Semi-supervised learning has attracted great attention in the field of machine learning, especially for medical image segmentation tasks, since it alleviates the heavy burden of collecting abundant densely annotated data for training. However, most of existing methods underestimate the importance of challenging regions (e.g. small branches or blurred edges) during training. We believe that these unlabeled regions may contain more crucial information to minimize the uncertainty prediction for the model and should be emphasized in the training process. Therefore, in this paper, we propose a novel Mutual Consistency Network (MC-Net) for semi-supervised left atrium segmentation from 3D MR images. Particularly, our MC-Net consists of one encoder and two slightly different decoders, and the prediction discrepancies of two decoders are transformed as an unsupervised loss by our designed cycled pseudo label scheme to encourage mutual consistency. Such mutual consistency encourages the two decoders to have consistent and low-entropy predictions and enables the model to gradually capture generalized features from these unlabeled challenging regions. We evaluate our MC-Net on the public Left Atrium (LA) database and it obtains impressive performance gains by exploiting the unlabeled data effectively. Our MC-Net outperforms six recent semi-supervised methods for left atrium segmentation, and sets the new state-of-the-art performance on the LA database.
翻译:在机器学习领域,特别是在医学图像分割任务方面,半监督的学习吸引了人们对机器学习的极大关注,特别是医疗图像分割任务,因为它减轻了为培训收集大量高密度附加说明的数据的沉重负担;然而,大多数现有方法低估了培训期间具有挑战性的区域(如小分支或模糊边缘)的重要性;我们认为,这些未标记的区域可能包含更为关键的信息,以尽量减少模型的不确定性预测,在培训过程中应强调这些区域;因此,我们在本文件中提议建立一个新型的相互协调网络(MC-Net),用于3D MR图像的半监督左端中左端分离。特别是,我们的MC-Net由一个编码器和两个略有不同的解码器组成,而两个解码器的预测差异被我们设计的循环假标签办法所改变为一种无监督的损失,以鼓励相互一致。这种相互一致鼓励这两个解析器有一贯性和低含量的预测,并使模型能够逐渐从这些未标记的挑战区域中获取通用的特征。我们评估了公共左端数据网络中的非MC-Net,利用了我们最近左端的六级数据库(LA)的成绩数据库,并获得了新的成绩。