Segmentation only uses sparse annotations: Unified weakly and semi-supervised learning in medical images
Segmentation only uses sparse annotations: Unified weakly and semi-supervised learning in medical images
复制标题
DOI：
10.1016/j.media.2022.102515
复制
发表时间：
2022-06-30
影响因子：
10.9
通讯作者：
Wu, Xiaojian
中科院分区：
文献类型：
--
作者：
Gao, Feng;Hu, Minhao;Wu, Xiaojian
由于分割标记通常是耗时的，并且注释医学图像需要专业知识，因此获得大规模、高质量的注释分割数据集是费力的。我们提出了一种新的弱监督和半监督框架SOUSA（Segmentation Only Uses Sparse Annotations），旨在从少量稀疏注释数据和大量未标记数据中学习。该框架包括教师模型和学生模型。student模型由scribbles和从scribbles导出的测地线距离图进行弱监督。同时，大量的未标记的数据与各种扰动被馈送到学生和教师模型。他们的输出预测的一致性是由均方误差（MSE）损失和精心设计的多角度投影重建（MPR）损失。大量的实验表明，我们提出的方法的鲁棒性和泛化能力。结果表明，我们的方法在多个数据集上的性能优于弱监督和半监督的最先进的方法。此外，当数据集的大小有限时，我们的方法与一些具有密集注释的完全监督方法相比具有竞争力的性能。(C)2022爱思唯尔有限公司版权所有。
Since segmentation labeling is usually time-consuming and annotating medical images requires professional expertise, it is laborious to obtain a large-scale, high-quality annotated segmentation dataset. We propose a novel weakly- and semi-supervised framework named SOUSA (Segmentation Only Uses Sparse Annotations), aiming at learning from a small set of sparse annotated data and a large amount of unlabeled data. The proposed framework contains a teacher model and a student model. The student model is weakly supervised by scribbles and a Geodesic distance map derived from scribbles. Meanwhile, a large amount of unlabeled data with various perturbations are fed to student and teacher models. The consistency of their output predictions is imposed by Mean Square Error (MSE) loss and a carefully designed Multi-angle Projection Reconstruction (MPR) loss. Extensive experiments are conducted to demonstrate the robustness and generalization ability of our proposed method. Results show that our method outperforms weakly- and semi-supervised state-of-the-art methods on multiple datasets. Furthermore, our method achieves a competitive performance with some fully supervised methods with dense annotation when the size of the dataset is limited. (C) 2022 Elsevier B.V. All rights reserved.