School of Biomedical Engineering, Faculty of Electronic Information and Electrical Engineering, Dalian University of Technology, Dalian, China.
Faculty of Information Technology, University of Jyväskylä, Jyväskylä, Finland.
Int J Comput Assist Radiol Surg. 2023 Feb;18(2):379-394. doi: 10.1007/s11548-022-02730-z. Epub 2022 Sep 1.
Training deep neural networks usually require a large number of human-annotated data. For organ segmentation from volumetric medical images, human annotation is tedious and inefficient. To save human labour and to accelerate the training process, the strategy of annotation by iterative deep learning recently becomes popular in the research community. However, due to the lack of domain knowledge or efficient human-interaction tools, the current AID methods still suffer from long training time and high annotation burden.
We develop a contour-based annotation by iterative deep learning (AID) algorithm which uses boundary representation instead of voxel labels to incorporate high-level organ shape knowledge. We propose a contour segmentation network with a multi-scale feature extraction backbone to improve the boundary detection accuracy. We also developed a contour-based human-intervention method to facilitate easy adjustments of organ boundaries. By combining the contour-based segmentation network and the contour-adjustment intervention method, our algorithm achieves fast few-shot learning and efficient human proofreading.
For validation, two human operators independently annotated four abdominal organs in computed tomography (CT) images using our method and two compared methods, i.e. a traditional contour-interpolation method and a state-of-the-art (SOTA) convolutional network (CNN) method based on voxel label representation. Compared to these methods, our approach considerably saved annotation time and reduced inter-rater variabilities. Our contour detection network also outperforms the SOTA nnU-Net in producing anatomically plausible organ shape with only a small training set.
Taking advantage of the boundary shape prior and the contour representation, our method is more efficient, more accurate and less prone to inter-operator variability than the SOTA AID methods for organ segmentation from volumetric medical images. The good shape learning ability and flexible boundary adjustment function make it suitable for fast annotation of organ structures with regular shape.
训练深度神经网络通常需要大量的人工标注数据。对于容积医学图像中的器官分割，人工标注既繁琐又低效。为了节省人力并加速训练过程，最近，通过迭代深度学习进行标注的策略在研究界变得流行起来。然而，由于缺乏领域知识或高效的人机交互工具，当前的 AID 方法仍然存在训练时间长和标注负担大的问题。
我们开发了一种基于轮廓的迭代深度学习（AID）算法，该算法使用边界表示代替体素标签，从而纳入高级器官形状知识。我们提出了一种具有多尺度特征提取骨干网络的轮廓分割网络，以提高边界检测精度。我们还开发了一种基于轮廓的人机交互方法，以方便对器官边界进行轻松调整。通过结合基于轮廓的分割网络和基于轮廓的调整干预方法，我们的算法实现了快速的少样本学习和高效的人工校对。
为了验证，两名操作人员分别使用我们的方法和两种对比方法（即传统的轮廓插值方法和基于体素标签表示的最新卷积网络（CNN）方法）在 CT 图像上独立标注了四个腹部器官。与这些方法相比，我们的方法大大节省了标注时间，减少了不同操作人员之间的差异。我们的轮廓检测网络在使用小训练集的情况下，在生成具有合理解剖结构的器官形状方面也优于 SOTA nnU-Net。
利用边界形状先验和轮廓表示，我们的方法比容积医学图像中器官分割的最新 AID 方法更高效、更准确，且不易受不同操作人员的影响。其良好的形状学习能力和灵活的边界调整功能使其适合对具有规则形状的器官结构进行快速标注。
