Test–Retest Reproducibility Analysis of Lung CT Image Features

Abstract

Quantitative size, shape, and texture features derived from computed tomographic (CT) images may be useful as predictive, prognostic, or response biomarkers in non-small cell lung cancer (NSCLC). However, to be useful, such features must be reproducible, non-redundant, and have a large dynamic range. We developed a set of quantitative three-dimensional (3D) features to describe segmented tumors and evaluated their reproducibility to select features with high potential to have prognostic utility. Thirty-two patients with NSCLC were subjected to unenhanced thoracic CT scans acquired within 15 min of each other under an approved protocol. Primary lung cancer lesions were segmented using semi-automatic 3D region growing algorithms. Following segmentation, 219 quantitative 3D features were extracted from each lesion, corresponding to size, shape, and texture, including features in transformed spaces (laws, wavelets). The most informative features were selected using the concordance correlation coefficient across test-retest, the biological range and a feature independence measure. There were 66 (30.14%) features with concordance correlation coefficient ≥ 0.90 across test-retest and acceptable dynamic range. Of these, 42 features were non-redundant after grouping features with R (2) Bet ≥ 0.95. These reproducible features were found to be predictive of radiological prognosis. The area under the curve (AUC) was 91% for a size-based feature and 92% for the texture features (runlength, laws). We tested the ability of image features to predict a radiological prognostic score on an independent NSCLC (39 adenocarcinoma) samples, the AUC for texture features (runlength emphasis, energy) was 0.84 while the conventional size-based features (volume, longest diameter) was 0.80. Test-retest and correlation analyses have identified non-redundant CT image features with both high intra-patient reproducibility and inter-patient biological range. Thus making the case that quantitative image features are informative and prognostic biomarkers for NSCLC.

Staging of Lung Cancer

“…95 In NSCLC, quantitative imaging features have been used to distinguish between adenocarcinoma and squamous cell subtypes and suggest tumor characteristics such as stage, metabolism, hypoxia, angiogenesis, and prognosis. 96,97 Using a publicly available dataset consisting of 32 NSCLC patients, Kumar and colleagues 98 have identified 39 of 327 CT features that are reproducible, nonredundant, and informative. Recently, quantitative CT texture and spatial analysis techniques used to analyze mediastinal lymph nodes in 43 patients with primary lung malignancies showed a sensitivity of 81% and specificity of 80% for detecting nodal metastatic disease.…”

Personalizing Medicine Through Hybrid Imaging and Medical Big Data Analysis

“…At the time neither the image quality nor the computational capacity was sufficient to operate with textural features. Thanks to recent advances in imaging and computational fields, several groups have investigated the potential of textural features in light of in vivo disease characterization [8,28,56,[148][149][150]. Routine clinical evaluation of PET images relies on the statistical analysis of Standardized Uptake Values (SUV) [151].…”

Sensitivity of Image Features to Noise in Conventional and Respiratory-Gated PET/CT Images of Lung Cancer: Uncorrelated Noise Effects

“…2,26-30 A full description of the CCC can be found in the studies by Lin 26 and Balagurunathan et al 27 A strength of agreement classification defined by McBride was used to classify CCC results (Table 2). 31 The mean CCC for each feature subtype was calculated, and the median and range for each feature across noise levels were plotted.…”