi‐Scale 3D U‐Nets architecture, which uses several U‐net blocks to capture long‐distance spatial information at different resolutions. We upsample feature maps at different resolutions to extract and utilize sufficient features, and we hypothesize that semantically similar features are easier to learn and process. In order to reduce the computational cost, we use 3D depthwise separable convolution instead of some standard 3D convolution. On BraTS 2015 testing set, we obtained dice scores of 0.85, 0.72, and 0.61 for the whole tumor, tumor core, and enhancing tumor, respectively. Our segmentation performance was competitive compared to other state‐of‐the‐art methods.

中文翻译:

Multi-Scale 3D U-Nets:一种自动分割脑肿瘤的方法

胶质瘤分割是手术和治疗中一项关键且具有挑战性的任务,也是后续评估胶质瘤的基础。磁共振成像广泛用于诊断大脑和神经系统异常。然而,脑肿瘤分割仍然是一项具有挑战性的任务,因为将脑肿瘤与正常组织区分开来很困难,肿瘤边界通常不明确,并且患者的形状、位置和范围存在高度可变性。因此需要设计有效的图像分割架构。在过去的几十年里,已经提出了许多用于脑肿瘤自动分割的算法。基于深度学习的方法在脑肿瘤分割方面取得了良好的性能。在本文中,我们提出了多尺度 3D U-Nets 架构,它使用多个 U-net 块来捕获不同分辨率的长距离空间信息。我们对不同分辨率的特征图进行上采样以提取和利用足够的特征,我们假设语义相似的特征更容易学习和处理。为了降低计算成本,我们使用 3D 深度可分离卷积代替一些标准的 3D 卷积。在 BraTS 2015 测试集上,我们分别获得了整个肿瘤、肿瘤核心和增强肿瘤的骰子评分 0.85、0.72 和 0.61。与其他最先进的方法相比,我们的分割性能具有竞争力。我们假设语义相似的特征更容易学习和处理。为了降低计算成本,我们使用 3D 深度可分离卷积代替一些标准的 3D 卷积。在 BraTS 2015 测试集上,我们分别获得了整个肿瘤、肿瘤核心和增强肿瘤的骰子评分 0.85、0.72 和 0.61。与其他最先进的方法相比,我们的分割性能具有竞争力。我们假设语义相似的特征更容易学习和处理。为了降低计算成本,我们使用 3D 深度可分离卷积代替一些标准的 3D 卷积。在 BraTS 2015 测试集上,我们分别获得了整个肿瘤、肿瘤核心和增强肿瘤的骰子评分 0.85、0.72 和 0.61。与其他最先进的方法相比,我们的分割性能具有竞争力。
更新日期:2019-09-18
down
wechat
bug