期刊
BIOENGINEERING-BASEL
卷 10, 期 1, 页码 -出版社
MDPI
DOI: 10.3390/bioengineering10010080
关键词
radiomics; cardiac magnetic resonance imaging; T1 and T2 mapping; collinearity; dimensionality reduction; spatial resampling; discretization bin width; filtering; hyperthophic cardiomyopathy
Radiomics and artificial intelligence have the potential to be valuable tools in clinical applications. This study assessed the effect of preprocessing, such as voxel size resampling, discretization, and filtering, on correlation-based dimensionality reduction of radiomic features from cardiac T1 and T2 maps. The results showed that the percentage of eliminated radiomic features was more dependent on resampling voxel size and discretization bin width for textural features. Correlation-based dimensionality reduction was less sensitive to preprocessing when considering T2 features compared to T1 features.
Radiomics and artificial intelligence have the potential to become a valuable tool in clinical applications. Frequently, radiomic analyses through machine learning methods present issues caused by high dimensionality and multicollinearity, and redundant radiomic features are usually removed based on correlation analysis. We assessed the effect of preprocessing-in terms of voxel size resampling, discretization, and filtering-on correlation-based dimensionality reduction in radiomic features from cardiac T1 and T2 maps of patients with hypertrophic cardiomyopathy. For different combinations of preprocessing parameters, we performed a dimensionality reduction of radiomic features based on either Pearson's or Spearman's correlation coefficient, followed by the computation of the stability index. With varying resampling voxel size and discretization bin width, for both T1 and T2 maps, Pearson's and Spearman's dimensionality reduction produced a slightly different percentage of remaining radiomic features, with a relatively high stability index. For different filters, the remaining features' stability was instead relatively low. Overall, the percentage of eliminated radiomic features through correlation-based dimensionality reduction was more dependent on resampling voxel size and discretization bin width for textural features than for shape or first-order features. Notably, correlation-based dimensionality reduction was less sensitive to preprocessing when considering radiomic features from T2 compared with T1 maps.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据