Department of Data Science & AI, Faculty of Information Technology, Monash University, Melbourne, VIC 3800, Australia.
Monash-Airdoc Research, Monash University, Melbourne, VIC 3800, Australia; Monash Medical AI, Monash eResearch Centre, Melbourne, VIC 3800, Australia.
Med Image Anal. 2022 Oct;81:102530. doi: 10.1016/j.media.2022.102530. Epub 2022 Jul 6.
In this paper, we propose a novel mutual consistency network (MC-Net+) to effectively exploit the unlabeled data for semi-supervised medical image segmentation. The MC-Net+ model is motivated by the observation that deep models trained with limited annotations are prone to output highly uncertain and easily mis-classified predictions in the ambiguous regions (e.g., adhesive edges or thin branches) for medical image segmentation. Leveraging these challenging samples can make the semi-supervised segmentation model training more effective. Therefore, our proposed MC-Net+ model consists of two new designs. First, the model contains one shared encoder and multiple slightly different decoders (i.e., using different up-sampling strategies). The statistical discrepancy of multiple decoders' outputs is computed to denote the model's uncertainty, which indicates the unlabeled hard regions. Second, we apply a novel mutual consistency constraint between one decoder's probability output and other decoders' soft pseudo labels. In this way, we minimize the discrepancy of multiple outputs (i.e., the model uncertainty) during training and force the model to generate invariant results in such challenging regions, aiming at regularizing the model training. We compared the segmentation results of our MC-Net+ model with five state-of-the-art semi-supervised approaches on three public medical datasets. Extension experiments with two standard semi-supervised settings demonstrate the superior performance of our model over other methods, which sets a new state of the art for semi-supervised medical image segmentation. Our code is released publicly at https://github.com/ycwu1997/MC-Net.
在本文中，我们提出了一种新颖的互一致性网络（MC-Net+），以有效地利用未标记数据进行半监督医学图像分割。MC-Net+模型的动机是观察到，用有限的注释训练的深度模型在医学图像分割的模糊区域（例如，粘连边缘或细分支）中，容易输出高度不确定且容易误分类的预测。利用这些具有挑战性的样本可以使半监督分割模型的训练更加有效。因此，我们提出的 MC-Net+模型包含两个新的设计。首先，该模型包含一个共享编码器和多个略有不同的解码器（即，使用不同的上采样策略）。计算多个解码器输出的统计差异来表示模型的不确定性，这表明了未标记的困难区域。其次，我们在一个解码器的概率输出和其他解码器的软伪标签之间应用了一种新的互一致性约束。通过这种方式，我们在训练过程中最小化多个输出的差异（即模型不确定性），并迫使模型在这些具有挑战性的区域中生成不变的结果，旨在对模型训练进行正则化。我们将 MC-Net+模型的分割结果与五个最先进的半监督方法在三个公共医学数据集上进行了比较。在两种标准半监督设置下的扩展实验表明，我们的模型优于其他方法，为半监督医学图像分割设定了新的技术水平。我们的代码在 https://github.com/ycwu1997/MC-Net 上公开发布。
