Effects of Interobserver Variability on 2D and 3D CT- and MRI-Based Texture Feature Reproducibility of Cartilaginous Bone Tumors

This study aims to investigate the influence of interobserver manual segmentation variability on the reproducibility of 2D and 3D unenhanced computed tomography (CT)- and magnetic resonance imaging (MRI)-based texture analysis. Thirty patients with cartilaginous bone tumors (10 enchondromas, 10 atypical cartilaginous tumors, 10 chondrosarcomas) were retrospectively included. Three radiologists independently performed manual contour-focused segmentation on unenhanced CT and T1-weighted and T2-weighted MRI by drawing both a 2D region of interest (ROI) on the slice showing the largest tumor area and a 3D ROI including the whole tumor volume. Additionally, a marginal erosion was applied to both 2D and 3D segmentations to evaluate the influence of segmentation margins. A total of 783 and 1132 features were extracted from original and filtered 2D and 3D images, respectively. Intraclass correlation coefficient ≥ 0.75 defined feature stability. In 2D vs. 3D contour-focused segmentation, the rates of stable features were 74.71% vs. 86.57% (p < 0.001), 77.14% vs. 80.04% (p = 0.142), and 95.66% vs. 94.97% (p = 0.554) for CT and T1-weighted and T2-weighted images, respectively. Margin shrinkage did not improve 2D (p = 0.343) and performed worse than 3D (p < 0.001) contour-focused segmentation in terms of feature stability. In 2D vs. 3D contour-focused segmentation, matching stable features derived from CT and MRI were 65.8% vs. 68.7% (p = 0.191), and those derived from T1-weighted and T2-weighted images were 76.0% vs. 78.2% (p = 0.285). 2D and 3D radiomic features of cartilaginous bone tumors extracted from unenhanced CT and MRI are reproducible, although some degree of interobserver segmentation variability highlights the need for reliability analysis in future studies.

[1]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[2]  M. Beer,et al.  Diagnostic value of MRI-based 3D texture analysis for tissue characterisation and discrimination of low-grade chondrosarcoma from enchondroma: a pilot study , 2018, European Radiology.

[3]  E. S. Durmaz,et al.  Influence of segmentation margin on machine learning–based high-dimensional quantitative CT texture analysis: a reproducibility study on renal clear cell carcinomas , 2019, European Radiology.

[4]  K. Verstraete,et al.  Dynamic contrast-enhanced MR imaging for differentiation between enchondroma and chondrosarcoma , 2013, European Radiology.

[5]  J. Bloem,et al.  Cartilaginous tumors: fast contrast-enhanced MR imaging. , 2000, Radiology.

[6]  Ron Kikinis,et al.  Repeatability of Multiparametric Prostate MRI Radiomics Features , 2018, Scientific Reports.

[7]  Thomas Frauenfelder,et al.  Influence of inter-observer delineation variability on radiomics stability in different tumor sites , 2018, Acta oncologica.

[8]  Valentina D. A. Corino,et al.  Assessment of Stability and Discrimination Capacity of Radiomic Features on Apparent Diffusion Coefficient Images , 2018, Journal of Digital Imaging.

[9]  Hye Jin Yoo,et al.  Differentiating high-grade from low-grade chondrosarcoma with MR imaging , 2009, European Radiology.

[10]  Perry J Pickhardt,et al.  CT Texture Analysis: Definitions, Applications, Biologic Correlates, and Challenges. , 2017, Radiographics : a review publication of the Radiological Society of North America, Inc.

[11]  Terry K Koo,et al.  A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research. , 2016, Journal Chiropractic Medicine.

[12]  E. S. Durmaz,et al.  Reliability of Single-Slice-Based 2D CT Texture Analysis of Renal Masses: Influence of Intra- and Interobserver Manual Segmentation Variability on Radiomic Feature Reproducibility. , 2019, AJR. American journal of roentgenology.

[13]  Guido Gerig,et al.  User-guided 3D active contour segmentation of anatomical structures: Significantly improved efficiency and reliability , 2006, NeuroImage.

[14]  N. Mao,et al.  Can clinical radiomics nomogram based on 3D multiparametric MRI features and clinical characteristics estimate early recurrence of pelvic chondrosarcoma? , 2020, Journal of magnetic resonance imaging : JMRI.

[15]  R. Steenbakkers,et al.  The Image Biomarker Standardization Initiative: Standardized Quantitative Radiomics for High-Throughput Image-based Phenotyping. , 2020, Radiology.

