바로가기  >

Abstract
In radiomics research, the issue of different instruments being used is significant. In this study, we compared three correction methods to reduce the batch effects in radiogenomic data from fluorodeoxyglucose (FDG) PET/CT images of lung cancer patients. Texture features of the FDG PET/CT images and genomic data were retrospectively obtained. The features were corrected with different methods: phantom correction, ComBat method, and Limma method. Batch effects were estimated using three analytic tools: principal component analysis (PCA), the k-nearest neighbor batch effect test (kBET), and the silhouette score. Finally, the associations of features and gene mutations were compared between each correction method. Although the kBET rejection rate and silhouette score were lower in the phantom-corrected data than in the uncorrected data, a PCA plot showed a similar variance. ComBat and Limma methods provided correction with low batch effects, and there was no significant difference in the results of the two methods. In ComBat- and Limma-corrected data, more texture features exhibited a significant association with the TP53 mutation than in those in the phantom-corrected data. This study suggests that correction with ComBat or Limma methods can be more effective or equally as effective as the phantom method in reducing batch effects.

Figure 1. PCA plots (top) and box plots of kBET rejection rates and silhouette scores (bottom) by each batch correction method. The p-values from the t-test compared with uncorrected data are noted in the top of each box plot.

Figure 2. Plots of p-values of logistic regression for (a) ComBat (Global), (b) ComBat (Reference 1), (c)

ComBat (Reference 2), and (d) Limma versus p-values for the phantom method (black dots in each box plot.

Affiliations

Hyunjong Lee # 1, Sujin Seo # 2, Sungho Won 2, Woong-Yang Park 3, Joon Young Choi 1, Kyung-Han Lee 1, Se-Hoon Lee 4, Seung Hwan Moon 5
1Department of Nuclear Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea.
2Department of Public Health Science, Graduate School of Public Health, Seoul National University, Gwanak_1 Gwanak-ro, Gwanak-gu, Seoul, 08826, Republic of Korea.
3Department of Molecular Cell Biology, Samsung Medical Center, Samsung Genome Institute, Samsung Advanced Institute of Health Science and Technology, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
4Division of Hematology/Oncology, Department of Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, Seoul, Republic of Korea.
5Department of Nuclear Medicine, Samsung Medical Center, Sungkyunkwan University School of Medicine, 81 Irwon-ro, Gangnam-gu, Seoul, 06351, Republic of Korea. seunghwan.moons.moon@samsung.com.
#Contributed equally.