Identification of CT radiomic features robust to acquisition and segmentation variations for improved prediction of radiotherapy-treated lung cancer patient recurrence.
[en] The primary objective of the present study was to identify a subset of radiomic features extracted from primary tumor imaged by computed tomography of early-stage non-small cell lung cancer patients, which remain unaffected by variations in segmentation quality and in computed tomography image acquisition protocol. The robustness of these features to segmentation variations was assessed by analyzing the correlation of feature values extracted from lesion volumes delineated by two annotators. The robustness to variations in acquisition protocol was evaluated by examining the correlation of features extracted from high-dose and low-dose computed tomography scans, both of which were acquired for each patient as part of the stereotactic body radiotherapy planning process. Among 106 radiomic features considered, 21 were identified as robust. An analysis including univariate and multivariate assessments was subsequently conducted to estimate the predictive performance of these robust features on the outcome of early-stage non-small cell lung cancer patients treated with stereotactic body radiation therapy. The univariate predictive analysis revealed that robust features demonstrated superior predictive potential compared to non-robust features. The multivariate analysis indicated that linear regression models built with robust features displayed greater generalization capabilities by outperforming other models in predicting the outcomes of an external validation dataset.
Disciplines :
Radiology, nuclear medicine & imaging
Author, co-author :
LOUIS, Thomas ; Centre Hospitalier Universitaire de Liège - CHU > > Service médical de médecine nucléaire et imagerie onco
Lucia, François; Division of Nuclear Medicine and Oncological Imaging, University Hospital of Liège, Liège, Belgium. francois.lucia@chu-brest.fr ; Radiation Oncology Department, University Hospital of Brest, Brest, France. francois.lucia@chu-brest.fr ; LaTIM, INSERM, UMR 1101, University of Brest, Brest, France. francois.lucia@chu-brest.fr
Cousin, François ; Université de Liège - ULiège > Département des sciences cliniques
MIEVIS, Carole ; Centre Hospitalier Universitaire de Liège - CHU > > Service médical de radiothérapie
Jansen, Nicolas ; Université de Liège - ULiège > Département des sciences cliniques
Duysinx, Bernard ; Université de Liège - ULiège > Département des sciences cliniques
Le Pennec, Romain; Nuclear Medicine Department, University Hospital of Brest, Brest, France ; GETBO INSERM UMR 1304, University of Brest, UBO, Brest, France
Visvikis, Dimitris; LaTIM, INSERM, UMR 1101, University of Brest, Brest, France
Nebbache, Malik; Radiation Oncology Department, University Hospital of Brest, Brest, France
Rehn, Martin; Radiation Oncology Department, University Hospital of Brest, Brest, France
Hamya, Mohamed; Radiation Oncology Department, University Hospital of Brest, Brest, France
Geier, Margaux; Medical Oncology Department, University Hospital of Brest, Brest, France
Salaun, Pierre-Yves; Nuclear Medicine Department, University Hospital of Brest, Brest, France ; GETBO INSERM UMR 1304, University of Brest, UBO, Brest, France
Schick, Ulrike; Radiation Oncology Department, University Hospital of Brest, Brest, France ; LaTIM, INSERM, UMR 1101, University of Brest, Brest, France
Hatt, Mathieu; LaTIM, INSERM, UMR 1101, University of Brest, Brest, France
Coucke, Philippe ; Université de Liège - ULiège > Département des sciences cliniques > Radiothérapie
Lovinfosse, Pierre ; Université de Liège - ULiège > Département de pharmacie
Hustinx, Roland ; Université de Liège - ULiège > Département des sciences cliniques > Médecine nucléaire
Identification of CT radiomic features robust to acquisition and segmentation variations for improved prediction of radiotherapy-treated lung cancer patient recurrence.
