Patch-Based Abnormality Maps for Improved Deep Learning-Based Classification of Huntington's Disease.
Patch-Based Abnormality Maps for Improved Deep Learning-Based Classification of Huntington's Disease.
复制标题
DOI：
10.1007/978-3-030-59728-3_62
复制
发表时间：
2020-09
期刊：
影响因子：
--
通讯作者：
Oguz I
中科院分区：
文献类型：
--
作者：
Hett K;Giraud R;Johnson H;Paulsen JS;Long JD;Oguz I
深度学习技术在许多医学成像应用中表现出最先进的性能。这些方法可以有效地学习特定的模式。深度学习的另一种方法是基于补丁的分级方法，其目的是检测受试者组之间的局部相似性和差异。与深度学习技术相比，后一种方法通常需要更少的训练数据。在这项工作中，我们提出了两个主要贡献：首先，我们结合了联合收割机基于补丁和深度学习的方法。其次，我们提出了一个新的基于补丁的异常度量的补丁为基础的分级方法。我们的方法使我们能够检测本地化的结构异常的测试图像相比，由各种健康对照的图像组成的模板库。我们评估我们的方法通过比较使用不同的功能和模型集的分类性能。我们的实验表明，与基于MRI强度的标准深度学习方法相比，我们新的基于补丁的异常度量将深度学习性能从91.3%提高到95.8%。
Deep learning techniques have demonstrated state-of-the-art performances in many medical imaging applications. These methods can efficiently learn specific patterns. An alternative approach to deep learning is patch-based grading methods, which aim to detect local similarities and differences between groups of subjects. This latter approach usually requires less training data compared to deep learning techniques. In this work, we propose two major contributions: first, we combine patch-based and deep learning methods. Second, we propose to extend the patch-based grading method to a new patch-based abnormality metric. Our method enables us to detect localized structural abnormalities in a test image by comparison to a template library consisting of images from a variety of healthy controls. We evaluate our method by comparing classification performance using different sets of features and models. Our experiments show that our novel patch-based abnormality metric increases deep learning performance from 91.3% to 95.8% of accuracy compared to standard deep learning approaches based on the MRI intensity.