[16]  Francesco Sardanelli,et al.  Statistical significance: p value, 0.05 threshold, and applications to radiomics—reasons for a conservative approach , 2020, European Radiology Experimental.

[17]  Robin L. Jones,et al.  Bone sarcomas: ESMO-PaedCan-EURACAN Clinical Practice Guidelines for diagnosis, treatment and follow-up. , 2018, Annals of oncology : official journal of the European Society for Medical Oncology.

[18]  Yusong Lin,et al.  Radiomic analysis of multiparametric magnetic resonance imaging for differentiating skull base chordoma and chondrosarcoma. , 2019, European journal of radiology.

[19]  Andriy Fedorov,et al.  Computational Radiomics System to Decode the Radiographic Phenotype. , 2017, Cancer research.

[20]  R. Cuocolo,et al.  CT and MRI radiomics of bone and soft-tissue sarcomas: a systematic review of reproducibility and validation strategies , 2021, Insights into Imaging.

[21]  J. Mongan,et al.  Checklist for Artificial Intelligence in Medical Imaging (CLAIM): A Guide for Authors and Reviewers. , 2020, Radiology. Artificial intelligence.

[22]  E. S. Durmaz,et al.  Radiomics of Renal Masses: Systematic Review of Reproducibility and Validation Strategies. , 2019, AJR. American journal of roentgenology.

[23]  Lorenzo Ugga,et al.  Machine Learning in Oncology: A Clinical Appraisal. , 2020, Cancer letters.

[24]  C. Laux,et al.  The impact of biopsy sampling errors and the quality of surgical margins on local recurrence and survival in chondrosarcoma , 2018, Cancer management and research.

[25]  Gaël Varoquaux,et al.  The NumPy Array: A Structure for Efficient Numerical Computation , 2011, Computing in Science & Engineering.

[26]  L. Sconfienza,et al.  Accuracy of CT and MRI to assess resection margins in primary malignant bone tumours having histology as the reference standard. , 2019, Clinical radiology.

[27]  J. Bloem,et al.  Radiologic differentiation of enchondromas, atypical cartilaginous tumors, and high‐grade chondrosarcomas—Improving tumor‐specific treatment: A paradigm in transit? , 2019, Cancer.

[28]  Mark W. Woolrich,et al.  FSL , 2012, NeuroImage.

[29]  A. Wilson,et al.  From the archives of the AFIP: imaging of primary chondrosarcoma: radiologic-pathologic correlation. , 2003, Radiographics : a review publication of the Radiological Society of North America, Inc.

[30]  R. Cuocolo,et al.  CT radiomics-based machine learning classification of atypical cartilaginous tumours and appendicular chondrosarcomas , 2021, Seminars in Musculoskeletal Radiology.

[31]  R Core Team,et al.  R: A language and environment for statistical computing. , 2014 .

[32]  L. Cavallo,et al.  Prediction of high proliferative index in pituitary macroadenomas using MRI-based radiomics and machine learning , 2019, Neuroradiology.

[33]  Bal Sanghera,et al.  Assessment of tumor heterogeneity: an emerging imaging tool for clinical practice? , 2012, Insights into Imaging.

[34]  A. Brunetti,et al.  MRI radiomics-based machine-learning classification of bone chondrosarcoma. , 2020, European journal of radiology.

[35]  C. V. van Kuijk,et al.  Impact of artificial intelligence on radiology: a EuroAIM survey among members of the European Society of Radiology , 2019, Insights into Imaging.

[36]  L. Sconfienza,et al.  Differential Diagnosis of Spine Tumors: My Favorite Mistake , 2019, Seminars in Musculoskeletal Radiology.

[37]  H. Douis,et al.  MRI differentiation of low-grade from high-grade appendicular chondrosarcoma , 2013, European Radiology.

[38]  Saskia Le Cessie,et al.  Assessment of Interobserver Variability and Histologic Parameters to Improve Reliability in Classification and Grading of Central Cartilaginous Tumors , 2009, The American journal of surgical pathology.

[39]  Christopher J. Hanrahan,et al.  Can imaging criteria distinguish enchondroma from grade 1 chondrosarcoma? , 2015, European journal of radiology.

[40]  J. Canales‐Vázquez,et al.  Radiomics of CT Features May Be Nonreproducible and Redundant: Influence of CT Acquisition Parameters. , 2018, Radiology.