Shape and texture-based radiomics signature on CT effectively discriminates benign from malignant renal masses.

Autor: Yap FY; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Varghese BA; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA. bino.varghese@med.usc.edu., Cen SY; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Hwang DH; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Lei X; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Desai B; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Lau C; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Yang LL; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Fullenkamp AJ; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Hajian S; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Rivas M; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Gupta MN; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Quinn BD; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA., Aron M; Department of Pathology, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA., Desai MM; Institute of Urology and the Catherine & Joseph Aresty, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA., Aron M; Institute of Urology and the Catherine & Joseph Aresty, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA., Oberai AA; Department of Aerospace and Mechanical Engineering, Viterbi School of Engineering, University of Southern California, Los Angeles, CA, USA., Gill IS; Institute of Urology and the Catherine & Joseph Aresty, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA., Duddalwar VA; Department of Radiology, Keck School of Medicine, University of Southern California, 1441 Eastlake Ave, Los Angeles, CA, 90033, USA.; Institute of Urology and the Catherine & Joseph Aresty, Keck School of Medicine, University of Southern California, Los Angeles, CA, USA.
Jazyk: angličtina
Zdroj: European radiology [Eur Radiol] 2021 Feb; Vol. 31 (2), pp. 1011-1021. Date of Electronic Publication: 2020 Aug 15.
DOI: 10.1007/s00330-020-07158-0
Abstrakt: Objectives: Using a radiomics framework to quantitatively analyze tumor shape and texture features in three dimensions, we tested its ability to objectively and robustly distinguish between benign and malignant renal masses. We assessed the relative contributions of shape and texture metrics separately and together in the prediction model.
Materials and Methods: Computed tomography (CT) images of 735 patients with 539 malignant and 196 benign masses were segmented in this retrospective study. Thirty-three shape and 760 texture metrics were calculated per tumor. Tumor classification models using shape, texture, and both metrics were built using random forest and AdaBoost with tenfold cross-validation. Sensitivity analyses on five sub-cohorts with respect to the acquisition phase were conducted. Additional sensitivity analyses after multiple imputation were also conducted. Model performance was assessed using AUC.
Results: Random forest classifier showed shape metrics featuring within the top 10% performing metrics regardless of phase, attaining the highest variable importance in the corticomedullary phase. Convex hull perimeter ratio is a consistently high-performing shape feature. Shape metrics alone achieved an AUC ranging 0.64-0.68 across multiple classifiers, compared with 0.67-0.75 and 0.68-0.75 achieved by texture-only and combined models, respectively.
Conclusion: Shape metrics alone attain high prediction performance and high variable importance in the combined model, while being independent of the acquisition phase (unlike texture). Shape analysis therefore should not be overlooked in its potential to distinguish benign from malignant tumors, and future radiomics platforms powered by machine learning should harness both shape and texture metrics.
Key Points: • Current radiomics research is heavily weighted towards texture analysis, but quantitative shape metrics should not be ignored in their potential to distinguish benign from malignant renal tumors. • Shape metrics alone can attain high prediction performance and demonstrate high variable importance in the combined shape and texture radiomics model. • Any future radiomics platform powered by machine learning should harness both shape and texture metrics, especially since tumor shape (unlike texture) is independent of the acquisition phase and more robust from the imaging variations.
Databáze: MEDLINE
Externí odkaz: