Detecting Outliers with Foreign Patch Interpolation-猫眼课题宝

DOI：

10.59275/j.melba.2022-e651

发表时间：

2020-11

期刊：

ArXiv

影响因子：

通讯作者：

中科院分区：

其他

文献类型：

作者：

Jeremy Tan;Benjamin Hou;James Batten;Huaqi Qiu;Bernhard Kainz

在医学成像中，异常值可以包含低/高强度、微小变形或完全改变的解剖结构。为了检测这些不规则性，学习正常和异常图像中存在的特征是有帮助的。然而，这是困难的，因为可能的异常范围很广，而且正常解剖结构可以自然变化的方式也很多。因此，我们利用正常解剖结构的自然变化来创造一系列合成异常。具体地，从两个独立的样本中提取相同的补丁区域，并用两个补丁之间的插值来替换。插值因子、斑块大小和斑块位置是从均匀分布中随机抽样的。训练宽残差编码器解码器以给出补丁及其插值因子的逐像素预测。这鼓励网络学习通常期望的特征，并识别在何处引入了外来模式。插值因子的估计值很好地适用于导出离群值分数。同时，像素级输出允许使用相同的模型进行像素级和主题级预测。https://github.com/jemtan/FPI

In medical imaging, outliers can contain hypo/hyper-intensities, minor deformations, or completely altered anatomy. To detect these irregularities it is helpful to learn the features present in both normal and abnormal images. However this is difficult because of the wide range of possible abnormalities and also the number of ways that normal anatomy can vary naturally. As such, we leverage the natural variations in normal anatomy to create a range of synthetic abnormalities. Specifically, the same patch region is extracted from two independent samples and replaced with an interpolation between both patches. The interpolation factor, patch size, and patch location are randomly sampled from uniform distributions. A wide residual encoder decoder is trained to give a pixel-wise prediction of the patch and its interpolation factor. This encourages the network to learn what features to expect normally and to identify where foreign patterns have been introduced. The estimate of the interpolation factor lends itself nicely to the derivation of an outlier score. Meanwhile the pixel-wise output allows for pixel- and subject- level predictions using the same model.Our code is available at https://github.com/jemtan/FPI

Detecting Outliers with Foreign Patch Interpolation

文献摘要

被引文献

相似文献