AFPNet: A 3D fully convolutional neural network with atrous-convolution feature pyramid for brain tumor segmentation via MRI images
AFPNet: A 3D fully convolutional neural network with atrous-convolution feature pyramid for brain tumor segmentation via MRI images
复制标题
AFPNet：具有空洞卷积特征金字塔的 3D 全卷积神经网络，用于通过 MRI 图像进行脑肿瘤分割
DOI：
10.1016/j.neucom.2020.03.097
复制
发表时间：
2020-08-18
期刊：
影响因子：
6
通讯作者：
Jia, Yuanyuan
中科院分区：
文献类型：
--
作者：
Zhou, Zexun;He, Zhongshi;Jia, Yuanyuan
传统的用于全自动脑肿瘤分割的深度卷积神经网络存在两个问题：重复池化/跨越导致的空间信息丢失和多尺度病变处理能力弱。为了克服第一个问题，我们使用具有单个步幅的3D逆卷积来代替池化/步幅，并为特征学习构建骨干。对于第二个问题，设计了一个三维反卷积特征金字塔，并将其添加到主干的末端。通过与上下文特征相结合，该结构提高了整体模型分割各种大小肿瘤的区分能力。最后，构造一个3D全连接条件随机场作为网络输出的后处理步骤，以获得外观和空间一致性的结构分割。在MRI数据集上进行的大量消融实验表明，该方法驱动的无损特征计算和多尺度信息融合是解决上述问题的可行方法。与公共基准上的最先进的方法相比，我们的方法具有竞争力的性能，可以有效地实施到临床医学应用。(C)2020爱思唯尔B.V.保留所有权利。
Traditional deep convolutional neural networks for fully automatic brain tumor segmentation have two problems: spatial information loss caused by both the repeated pooling/striding and weak ability of multi-scale lesion processing. To overcome the first problem, we use a 3D atrous-convolution with a single stride to replace pooling/striding and build the backbone for feature learning. For the second problem, a 3D atrous-convolution feature pyramid is designed and added to the end of the backbone. By integrating with contextual features, this structure improves the discriminating ability of the overall model to segment tumors with various sizes. Finally, a 3D fully connected Conditional Random Field is constructed as a post-processing step for the network's output to obtain structural segmentation of both the appearance and spatial consistency. Abundant ablation experiments carried on Magnetic Resonance Imaging datasets demonstrate that lossless feature computation and multi-scale information fusion driven by our method are feasible to address the above problems. Compared with the state-of-the-art methods on the public benchmarks, our method achieves competitive performance and can be efficiently implemented into the clinical medical application. (C) 2020 Elsevier B.V. All rights reserved.