IEEE Trans Biomed Eng. 2020 Oct;67(10):2710-2720. doi: 10.1109/TBME.2020.2969608. Epub 2020 Jan 27.
Obtaining accurate segmentation of the prostate and nearby organs at risk (e.g., bladder and rectum) in CT images is critical for radiotherapy of prostate cancer. Currently, the leading automatic segmentation algorithms are based on Fully Convolutional Networks (FCNs), which achieve remarkable performance but usually need large-scale datasets with high-quality voxel-wise annotations for full supervision of the training. Unfortunately, such annotations are difficult to acquire, which becomes a bottleneck to build accurate segmentation models in real clinical applications. In this paper, we propose a novel weakly supervised segmentation approach that only needs 3D bounding box annotations covering the organs of interest to start the training. Obviously, the bounding box includes many non-organ voxels that carry noisy labels to mislead the segmentation model. To this end, we propose the label denoising module and embed it into the iterative training scheme of the label denoising network (LDnet) for segmentation. The labels of the training voxels are predicted by the tentative LDnet, while the label denoising module identifies the voxels with unreliable labels. As only the good training voxels are preserved, the iteratively re-trained LDnet can refine its segmentation capability gradually. Our results are remarkable, i.e., reaching ∼ 94% (prostate), ∼ 91% (bladder), and ∼ 86% (rectum) of the Dice Similarity Coefficients (DSCs), compared to the case of fully supervised learning upon high-quality voxel-wise annotations and also superior to several state-of-the-art approaches. To our best knowledge, this is the first work to achieve voxel-wise segmentation in CT images from simple 3D bounding box annotations, which can greatly reduce many labeling efforts and meet the demands of the practical clinical applications.
在 CT 图像中准确分割前列腺和附近的危险器官（例如膀胱和直肠）对于前列腺癌的放射治疗至关重要。目前，领先的自动分割算法基于全卷积网络（FCN），它们可以实现出色的性能，但通常需要具有高质量体素注释的大规模数据集来进行全面监督训练。不幸的是，此类注释难以获取，这成为在实际临床应用中构建准确分割模型的瓶颈。在本文中，我们提出了一种新颖的弱监督分割方法，仅需要覆盖感兴趣器官的 3D 边界框注释即可开始训练。显然，边界框包含许多携带误导分割模型的噪声标签的非器官体素。为此，我们提出了标签去噪模块，并将其嵌入到标签去噪网络（LDnet）的迭代训练方案中进行分割。训练体素的标签由初步的 LDnet 预测，而标签去噪模块则识别出具有不可靠标签的体素。由于仅保留了良好的训练体素，因此迭代重新训练的 LDnet 可以逐渐提高其分割能力。我们的结果非常显著，即达到了约 94%（前列腺）、约 91%（膀胱）和约 86%（直肠）的 Dice 相似系数（DSC），与使用高质量体素注释的完全监督学习相比，也优于几种最先进的方法。据我们所知，这是首次从简单的 3D 边界框注释实现 CT 图像体素分割的工作，这可以大大减少许多标记工作并满足实际临床应用的需求。
