Semi-supervised segmentation remains challenging in medical imaging since the amount of annotated medical data is often scarce and there are many blurred pixels near the adhesive edges or in the low-contrast regions. To address the issues, we advocate to firstly constrain the consistency of pixels with and without strong perturbations to apply a sufficient smoothness constraint and further encourage the class-level separation to exploit the low-entropy regularization for the model training. Particularly, in this paper, we propose the SS-Net for semi-supervised medical image segmentation tasks, via exploring the pixel-level smoothness and inter-class separation at the same time. The pixel-level smoothness forces the model to generate invariant results under adversarial perturbations. Meanwhile, the inter-class separation encourages individual class features should approach their corresponding high-quality prototypes, in order to make each class distribution compact and separate different classes. We evaluated our SS-Net against five recent methods on the public LA and ACDC datasets. Extensive experimental results under two semi-supervised settings demonstrate the superiority of our proposed SS-Net model, achieving new state-of-the-art (SOTA) performance on both datasets. The code is available at https://github.com/ycwu1997/SS-Net.
翻译:在医学成像中,半监督的分解仍然具有挑战性,因为附加说明的医疗数据量往往很少,而且在同一时间,在粘合边缘附近或低调区域有许多模糊的像素。为了解决问题,我们主张首先限制像素与像素的一致性,在没有强烈扰动的情况下,采用足够的顺畅性限制,并进一步鼓励等级分解,利用低渗透性规范化模式培训。特别是,在本文件中,我们提议采用SS-Net,进行半监控性医学图象分解任务,同时探索像素水平的平滑和阶级间分解。平流层平滑促使模型在对抗性扰动下产生异样结果。与此同时,各类分解鼓励个别类特征接近相应的高品质原型,以便使每个班级的分发契约和不同的类别都达到。我们评估了我们的SS-Net,在公共洛杉矶和ACDC数据集的五种最新方法。在两种半监视性平流/间结构下的广泛实验结果,在两种半监视性结构下,显示我们提议的SS-SO-com的运行模式。