Department of Telecommunications Engineering, Faculty of Engineering, University of Guilan, Rasht, Iran.
Faculty of Management and Accounting, Allameh Tabataba'i University, Tehran, Iran.
Sci Rep. 2021 May 25;11(1):10930. doi: 10.1038/s41598-021-90428-8.
Brain tumor localization and segmentation from magnetic resonance imaging (MRI) are hard and important tasks for several applications in the field of medical analysis. As each brain imaging modality gives unique and key details related to each part of the tumor, many recent approaches used four modalities T1, T1c, T2, and FLAIR. Although many of them obtained a promising segmentation result on the BRATS 2018 dataset, they suffer from a complex structure that needs more time to train and test. So, in this paper, to obtain a flexible and effective brain tumor segmentation system, first, we propose a preprocessing approach to work only on a small part of the image rather than the whole part of the image. This method leads to a decrease in computing time and overcomes the overfitting problems in a Cascade Deep Learning model. In the second step, as we are dealing with a smaller part of brain images in each slice, a simple and efficient Cascade Convolutional Neural Network (C-ConvNet/C-CNN) is proposed. This C-CNN model mines both local and global features in two different routes. Also, to improve the brain tumor segmentation accuracy compared with the state-of-the-art models, a novel Distance-Wise Attention (DWA) mechanism is introduced. The DWA mechanism considers the effect of the center location of the tumor and the brain inside the model. Comprehensive experiments are conducted on the BRATS 2018 dataset and show that the proposed model obtains competitive results: the proposed method achieves a mean whole tumor, enhancing tumor, and tumor core dice scores of 0.9203, 0.9113 and 0.8726 respectively. Other quantitative and qualitative assessments are presented and discussed.
脑肿瘤的定位和分割是医学分析领域中几个应用的难题和重点。由于每种脑成像模式都提供了与肿瘤各部分相关的独特和关键细节，因此最近许多方法都使用了 T1、T1c、T2 和 FLAIR 这四种模式。尽管它们中的许多方法在 BRATS 2018 数据集上获得了有前景的分割结果，但它们存在复杂的结构，需要更多的时间来训练和测试。因此，在本文中，为了获得一个灵活有效的脑肿瘤分割系统，我们首先提出了一种预处理方法，只对图像的一小部分进行处理，而不是对图像的整个部分进行处理。这种方法减少了计算时间，并克服了级联深度学习模型中的过拟合问题。在第二步中，由于我们在每个切片中处理的是脑图像的一小部分，因此提出了一种简单而高效的级联卷积神经网络（C-ConvNet/C-CNN）。这个 C-CNN 模型在两条不同的路径中挖掘局部和全局特征。此外，为了提高脑肿瘤分割的准确性，与现有模型相比，我们引入了一种新的距离感知注意力（DWA）机制。该 DWA 机制考虑了肿瘤中心位置和模型内部大脑的影响。我们在 BRATS 2018 数据集上进行了全面的实验，结果表明，所提出的模型取得了有竞争力的结果：所提出的方法在全肿瘤、增强肿瘤和肿瘤核心的骰子得分分别达到 0.9203、0.9113 和 0.8726。还提出并讨论了其他定量和定性评估。
