SynergyNet: A Fusion Framework for Multiple Sclerosis Brain MRI Segmentation with Local Refinement
SynergyNet: A Fusion Framework for Multiple Sclerosis Brain MRI Segmentation with Local Refinement
复制标题
DOI：
10.1109/isbi45749.2020.9098610
复制
发表时间：
2020-04
期刊：
影响因子：
--
通讯作者：
Y. S. Vang;Yingxin Cao;P. Chang;D. Chow;A. Brandt;F. Paul;M. Scheel;Xiaohui Xie
中科院分区：
文献类型：
--
作者：
Y. S. Vang;Yingxin Cao;P. Chang;D. Chow;A. Brandt;F. Paul;M. Scheel;Xiaohui Xie
多发性硬化症（MS）病变在大小和数量上的高度不规则性往往证明了自动化系统在MS病变分割任务中的困难。当前最先进的MS分割算法要么只采用全局视角，要么只采用基于补丁的局部视角分割方法。虽然全局图像分割对于大中型病灶可以获得较好的分割效果，但对于较小病灶的分割效果较差。另一方面，基于patch的局部分割忽略了大脑的空间信息。在这项工作中，我们提出了SynergyNet，这是一个通过融合来自全局和局部视角的数据来分割MS病变的网络，以改善不同病变大小的分割。我们通过利用U-Net架构实现全局分割，并通过使用Mask R-CNN框架增强U-Net来实现局部分割。在这两个分支之间共享较低的层有利于端到端训练，并且证明了比简单地集成两个框架更有优势。我们在两个独立的数据集上评估了我们的方法，分别包含765卷和21卷。我们提出的方法在第一个数据集中Dice得分和病变真阳性率分别提高了2.55%和5.0%，假阳性率降低了20%以上，在第二个数据集中Dice得分和病变真阳性率平均提高了10%和32%。结果表明，我们的框架融合局部和全局的观点是有利于分割病变与异质大小。
The high irregularity of multiple sclerosis (MS) lesions in sizes and numbers often proves difficult for automated systems on the task of MS lesion segmentation. Current State-of-the-art MS segmentation algorithms employ either only global perspective or just patch-based local perspective segmentation approaches. Although global image segmentation can obtain good segmentation for medium to large lesions, its performance on smaller lesions lags behind. On the other hand, patch-based local segmentation disregards spatial information of the brain. In this work, we propose SynergyNet, a network segmenting MS lesions by fusing data from both global and local perspectives to improve segmentation across different lesion sizes. We achieve global segmentation by leveraging the U-Net architecture and implement the local segmentation by augmenting U-Net with the Mask R-CNN framework. The sharing of lower layers between these two branches benefits end-to-end training and proves advantages over simple ensemble of the two frameworks. We evaluated our method on two separate datasets containing 765 and 21 volumes respectively. Our proposed method can improve 2.55% and 5.0% for Dice score and lesion true positive rates respectively while reducing over 20% in false positive rates in the first dataset, and improve in average 10% and 32% for Dice score and lesion true positive rates in the second dataset. Results suggest that our framework for fusing local and global perspectives is beneficial for segmentation of lesions with heterogeneous sizes.