当前位置: X-MOL 学术IEEE J. Biomed. Health Inform. › 论文详情
Our official English website, www.x-mol.net, welcomes your feedback! (Note: you will need to create a separate account there.)
Deep Attention and Graphical Neural Network for Multiple Sclerosis Lesion Segmentation From MR Imaging Sequences
IEEE Journal of Biomedical and Health Informatics ( IF 7.7 ) Pub Date : 2021-09-01 , DOI: 10.1109/jbhi.2021.3109119
Zhanlan Chen 1, 2 , Xiuying Wang 3 , Jing Huang 4 , Jie Lu 4 , Jiangbin Zheng 1
Affiliation  

The segmentation of multiple sclerosis (MS) lesions from MR imaging sequences remains a challenging task, due to the characteristics of variant shapes, scattered distributions and unknown numbers of lesions. However, the current automated MS segmentation methods with deep learning models face the challenges of (1) capturing the scattered lesions in multiple regions and (2) delineating the global contour of variant lesions. To address these challenges, in this paper, we propose a novel attention and graph-driven network (DAG-Net), which incorporates (1) the spatial correlations for embracing the lesions in distant regions and (2) the global context for better representing lesions of variant features in a unified architecture. Firstly, the novel local attention coherence mechanism is designed to construct dynamic and expansible graphs for the spatial correlations between pixels and their proximities. Secondly, the proposed spatial-channel attention module enhances features to optimize the global contour delineation, by aggregating relevant features. Moreover, with the dynamic graphs, the learning process of the DAG-Net is interpretable, which in turns support the reliability of segmentation results. Extensive experiments were conducted on a public ISBI2015 dataset and an in-house dataset in comparison to state-of-the-art methods, based on geometrical and clinical metrics. The experimental results validate the effectiveness of proposed DAG-Net on segmenting variant and scatted lesions in multiple regions.

中文翻译:

用于从 MR 成像序列中分割多发性硬化病灶的深度注意和图形神经网络

由于不同形状、分散分布和未知数量的病灶的特点,从 MR 成像序列中分割多发性硬化 (MS) 病灶仍然是一项具有挑战性的任务。然而,当前具有深度学习模型的自动 MS 分割方法面临以下挑战:(1)捕获多个区域中的分散病变和(2)描绘变异病变的全局轮廓。为了应对这些挑战,在本文中,我们提出了一种新颖的注意力和图驱动网络 (DAG-Net),它结合了 (1) 用于包含远处区域病变的空间相关性和 (2) 更好地表示的全局上下文统一架构中的变异特征的病变。第一,新颖的局部注意力相干机制旨在为像素及其邻近度之间的空间相关性构建动态且可扩展的图。其次,所提出的空间通道注意模块通过聚合相关特征来增强特征以优化全局轮廓描绘。此外,通过动态图,DAG-Net 的学习过程是可解释的,这反过来又支持了分割结果的可靠性。基于几何和临床指标,与最先进的方法相比,在公共 ISBI2015 数据集和内部数据集上进行了广泛的实验。实验结果验证了所提出的 DAG-Net 在分割多个区域中的变异和散布病灶方面的有效性。所提出的空间通道注意模块通过聚合相关特征来增强特征以优化全局轮廓描绘。此外,通过动态图,DAG-Net 的学习过程是可解释的,这反过来又支持了分割结果的可靠性。基于几何和临床指标,与最先进的方法相比,在公共 ISBI2015 数据集和内部数据集上进行了广泛的实验。实验结果验证了所提出的 DAG-Net 在分割多个区域中的变异和散布病灶方面的有效性。所提出的空间通道注意模块通过聚合相关特征来增强特征以优化全局轮廓描绘。此外,通过动态图,DAG-Net 的学习过程是可解释的,这反过来又支持了分割结果的可靠性。基于几何和临床指标,与最先进的方法相比,在公共 ISBI2015 数据集和内部数据集上进行了广泛的实验。实验结果验证了所提出的 DAG-Net 在分割多个区域中的变异和散布病灶方面的有效性。这反过来又支持了分割结果的可靠性。基于几何和临床指标,与最先进的方法相比,在公共 ISBI2015 数据集和内部数据集上进行了广泛的实验。实验结果验证了所提出的 DAG-Net 在分割多个区域中的变异和散布病灶方面的有效性。这反过来又支持了分割结果的可靠性。基于几何和临床指标,与最先进的方法相比,在公共 ISBI2015 数据集和内部数据集上进行了广泛的实验。实验结果验证了所提出的 DAG-Net 在分割多个区域中的变异和散布病灶方面的有效性。
更新日期:2021-09-01
down
wechat
bug