E Forde1, M Leech2, C Robert3, E Herron4, L Marignol2. 1. Applied Radiation Therapy Trinity, Discipline of Radiation Therapy, Trinity St James' Cancer Institute, Trinity College Dublin, Dublin, Ireland. Electronic address: eforde@tcd.ie. 2. Applied Radiation Therapy Trinity, Discipline of Radiation Therapy, Trinity St James' Cancer Institute, Trinity College Dublin, Dublin, Ireland. 3. Molecular Radiotherapy and Innovative Therapeutics, INSERM UMR1030, Gustave Roussy Cancer Campus, Université Paris Salcay, Villejuif, France. 4. Department of Psychiatry School of Medicine, Trinity College Dublin, Dublin, Ireland.
Abstract
PURPOSE: This study aimed to quantify the variability in the values of radiomic features extracted from a right parotid gland (RPG) delineated by a series of independent observers. METHODS: This was a secondary analysis of anonymous data from a delineation workshop. Inter-observer variability of the RPG from 40 participants was quantified using DICE similarity coefficient (DSC) and Hausdorff distance (HD). An additional contour was generated using Varian SmartSegmentation. Radiomic features extracted include four shape features, six histogram features, and 32 texture features. The absolute mean paired percentage difference (PPD) in feature values from the expert and participants were ranked . Feature robustness was classified using pre- determined thresholds. RESULTS: 63% of participants achieved a DSC > 0.7, the auto- segmentation DSC was 0.76. The average HD for the participants was 16.16 mm ± 0.66 mm, and 15.16 mm for the auto-segmentation. 48% (n = 20) and 33% (n = 14) of features were deemed to be robust with a mean absolute PPD < 5%, for the auto-segmentation and manual delineations respectively; the majority of which were from the grey-run length matrix family. 7% (n = 3) of features from the auto- segmentation and 10% (n = 4) from the manual contours were deemed to be unstable with a mean absolute PPD > 50%. The value of the most robust feature was not related to DSC and HD. CONCLUSION: Inter-observer delineation variability affects the value of the radiomic features extracted from the RPG. This study identifies the radiomic features least sensitive to these uncertainties. Further investigation of the clinical relevance of these features in prediction of xerostomia is warranted.
PURPOSE: This study aimed to quantify the variability in the values of radiomic features extracted from a right parotid gland (RPG) delineated by a series of independent observers. METHODS: This was a secondary analysis of anonymous data from a delineation workshop. Inter-observer variability of the RPG from 40 participants was quantified using DICE similarity coefficient (DSC) and Hausdorff distance (HD). An additional contour was generated using Varian SmartSegmentation. Radiomic features extracted include four shape features, six histogram features, and 32 texture features. The absolute mean paired percentage difference (PPD) in feature values from the expert and participants were ranked . Feature robustness was classified using pre- determined thresholds. RESULTS: 63% of participants achieved a DSC > 0.7, the auto- segmentation DSC was 0.76. The average HD for the participants was 16.16 mm ± 0.66 mm, and 15.16 mm for the auto-segmentation. 48% (n = 20) and 33% (n = 14) of features were deemed to be robust with a mean absolute PPD < 5%, for the auto-segmentation and manual delineations respectively; the majority of which were from the grey-run length matrix family. 7% (n = 3) of features from the auto- segmentation and 10% (n = 4) from the manual contours were deemed to be unstable with a mean absolute PPD > 50%. The value of the most robust feature was not related to DSC and HD. CONCLUSION: Inter-observer delineation variability affects the value of the radiomic features extracted from the RPG. This study identifies the radiomic features least sensitive to these uncertainties. Further investigation of the clinical relevance of these features in prediction of xerostomia is warranted.
Authors: Ryder M Schmidt; Rodrigo Delgadillo; John C Ford; Kyle R Padgett; Matthew Studenski; Matthew C Abramowitz; Benjamin Spieler; Yihang Xu; Fei Yang; Nesrin Dogan Journal: Sci Rep Date: 2021-11-23 Impact factor: 4.379