Ankur M Doshi1, Angela Tong1, Matthew S Davenport2, Ahmed Khalaf3, Rafah Mresh3, Henry Rusinek1, Nicola Schieda4, Atul Shinagare5, Andrew D Smith3, Rebecca Thornhill4, Raghunandan Vikram6, Hersh Chandarana1. 1. NYU Langone Health, Department of Radiology, 660 First Ave, New York, NY 10016. 2. Department of Radiology, University of Michigan Health Systems, 1500 E Medical Center Dr, Ann Arbor, MI 48109. 3. Department of Radiology, University of Alabama at Birmingham, 619 19th St S, JTN 452, Birmingham, AL 35249-6830. 4. Department of Medical Imaging, The Ottawa Hospital, The University of Ottawa, 1053 Carling Ave, Ottawa, ON K1Y 4E9, Canada. 5. Department of Radiology, Brigham and Women's Hospital, Harvard Medical School, 75 Francis St, Boston, MA 02115. 6. Department of Diagnostic Radiology, The University of Texas M. D. Anderson Cancer Center, 1515 Holcombe Blvd., Unit 1350, Houston, TX 77030-4009.
Abstract
Background: Multiple commercial and open-source software applications are available for texture analysis. Nonstandard techniques can cause undesirable variability that impedes result reproducibility and limits clinical utility. Objective: The purpose of this study is to measure agreement of texture metrics extracted by 6 software packages. Methods: This retrospective study included 40 renal cell carcinomas with contrast-enhanced CT from The Cancer Genome Atlas and Imaging Archive. Images were analyzed by 7 readers at 6 sites. Each reader used 1 of 6 software packages to extract commonly studied texture features. Inter and intra-reader agreement for segmentation was assessed with intra-class correlation coefficients. First-order (available in 6 packages) and second-order (available in 3 packages) texture features were compared between software pairs using Pearson correlation. Results: Inter- and intra-reader agreement was excellent (ICC 0.93-1). First-order feature correlations were strong (r>0.8, p<0.001) between 75% (21/28) of software pairs for mean and standard deviation, 48% (10/21) for entropy, 29% (8/28) for skewness, and 25% (7/28) for kurtosis. Of 15 second-order features, only co-occurrence matrix correlation, grey-level non-uniformity, and run-length non-uniformity showed strong correlation between software packages (0.90-1, p<0.001). Conclusion: Variability in first and second order texture features was common across software configurations and produced inconsistent results. Standardized algorithms and reporting methods are needed before texture data can be reliably used for clinical applications. Clinical Impact: It is important to be aware of variability related to texture software processing and configuration when reporting and comparing outputs.
Background: Multiple commercial and open-source software applications are available for texture analysis. Nonstandard techniques can cause undesirable variability that impedes result reproducibility and limits clinical utility. Objective: The purpose of this study is to measure agreement of texture metrics extracted by 6 software packages. Methods: This retrospective study included 40 renal cell carcinomas with contrast-enhanced CT from The Cancer Genome Atlas and Imaging Archive. Images were analyzed by 7 readers at 6 sites. Each reader used 1 of 6 software packages to extract commonly studied texture features. Inter and intra-reader agreement for segmentation was assessed with intra-class correlation coefficients. First-order (available in 6 packages) and second-order (available in 3 packages) texture features were compared between software pairs using Pearson correlation. Results: Inter- and intra-reader agreement was excellent (ICC 0.93-1). First-order feature correlations were strong (r>0.8, p<0.001) between 75% (21/28) of software pairs for mean and standard deviation, 48% (10/21) for entropy, 29% (8/28) for skewness, and 25% (7/28) for kurtosis. Of 15 second-order features, only co-occurrence matrix correlation, grey-level non-uniformity, and run-length non-uniformity showed strong correlation between software packages (0.90-1, p<0.001). Conclusion: Variability in first and second order texture features was common across software configurations and produced inconsistent results. Standardized algorithms and reporting methods are needed before texture data can be reliably used for clinical applications. Clinical Impact: It is important to be aware of variability related to texture software processing and configuration when reporting and comparing outputs.
Authors: Lu-Ping Li; Alexander S Leidner; Emily Wilt; Artem Mikheev; Henry Rusinek; Stuart M Sprague; Orly F Kohn; Anand Srivastava; Pottumarthi V Prasad Journal: J Clin Med Date: 2022-04-01 Impact factor: 4.241
Authors: Peter Raab; Rouzbeh Banan; Arash Akbarian; Majid Esmaeilzadeh; Madjid Samii; Amir Samii; Helmut Bertalanffy; Ulrich Lehmann; Joachim K Krauss; Heinrich Lanfermann; Christian Hartmann; Roland Brüning Journal: Cancers (Basel) Date: 2022-03-09 Impact factor: 6.639