Computer School, University of South China, Hengyang 421001, Hunan, People's Republic of China.
Department of Anesthesiology'People's Hospital of Longhua, Shenzhen 518109, People's Republic of China.
Phys Med Biol. 2022 Aug 30;67(17). doi: 10.1088/1361-6560/ac89c8.
A semi-supervised learning method is an essential tool for applying medical image segmentation. However, the existing semi-supervised learning methods rely heavily on the limited labeled data. The generalization performance of image segmentation is improved to reduce the need for the number of labeled samples and the difficulty of parameter tuning by extending the consistency regularization.We propose a new regularization-driven Mean Teacher model based on semi-supervised learning for medical image segmentation in this work. We introduce a regularization-driven strategy with virtual adversarial training to improve segmentation performance and the robustness of the Mean Teacher model. We optimize the unsupervised loss function and the regularization term with an entropy minimum to smooth the decision boundary.We extensively evaluate the proposed method on the International Skin Imaging Cooperation 2017(ISIC2017) and COVID-19 CT segmentation datasets. Our proposed approach gains more accurate results on challenging 2D images for semi-supervised medical image segmentation. Compared with the state-of-the-art methods, the proposed approach has significantly improved and is superior to other semi-supervised segmentation methods.The proposed approach can be extended to other medical segmentation tasks and can reduce the burden of physicians to some extent.
一种半监督学习方法是应用医学图像分割的重要工具。然而，现有的半监督学习方法严重依赖于有限的标记数据。通过扩展一致性正则化，我们提出了一种新的正则化驱动的Mean Teacher 模型，用于医学图像分割的半监督学习。我们引入了一种正则化驱动的策略，结合虚拟对抗训练，以提高分割性能和 Mean Teacher 模型的鲁棒性。我们通过最小化熵来优化无监督损失函数和正则化项，以平滑决策边界。我们在国际皮肤成像合作 2017 年(ISIC2017)和 COVID-19 CT 分割数据集上广泛评估了所提出的方法。我们的方法在具有挑战性的 2D 图像上获得了更准确的半监督医学图像分割结果。与最先进的方法相比，所提出的方法显著提高，优于其他半监督分割方法。该方法可以扩展到其他医学分割任务，并在一定程度上减轻医生的负担。
