Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation
Deep 3D Convolutional Encoder Networks With Shortcuts for Multiscale Feature Integration Applied to Multiple Sclerosis Lesion Segmentation
复制标题
DOI：
10.1109/tmi.2016.2528821
复制
发表时间：
2016-05-01
影响因子：
10.6
通讯作者：
Tam, Roger
中科院分区：
文献类型：
--
作者：
Brosch, Tom;Tang, Lisa Y. W.;Tam, Roger
提出了一种基于带最短连接的深度3D卷积编码网络的分割方法，并将其应用于磁共振图像中多发性硬化(MS)病变的分割。我们的模型是一个由两条相互连接的路径组成的神经网络，一个卷积路径，它学习越来越抽象和更高层次的图像特征，以及一个去卷积路径，它在体素级别预测最终的分割。特征提取和预测路径的联合训练允许自动学习不同尺度上的特征，这些特征针对图像类型和分割任务的任何给定组合的精确度进行了优化。此外，两条通路之间的快捷连接允许整合高水平和低水平特征，这使得能够分割各种大小的病变。我们在两个公开可用的数据集(MICCAI 2008和ISBI 2015 Challenges)上对我们的方法进行了评估，结果表明，即使只有相对较小的数据集可供训练，我们的方法也可以与排名靠前的最先进方法相媲美。此外，我们在一项MS临床试验的大型数据集上，将我们的方法与五种免费且广泛使用的MS病变分割方法(EMS、LST-LPA、LST-LGA、病变TOADS和SLS)进行了比较。结果表明，我们的方法在广泛的病变大小范围内始终优于其他方法。
We propose a novel segmentation approach based on deep 3D convolutional encoder networks with shortcut connections and apply it to the segmentation of multiple sclerosis (MS) lesions in magnetic resonance images. Our model is a neural network that consists of two interconnected pathways, a convolutional pathway, which learns increasingly more abstract and higher-level image features, and a deconvolutional pathway, which predicts the final segmentation at the voxel level. The joint training of the feature extraction and prediction pathways allows for the automatic learning of features at different scales that are optimized for accuracy for any given combination of image types and segmentation task. In addition, shortcut connections between the two pathways allow high- and low-level features to be integrated, which enables the segmentation of lesions across a wide range of sizes. We have evaluated our method on two publicly available data sets (MICCAI 2008 and ISBI 2015 challenges) with the results showing that our method performs comparably to the top-ranked state-of-the-art methods, even when only relatively small data sets are available for training. In addition, we have compared our method with five freely available and widely used MS lesion segmentation methods (EMS, LST-LPA, LST-LGA, Lesion-TOADS, and SLS) on a large data set from an MS clinical trial. The results show that our method consistently outperforms these other methods across a wide range of lesion sizes.