arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1505.03540cs.CVcs.AI
收藏

基于深度神经网络的脑肿瘤分割

Brain Tumor Segmentation with Deep Neural Networks

Université de Sherbrooke(舍布鲁克大学);École Normale supérieure(巴黎高等师范学院);Université de Montréal(蒙特利尔大学);École polytechnique(巴黎综合理工学院);École Polytechnique de Montréal(蒙特利尔工程学院);Twitter(推特)

Mohammad Havaei, Axel Davy, David Warde-Farley, Antoine Biard, Aaron Courville, Yoshua Bengio, Chris Pal, Pierre-Marc Jodoin, Hugo Larochelle

摘要:

本文提出了一种基于深度神经网络(DNNs)的全自动脑肿瘤分割方法。所提出的网络是针对MR图像中的胶质母细胞瘤(低级别和高级别)而设计的。就其本质而言,这些肿瘤可以出现在大脑的任何地方,几乎具有任何形状,大小和对比度。这些原因促使我们探索一种机器学习解决方案,该解决方案利用灵活、高容量的DNN,同时非常高效。在这里,我们给出了不同的模型选择,我们发现是必要的,以获得有竞争力的性能的描述。我们特别探索基于卷积神经网络(CNN)的不同架构,即专门适用于图像数据的DNN。我们提出了一种新的CNN架构,它不同于传统上用于计算机视觉。我们的CNN同时利用本地特征和更多的全局上下文特征。此外,与CNN的大多数传统用途不同,我们的网络使用的最终层是完全连接层的卷积实现,可以实现40倍的速度。我们还描述了一个2阶段的训练过程,使我们能够解决与肿瘤标记不平衡相关的困难。最后,我们探索了一种级联架构,其中基本CNN的输出被视为后续CNN的额外信息源。2013年BRATS测试数据集上报告的结果显示,我们的架构比目前发布的最先进的架构有所改进,同时速度提高了30倍以上。

英文摘要:

In this paper, we present a fully automatic brain tumor segmentation method based on Deep Neural Networks (DNNs). The proposed networks are tailored to glioblastomas (both low and high grade) pictured in MR images. By their very nature, these tumors can appear anywhere in the brain and have almost any kind of shape, size, and contrast. These reasons motivate our exploration of a machine learning solution that exploits a flexible, high capacity DNN while being extremely efficient. Here, we give a description of different model choices that we've found to be necessary for obtaining competitive performance. We explore in particular different architectures based on Convolutional Neural Networks (CNN), i.e. DNNs specifically adapted to image data. We present a novel CNN architecture which differs from those traditionally used in computer vision. Our CNN exploits both local features as well as more global contextual features simultaneously. Also, different from most traditional uses of CNNs, our networks use a final layer that is a convolutional implementation of a fully connected layer which allows a 40 fold speed up. We also describe a 2-phase training procedure that allows us to tackle difficulties related to the imbalance of tumor labels. Finally, we explore a cascade architecture in which the output of a basic CNN is treated as an additional source of information for a subsequent CNN. Results reported on the 2013 BRATS test dataset reveal that our architecture improves over the currently published state-of-the-art while being over 30 times faster.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