Robust Radiomics Feature Quantification Using Semiautomatic Volumetric Segmentation

By Chintan Parmar, E. Rios Velazquez, R. Leijenaar, M. Jermoumi, S. Carvalho, R. Mak, S. Mitra, B. U. Shankar, Ron Kikinis, Benjamin Haibe-Kains and 2 more. PLoS ONE, 2014

567 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Pulmonary and Respiratory Medicine, Radiology, Nuclear Medicine and Imaging

View Paper: https://www.semanticscholar.org/paper/18292001f06b3fe7fe622df696351d8ceff793e2

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Pulmonary and Respiratory Medicine

In Radiology, Nuclear Medicine and Imaging

Citations in the corpus

The Applications of Radiomics in Precision Diagnosis and Treatment of Oncology: Opportunities and Challenges (2019, methodology): “Balagurunathan et al [55] Retrospective, single center study 32 + 59 329 (shape, size, and texture) concordance correlation coefficient, and K-M CT Prognosis”
Applications and limitations of radiomics (2016, methodology): “In a study, Parmar et al (2014) investigated the prognostic values of 440 radiomic features using fourteen feature selection methods and twelve classification models in >460 lung cancer patients (Parmar et al 2015a).”
CT-based radiomic signature predicts distant metastasis in lung adenocarcinoma. (2015, background): “The advantage of the radiomic shape features is that they can be automatically acquired, reproducible [10–12], and take into account the whole tumor volume, whereas clinically assessed tumor diameters aremanually drawn on a CT slice and are therefore limited to one dimension of the tumor.”
Radiomic Machine-Learning Classifiers for Prognostic Biomarkers of Head and Neck Cancer (2015, background): “Several studies have investigated the variability of radiomic features with respect to different imaging scanners (39, 40), tumor delineation methods (13, 41), reconstruction methods (42), discretization (43), etc.”
Machine Learning methods for Quantitative Radiomic Biomarkers (2015, background): “Several studies have investigated various radiomic features in terms of their prognostic or predictive abilities and reliability across different clinical settings 4–10 .”
Repeatability and Reproducibility of Radiomic Features: A Systematic Review (2018, unknown): “Parmar et al (42), 2014 NSCLC PET 20 Yes 56 FO, SM, TA ICC Reproducibility”