Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning.
Automated Segmentation of Infarct Lesions in T1-Weighted MRI Scans Using Variational Mode Decomposition and Deep Learning.
复制标题
DOI：
10.3390/s21061952
复制
发表时间：
2021-03-10
期刊：
影响因子：
--
通讯作者：
Pintavirooj C
中科院分区：
文献类型：
--
作者：
Paing MP;Tungjitkusolmun S;Bui TH;Visitsattapongse S;Pintavirooj C
在减少脑梗塞的残疾和死亡风险方面，自动分割方法对于早期发现、迅速行动和立即治疗至关重要。本文旨在开发一种从T1加权脑扫描中分割脑梗塞病变的全自动方法。作为一个关键的创新之处，该方法结合了变分模式分解和基于深度学习的分割方法，充分利用了这两种方法的优点，并提供了更好的结果。本文的主要技术贡献有三个。首先，将变分模式分解作为一种预处理来区分梗死灶和不需要的非梗死灶。其次，为了减少基于深度学习的分割任务的工作量，提出了重叠块策略。最后，开发了一个三维U网模型，用于对脑梗塞病变进行斑块分割。来自公共数据集中的239次脑扫描被用来开发和评估所提出的方法。实验结果表明，该自动分割算法的平均芯片相似系数为0.6684，平均交集系数为0.5022，平均对称表面距离为0.3932。
Automated segmentation methods are critical for early detection, prompt actions, and immediate treatments in reducing disability and death risks of brain infarction. This paper aims to develop a fully automated method to segment the infarct lesions from T1-weighted brain scans. As a key novelty, the proposed method combines variational mode decomposition and deep learning-based segmentation to take advantages of both methods and provide better results. There are three main technical contributions in this paper. First, variational mode decomposition is applied as a pre-processing to discriminate the infarct lesions from unwanted non-infarct tissues. Second, overlapped patches strategy is proposed to reduce the workload of the deep-learning-based segmentation task. Finally, a three-dimensional U-Net model is developed to perform patch-wise segmentation of infarct lesions. A total of 239 brain scans from a public dataset is utilized to develop and evaluate the proposed method. Empirical results reveal that the proposed automated segmentation can provide promising performances with an average dice similarity coefficient (DSC) of 0.6684, intersection over union (IoU) of 0.5022, and average symmetric surface distance (ASSD) of 0.3932, respectively.
登录
查看更多内容
影响因子：
4.8
作者：
Pustina D;Coslett HB;Turkeltaub PE;Tustison N;Schwartz MF;Avants B
通讯作者：
Avants B
影响因子：
2.4
作者：
Yeghiazaryan, Varduhi;Voiculescu, Irina
通讯作者：
Voiculescu, Irina
影响因子：
4.2
作者：
Xue, Yunzhe;Farhat, Fadi G.;Graves, William W.
通讯作者：
Graves, William W.
D-UNet：用于慢性中风病变分割的维度融合U形网络
DOI：
10.1109/tcbb.2019.2939522
发表时间：
2021-05-01
影响因子：
4.5
作者：
Zhou, Yongjin;Huang, Weijian;Wang, Shanshan
通讯作者：
Wang, Shanshan
影响因子：
18.6
作者：
Ali, Farman;El-Sappagh, Shaker;Kwak, Kyung-Sup
通讯作者：
Kwak, Kyung-Sup