Department of Biomedical Engineering, School of Life Science, Beijing Institute of Technology, Beijing, China.
Sixth Medical Center of PLA General Hospital, Beijing, China.
J Appl Clin Med Phys. 2020 Sep;21(9):215-226. doi: 10.1002/acm2.12985. Epub 2020 Aug 18.
Focal cortical dysplasia (FCD) is a common cause of epilepsy; the only treatment is surgery. Therefore, detecting FCD using noninvasive imaging technology can help doctors determine whether surgical intervention is required. Since FCD lesions are small and not obvious, diagnosing FCD through visual evaluations of magnetic resonance imaging (MRI) scans is difficult. The purpose of this study is to detect and segment histologically confirmed FCD lesions in images of normal fluid-attenuated inversion recovery (FLAIR)-negative lesions using convolutional neural network (CNN) technology.
The technique involves training a six-layer CNN named Net-Pos, which consists of two convolutional layers (CLs); two pooling layers (PLs); and two fully connected (FC) layers, including 60 943 learning parameters. We employed activation maximization (AM) to optimize a series of pattern image blocks (PIBs) that were most similar to a lesion image block by using the trained Net-Pos. We developed an AM and convolutional localization (AMCL) algorithm that employs the mean PIBs combined with convolution to locate and segment FCD lesions in FLAIR-negative patients. Five evaluation indices, namely, recall, specificity, accuracy, precision, and the Dice coefficient, were applied to evaluate the localization and segmentation performance of the algorithm.
The PIBs most similar to an FCD lesion image block were identified by the trained Net-Pos as image blocks with brighter central areas and darker surrounding image blocks. The technique was evaluated using 18 FLAIR-negative lesion images from 12 patients. The subject-wise recall of the AMCL algorithm was 83.33% (15/18). The Dice coefficient for the segmentation performance was 52.68.
We developed a novel algorithm referred to as the AMCL algorithm with mean PIBs to effectively and automatically detect and segment FLAIR-negative FCD lesions. This work is the first study to apply a CNN-based model to detect and segment FCD lesions in images of FLAIR-negative lesions.
局灶性皮质发育不良（FCD）是癫痫的常见病因；唯一的治疗方法是手术。因此，使用非侵入性成像技术检测 FCD 可以帮助医生确定是否需要手术干预。由于 FCD 病变较小且不明显，通过磁共振成像（MRI）扫描的视觉评估来诊断 FCD 较为困难。本研究旨在使用卷积神经网络（CNN）技术检测和分割经组织学证实的正常液体衰减反转恢复（FLAIR）阴性病变图像中的 FCD 病变。
该技术涉及训练一个名为 Net-Pos 的六层 CNN，它由两个卷积层（CL）；两个池化层（PL）；和两个完全连接（FC）层组成，包含 60943 个学习参数。我们使用激活最大化（AM）通过使用训练好的 Net-Pos 优化与病变图像块最相似的一系列模式图像块（PIB）。我们开发了一种 AM 和卷积定位（AMCL）算法，该算法使用平均 PIB 结合卷积来定位和分割 FLAIR 阴性患者的 FCD 病变。我们应用了五个评估指标，即召回率、特异性、准确性、精度和 Dice 系数，来评估算法的定位和分割性能。
经过训练的 Net-Pos 确定与 FCD 病变图像块最相似的 PIB 为中央区域较亮、周围图像块较暗的图像块。该技术使用 12 名患者的 18 个 FLAIR 阴性病变图像进行了评估。AMCL 算法的受试者召回率为 83.33%（15/18）。分割性能的 Dice 系数为 52.68。
我们开发了一种新的算法，称为 AMCL 算法，该算法使用平均 PIB 来有效且自动地检测和分割 FLAIR 阴性 FCD 病变。这是首次应用基于 CNN 的模型来检测和分割 FLAIR 阴性病变图像中的 FCD 病变的研究。
