A novel automatic image segmentation technique in magnetic resonance imaging (MRI) based on di‐phase midway convolution and deconvolution network is proposed. It consists of three convolutional and deconvolutional blocks for downsampling and upsampling layers respectively. In first block, each input slice is separately convolved using two paths with 3 × 3 and 7 × 7 kernels to produce different feature maps. Then the mean value of these feature maps is processed into upcoming blocks in downsampling and upsampling layers. This processed outcome is classified and segmented using softmax classification. Further, the volume, probability density distribution of tumor, and normal tissue regions are calculated using tissue‐type mapping technique. This method is extensively tested with BRATS 2012, BRATS 2013, and BRATS 2018 data sets. Our experimental results achieved higher dice similarity coefficient values of 24.3%, 27.5%, and 3.4%, respectively, for these three data sets when compared to the state‐of‐art brain tumor segmentation methods.

中文翻译：

---

双相中途卷积和解卷积网络用于MRI图像中的脑肿瘤分割

提出了一种基于双相中途卷积和反卷积网络的磁共振成像自动图像分割技术。它由三个卷积和反卷积块组成，分别用于下采样和上采样层。在第一个块中，使用具有3×3和7×7内核的两条路径分别对每个输入切片进行卷积，以生成不同的特征图。然后，将这些特征图的平均值处理为下采样和上采样层中的后续块。使用softmax分类对经过处理的结果进行分类和细分。此外，使用组织类型标测技术计算肿瘤的体积，概率密度分布以及正常组织区域。BRATS 2012，BRATS 2013和BRATS 2018数据集对该方法进行了广泛的测试。