Features reproducibility and the generalizability of the models are currently among the most important limitations when integrating radiomics into the clinics. Radiomic features are sensitive to imaging acquisition protocols, reconstruction algorithms and parameters, as well as by the different steps of the usual radiomics workflow. We propose a framework for comparing the reproducibility of different pre-processing steps in PET/CT radiomic analysis in the prediction of disease free survival (DFS) across multi-scanners/centers.
We evaluated and compared the prediction performance of several models that differ in i) the type of intensity discretization, ii) feature selection method, iii) features type i.e, original or tumour to liver ratio radiomic features (OR or TLR). We trained our models using data from one scanner/center and tested on two external scanner/centers. Our results show that there is a low reproducibility in predictions across scanners and discretization methods. Despite of this, TLR based models were generally more robust than OR. Maximum relevance minimum redundancy (MRMR) forward feature selection with Pearson correlation was the feature selection method that had the best mean area under the precision recall curve when using it combining the features from all discretization’s bin’s number (D_All_FBN) with TLR features for two of the four classifiers.
We evaluated and compared the prediction performance of several models in a data set containing hundred fifty-eight patients with locally advanced cervical cancer (LACC) from three distinct scanners. In our cohort of LAAC patients pre-processing of radiomic features in [18F]FDG PET affects DFS predictions performances across scanners and combining the D_All_FBN TLR approach with the MRMR forward Pearson feature selection method might help increasing robustness of radiomic studies.