Advertisement

Correction for Systematic Bias in Radiomics Measurements Due to Variation in Imaging Protocols

  • Jocelyn Hoye
    Affiliations
    Carl E. Ravin Advanced Imaging Laboratories, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Medical Physics Graduate Program, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Department of Radiology, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA
    Search for articles by this author
  • Taylor Smith
    Affiliations
    Carl E. Ravin Advanced Imaging Laboratories, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Medical Physics Graduate Program, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Department of Radiology, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA
    Search for articles by this author
  • Ehsan Abadi
    Affiliations
    Carl E. Ravin Advanced Imaging Laboratories, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Department of Radiology, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA
    Search for articles by this author
  • Justin B Solomon
    Affiliations
    Duke University Medical Physics Graduate Program, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke Clinical Imaging Physics Group, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA
    Search for articles by this author
  • Ehsan Samei
    Correspondence
    Address correspondence to: E.S.
    Affiliations
    Carl E. Ravin Advanced Imaging Laboratories, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Medical Physics Graduate Program, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Department of Radiology, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke Clinical Imaging Physics Group, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Department of Physics, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Department of Biomedical Engineering, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA

    Duke University Department of Electrical and Computer Engineering, 2424 Erwin Rd, Suite 302, Durham, North Carolina, 27705, USA
    Search for articles by this author

      Rationale and Objectives

      The accuracy of measured radiomics features is affected by CT imaging protocols. This study aims to ascertain if applying bias corrections can improve the classification performance of the radiomics features.

      Materials and Methods

      A cohort of 144 Non-Small Cell Lung Cancer patient CT images was used to calculate radiomics features for use in predictive models of patient pathological stage. Simulation models of the tumors, matched to patient lesion qualities of size, contrast, and degree of spiculation, were used to both create and assess protocol-specific correction factors. The usefulness of correction was first assessed by applying the corrections to simulated lesion phantoms with known properties using a corrected paired Student's t-test. The sensitivity of radiomics features to correction factors was assessed by applying a library of possible theoretical correction factors to the uncorrected radiomics from the patient data. The data were then used to assess the effect of the correction on prediction performance (AUC) from a logistic regression radiomics model across the patient cases.

      Results

      The correction factors were shown to reduce the bias of radiomics features, caused by protocols, provided that the correction factors were derived from lesion models with similar properties. The sensitivity of the radiomics features to changes due to protocol effects was on average 89% among all features. The corrections applied to patient data resulted in a small increase of 0.0074 in AUC that was not statistically significant (p=0.60).

      Conclusion

      Protocol-specific correction factors can be applied to radiomics studies to control for biases introduced by different imaging protocols. The correction factors should ideally be lesion-specific, derived using lesion models that echo patient lesion characteristics in terms of size, contrast, and degree of spiculation. Small corrections in the 10% range offers only a small improvement in the predictability of radiomics.

      Key Words

      To read this article in full you will need to make a payment

      Purchase one-time access:

      Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online access
      One-time access price info
      • For academic or personal research use, select 'Academic and Personal'
      • For corporate R&D use, select 'Corporate R&D Professionals'

      Subscribe:

      Subscribe to Academic Radiology
      Already a print subscriber? Claim online access
      Already an online subscriber? Sign in
      Institutional Access: Sign in to ScienceDirect

