MENU

Click here to

×

Are you sure ?

Yes, do it No, cancel

Standardization in Quantitative Imaging: A Comparison of Radiomics Feature Values Obtained by Different Software Packages On a Set of Digital Reference Objects

M McNitt-Gray1*, S Napel2 , J Kalpathy-Cramer3 , A Jaggi2 , D Cherezov4 , D Goldgof4 , H Yang5 , E Jones6 , M Muzi7 , N Emaminejad1 , M Wahi-Anwar1 , Y Balagurunathan8 , M Abdalah8 , B Zhao5 , L Hadjiiski9 , L Pierce7 , K Farahani10 , (1) David Geffen School of Medicine at UCLA, Los Angeles, CA, (2) Stanford Univ School of Medicine, Stanford, CA, (3) Massachusetts General Hospital, Boston, MA, (4) University of South Florida, Tampa, FL, (5) Columbia University, New York, NY, (6) UCSF, San Francisco, CA, (7) University of Washington, Seattle, WA (8) Moffitt Cancer Center, Tampa, FL, (9) University of Michigan, Ann Arbor, MI, (10) National Cancer Institute, Bethesda, MD

Presentations

(Tuesday, 7/16/2019) 4:30 PM - 6:00 PM

Room: 304ABC

Purpose: Many groups are developing predictive models based on radiomics features. The purpose of this work was to investigate the agreement and variations in these features as computed by several software packages using standardized quantitative imaging feature definitions and common image datasets.

Methods: Seven sites from the NCI’s Quantitative Imaging Network PET-CT working group participated in this project. First, nine commonly used quantitative imaging features were selected for comparison and included features that describe morphology, intensity, shape and texture. A standard lexicon developed by the International Biomarker Standardisation Initiative (IBSI) was adopted as the feature definition reference. Each site described their software package’s implementation for each feature, based on the lexicon. Three 3D Digital Reference Objects (DROs) were developed specifically for this effort: a uniform sphere, a sphere with intensity variations, and a complex shape object with uniform intensity. To eliminate variation in radiomics features caused by segmentation differences, each DRO was accompanied by a Volume of Interest (VOI), from which the features were calculated. Each participating site reported the computed feature values for each DRO. The percent coefficient of variation (CV) was calculated across software packages for each feature on each phantom.

Results: Eight sets of results were submitted. Six of the nine features demonstrated excellent agreement across submissions with CV < 1%, including: Approximate Volume, 2D diameter, 3D diameter, Mean Intensity, Standard Deviation and Kurtosis (with Fisher adjustment). Larger variations (CV 15% and higher) were observed for Surface Area, Sphericity and GLCM Entropy Texture features, which are being investigated further.

Conclusion: By computing a subset of nine common radiomics features using a variety of software packages on DROs, we have shown that while several features agree strongly, others do not. This highlights the need for standardization in feature definitions and proof of equivalence of computational methods.

Funding Support, Disclosures, and Conflict of Interest: Supported by the National Cancer Institute's Quantitative Imaging Network (QIN) through the following grants: U01CA181156; U01CA187947; U01CA154601; U01CA143062; U01CA225427; U01CA225431; U01CA148131; U01CA179106

Keywords

Quantitative Imaging, Image Analysis, Computer Vision

Taxonomy

IM- CT: Quantitative imaging/analysis

Contact Email