Wei Hao, Tang Xiangyu, Zhang Minqing, Li Qingfeng, Xing Xiaodan, Sean Zhou Xiang, Xue Zhong, Zhu Wenzhen, Chen Zailiang, Shi Feng
School of Computer Science and Engineering, Central South University, Hunan, 410083, China.
Shanghai United Imaging Intelligence Co., Ltd., Shanghai, 201807, China.
Med Phys. 2020 Nov;47(11):5531-5542. doi: 10.1002/mp.14302. Epub 2020 Oct 15.
The human brain has two cerebral hemispheres that are roughly symmetric and separated by a midline, which is nearly a straight line shown in axial computed tomography (CT) images in healthy subjects. However, brain diseases such as hematoma and tumors often cause midline shift, where the degree of shift can be regarded as a quantitative indication in clinical practice. To facilitate clinical evaluation, we need computer-aided methods to automate this quantification. Nevertheless, most existing studies focused on the landmark- or symmetry-based methods that provide only the existence of shift or its maximum distance, which could be easily affected by anatomical variability and large brain deformations. Intuitive results such as midline delineation or measurement are lacking. In this study, we focus on developing an automated and robust method based on the fully convolutional neural network for the delineation of midline in largely deformed brains.
We propose a novel regression-based line detection network (RLDN) for the robust midline delineation, especially in largely deformed brains. Specifically, to improve the robustness of delineation in largely deformed brains, we regard the delineation of the midline as the skeleton extraction task and then use the multiscale bidirectional integration module to acquire more representative features. Based on the skeleton extraction, we incorporate the regression task into it to delineate more accurate and continuous midline, especially in largely deformed brains. Our study utilized the public CQ 500 dataset (128 subjects) for training with hold-out validation on 61 subjects from a private cohort accrued from a local hospital.
The mean line distance error and F1-score were 1.17 ± 0.72 mm with 0.78 on CQ 500 test set, and 4.15 ± 3.97 mm with 0.61 on the private dataset. Besides, significant differences (P < 0.05) were observed between our method and other comparative ones on these two datasets.
This work provides a novel solution to acquire robust delineation of the midline, especially in largely deformed brains, and achieves state-of-the-art performance on the public and our private dataset, which makes it possible for automated diagnosis of relevant brain diseases in the future.
人类大脑有两个大致对称的脑半球，由一条中线分隔，在健康受试者的轴向计算机断层扫描（CT）图像中，这条中线几乎是一条直线。然而，诸如血肿和肿瘤等脑部疾病常常会导致中线移位，在临床实践中，移位程度可被视为一种定量指标。为便于临床评估，我们需要计算机辅助方法来自动进行这种量化。尽管如此，大多数现有研究集中在基于地标或对称的方法上，这些方法仅能提供移位的存在情况或其最大距离，这很容易受到解剖变异和大脑大变形的影响。缺乏诸如中线描绘或测量等直观结果。在本研究中，我们专注于开发一种基于全卷积神经网络的自动化且稳健的方法，用于在严重变形的大脑中描绘中线。
我们提出了一种新颖的基于回归的线检测网络（RLDN），用于稳健的中线描绘，特别是在严重变形的大脑中。具体而言，为提高在严重变形大脑中描绘的稳健性，我们将中线描绘视为骨架提取任务，然后使用多尺度双向集成模块来获取更具代表性的特征。基于骨架提取，我们将回归任务纳入其中，以描绘更准确和连续的中线，特别是在严重变形的大脑中。我们的研究利用公共CQ 500数据集（128名受试者）进行训练，并对来自当地医院的一个私人队列中的61名受试者进行留出验证。
在CQ 500测试集上，平均线距离误差和F1分数分别为1.17±0.72毫米和0.78，在私人数据集上分别为4.15±3.97毫米和0.61。此外，在这两个数据集上，我们的方法与其他比较方法之间观察到显著差异（P<0.05）。
这项工作提供了一种新颖的解决方案，可在特别是严重变形的大脑中获得稳健的中线描绘，并在公共数据集和我们的私人数据集上实现了最先进的性能，这使得未来对相关脑部疾病进行自动诊断成为可能。
