Fully automated detection of breast cancer in screening MRI using convolutional neural networks
Fully automated detection of breast cancer in screening MRI using convolutional neural networks
复制标题
DOI：
10.1117/1.jmi.5.1.014502
复制
发表时间：
2018-01-01
影响因子：
2.4
通讯作者：
Gubern-Merida, Albert
中科院分区：
文献类型：
--
作者：
Dalmis, Mehmet Ufuk;Vreemann, Suzan;Gubern-Merida, Albert
当前用于对比增强的乳腺MRI的计算机辅助检测（CADe）系统依赖于从对比增强的早期阶段获得的空间信息和从后期阶段获得的时间信息。然而，晚期信息可能在筛选环境中不可用，例如在简化的MRI协议中，其中采集仅限于早期扫描。我们使用深度学习开发了一个CADe系统，该系统利用了从早期扫描中获得的空间信息。该系统使用候选位置中的三维（3-D）形态信息和由两个乳房的增强差异引起的对称信息。我们比较了所提出的系统，以前开发的系统，它使用全动态乳腺MRI协议。为了训练和测试，我们使用了385个MRI扫描，其中包含161个恶性病变。通过对1/8- 8假阳性之间的灵敏度值取平均值来测量性能。在我们的实验中，与先前的CADe系统（0.5325 +/-0.0547）相比，所提出的系统获得了显著（p = 0.008）更高的平均灵敏度（0.6429 +/-0.0537）。总之，我们开发了一种CADe系统，该系统能够利用从早期扫描获得的空间信息，并可用于使用缩写MRI协议的筛选程序。(c)2018年，美国光电仪器工程师学会（SPIE）
Current computer-aided detection (CADe) systems for contrast-enhanced breast MRI rely on both spatial information obtained from the early-phase and temporal information obtained from the late-phase of the contrast enhancement. However, late-phase information might not be available in a screening setting, such as in abbreviated MRI protocols, where acquisition is limited to early-phase scans. We used deep learning to develop a CADe system that exploits the spatial information obtained from the early-phase scans. This system uses three-dimensional (3-D) morphological information in the candidate locations and the symmetry information arising from the enhancement differences of the two breasts. We compared the proposed system to a previously developed system, which uses the full dynamic breast MRI protocol. For training and testing, we used 385 MRI scans, containing 161 malignant lesions. Performance was measured by averaging the sensitivity values between 1/8-eight false positives. In our experiments, the proposed system obtained a significantly (p = 0.008) higher average sensitivity (0.6429 +/- 0.0537) compared with that of the previous CADe system (0.5325 +/- 0.0547). In conclusion, we developed a CADe system that is able to exploit the spatial information obtained from the early-phase scans and can be used in screening programs where abbreviated MRI protocols are used. (c) 2018 Society of Photo-Optical Instrumentation Engineers (SPIE).