Comparison of PET and CT radiomics for prediction of local tumor control in head and neck squamous cell carcinoma

被引:114
作者
Bogowicz, Marta [1 ]
Riesterer, Oliver
Stark, Luisa Sabrina
Studer, Gabriela
Unkelbach, Jan
Guckenberger, Matthias
Tanadini-Lang, Stephanie
机构
[1] Univ Hosp Zurich, Dept Radiat Oncol, Ramistr 100, CH-8091 Zurich, Switzerland
关键词
RADIOTHERAPY; CANCER; VALIDATION;
D O I
10.1080/0284186X.2017.1346382
中图分类号
R73 [肿瘤学];
学科分类号
100214 ;
摘要
Purpose: An association between radiomic features extracted from CT and local tumor control in the head and neck squamous cell carcinoma (HNSCC) has been shown. This study investigated the value of pretreatment functional imaging (18F-FDG PET) radiomics for modeling of local tumor control. Material and Methods: Data from HNSCC patients (n = 121) treated with definitive radiochemotherapy were used for model training. In total, 569 radiomic features were extracted from both contrast-enhanced CT and 18F-FDG PET images in the primary tumor region. CT, PET and combined PET/CT radiomic models to assess local tumor control were trained separately. Five feature selection and three classification methods were implemented. The performance of the models was quantified using concordance index (CI) in 5-fold cross validation in the training cohort. The best models, per image modality, were compared and verified in the independent validation cohort (n = 51). The difference in CI was investigated using bootstrapping. Additionally, the observed and radiomics-based estimated probabilities of local tumor control were compared between two risk groups. Results: The feature selection using principal component analysis and the classification based on the multivariabale Cox regression with backward selection of the variables resulted in the best models for all image modalities (CICT = 0.72, CIPET = 0.74, CIPET/CT = 0.77). Tumors more homogenous in CT density (decreased GLSZM(size_zone_entropy)) and with a focused region of high FDG uptake (higher GLSZM(SZLGE)) indicated better prognosis. No significant difference in the performance of the models in the validation cohort was observed (CICT = 0.73, CIPET = 0.71, CIPET/CT = 0.73). However, the CT radiomics-based model overestimated the probability of tumor control in the poor prognostic group (predicted = 68%, observed = 56%). Conclusions: Both CT and PET radiomics showed equally good discriminative power for local tumor control modeling in HNSCC. However, CT-based predictions overestimated the local control rate in the poor prognostic validation cohort, and thus, we recommend to base the local control modeling on the 18F-FDG PET.
引用
收藏
页码:1531 / 1536
页数:6
相关论文
共 23 条
  • [1] Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach
    Aerts, Hugo J. W. L.
    Velazquez, Emmanuel Rios
    Leijenaar, Ralph T. H.
    Parmar, Chintan
    Grossmann, Patrick
    Cavalho, Sara
    Bussink, Johan
    Monshouwer, Rene
    Haibe-Kains, Benjamin
    Rietveld, Derek
    Hoebers, Frank
    Rietbergen, Michelle M.
    Leemans, C. Rene
    Dekker, Andre
    Quackenbush, John
    Gillies, Robert J.
    Lambin, Philippe
    [J]. NATURE COMMUNICATIONS, 2014, 5
  • [2] Human Papillomavirus and Survival of Patients with Oropharyngeal Cancer
    Ang, K. Kian
    Harris, Jonathan
    Wheeler, Richard
    Weber, Randal
    Rosenthal, David I.
    Nguyen-Tan, Phuc Felix
    Westra, William H.
    Chung, Christine H.
    Jordan, Richard C.
    Lu, Charles
    Kim, Harold
    Axelrod, Rita
    Silverman, C. Craig
    Redmond, Kevin P.
    Gillison, Maura L.
    [J]. NEW ENGLAND JOURNAL OF MEDICINE, 2010, 363 (01) : 24 - 35
  • [3] Locally advanced head and neck cancer treated with accelerated radiotherapy, the hypoxic modifier nimorazole and weekly cisplatin. Results from the DAHANCA 18 phase II study
    Bentzen, Jens
    Toustrup, Kasper
    Eriksen, Jesper Grau
    Primdahl, Hanne
    Andersen, Lisbeth Juhler
    Overgaard, Jens
    [J]. ACTA ONCOLOGICA, 2015, 54 (07) : 1001 - 1007
  • [4] Bogowicz M, 2017, INT J RAD O IN PRESS
  • [5] The prognostic value of the hypoxia markers CA IX and GLUT I and the cytokines VEGF and IL 6 in head and neck squamous cell carcinoma treated by radiotherapy chemotherapy
    De Schutter, H
    Landuyt, W
    Verbeken, E
    Goethals, L
    Hermans, R
    Nuyts, S
    [J]. BMC CANCER, 2005, 5 (1)
  • [6] Characterization of PET/CT images using texture analysis: the past, the presenta... any future?
    Hatt, Mathieu
    Tixier, Florent
    Pierce, Larry
    Kinahan, Paul E.
    Le Rest, Catherine Cheze
    Visvikis, Dimitris
    [J]. EUROPEAN JOURNAL OF NUCLEAR MEDICINE AND MOLECULAR IMAGING, 2017, 44 (01) : 151 - 165
  • [7] Texture analysis on parametric maps derived from dynamic contrast-enhanced magnetic resonance imaging in head and neck cancer
    Jansen, Jacobus F. A.
    Lu, Yonggang
    Gupta, Gaorav
    Lee, Nancy Y.
    Stambuk, Hilda E.
    Mazaheri, Yousef
    Deasy, Joseph O.
    Shukla-Dave, Amita
    [J]. WORLD JOURNAL OF RADIOLOGY, 2016, 8 (01): : 90 - 97
  • [8] Tumor progression in waiting time for radiotherapy in head and neck cancer
    Jensen, Anni Ravnsbaek
    Nellemann, Hanne Marie
    Overgaard, Jens
    [J]. RADIOTHERAPY AND ONCOLOGY, 2007, 84 (01) : 5 - 10
  • [9] Emerging biomarkers in head and neck cancer in the era of genomics
    Kang, Hyunseok
    Kiess, Ana
    Chung, Christine H.
    [J]. NATURE REVIEWS CLINICAL ONCOLOGY, 2015, 12 (01) : 11 - 26
  • [10] Radiomics: Extracting more information from medical images using advanced feature analysis
    Lambin, Philippe
    Rios-Velazquez, Emmanuel
    Leijenaar, Ralph
    Carvalho, Sara
    van Stiphout, Ruud G. P. M.
    Granton, Patrick
    Zegers, Catharina M. L.
    Gillies, Robert
    Boellard, Ronald
    Dekker, Andre
    Aerts, Hugo J. W. L.
    [J]. EUROPEAN JOURNAL OF CANCER, 2012, 48 (04) : 441 - 446