We propose a dual pathway, 11-layers deep, three-dimensional Convolutional Neural Network for the challenging task of brain lesion segmentation. The devised architecture is the result of an in-depth analysis of the limitations of current networks proposed for similar applications. To overcome the computational burden of processing 3D medical scans, we have developed an efficient and effective dense training scheme which automatically adapts to the inherent class imbalance present in the data. The training makes use of the notion of image segments which joins multiple patches from the same image into one pass through the network. Further, we analyze the development of deeper, thus more discriminative 3D CNNs. In order to incorporate both local and larger contextual information, we employ a dual pathway architecture that processes the input images at multiple scales simultaneously. For post-processing of the network's soft segmentation, we use a 3D fully connected Conditional Random Field which effectively removes false positives. Our pipeline is extensively evaluated on three challenging tasks of lesion segmentation in multi-channel MRI patient data with traumatic brain injuries, brain tumors, and ischemic stroke. We improve on the state-of-the-art for all three applications, with top ranking performance on the public benchmarks BRATS 2015 and ISLES 2015. Our method is computationally efficient and achieves a segmentation of a brain scan in less than six minutes. The source code of our implementation is made publicly available.

本文介绍了一种分割脑损伤的新方法，主要采用3D卷积神经网络，同时处理不同尺度的图像，通过实验证明具有更好的性能。

基于多尺度3D卷积神经网络和完全连接条件随机场的高效脑部病变分割