Optimization and validation of voxel size-related radiomics variability by combatting batch effect harmonization in pulmonary nodules: a phantom and clinical study

Yaoyao Zhuo; Jie Shen; Yi Zhan; Ye Tian; Mingfeng Yu; Shuyi Yang; Peiyan Ye; Li Fan; Zhiyong Zhang; Fei Shan

doi:10.21037/qims-22-992

Optimization and validation of voxel size-related radiomics variability by combatting batch effect harmonization in pulmonary nodules: a phantom and clinical study

Quant Imaging Med Surg. 2023 Sep 1;13(9):6139-6151. doi: 10.21037/qims-22-992. Epub 2023 Jul 13.

Authors

Yaoyao Zhuo^#^{1

2}, Jie Shen^#², Yi Zhan², Ye Tian³, Mingfeng Yu⁴, Shuyi Yang¹, Peiyan Ye⁵, Li Fan⁶, Zhiyong Zhang^#^{1

2

7}, Fei Shan^#^{2

7}

Affiliations

¹ Department of Radiology, Zhongshan Hospital, Fudan University, Shanghai, China.
² Department of Radiology, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China.
³ Department of Radiology, Beilun Second People's Hospital, Ningbo, China.
⁴ Department of Thoracic Surgery, Beilun Second People's Hospital, Ningbo, China.
⁵ Department of Traditional Chinese Medicine, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China.
⁶ Department of Radiology, Changzheng Hospital, Naval Medical University, Shanghai, China.
⁷ Research Institute of Big Data, Fudan University, Shanghai, China.

^# Contributed equally.

Abstract

Background: Broad generalization of radiomics-assisted models may be impeded by concerns about variability. This study aimed to evaluate the merit of combatting batch effect (ComBat) harmonization in reducing the variability of voxel size-related radiomics in both phantom and clinical study in comparison with image resampling correction method.

Methods: A pulmonary phantom with 22 different types of nodules was scanned by computed tomography (CT) with different voxel sizes. The variability of voxel size-related radiomics features was evaluated using concordance correlation coefficient (CCC), dynamic range (DR), and intraclass correlation coefficient (ICC). ComBat and image resampling compensation methods were used to reduce variability of voxel size-related radiomics. The percentage of robust radiomics features was compared before and after optimization. Pathologically differential diagnosis of invasive adenocarcinoma (IAC) from adenocarcinoma in situ (AIS) and minimally invasive adenocarcinoma (MIA) (AIS-MIA group) was used for clinical validation in 134 patients.

Results: Before optimization, the number of excellent features in the phantom and clinical data was 26.12% and 32.31%, respectively. The excellent features were increased after image resampling and ComBat correction. For clinical optimization, the effect of the ComBat compensation method was significantly better than that of image resampling, with excellent features reaching 90.96% and poor features only amounting to 4.96%. In addition, the hierarchical clustering analysis showed that the first-order and shape features had better robustness than did texture features. In clinical validation, the area under the curve (AUC) of the testing set was 0.865 after ComBat correction.

Conclusions: The ComBat harmonization can optimize voxel size-related CT radiomics variability in pulmonary nodules more efficiently than image resampling harmonization.

Keywords: Combatting batch effect (ComBat); computed tomography radiomics (CT radiomics); image resampling; pulmonary nodule; radiomics variability.