P.E. Postmus et al. Early and locally advanced non-small-cell lung cancer (NSCLC): ESMO Clinical Practice Guidelines for diagnosis, treatment and follow-up Ann. Oncol. 2017 28 1 21 10.1093/ANNONC/MDX222
R. Timmerman et al. Stereotactic body radiation therapy for inoperable early stage lung cancer JAMA 2010 303 11 1070 1076 1:CAS:528:DC%2BC3cXjsF2qs7Y%3D 10.1001/JAMA.2010.261 20233825 2907644
A.T. Davis A.L. Palmer A. Nisbet Can CT scan protocols used for radiotherapy treatment planning be adjusted to optimize image quality and patient dose? A systematic review Br. J. Radiol. 2017 90 1076 10.1259/BJR.20160406
S.C. Vaz et al. Joint EANM/SNMMI/ESTRO practice recommendations for the use of 2-[18F]FDG PET/CT external beam radiation treatment planning in lung cancer V1.0 Eur. J. Nucl. Med. Mol. Imaging 2022 49 4 1386 1406 10.1007/S00259-021-05624-5 35022844 8921015
E. Gkika A.L. Grosu U. Nestle The use of 18F-FDG PET/CT for radiotherapy treatment planning in non-small cell lung cancer: A mini-review Precis. Cancer Med. 2023 6 1 10.21037/PCM-22-38/COIF
P. Lambin et al. Radiomics: Extracting more information from medical images using advanced feature analysis Eur. J. Cancer 2012 48 4 441 446 10.1016/J.EJCA.2011.11.036 22257792 4533986
W. Mu et al. Non-invasive decision support for NSCLC treatment using PET/CT radiomics Nat. Commun. 2020 11 1 1 11 2020NatCo.11..1O 1:CAS:528:DC%2BB3cXitFCksL7L 10.1038/s41467-020-19116-x
M. Sollini L. Cozzi L. Antunovic A. Chiti M. Kirienko PET Radiomics in NSCLC: State of the art and a proposal for harmonization of methodology Sci. Rep. 2017 7 1 1 15 1:CAS:528:DC%2BC1cXhs12msrnL 10.1038/s41598-017-00426-y
A.N. Frix et al. Radiomics in lung diseases imaging: State-of-the-art for clinicians J. Pers. Med. 2021 11 7 602 10.3390/JPM11070602 34202096 8306026
P. Lovinfosse et al. FDG PET/CT texture analysis for predicting the outcome of lung cancer treated by stereotactic body radiation therapy Eur. J. Nucl. Med. Mol. Imaging 2016 43 8 1453 1460 1:CAS:528:DC%2BC28XitlOksLY%3D 10.1007/S00259-016-3314-8/FIGURES/2 26830299
J.E. Park S.Y. Park H.J. Kim H.S. Kim Reproducibility and generalizability in radiomics modeling: Possible strategies in radiologic and statistical perspectives Korean J. Radiol. 2019 20 7 1124 10.3348/KJR.2018.0070 31270976 6609433
E.J. Limkin et al. Promises and challenges for the implementation of computational medical imaging (radiomics) in oncology Ann. Oncol. 2017 28 6 1191 1206 1:STN:280:DC%2BC1c3jvVWlsw%3D%3D 10.1093/ANNONC/MDX034 28168275
S.H. Lee H.H. Cho H.Y. Lee H. Park Clinical impact of variability on CT radiomics and suggestions for suitable feature selection: A focus on lung cancer Cancer Imaging 2019 19 1 1 12 10.1186/S40644-019-0239-Z/TABLES/5
D. Mackin et al. Measuring CT scanner variability of radiomics features HHS Public Access Invest. Radiol. 2015 50 11 757 765 10.1097/RLI.0000000000000180 26115366 4598251
W.E. Johnson C. Li A. Rabinovic Adjusting batch effects in microarray expression data using empirical Bayes methods Biostatistics 2007 8 1 118 127 10.1093/BIOSTATISTICS/KXJ037 16632515
H. Horng et al. Generalized ComBat harmonization methods for radiomic features with multi-modal distributions and multiple batch effects Sci. Rep. 2022 12 1 1 12 2022NatSR.12..2H 1:CAS:528:DC%2BB38Xnt1ymsbc%3D 10.1038/s41598-022-08412-9
F. Orlhac et al. A guide to ComBat harmonization of imaging biomarkers in multicenter studies J. Nucl. Med. 2022 63 2 172 179 10.2967/JNUMED.121.262464 34531263 8805779
A. Zwanenburg et al. The image biomarker standardization initiative: Standardized quantitative radiomics for high-throughput image-based phenotyping Radiology 2020 295 2 328 10.1148/RADIOL.2020191145 32154773
M. Hatt et al. Joint EANM/SNMMI guideline on radiomics in nuclear medicine Eur. J. Nucl. Med. Mol. Imaging 2022 50 2 352 375 10.1007/S00259-022-06001-6 36326868 9816255
J. Zhong et al. Robustness of radiomics features of virtual unenhanced and virtual monoenergetic images in dual-energy CT among different imaging platforms and potential role of CT number variability Insights Imaging 2023 14 1 1 13 10.1186/S13244-023-01426-5/TABLES/4
Y. Chen et al. Robustness of CT radiomics features: Consistency within and between single-energy CT and dual-energy CT Eur. Radiol. 2022 32 8 5480 5490 1:CAS:528:DC%2BB38XmsFWksbo%3D 10.1007/S00330-022-08628-3/TABLES/3 35192011 9279234
G.A. Bartholomeus et al. Robustness of pulmonary nodule radiomic features on computed tomography as a function of varying radiation dose levels—a multi-dose in vivo patient study Eur. Radiol. 2023 33 10 7044 7055 10.1007/S00330-023-09643-8/FIGURES/6 37074424 10511375
N. Emaminejad M.W. Wahi-Anwar G.H.J. Kim W. Hsu M. Brown M. McNitt-Gray Reproducibility of lung nodule radiomic features: multivariable and univariable investigations that account for interactions between CT acquisition and reconstruction parameters Med. Phys. 2021 48 6 2906 10.1002/MP.14830 33706419
