The impact of image reconstruction settings on 18F-FDG PET radiomic features: multi-scanner phantom and patient studies
- 1.2k Downloads
The purpose of this study was to investigate the robustness of different PET/CT image radiomic features over a wide range of different reconstruction settings.
Phantom and patient studies were conducted, including two PET/CT scanners. Different reconstruction algorithms and parameters including number of sub-iterations, number of subsets, full width at half maximum (FWHM) of Gaussian filter, scan time per bed position and matrix size were studied. Lesions were delineated and one hundred radiomic features were extracted. All radiomics features were categorized based on coefficient of variation (COV).
Forty seven percent features showed COV ≤ 5% and 10% of which showed COV > 20%. All geometry based, 44% and 41% of intensity based and texture based features were found as robust respectively. In regard to matrix size, 56% and 6% of all features were found non-robust (COV > 20%) and robust (COV ≤ 5%) respectively.
Variability and robustness of PET/CT image radiomics in advanced reconstruction settings is feature-dependent, and different settings have different effects on different features. Radiomic features with low COV can be considered as good candidates for reproducible tumour quantification in multi-center studies.
• PET/CT image radiomics is a quantitative approach assessing different aspects of tumour uptake.
• Radiomic features robustness is an important issue over different image reconstruction settings.
• Variability and robustness of PET/CT image radiomics in advanced reconstruction settings is feature-dependent.
• Robust radiomic features can be considered as good candidates for tumour quantification
KeywordsPET/CT Radiomics Robustness Reconstruction settings Quantification
Positron Emission Tomography
Standard Uptake Value
Non-Small Cell Lung Carcinoma
Magnetic Resonance Imaging
National Electrical Manufacturers Association
Lesions to Background Ratio
Ordered Subset Expectation Maximization
Point Spread Function
Time of Flight
Full Width at Half Maximum
Volume of Interest
Gray Level Co-occurrence Matrix
Gray-Level Run-Length Matrix
Gray-Level Size Zone Matrix
Neighboring Gray Level Dependence
Neighborhood Gray-Tone Difference Matrix
Texture Feature Coding
Coefficient Of Variation
Filtered Back Projection
Response Evaluation Criteria in Solid Tumours
PET Response Criteria in Solid Tumours
The authors sincerely thank the PET/CT Departments at Masih Daneshvari and Shariati Hospitals for their collaboration and facilities.
Compliance with ethical standards
The scientific guarantor of this publication is Hamid Abdollahi, BS, MS, PhD.
Conflict of interest
The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.
This study has received funding by the Iran University of Medical Sciences, Tehran, Iran with the grant number 27870.
Statistics and biometry
All authors kindly provided statistical advice for this manuscript.
One of the authors has significant statistical expertise.
Institutional Review Board approval was obtained.
Written informed consent was obtained from all subjects (patients) in this study.
• diagnostic or prognostic study/experimental
• multicenter study
- 1.Wahl RL (2008) Principles and practice of PET and PET/CT. Lippincott Williams & Wilkins, PhiladelphiaGoogle Scholar
- 2.Rahmim A, Wahl R (2006) An overview of clinical PET/CT. Iran J Nucl Med 14:1–14Google Scholar
- 3.Hatt M, Majdoub M, Vallieres M, Tixier F, Le Rest CC, Groheux D et al (2015) F-18-FDG PET uptake characterization through texture analysis: investigating the complementary nature of heterogeneity and functional tumor volume in a multi-cancer site patient cohort. J Nucl Med 56:38–44CrossRefPubMedGoogle Scholar
- 4.Tixier F, Le Rest CC, Hatt M, Albarghach N, Pradier O, Metges JP et al (2011) Intratumor heterogeneity characterized by textural features on baseline (18)F-FDG pet images predicts response to concomitant radiochemotherapy in esophageal cancer. J Nucl Med 52:369–378CrossRefPubMedPubMedCentralGoogle Scholar
- 10.Oh J, Apte A, Folkerts M, Kohutek Z, Wu A, Rimmer A, Lee N, Deasy J. (2014) FDG-PET-based radiomics to predict local control and survival following radiotherapy. Annual Meeting of The American Association of Physicists in Medicine 2014Google Scholar
- 12.Soufi M, Kamali-Asl A, Geramifar P, Rahmim A (2016) A novel framework for automated segmentation and labeling of homogeneous versus heterogeneous lung tumors in [18F]FDG PET imaging. Molec Imag Biol. In Press. doi: 10.1007/s11307-016-1015-0
- 17.Rahmim A, Salimpour Y, Jain S, Blinder S, Klyuzhin IS, Smith G, et al. (2016) Application of texture analysis to DAT SPECT imaging: relationship to clinical assesments. NeuroImage: Clin 12. doi: 10.1016/j.nicl.2016.02.012
- 21.Ashrafinia S, Gonzalez EM, Mohy-ud-Din H, Jha A, Subramaniam RM, Rahmim A (2016) Adaptive PSF modeling for enhanced heterogeneity quantification in oncologic PET imaging. Proc Soc Nuc Med Med Imag Ann Meet 57:497Google Scholar
- 22.Shiri IRA, Abdollahi H, Ghafarian P, Bitarafan-Rajabi A, AY MR, BakhshaieshKaram M, (Suppl 1) (2016) Radiomics texture features variability and reproducibility in advance image reconstruction setting of oncological PET/CT. Eur J Nucl Med Mol Imaging 43:S1-S734Google Scholar