Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation
Transformation-Consistent Self-Ensembling Model for Semisupervised Medical Image Segmentation
复制标题
用于半监督医学图像分割的变换一致自集成模型
DOI：
10.1109/tnnls.2020.2995319
复制
发表时间：
2021-02-01
影响因子：
10.4
通讯作者：
Heng, Pheng-Ann
中科院分区：
文献类型：
--
作者：
Li, Xiaomeng;Yu, Lequan;Heng, Pheng-Ann
针对医学成像领域，监督式深度学习的一个常见不足是缺乏标记数据，而这些数据的收集通常既昂贵又耗时。本文提出了一种新的医学图像分割的半监督方法，其中通过仅针对标记输入的共同监督损失和针对标记和未标记数据的正则化损失的加权组合来优化网络。为了利用未标记的数据，我们的方法鼓励在不同扰动下对相同输入的训练中网络进行一致的预测。在半监督分割任务中，我们在自集成模型中引入了一种变换一致性策略，以增强像素级预测的正则化效果。为了进一步改善正则化效果，我们以更广义的形式扩展了变换，包括缩放和优化教师模型的一致性损失，这是学生模型权重的平均值。我们在三个典型但具有挑战性的医学图像分割任务上广泛验证了所提出的半监督方法：1）国际皮肤成像协作组（ISIC）2017数据集中皮肤镜图像的皮肤病变分割; 2）视网膜眼底青光眼挑战（REFUGE）数据集中眼底图像的视盘（OD）分割;以及3）来自肝脏肿瘤分割挑战（LiTS）数据集中的体积CT扫描的肝脏分割。与现有方法相比，该方法在二维/三维医学图像分割中表现出了上级的性能，证明了该方法在医学图像分割中的有效性。
A common shortfall of supervised deep learning for medical imaging is the lack of labeled data, which is often expensive and time consuming to collect. This article presents a new semisupervised method for medical image segmentation, where the network is optimized by a weighted combination of a common supervised loss only for the labeled inputs and a regularization loss for both the labeled and unlabeled data. To utilize the unlabeled data, our method encourages consistent predictions of the network-in-training for the same input under different perturbations. With the semisupervised segmentation tasks, we introduce a transformation-consistent strategy in the self-ensembling model to enhance the regularization effect for pixel-level predictions. To further improve the regularization effects, we extend the transformation in a more generalized form including scaling and optimize the consistency loss with a teacher model, which is an averaging of the student model weights. We extensively validated the proposed semisupervised method on three typical yet challenging medical image segmentation tasks: 1) skin lesion segmentation from dermoscopy images in the International Skin Imaging Collaboration (ISIC) 2017 data set; 2) optic disk (OD) segmentation from fundus images in the Retinal Fundus Glaucoma Challenge (REFUGE) data set; and 3) liver segmentation from volumetric CT scans in the Liver Tumor Segmentation Challenge (LiTS) data set. Compared with state-of-the-art, our method shows superior performance on the challenging 2-D/3-D medical images, demonstrating the effectiveness of our semisupervised method for medical image segmentation.