An algorithm for learning shape and appearance models without annotations
An algorithm for learning shape and appearance models without annotations
复制标题
DOI：
10.1016/j.media.2019.04.008
复制
发表时间：
2018-07
影响因子：
10.9
通讯作者：
J. Ashburner;Mikael Brudfors;Kevin Bronik;Yaël Balbastre
中科院分区：
文献类型：
--
作者：
J. Ashburner;Mikael Brudfors;Kevin Bronik;Yaël Balbastre
本文提出了一个自动学习医学（和某些其他）图像的形状和外观模型的框架。开发该算法的目的是最终实现对大脑图像数据的分布式隐私保护分析，这样共享信息（形状和外观基础函数）可以跨站点传递，而编码单个图像的潜在变量在每个站点内保持安全。这些潜在变量被提出作为隐私保护数据挖掘应用的特征。该方法在2D人脸图像的KDEF数据集上进行了定性演示，表明它可以对齐传统上需要使用手动注释数据（手动定义地标等）训练的形状和外观模型的图像。它被应用于手写数字的MNIST数据集，以显示其在机器学习应用中的潜力，特别是在训练数据有限的情况下。该模型能够处理“缺失数据”，这使得它可以根据预测遗漏体素的程度进行交叉验证。通过将衍生特征应用于1900多个分割的t1加权MR图像数据集（包括来自COBRE和ABIDE数据集的图像），评估了将个体分类为患者组的适用性。
This paper presents a framework for automatically learning shape and appearance models for medical (and certain other) images. The algorithm was developed with the aim of eventually enabling distributed privacy-preserving analysis of brain image data, such that shared information (shape and appearance basis functions) may be passed across sites, whereas latent variables that encode individual images remain secure within each site. These latent variables are proposed as features for privacy-preserving data mining applications.The approach is demonstrated qualitatively on the KDEF dataset of 2D face images, showing that it can align images that traditionally require shape and appearance models trained using manually annotated data (manually defined landmarks etc.). It is applied to the MNIST dataset of handwritten digits to show its potential for machine learning applications, particularly when training data is limited. The model is able to handle “missing data”, which allows it to be cross-validated according to how well it can predict left-out voxels. The suitability of the derived features for classifying individuals into patient groups was assessed by applying it to a dataset of over 1900 segmented T1-weighted MR images, which included images from the COBRE and ABIDE datasets.