Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks
Automatic Detection of Cerebral Microbleeds From MR Images via 3D Convolutional Neural Networks
复制标题
DOI：
10.1109/tmi.2016.2528129
复制
发表时间：
2016-05-01
影响因子：
10.6
通讯作者：
Heng, Pheng-Ann
中科院分区：
文献类型：
--
作者：
Dou, Qi;Chen, Hao;Heng, Pheng-Ann
脑微出血（CMB）是血管附近的小出血。它们已被认为是许多脑血管疾病和认知功能障碍的重要诊断生物标志物。在当前的临床常规中，CMB由放射科医师手动标记，但是该过程费力、耗时并且容易出错。在本文中，我们提出了一种新的自动方法来检测CMB磁共振（MR）图像，利用三维卷积神经网络（CNN）。与以前采用低级手工描述符或2D CNN的方法相比，我们的方法可以充分利用MR体积中的空间上下文信息来提取更具代表性的CMB高级特征，从而实现更好的检测准确性。为了进一步提高检测性能，同时降低计算成本，我们提出了一个级联框架下的3D CNN的CMB检测任务。我们首先利用3D全卷积网络（FCN）策略来检索具有高概率的CMB候选者，然后应用经过良好训练的3D CNN判别模型来区分CMB和硬模仿。与传统的滑动窗口检测策略相比，该方法可以去除大量的冗余计算，大大提高检测速度。我们构建了一个包含320个体积MR扫描的大型数据集，并进行了广泛的实验来验证所提出的方法，该方法实现了93.16%的高灵敏度，每个受试者的平均假阳性数为2.74，远远优于使用低级描述符或2D CNN的先前方法。原则上，所提出的方法可以适用于来自体积医学数据的其他生物标志物检测任务。
Cerebral microbleeds (CMBs) are small haemorrhages nearby blood vessels. They have been recognized as important diagnostic biomarkers for many cerebrovascular diseases and cognitive dysfunctions. In current clinical routine, CMBs are manually labelled by radiologists but this procedure is laborious, time-consuming, and error prone. In this paper, we propose a novel automatic method to detect CMBs from magnetic resonance (MR) images by exploiting the 3D convolutional neural network (CNN). Compared with previous methods that employed either low-level hand-crafted descriptors or 2D CNNs, our method can take full advantage of spatial contextual information in MR volumes to extract more representative high-level features for CMBs, and hence achieve a much better detection accuracy. To further improve the detection performance while reducing the computational cost, we propose a cascaded framework under 3D CNNs for the task of CMB detection. We first exploit a 3D fully convolutional network (FCN) strategy to retrieve the candidates with high probabilities of being CMBs, and then apply a well-trained 3D CNN discrimination model to distinguish CMBs from hard mimics. Compared with traditional sliding window strategy, the proposed 3D FCN strategy can remove massive redundant computations and dramatically speed up the detection process. We constructed a large dataset with 320 volumetric MR scans and performed extensive experiments to validate the proposed method, which achieved a high sensitivity of 93.16% with an average number of 2.74 false positives per subject, outperforming previous methods using low-level descriptors or 2D CNNs by a significant margin. The proposed method, in principle, can be adapted to other biomarker detection tasks from volumetric medical data.