Division of Biostatistics, Department of Family Medicine and Public Health, University of California San Diego, La Jolla, 92093, USA.
Department of Mathematics and Statistics, San Diego State University, San Diego, CA, 92182, USA.
Sci Rep. 2020 Nov 23;10(1):20336. doi: 10.1038/s41598-020-77264-y.
We propose a random forest classifier for identifying adequacy of liver MR images using handcrafted (HC) features and deep convolutional neural networks (CNNs), and analyze the relative role of these two components in relation to the training sample size. The HC features, specifically developed for this application, include Gaussian mixture models, Euler characteristic curves and texture analysis. Using HC features outperforms the CNN for smaller sample sizes and with increased interpretability. On the other hand, with enough training data, the combined classifier outperforms the models trained with HC features or CNN features alone. These results illustrate the added value of HC features with respect to CNNs, especially when insufficient data is available, as is often found in clinical studies.
我们提出了一种随机森林分类器，用于使用手工制作（HC）特征和深度卷积神经网络（CNNs）来识别肝脏磁共振图像的充分性，并分析这两个组件相对于训练样本大小的相对作用。HC 特征是专门为此应用开发的，包括高斯混合模型、欧拉特征曲线和纹理分析。在较小的样本量下，使用 HC 特征比 CNN 表现更好，并且具有更高的可解释性。另一方面，随着训练数据的增加，组合分类器的性能优于仅使用 HC 特征或 CNN 特征训练的模型。这些结果说明了 HC 特征相对于 CNN 的附加价值，特别是在数据不足的情况下，这种情况在临床研究中经常出现。
