Analysis of multiplanar integration based on uncertainty estimation in automatic segmentation of abdominal organs in 3D CT image using 2D Bayesian U-Net
Analysis of multiplanar integration based on uncertainty estimation in automatic segmentation of abdominal organs in 3D CT image using 2D Bayesian U-Net
复制标题
使用 2D 贝叶斯 U-Net 进行 3D CT 图像腹部器官自动分割中基于不确定性估计的多平面积分分析
DOI：
10.1117/12.2590794
复制
发表时间：
2021
期刊：
影响因子：
--
通讯作者：
Sato Yoshinobu
中科院分区：
文献类型：
--
作者：
Masaki Yuto;Otake Yoshito;Soufi Mazen;Hori Masatoshi;Onishi Hiromitsu;Tomiyama Noriyuki;Sato Yoshinobu
最近，有研究表明，可以通过在深度学习的神经网络结构中集成蒙特卡洛（MC）dropout [1]来估计不确定性。我们的小组提出了贝叶斯U网[2]，它集成了MC dropout和U网[3]架构，并研究了分割精度（Dice）和MC dropout推断的不确定性之间的关系。在CT图像中的肌肉骨骼结构的自动分割的不确定性和错误之间的高度相关性。在另一项研究中，通过独立为每个解剖平面训练的卷积神经网络（CNN）基于预测概率进行投票所获得的分割的整合[4]可以进一步提高分割精度并减少计算时间。然而，据我们所知，基于不确定性的集成还没有被研究。在本文中，我们应用了3个贝叶斯U-网，每个训练的2D切片在三个解剖平面之一，两相对比增强CT图像的48例（97张图像）与手动分割的17个器官。我们报告的解剖平面的不确定性的变化，并最终评估多平面集成为基础的预测相比，单平面为基础的预测。与仅从轴向平面获得的分割相比，9个器官中基于不确定性的积分显着提高了以Dice系数（DC）表示的分割准确度（p<0.05）。所有的分割结果都显示出不确定性与DC之间的负相关性。我们发现，通过整合多平面分割结果的不确定性估计的基础上，可以提高分割精度。
Recently, it has been shown that the uncertainty can be estimated by integrating Monte Carlo (MC) dropout [1] in the neural network structure in deep learning. Our group proposed Bayesian U-Net [2], which integrates MC dropout with U-Net [3] architecture, and investigated the relationship between the segmentation accuracy (Dice) and the uncertainty inferred by MC dropout. High correlation between the uncertainty and the errors in the automatic segmentation of musculoskeletal structures in CT images was obtained. In a different study, the integration of the segmentations obtained by voting based on prediction probabilities by convolutional neural networks (CNNs) trained for each anatomical plane independently [4] could further improve the segmentation accuracy and reduced the calculation time. However, as far as we know, the uncertainty-based integration has not been investigated yet. In this paper, we applied 3 Bayesian U-Nets, each trained on 2D slices in one of the three anatomical planes, to two-phase contrast-enhanced CT images of 48 cases (97 images) with manual segmentation of 17 organs. We report the variations in the uncertainties with respect to the anatomical planes, and finally evaluate the multiplanar integration-based predictions compared with single plane-based predictions. The segmentation accuracy, represented by Dice coefficient (DC), was significantly improved by the uncertainty-based integration in 9 organs (p<0.05) compared with segmentations obtained only from the axial plane. All segmentation results showed a negative correlation between the uncertainty and DC. We found that the segmentation accuracy could be improved by integrating the multiplanar segmentation results based on uncertainty estimation.