Robust Radiomics feature quantification using semiautomatic volumetric segmentation

Abstract

Due to advances in the acquisition and analysis of medical imaging, it is currently possible to quantify the tumor phenotype. The emerging field of Radiomics addresses this issue by converting medical images into minable data by extracting a large number of quantitative imaging features. One of the main challenges of Radiomics is tumor segmentation. Where manual delineation is time consuming and prone to inter-observer variability, it has been shown that semi-automated approaches are fast and reduce inter-observer variability. In this study, a semiautomatic region growing volumetric segmentation algorithm, implemented in the free and publicly available 3D-Slicer platform, was investigated in terms of its robustness for quantitative imaging feature extraction. Fifty-six 3D-radiomic features, quantifying phenotypic differences based on tumor intensity, shape and texture, were extracted from the computed tomography images of twenty lung cancer patients. These radiomic features were derived from the 3D-tumor volumes defined by three independent observers twice using 3D-Slicer, and compared to manual slice-by-slice delineations of five independent physicians in terms of intra-class correlation coefficient (ICC) and feature range. Radiomic features extracted from 3D-Slicer segmentations had significantly higher reproducibility (ICC = 0.85±0.15, p = 0.0009) compared to the features extracted from the manual segmentations (ICC = 0.77±0.17). Furthermore, we found that features extracted from 3D-Slicer segmentations were more robust, as the range was significantly smaller across observers (p = 3.819e-07), and overlapping with the feature ranges extracted from manual contouring (boundary lower: p = 0.007, higher: p = 5.863e-06). Our results show that 3D-Slicer segmented tumor volumes provide a better alternative to the manual delineation for feature quantification, as they yield more reproducible imaging descriptors. Therefore, 3D-Slicer can be employed for quantitative image feature extraction and image data mining research in large patient cohorts.

Figure 1. Schematic diagram depicting the overview of the analysis.

A: First, we performed five manual delineations and six 3D-Slicer segmentations (three observers twice) on twenty lung tumors. B: Second, fifty-six radiomic features quantifying tumor intensity, texture and shape were extracted from these segmentations. C: Third, the resulting feature matrices were compared for robustness of the feature values.

Figure 2. Feature wise comparison of Intra-class correlation coefficients (ICC) between manual and 3D-Slicer segmentations.

A: First order statistics features. B: Shape based features. C: Textural features.

Figure 3. Box-plot comparing intra- and inter-observer reproducibility (ICC) of radiomic features.

High inter- and intra- observer reproducibility (ICC) was observed for 3D-Slicer segmentations compared to the inter-observer reproducibility (ICC) of manual delineations. From left the first box refers to the manual inter-observer reproducibility (ICC), second and third boxes refer to the inter-observer reproducibility (ICC) of two different 3D-Slicer segmentation runs. Remaining three boxes refer to the intra-observer reproducibility (ICC) of 3D-Slicer segmentations.

Figure 4. Comparison of normalized feature range between manual and 3D-Slicer segmentation groups.

Radiomic features derived from 3D-Slicer segmentations had significantly smaller and overlapping range compared to that from manual delineations.