Department of Computer Science, University of Manitoba, Winnipeg, MB, R3T 2N2, Canada.
Department of Biochemistry and Medical Genetics, University of Manitoba, Room 308 - Basic Medical Sciences Building, 745 Bannatyne Avenue, Winnipeg, MB, R3E 0J3, Canada.
BMC Bioinformatics. 2022 Aug 17;23(Suppl 7):343. doi: 10.1186/s12859-022-04878-6.
A recurring problem in image segmentation is a lack of labelled data. This problem is especially acute in the segmentation of lung computed tomography (CT) of patients with Coronavirus Disease 2019 (COVID-19). The reason for this is simple: the disease has not been prevalent long enough to generate a great number of labels. Semi-supervised learning promises a way to learn from data that is unlabelled and has seen tremendous advancements in recent years. However, due to the complexity of its label space, those advancements cannot be applied to image segmentation. That being said, it is this same complexity that makes it extremely expensive to obtain pixel-level labels, making semi-supervised learning all the more appealing. This study seeks to bridge this gap by proposing a novel model that utilizes the image segmentation abilities of deep convolution networks and the semi-supervised learning abilities of generative models for chest CT images of patients with the COVID-19.
We propose a novel generative model called the shared variational autoencoder (SVAE). The SVAE utilizes a five-layer deep hierarchy of latent variables and deep convolutional mappings between them, resulting in a generative model that is well suited for lung CT images. Then, we add a novel component to the final layer of the SVAE which forces the model to reconstruct the input image using a segmentation that must match the ground truth segmentation whenever it is present. We name this final model StitchNet.
We compare StitchNet to other image segmentation models on a high-quality dataset of CT images from COVID-19 patients. We show that our model has comparable performance to the other segmentation models. We also explore the potential limitations and advantages in our proposed algorithm and propose some potential future research directions for this challenging issue.
图像分割中一个反复出现的问题是缺乏标记数据。这个问题在 2019 年冠状病毒病（COVID-19）患者的肺部计算机断层扫描（CT）的分割中尤为突出。原因很简单：这种疾病还没有流行足够长的时间来产生大量的标签。半监督学习承诺了一种从无标签数据中学习的方法，近年来取得了巨大的进展。然而，由于其标签空间的复杂性，这些进展不能应用于图像分割。也就是说，正是这种复杂性使得获得像素级标签极其昂贵，这使得半监督学习更具吸引力。本研究旨在通过提出一种新的模型来弥合这一差距，该模型利用深度卷积网络的图像分割能力和生成模型的半监督学习能力，对 COVID-19 患者的胸部 CT 图像进行分割。
我们提出了一种新的生成模型，称为共享变分自动编码器（SVAE）。SVAE 利用了五层潜在变量的深度层次结构和它们之间的深度卷积映射，从而产生了一种非常适合肺部 CT 图像的生成模型。然后，我们在 SVAE 的最后一层添加了一个新的组件，该组件迫使模型使用与地面真实分割匹配的分割来重建输入图像，只要有地面真实分割存在。我们将这个最终模型命名为 StitchNet。
我们在一个来自 COVID-19 患者的高质量 CT 图像数据集上，将 StitchNet 与其他图像分割模型进行了比较。我们表明，我们的模型与其他分割模型具有相当的性能。我们还探讨了我们提出的算法的潜在局限性和优势，并为这一具有挑战性的问题提出了一些潜在的未来研究方向。
