Abstract:
Semi-supervised segmentation plays an important role in computer vision and medical image analysis and can alleviate the burden of acquiring abundant expert-annotated images. In this paper, we developed a residual-driven semi-supervised segmentation method (termed RDMT) based on the classical mean teacher (MT) framework by introducing a novel model-level residual perturbation and an exponential Dice (eDice) loss. The introduced perturbation was integrated into the exponential moving average (EMA) scheme to enhance the performance of the MT, while the eDice loss was used to improve the detection sensitivity of a given network to object boundaries. We validated the developed method by applying it to segment 3D Left Atrium (LA) and 2D optic cup (OC) from the public LASC and REFUGE datasets based on the V-Net and U-Net, respectively. Extensive experiments demonstrated that the developed method achieved the average Dice score of 0.8776 and 0.7751, when trained on 10% and 20% labeled images, respectively for the LA and OC regions depicted on the LASC and REFUGE datasets. It significantly outperformed the MT and can compete with several existing semi-supervised segmentation methods (i.e., HCMT, UAMT, DTC and SASS).
摘要:
半监督分割在计算机视觉和医学图像分析中起着重要的作用,可以减轻获取大量专家注释图像的负担。在本文中,我们通过引入新颖的模型级残差扰动和指数骰子(eDice)损失,开发了一种基于经典均值教师(MT)框架的残差驱动半监督分割方法(称为RDMT)。引入的扰动被集成到指数移动平均(EMA)方案中,以增强MT的性能,而eDice损失用于提高给定网络对对象边界的检测灵敏度。我们通过将其应用于基于V-Net和U-Net的公共LASC和REFUGE数据集中的3D左中庭(LA)和2D光学杯(OC)来验证所开发的方法,分别。大量实验表明,当在10%和20%的标记图像上训练时,开发的方法获得了平均Dice评分为0.8776和0.7751。分别用于LASC和REFUGE数据集上描绘的LA和OC区域。它的性能明显优于MT,并且可以与几种现有的半监督分割方法(即,HCMT,UAMT,DTC和SASS)。