H. Bagher-Ebadian F. Siddiqui C. Liu B. Movsas I.J. Chetty On the impact of smoothing and noise on robustness of CT and CBCT radiomics features for patients with head and neck cancers Med. Phys. 2017 44 5 1755 1770 10.1002/MP.12188 28261818
J. Zhang et al. Radiomic feature repeatability and its impact on prognostic model generalizability: A multi-institutional study on nasopharyngeal carcinoma patients Radiother. Oncol. 2023 183 1 10.1016/j.radonc.2023.109578
X. Teng et al. Improving radiomic model reliability using robust features from perturbations for head-and-neck carcinoma Front. Oncol. 2022 12 10.3389/FONC.2022.974467 36313629 9614273
X. Teng et al. Building reliable radiomic models using image perturbation Sci. Rep. 2022 12 1 1 10 2022NatSR.12..10T 1:CAS:528:DC%2BB38Xhs1SktrnI 10.1038/s41598-022-14178-x
L. Escudero Sanchez L. Rundo A.B. Gill M. Hoare E. Mendes Serrao E. Sala Robustness of radiomic features in CT images with different slice thickness, comparing liver tumour and muscle Sci. Rep. 2021 11 1 1 15 1:CAS:528:DC%2BB3MXpt1WksL4%3D 10.1038/s41598-021-87598-w
S.J. Gao et al. Prediction of distant metastases after stereotactic body radiation therapy for early stage NSCLC: Development and external validation of a multi-institutional model J. Thorac. Oncol. 2023 18 3 339 349 10.1016/J.JTHO.2022.11.007 36396062
T. Eriguchi et al. Relationship between dose prescription methods and local control rate in stereotactic body radiotherapy for early stage non-small-cell lung cancer: Systematic review and meta-analysis Cancers 2022 14 15 10.3390/CANCERS14153815/S1
S. Senthi F.J. Lagerwaard C.J.A. Haasbeek B.J. Slotman S. Senan Patterns of disease recurrence after stereotactic ablative radiotherapy for early stage non-small-cell lung cancer: A retrospective analysis Lancet Oncol. 2012 13 8 802 809 10.1016/S1470-2045(12)70242-5 22727222
E.R. Velazquez et al. Volumetric CT-based segmentation of NSCLC using 3D-Slicer Sci. Rep. 2013 3 1 10.1038/SREP03529
J.J.M. Van Griethuysen et al. Computational radiomics system to decode the radiographic phenotype Cancer Res. 2017 77 21 1:CAS:528:DC%2BC2sXhslOltbnL 10.1158/0008-5472.CAN-17-0339 29092951 5672828
L.R. Dice Measures of the amount of ecologic association between species Ecology 1945 26 3 297 302 10.2307/1932409
T.K. Koo M.Y. Li A guideline of selecting and reporting intraclass correlation coefficients for reliability research J. Chiropr. Med. 2016 15 2 155 10.1016/J.JCM.2016.02.012 27330520 4913118
Nickerson, C. A. E. A note on ‘a concordance correlation coefficient to evaluate reproducibility’. Biometrics 53 (4), 1503–1507 [Online]. Available: https://www.jstor.org/stable/2533516 (1997).
J. Kim J.H. Lee A novel graphical evaluation of agreement BMC Med. Res. Methodol. 2022 22 1 1 9 10.1186/S12874-022-01532-W/FIGURES/5
Lin, L. I. K. A concordance correlation coefficient to evaluate reproducibility. Biometrics 45 (1), 255–268. Available: https://www.jstor.org/stable/2532051 (1989).
S.S. Shapiro M.B. Wilk An analysis of variance test for normality (complete samples) Biometrika 1965 52 3–4 591 611 205384 10.1093/BIOMET/52.3-4.591
S. Holm A simple sequentially rejective multiple test procedure Scand. J. Stat. 1979 6 2 65 70 538597
H.B. Mann D.R. Whitney On a test of whether one of two random variables is stochastically larger than the other Ann. Math. Statist. 1947 18 1 50 60 22058 10.1214/AOMS/1177730491
Y. Chen Y. Yang The one standard error rule for model selection: Does it work? Stats (Basel) 2021 4 4 868 892 10.3390/STATS4040051
H. Akaike Information theory and an extension of information the maximum theory likelihood and an principle extension of the maximum likelihood principle Biogeochemistry 1998 1998 199 213 10.1007/978-1-4612-1694-0_15/COVER
R. Reiazi et al. The impact of the variation of imaging parameters on the robustness of Computed Tomography radiomic features: A review Comput. Biol. Med. 2021 133 10.1016/J.COMPBIOMED.2021.104400 33930766
B.A. Varghese et al. Identification of robust and reproducible CT-texture metrics using a customized 3D-printed texture phantom J. Appl. Clin. Med. Phys. 2021 22 2 98 10.1002/ACM2.13162 33434374 7882093
H.J.W.L. Aerts et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach Nat. Commun. 2014 5 1 10.1038/NCOMMS5006
J.E. van Timmeren D. Cester S. Tanadini-Lang H. Alkadhi B. Baessler Radiomics in medical imaging—‘how-to’ guide and critical reflection Insights Imaging 2020 11 1 1 16 10.1186/S13244-020-00887-2/TABLES/3
I. Zhovannik et al. Learning from scanners: Bias reduction and feature correction in radiomics Clin. Transl. Radiat. Oncol. 2019 19 33 38 10.1016/J.CTRO.2019.07.003 31417963 6690665
