CT and MRI radiomic features of lung cancer (NSCLC): comparison and software consistency

Abstract

Background: Radiomics is a quantitative approach that allows the extraction of mineable data from medical images. Despite the growing clinical interest, radiomics studies are affected by variability stemming from analysis choices. We aimed to investigate the agreement between two open-source radiomics software for both contrast-enhanced computed tomography (CT) and contrast-enhanced magnetic resonance imaging (MRI) of lung cancers and to preliminarily evaluate the existence of radiomic features stable for both techniques.

Methods: Contrast-enhanced CT and MRI images of 35 patients affected with non-small cell lung cancer (NSCLC) were manually segmented and preprocessed using three different methods. Sixty-six Image Biomarker Standardisation Initiative-compliant features common to the considered platforms, PyRadiomics and LIFEx, were extracted. The correlation among features with the same mathematical definition was analyzed by comparing PyRadiomics and LIFEx (at fixed imaging technique), and MRI with CT results (for the same software).

Results: When assessing the agreement between LIFEx and PyRadiomics across the considered resampling, the maximum statistically significant correlations were observed to be 94% for CT features and 95% for MRI ones. When examining the correlation between features extracted from contrast-enhanced CT and MRI using the same software, higher significant correspondences were identified in 11% of features for both software.

Conclusions: Considering NSCLC, (i) for both imaging techniques, LIFEx and PyRadiomics agreed on average for 90% of features, with MRI being more affected by resampling and (ii) CT and MRI contained mostly non-redundant information, but there are shape features and, more importantly, texture features that can be singled out by both techniques.

Relevance statement: Identifying and selecting features that are stable cross-modalities may be one of the strategies to pave the way for radiomics clinical translation.

Key points: • More than 90% of LIFEx and PyRadiomics features contain the same information. • Ten percent of features (shape, texture) are stable among contrast-enhanced CT and MRI. • Software compliance and cross-modalities stability features are impacted by the resampling method.

Keywords: Biomarkers; Lung neoplasms; Magnetic resonance imaging; Radiomics; Tomography (x-ray computed).

Fig. 1

Consistency between radiomic features extracted with LIFEx and PyRadiomics, expressed through ICC, from MRI (a) and CT (b) images. Ext.res. External resampling, Or.vox-siz. Original voxel size, Soft.res. Software resampling

Fig. 2

Comparison between features distributions computed by LIFEx and PyRadiomics platforms from MRI acquisitions. The top panel line represents a feature with excellent reliability (Skewness), while the bottom panel line a feature with poor reliability (GLCM Inverse Variance) for the three options considered: original voxel size (a); software (internal) resampling (b); external resampling (c). Ext.res. External resampling, Or.vox-siz. Original voxel size, Soft.res. Software resampling

Fig. 3

Comparison between feature distributions computed by LIFEx and PyRadiomics platforms from CT images. The top panel line shows a feature with excellent reliability (Entropy), while the bottom panel line displays a feature with poor reliability (GLZLM Large Zone Emphasis), for the three options considered: original voxel size (a); software (internal) resampling (b); external resampling (c). Ext.res. External resampling, Or.vox-siz. Original voxel size, Soft.res. Software resampling

Fig. 4

Agreement between radiomic features extracted from CT and MRI images, expressed through ICC, for PyRadiomics (a) and LIFEx (b). Ext.res. External resampling, Or.vox-siz. Original voxel size, Soft.res. Software resampling