Ruben T H M Larue1, Janna E van Timmeren1, Evelyn E C de Jong1, Giacomo Feliciani1, Ralph T H Leijenaar1, Wendy M J Schreurs2, Meindert N Sosef3, Frank H P J Raat4, Frans H R van der Zande5, Marco Das6, Wouter van Elmpt1, Philippe Lambin1. 1. a Department of Radiation Oncology (MAASTRO, the D-Lab), GROW-School for Oncology and Developmental Biology , Maastricht University Medical Centre , Maastricht , The Netherlands. 2. b Department of Nuclear Medicine , Zuyderland Medical Centre , Heerlen , The Netherlands. 3. c Department of Surgery , Zuyderland Medical Centre , Heerlen , The Netherlands. 4. d Department of Radiology , Laurentius Medical Centre , Roermond , The Netherlands. 5. e Department of Radiology , Vie Curi Medical Centre , Venlo , The Netherlands. 6. f Department of Radiology , Maastricht University Medical Centre , Maastricht , The Netherlands.
Abstract
BACKGROUND: Radiomic analyses of CT images provide prognostic information that can potentially be used for personalized treatment. However, heterogeneity of acquisition- and reconstruction protocols influences robustness of radiomic analyses. The aim of this study was to investigate the influence of different CT-scanners, slice thicknesses, exposures and gray-level discretization on radiomic feature values and their stability. MATERIAL AND METHODS: A texture phantom with ten different inserts was scanned on nine different CT-scanners with varying tube currents. Scans were reconstructed with 1.5 mm or 3 mm slice thickness. Image pre-processing comprised gray-level discretization in ten different bin widths ranging from 5 to 50 HU and different resampling methods (i.e., linear, cubic and nearest neighbor interpolation to 1 × 1 × 3 mm3 voxels) were investigated. Subsequently, 114 textural radiomic features were extracted from a 2.1 cm3 sphere in the center of each insert. The influence of slice thickness, exposure and bin width on feature values was investigated. Feature stability was assessed by calculating the concordance correlation coefficient (CCC) in a test-retest setting and for different combinations of scanners, tube currents and slice thicknesses. RESULTS: Bin width influenced feature values, but this only had a marginal effect on the total number of stable features (CCC > 0.85) when comparing different scanners, slice thicknesses or exposures. Most radiomic features were affected by slice thickness, but this effect could be reduced by resampling the CT-images before feature extraction. Statistics feature 'energy' was the most dependent on slice thickness. No clear correlation between feature values and exposures was observed. CONCLUSIONS: CT-scanner, slice thickness and bin width affected radiomic feature values, whereas no effect of exposure was observed. Optimization of gray-level discretization to potentially improve prognostic value can be performed without compromising feature stability. Resampling images prior to feature extraction decreases the variability of radiomic features.
BACKGROUND: Radiomic analyses of CT images provide prognostic information that can potentially be used for personalized treatment. However, heterogeneity of acquisition- and reconstruction protocols influences robustness of radiomic analyses. The aim of this study was to investigate the influence of different CT-scanners, slice thicknesses, exposures and gray-level discretization on radiomic feature values and their stability. MATERIAL AND METHODS: A texture phantom with ten different inserts was scanned on nine different CT-scanners with varying tube currents. Scans were reconstructed with 1.5 mm or 3 mm slice thickness. Image pre-processing comprised gray-level discretization in ten different bin widths ranging from 5 to 50 HU and different resampling methods (i.e., linear, cubic and nearest neighbor interpolation to 1 × 1 × 3 mm3 voxels) were investigated. Subsequently, 114 textural radiomic features were extracted from a 2.1 cm3 sphere in the center of each insert. The influence of slice thickness, exposure and bin width on feature values was investigated. Feature stability was assessed by calculating the concordance correlation coefficient (CCC) in a test-retest setting and for different combinations of scanners, tube currents and slice thicknesses. RESULTS: Bin width influenced feature values, but this only had a marginal effect on the total number of stable features (CCC > 0.85) when comparing different scanners, slice thicknesses or exposures. Most radiomic features were affected by slice thickness, but this effect could be reduced by resampling the CT-images before feature extraction. Statistics feature 'energy' was the most dependent on slice thickness. No clear correlation between feature values and exposures was observed. CONCLUSIONS: CT-scanner, slice thickness and bin width affected radiomic feature values, whereas no effect of exposure was observed. Optimization of gray-level discretization to potentially improve prognostic value can be performed without compromising feature stability. Resampling images prior to feature extraction decreases the variability of radiomic features.
Authors: Mohammadhadi Khorrami; Kaustav Bera; Patrick Leo; Pranjal Vaidya; Pradnya Patil; Rajat Thawani; Priya Velu; Prabhakar Rajiah; Mehdi Alilou; Humberto Choi; Michael D Feldman; Robert C Gilkeson; Philip Linden; Pingfu Fu; Harvey Pass; Vamsidhar Velcheti; Anant Madabhushi Journal: Lung Cancer Date: 2020-02-26 Impact factor: 5.705
Authors: Linda M Pak; Jayasree Chakraborty; Mithat Gonen; William C Chapman; Richard K G Do; Bas Groot Koerkamp; Kees Verhoef; Ser Yee Lee; Marco Massani; Eric P van der Stok; Amber L Simpson Journal: J Am Coll Surg Date: 2018-02-15 Impact factor: 6.113
Authors: Valerio Nardone; Alfonso Reginelli; Cesare Guida; Maria Paola Belfiore; Michelangelo Biondi; Maria Mormile; Fabrizio Banci Buonamici; Eugenio Di Giorgio; Marco Spadafora; Paolo Tini; Roberta Grassi; Luigi Pirtoli; Pierpaolo Correale; Salvatore Cappabianca; Roberto Grassi Journal: Med Oncol Date: 2020-03-31 Impact factor: 3.064