Analysis of the Influence of Diffeomorphic Normalization in the Prediction of Stable VS Progressive MCI Conversion with Convolutional Neural Networks
Analysis of the Influence of Diffeomorphic Normalization in the Prediction of Stable VS Progressive MCI Conversion with Convolutional Neural Networks
复制标题
微分同胚归一化对卷积神经网络预测稳定VS渐进MCI转换的影响分析
DOI：
10.1109/isbi45749.2020.9098445
复制
发表时间：
2020
期刊：
影响因子：
--
通讯作者：
Adni
中科院分区：
文献类型：
--
作者：
Ubaldo Ramon;Monica Hernandez;Elvira Mayordomo;Adni
我们研究了Spasov深度学习系统在渐进MCI与稳定MCI区分问题上选择同构归一化的效果。我们考虑了不同程度的规范化（无，仿射和非刚性规范化）和两个同构配准方法（ANTS和BL PDE-LDDMM）与不同的图像相似性度量（SSD，NCC和INCC）产生定性不同的变形模型和定量不同程度的配准精度。BL PDE-LDDMM NCC实现了最佳性能准确性，中值为89%。令人惊讶的是，no和仿射归一化的准确性也是最高的，这表明深度学习系统足够强大，可以在不需要归一化的情况下学习pMCI与sMCI区分的准确模型。然而，BL PDE-LDDMM SSD和NCC获得了最佳灵敏度值，中值为97%和94%，而其余方法的灵敏度保持在88%以下。
We study the effect of the selection of diffeomorphic normalization in the performance of Spasov's deep-learning system for the problem of progressive MCI vs stable MCI discrimination. We considered different degrees of normalization (no, affine and non-rigid normalization) and two diffeomorphic registration methods (ANTS and BL PDE-LDDMM) with different image similarity metrics (SSD, NCC, and lNCC) yielding qualitatively different deformation models and quantitatively different degrees of registration accuracy. BL PDE-LDDMM NCC achieved the best performing accuracy with median values of 89%. Surprisingly, the accuracy of no and affine normalization was also among the highest, indicating that the deep-learning system is powerful enough to learn accurate models for pMCI vs sMCI discrimination without the need for normalization. However, the best sensitivity values were obtained by BL PDE-LDDMM SSD and NCC with median values of 97% and 94% while the sensitivity of the remaining methods stayed under 88%.