CT Slice Thickness and Convolution Kernel Affect Performance of a Radiomic Model for Predicting EGFR Status in Non-Small Cell Lung Cancer: A Preliminary Study

Abstract

We evaluated whether the optimal selection of CT reconstruction settings enables the construction of a radiomics model to predict epidermal growth factor receptor (EGFR) mutation status in primary lung adenocarcinoma (LAC) using standard of care CT images. Fifty-one patients (EGFR:wildtype = 23:28) with LACs of clinical stage I/II/IIIA were included in the analysis. The LACs were segmented in four conditions, two slice thicknesses (Thin: 1 mm; Thick: 5 mm) and two convolution kernels (Sharp: B70f/B70s; Smooth: B30f/B31f/B31s), which constituted four groups: (1) Thin-Sharp, (2) Thin-Smooth, (3) Thick-Sharp, and (4) Thick-Smooth. Machine learning algorithms selected and combined 1,695 quantitative image features to build prediction models. The performance of prediction models was assessed by calculating the area under the curve (AUC). The best prediction model yielded AUC (95%CI) = 0.83 (0.68, 0.92) using the Thin-Smooth reconstruction setting. The AUC of models using thick slices was significantly lower than that of thin slices (P < 10−3), whereas the impact of reconstruction kernel was not significant. Our study showed that the optimal prediction of EGFR mutational status in early stage LACs was achieved by using thin CT-scan slices, independently of convolution kernels. Results from the prediction model suggest that tumor heterogeneity is associated with EGFR mutation.

Radiomics as a personalized medicine tool in lung cancer: Separating the hope from the hype

“… B Patient motion affects feature reproducibility [ 80 , 92 , 93 ] Set motion tolerances, reduce ROI boundaries [ 80 ], use single phase from 4D images [ 92 ], find robust features using 4DCT data [ 93 ]. Image acquisition and reconstruction C Image resolution parameters (voxel size, slice thickness) affect feature values [ 79 , 88 , [94] , [95] , [96] , [97] , [98] ] model performance [ 99 ]. Control resolution [ 79 ] parameters in prospective studies, resample to common resolution and voxel depth [ [94] , [95] , [96] , 98 ], apply smoothing image filters [ 95 ], apply deep learning methods [ 100 ].…”

Homological radiomics analysis for prognostic prediction in lung cancer patients

“…Mackin et al demonstrated that the inter-scanner variability of conventional features calculated from CT images should be considered based on the characteristics inherent to scanners [51]. Li et al reported that using CT images with thicker slices significantly reduces the accuracy of support vector machines when using conventional features in the identification of gene-mutated NSCLC patients [52]. Furthermore, the impact of variations in patient populations on accuracy is unclear because this study focused on a single database.…”

“…The signatures of the HFs in this study were composed of reproducible features, which are robust in terms of inter-observer variability in GTVs, because irreproducible features (ICCs < 0.8) were removed during the construction of signatures (Subsection 2.2.3). In contrast, conventional features computed from CT images were likely to be irreproducible, due to variations in scanner/scanning protocols [51,52] or populations. Mackin et al demonstrated that the inter-scanner variability of conventional features calculated from CT images should be considered based on the characteristics inherent to scanners [51].…”

<p>Evaluating Solid Lung Adenocarcinoma Anaplastic Lymphoma Kinase Gene Rearrangement Using Noninvasive Radiomics Biomarkers</p>

“…According to a recent NSCLC EGFR radiomics study, compared with thick CT slice (5 mm), thin slice (1 mm) achieved the best prediction value, independently of convolution kernels. 44 In this retrospective study, nevertheless, in view of image standardization among each scan and avoiding interpolation, all CT images carried equal slice thickness of 5 mm.…”