3D deeply supervised network for automated segmentation of volumetric medical images
3D deeply supervised network for automated segmentation of volumetric medical images
复制标题
DOI：
10.1016/j.media.2017.05.001
复制
发表时间：
2017-10-01
影响因子：
10.9
通讯作者：
Heng, Pheng-Ann
中科院分区：
文献类型：
--
作者：
Dou, Qi;Yu, Lequan;Heng, Pheng-Ann
虽然深度卷积神经网络（CNN）在2D医学图像分割方面取得了显着的成功，但由于一些相互影响的挑战，包括体积图像中复杂的解剖环境，3D网络的优化困难和训练样本不足，CNN从3D医学图像中分割重要器官或结构仍然是一项艰巨的任务。在本文中，我们提出了一种新型高效的3D全卷积网络，配备了3D深度监督机制，以全面应对这些挑战;我们称之为3D DSN。我们提出的3D DSN能够进行卷到卷的学习和推理，这可以消除冗余计算并减轻在有限的训练数据上过度拟合的风险。更重要的是，3D深度监督机制可以有效科普训练3D深度模型时梯度消失或爆炸的优化问题，加快收敛速度，同时提高辨别能力。这种机制是通过导出一个目标函数来开发的，该目标函数直接指导网络中的下层和上层的训练，从而可以在训练过程中抵消不稳定梯度变化的不利影响。我们还采用了一个完全连接的条件随机场模型作为后处理步骤，以改善分割结果。我们已经在两个典型但具有挑战性的体积医学图像分割任务上广泛验证了所提出的3D DSN：（i）来自3D CT扫描的肝脏分割和（ii）来自3D MR图像的整个心脏和大血管分割，通过参与与MICCAI一起举办的两个重大挑战。我们在这两个挑战中以更快的速度实现了具有竞争力的分割结果，从而证实了我们提出的3D DSN的有效性。(C)2017爱思唯尔B. V.保留所有权利。
While deep convolutional neural networks (CNNs) have achieved remarkable success in 2D medical image segmentation, it is still a difficult task for CNNs to segment important organs or structures from 3D medical images owing to several mutually affected challenges, including the complicated anatomical environments in volumetric images, optimization difficulties of 3D networks and inadequacy of training samples. In this paper, we present a novel and efficient 3D fully convolutional network equipped with a 3D deep supervision mechanism to comprehensively address these challenges; we call it 3D DSN. Our proposed 3D DSN is capable of conducting volume-to-volume learning and inference, which can eliminate redundant computations and alleviate the risk of over-fitting on limited training data. More importantly, the 3D deep supervision mechanism can effectively cope with the optimization problem of gradients vanishing or exploding when training a 3D deep model, accelerating the convergence speed and simultaneously improving the discrimination capability. Such a mechanism is developed by deriving an objective function that directly guides the training of both lower and upper layers in the network, so that the adverse effects of unstable gradient changes can be counteracted during the training procedure. We also employ a fully connected conditional random field model as a post-processing step to refine the segmentation results. We have extensively validated the proposed 3D DSN on two typical yet challenging volumetric medical image segmentation tasks: (i) liver segmentation from 3D CT scans and (ii) whole heart and great vessels segmentation from 3D MR images, by participating two grand challenges held in conjunction with MICCAI. We have achieved competitive segmentation results to state-of-the-art approaches in both challenges with a much faster speed, corroborating the effectiveness of our proposed 3D DSN. (C) 2017 Elsevier B.V. All rights reserved.