Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network
Toward Automatic Detection of Radiation-Induced Cerebral Microbleeds Using a 3D Deep Residual Network
复制标题
DOI：
10.1007/s10278-018-0146-z
复制
发表时间：
2019-10-01
影响因子：
4.4
通讯作者：
Lupo, Janine M.
中科院分区：
文献类型：
--
作者：
Chen, Yicheng;Villanueva-Meyer, Javier E.;Lupo, Janine M.
脑微出血是大脑中的小灶性出血，在许多疾病中普遍存在，由于其作为疾病负担、临床结果和治疗延迟效果的替代标志物的潜力而受到越来越多的关注。手动检测非常费力，而使用传统算法自动检测和标记这些病变具有挑战性。受到计算机视觉领域深度卷积神经网络最近成功的启发，我们开发了一种 3D 深度残差网络，可以区分真实的微出血和基于传统算法的先前开发技术的误报模仿。使用磁敏感加权成像在 7 T 下扫描的 73 名放射诱发脑微出血患者的数据集来训练和评估我们的模型。通过最终的网络，我们在 12 名测试患者中保持了 95% 的真实微出血，平均误报数量减少了 89%，检测精度达到 71.9%，高于现有已发表的方法。还通过与神经放射科医生的评分进行比较来评估网络预测的似然评分，并观察到良好的相关性。
Cerebral microbleeds, which are small focal hemorrhages in the brain that are prevalent in many diseases, are gaining increasing attention due to their potential as surrogate markers of disease burden, clinical outcomes, and delayed effects of therapy. Manual detection is laborious and automatic detection and labeling of these lesions is challenging using traditional algorithms. Inspired by recent successes of deep convolutional neural networks in computer vision, we developed a 3D deep residual network that can distinguish true microbleeds from false positive mimics of a previously developed technique based on traditional algorithms. A dataset of 73 patients with radiation-induced cerebral microbleeds scanned at 7 T with susceptibility-weighted imaging was used to train and evaluate our model. With the resulting network, we maintained 95% of the true microbleeds in 12 test patients and the average number of false positives was reduced by 89%, achieving a detection precision of 71.9%, higher than existing published methods. The likelihood score predicted by the network was also evaluated by comparing to a neuroradiologist's rating, and good correlation was observed.