      References

        • Gillies RJ
        • Kinahan PE
        • Hricak H
        Radiomics: images are more than pictures, they are data.
        Radiology. 2015; 278: 563-577
        • Samei E
        • Hoye J
        CT-Based Quantification.
        Computed Tomography. edn. Springer, 2020: 289-304
        • Mackin D
        • Fave X
        • Zhang L
        • Fried D
        • Yang J
        • Taylor B
        • Rodriguez-Rivera E
        • Dodge C
        • Jones AK
        • Court L
        Measuring CT scanner variability of radiomics features.
        Investigative radiology. 2015; 50: 757
        • Foy JJ
        • Armato SG
        • Al-Hallaq HA
        Effects of variability in radiomics software packages on classifying patients with radiation pneumonitis.
        J Med Imaging (Bellingham). 2020; 7: 014504
        • Zhao B
        • Tan Y
        • Tsai WY
        • Schwartz LH
        • Lu L
        Exploring variability in CT characterization of tumors: a preliminary phantom study.
        Translational oncology. 2014; 7: 88-93
        • Zhao B
        • James LP
        • Moskowitz CS
        • Guo P
        • Ginsberg MS
        • Lefkowitz RA
        • Qin Y
        • Riely GJ
        • Kris MG
        • Schwartz LH
        Evaluating Variability in Tumor Measurements from Same-day Repeat CT Scans of Patients with Non–Small Cell Lung Cancer.
        Radiology. 2009; 252: 263-272
        • Hoye J
        • Solomon J
        • Sauer TJ
        • Robins M
        • Samei E
        Systematic analysis of bias and variability of morphologic features for lung lesions in computed tomography.
        JMIOBU. 2019; 6013504
        • Robins M
        • Solomon J
        • Hoye J
        • Abadi E
        • Marin D
        • Samei E
        Systematic analysis of bias and variability of texture measurements in computed tomography.
        JMIOBU. 2019; 6033503
        • Ger RB
        • Zhou S
        • Chi P-CM
        • Lee HJ
        • Layman RR
        • Jones AK
        • Goff DL
        • Fuller CD
        • Howell RM
        • Li H
        • et al.
        Comprehensive Investigation on Controlling for CT Imaging Variabilities in Radiomics Studies.
        Scientific Reports. 2018; 8: 13047
        • Mackin D
        • Fave X
        • Zhang L
        • Yang J
        • Jones AK
        • Ng CS
        • Court LJ
        Comprehensive Investigation on Controlling for CT Imaging Variabilities in Radiomics Studies.
        PLoS One. 2017; 12
        • Orlhac F
        • Frouin F
        • Nioche C
        • Ayache N
        • Buvat I
        Validation of a method to compensate multicenter effects affecting CT Radiomics.
        Radiology. 2019; 182023
        • Bakr S
        • Gevaert O
        • Echegaray S
        • Ayers K
        • Zhou M
        • Shafiq M
        • Zheng H
        • Benson JA
        • Zhang W
        • Leung ANJSd
        A radiogenomic dataset of non-small cell lung cancer.
        Sci Data. 2018; 5: 1-9
        • Solomon J
        • Samei E
        A generic framework to simulate realistic lung, liver and renal pathologies in CT imaging.
        Physics in medicine and biology. 2014; 59: 6637
        • Sisternes L
        • Brankov JG
        • Zysk AM
        • Schmidt RA
        • Nishikawa RM
        • Wernick MN
        A computational model to generate simulated three‐dimensional breast masses.
        Medical physics. 2015; 42: 1098-1118
        • Solomon J
        • Wilson J
        • Samei E
        Characteristic image quality of a third generation dual-source MDCT scanner: Noise, resolution, and detectability.
        Medical Physics. 2015; 42: 4941-4953
        • Solomon J
        • Zhang Y
        • Wilson J
        • Samei E
        An automated software tool for task-based image quality assessment and matching in clinical CT using the TG-233 Framework.
        MEDICAL PHYSICS: 2018: WILEY 111 RIVER ST. HOBOKEN 07030-5774, NJ USA2018 (E134-E134)
        • Boedeker KL
        • Cooper VN
        • McNitt-Gray MF
        Application of the noise power spectrum in modern diagnostic MDCT: part I. Measurement of noise power spectra and noise equivalent quanta.
        Phys Med Biol. 2007; 5: 4027
        • Andersen HK
        • Völgyes D
        • Martinsen ACT
        Image quality with iterative reconstruction techniques in CT of the lungs—A phantom study.
        Eur J Radiol Open. 2018; 5: 35-40
        • Mackin D
        • Ger R
        • Gay S
        • Dodge C
        • Zhang L
        • Yang J
        • Jones AK
        Matching and Homogenizing Convolution Kernels for Quantitative Studies in Computed Tomography.
        Invest Radiol. 2019; 54: 28-295
        • Christianson O
        • Winslow J
        • Frush DP
        • Samei E
        Automated technique to measure noise in clinical CT examinations.
        AJR Am J Roentgenol. 2015; 205: W93-W99
        • Whitaker RT
        A level-set approach to 3D reconstruction from range data.
        International journal of computer vision. 1998; 29: 203-231
        • Hatt M
        • Vallieres M
        • Visvikis D
        • Zwanenburg A
        IBSI: an international community radiomics standardization initiative.
        Journal of Nuclear Medicine. 2018; 59: 287
        • Ines AV
        • Hansen JW
        Bias correction of daily GCM rainfall for crop simulation studies.
        Agricultural and forest meteorology. 2006; 138: 44-53
        • Nadeau C
        • Bengio Y
        Inference for the generalization error.
        Machine learning. 2003; 52: 239-281
        • Whitney HM
        • Giger ML
        Improvement of classification performance using harmonization across field strength of radiomic features extracted from DCE-MR images of the breast.
        Medical Imaging 2020: Computer-Aided Diagnosis: 2020. International Society for Optics and Photonics, 2020113140X
        • Abadi E
        • Harrawood B
        • Sharma S
        • Kapadia A
        • Segars WP
        • Samei E
        DukeSim: A realistic, rapid, and scanner-specific simulation framework in computed tomography.
        IEEE transactions on medical imaging. 2018;