arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1808.07553cs.CV
收藏

缺失数据纵向研究的预测图像回归

Predictive Image Regression for Longitudinal Studies with Missing Data

University of Georgia（佐治亚大学）

Sharmin Pathan, Yi Hong

备注：
1st Conference on Medical Imaging with Deep Learning (MIDL 2018), Amsterdam, The Netherlands
阅读 PDF
arXiv 页面 ↗HTML 原文 ↗

摘要：

本文提出了一种基于大变形几何度量映射（LDDMM）和深度神经网络的缺失数据纵向图像预测回归模型。我们的模型不是直接预测图像扫描，而是预测与基线图像相关的矢量动量序列。该动量序列在LDDMM框架中参数化原始图像序列，并且位于基线图像的切空间中，该切空间是欧几里得的。具有长期-短期记忆（LSTM）单元的递归网络对矢量动量序列中的时变变化进行编码，卷积神经网络（CNN）对矢量动量的基线图像进行编码。由LSTM和CNN提取的特征被馈送到解码器网络中以重构矢量动量序列，该矢量动量序列通过用LDDMM拍摄使基线图像变形来用于图像序列预测。为了处理在某些时间点丢失的图像，我们采用二进制掩码来忽略它们在损失计算中的重建。我们在综合生成的图像和来自OASIS数据集的脑MRI上评估我们的模型。实验结果表明，在这两个数据集的时空变化的有前途的预测，无论是大的或微妙的变化，纵向图像序列。

英文摘要：

In this paper, we propose a predictive regression model for longitudinal images with missing data based on large deformation diffeomorphic metric mapping (LDDMM) and deep neural networks. Instead of directly predicting image scans, our model predicts a vector momentum sequence associated with a baseline image. This momentum sequence parameterizes the original image sequence in the LDDMM framework and lies in the tangent space of the baseline image, which is Euclidean. A recurrent network with long term-short memory (LSTM) units encodes the time-varying changes in the vector-momentum sequence, and a convolutional neural network (CNN) encodes the baseline image of the vector momenta. Features extracted by the LSTM and CNN are fed into a decoder network to reconstruct the vector momentum sequence, which is used for the image sequence prediction by deforming the baseline image with LDDMM shooting. To handle the missing images at some time points, we adopt a binary mask to ignore their reconstructions in the loss calculation. We evaluate our model on synthetically generated images and the brain MRIs from the OASIS dataset. Experimental results demonstrate the promising predictions of the spatiotemporal changes in both datasets, irrespective of large or subtle changes in longitudinal image sequences.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。

↑