IEEE J Biomed Health Inform. 2021 May;25(5):1724-1734. doi: 10.1109/JBHI.2020.3024188. Epub 2021 May 11.
In this work, we have focused on the segmentation of Focal Cortical Dysplasia (FCD) regions from MRI images. FCD is a congenital malformation of brain development that is considered as the most common causative of intractable epilepsy in adults and children. To our knowledge, the latest work concerning the automatic segmentation of FCD was proposed using a fully convolutional neural network (FCN) model based on UNet. While there is no doubt that the model outperformed conventional image processing techniques by a considerable margin, it suffers from several pitfalls. First, it does not account for the large semantic gap of feature maps passed from the encoder to the decoder layer through the long skip connections. Second, it fails to leverage the salient features that represent complex FCD lesions and suppress most of the irrelevant features in the input sample. We propose Multi-Res-Attention UNet; a novel hybrid skip connection-based FCN architecture that addresses these drawbacks. Moreover, we have trained it from scratch for the detection of FCD from 3 T MRI 3D FLAIR images and conducted 5-fold cross-validation to evaluate the model. FCD detection rate (Recall) of 92% was achieved for patient wise analysis.
在这项工作中，我们专注于从 MRI 图像中分割局灶性皮质发育不良 (FCD) 区域。FCD 是一种先天性的脑发育畸形，被认为是导致成人和儿童难治性癫痫的最常见原因。据我们所知，最近有关 FCD 自动分割的工作是使用基于 UNet 的全卷积神经网络 (FCN) 模型提出的。虽然毫无疑问，该模型在很大程度上优于传统的图像处理技术，但它存在几个缺陷。首先，它没有考虑到通过长 skip 连接从编码器传递到解码器层的特征图的大语义差距。其次，它无法利用表示复杂 FCD 病变的显著特征，并抑制输入样本中的大多数不相关特征。我们提出了多分辨率注意 UNet；一种新颖的基于混合 skip connection 的 FCN 架构，可解决这些缺点。此外，我们从头开始对 3T MRI 3D FLAIR 图像进行 FCD 检测，并进行 5 倍交叉验证来评估模型。在患者分析中，FCD 的检测率（召回率）达到了 92%。
