ICTEAM, UCLouvain, Louvain-la-Neuve 1348, Belgium.
iMMC, UCLouvain, Louvain-la-Neuve 1348, Belgium; Institute of Experimental and Clinical Research, UCLouvain, Louvain-la-Neuve 1348, Belgium.
Comput Biol Med. 2022 Sep;148:105932. doi: 10.1016/j.compbiomed.2022.105932. Epub 2022 Aug 2.
High-resolution non-destructive 3D microCT imaging allows the visualization and structural characterization of mineralized cartilage and bone. Deriving statistically relevant quantitative structural information about these tissues, however, requires automated segmentation procedures, mainly because manual contouring is user-biased and time-consuming. Despite the increased spatial resolution in microCT 3D volumes, automatic segmentation of mineralized cartilage versus bone remains non-trivial since they have similar grayscale values. Our work investigates how reliable 2D segmentation masks can be predicted automatically based on a (set of) convolutional neural network(s) trained with a limited number of manually annotated samples. To do that, we compared different strategies to select the 2D samples to annotate and considered ensemble learning and test-time augmentation (TTA) to mitigate the limited accuracy and robustness resulting from the small number of annotated training samples. We show that, for a fixed amount of annotated image samples, 2D microCT slices to annotate should preferably be selected in distinct 3D volumes, at regular intervals, rather than being grouped in adjacent slices of a same 3D volume. Two main lessons are drawn regarding the use of ensembles or TTA instead of a single model. First, ensemble learning is shown to improve segmentation accuracy and to reduce the mean and standard deviation of the absolute errors in cartilage characteristics obtained with different initializations of the neural network training process. In contrast, TTA appears to be unable to improve the model's robustness to unlucky initializations. Second, both TTA and ensembling improved the model's confidence in its predictions and segmentation failure detection.
高分辨率无损 3D 微计算机断层扫描成像允许对矿化软骨和骨进行可视化和结构特征分析。然而，要从这些组织中得出具有统计学意义的定量结构信息，需要自动化分割程序，主要是因为手动轮廓绘制存在用户偏见且耗时。尽管微计算机断层扫描 3D 体素的空间分辨率有所提高，但由于矿化软骨和骨的灰度值相似，因此自动分割它们仍然具有挑战性。我们的工作研究了如何基于经过有限数量的手动注释样本训练的（一组）卷积神经网络，自动预测可靠的 2D 分割掩模。为此，我们比较了不同的策略来选择要注释的 2D 样本，并考虑了集成学习和测试时增强（TTA），以减轻由于注释训练样本数量少而导致的准确性和鲁棒性有限的问题。我们表明，对于固定数量的注释图像样本，最好在不同的 3D 体素中以规则的间隔选择要注释的 2D 微计算机断层扫描切片，而不是将它们分组在同一 3D 体素的相邻切片中。关于使用集成或 TTA 代替单个模型，我们得出了两个主要结论。首先，集成学习被证明可以提高分割准确性，并减少使用神经网络训练过程的不同初始化获得的软骨特征的绝对误差的平均值和标准差。相比之下，TTA 似乎无法提高模型对不幸初始化的鲁棒性。其次，TTA 和集成都提高了模型对其预测和分割失败的置信度。
