Online citations, reference lists, and bibliographies.

Predictive Modeling Of Outcomes Following Definitive Chemoradiotherapy For Oropharyngeal Cancer Based On FDG-PET Image Characteristics.

Michael R. Folkert, Jeremy S Setton, Aditya P. Apte, Milan Grkovski, Robert J Young, Heiko Schöder, W. L. Thorstad, Nancy Y. Lee, Joseph O. Deasy, Jung Hun Oh
Published 2017 · Physics, Medicine
Cite This
Download PDF
Analyze on Scholarcy
Share
In this study, we investigate the use of imaging feature-based outcomes research ('radiomics') combined with machine learning techniques to develop robust predictive models for the risk of all-cause mortality (ACM), local failure (LF), and distant metastasis (DM) following definitive chemoradiation therapy (CRT). One hundred seventy four patients with stage III-IV oropharyngeal cancer (OC) treated at our institution with CRT with retrievable pre- and post-treatment 18F-fluorodeoxyglucose positron emission tomography (FDG-PET) scans were identified. From pre-treatment PET scans, 24 representative imaging features of FDG-avid disease regions were extracted. Using machine learning-based feature selection methods, multiparameter logistic regression models were built incorporating clinical factors and imaging features. All model building methods were tested by cross validation to avoid overfitting, and final outcome models were validated on an independent dataset from a collaborating institution. Multiparameter models were statistically significant on 5 fold cross validation with the area under the receiver operating characteristic curve (AUC)  =  0.65 (p  =  0.004), 0.73 (p  =  0.026), and 0.66 (p  =  0.015) for ACM, LF, and DM, respectively. The model for LF retained significance on the independent validation cohort with AUC  =  0.68 (p  =  0.029) whereas the models for ACM and DM did not reach statistical significance, but resulted in comparable predictive power to the 5 fold cross validation with AUC  =  0.60 (p  =  0.092) and 0.65 (p  =  0.062), respectively. In the largest study of its kind to date, predictive features including increasing metabolic tumor volume, increasing image heterogeneity, and increasing tumor surface irregularity significantly correlated to mortality, LF, and DM on 5 fold cross validation in a relatively uniform single-institution cohort. The LF model also retained significance in an independent population.
This paper references
10.1088/0031-9155/54/1/R01
Biological imaging in radiation therapy: role of positron emission tomography.
Ursula Nestle (2009)
10.1148/radiology.143.1.7063747
The meaning and use of the area under a receiver operating characteristic (ROC) curve.
James A Hanley (1982)
10.1007/s12149-012-0604-5
Superior prognostic utility of gross and metabolic tumor volume compared to standardized uptake value using PET/CT in head and neck squamous cell carcinoma patients treated with intensity-modulated radiotherapy
Paul B Romesser (2012)
10.2967/jnumed.112.119289
Textural Features of Pretreatment 18F-FDG PET/CT Images: Prognostic Significance in Patients with Advanced T-Stage Oropharyngeal Squamous Cell Carcinoma
Nai-Ming Cheng (2013)
10.1016/j.compbiomed.2014.04.014
A review on segmentation of positron emission tomography images
Brent Foster (2014)
10.1258/ar.2011.100510
Multiparametric analysis of magnetic resonance images for glioma grading and patient survival time prediction
Benjamón Garzín (2011)
10.1002/cncr.28150
High intratumor genetic heterogeneity is related to worse outcome in patients with head and neck squamous cell carcinoma.
Edmund A Mroz (2013)
10.1002/jmri.25119
Breast cancer molecular subtype classifier that incorporates MRI features.
Elizabeth J. Sutton (2016)
10.1186/1758-3284-2-19
FDG-PET staging and importance of lymph node SUV in head and neck cancer
Gregory J Kubicek (2010)
10.2967/jnumed.108.057208
PET Monitoring of Therapy Response in Head and Neck Squamous Cell Carcinoma
Heiko Schöder (2009)
10.1016/S0167-9473(99)00077-8
A new nonparametric method for variance estimation and confidence interval construction for Spearman's rank correlation
Craig B. Borkowf (2000)
10.1016/j.ygyno.2013.01.017
The value of 18F-FDG PET/CT in recurrent gynecologic malignancies prior to pelvic exenteration.
Irene A. Burger (2013)
10.1200/JCO.2002.02.590
Diagnostic and Prognostic Value of [18F]Fluorodeoxyglucose Positron Emission Tomography for Recurrent Head and Neck Squamous Cell Carcinoma
Richard J Wong (2002)
10.1007/s00259-014-2961-x
FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0
Ronald Boellaard (2014)
10.1002/hed.23784
Prognostic value of pretreatment 18F-fluorodeoxyglucose positron emission tomography/CT volume-based parameters in patients with oropharyngeal squamous cell carcinoma with known p16 and p53 status.
Masahiro Kikuchi (2015)
10.1109/TMI.2008.2004425
Coregistered FDG PET/CT-Based Textural Characterization of Head and Neck Cancer for Radiation Treatment Planning
Huan Yu (2009)
10.1158/1078-0432.CCR-13-2810
Improved Differentiation of Benign and Malignant Breast Tumors with Multiparametric 18Fluorodeoxyglucose Positron Emission Tomography Magnetic Resonance Imaging: A Feasibility Study
Katja Pinker (2014)
10.1148/RADIOL.2016152234
Radiomics Signature: A Potential Biomarker for the Prediction of Disease-Free Survival in Early-Stage (I or II) Non-Small Cell Lung Cancer.
Yanqi Huang (2016)
10.1118/1.4867856
Specific recommendations for accurate and direct use of PET-CT in PET guided radiotherapy for head and neck sites.
Christopher M Thomas (2014)
10.2967/jnumed.114.144055
18F-FDG PET Uptake Characterization Through Texture Analysis: Investigating the Complementary Nature of Heterogeneity and Functional Tumor Volume in a Multi–Cancer Site Patient Cohort
Mathieu Hatt (2015)
10.1016/j.compmedimag.2008.05.005
Medical image analysis of 3D CT images based on extension of Haralick texture features
Ludvík Tesar (2008)
10.1016/j.radonc.2008.11.008
Use of PET and PET/CT for radiation therapy planning: IAEA expert report 2006-2007.
Michael MacManus (2009)
10.1016/j.oraloncology.2014.06.018
The relative prognostic utility of standardized uptake value, gross tumor volume, and metabolic tumor volume in oropharyngeal cancer patients treated with platinum based concurrent chemoradiation with a pre-treatment [(18)F] fluorodeoxyglucose positron emission tomography scan.
Paul B Romesser (2014)
10.1016/S1095-0397(99)00016-3
Tumor Treatment Response Based on Visual and Quantitative Changes in Global Tumor Glycolysis Using PET-FDG Imaging. The Visual Response Score and the Change in Total Lesion Glycolysis.
Steven M. Larson (1999)
10.1007/BF01413859
Estimating MLP generalisation ability without a test set using fast, approximate leave-one-out cross-validation
Andrew J. Myles (2005)
10.1016/j.media.2016.05.007
Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction
Chunfeng Lian (2016)
10.1016/j.patcog.2008.08.011
Exploring feature-based approaches in PET images for predicting cancer treatment outcomes
Issam El-Naqa (2009)
10.1080/01621459.1927.10502953
Probable Inference, the Law of Succession, and Statistical Inference
Edwin Bidwell Wilson (1927)
10.2967/jnumed.107.044792
Clinical Utility of 18F-FDG PET/CT in Assessing the Neck After Concurrent Chemoradiotherapy for Locoregional Advanced Head and Neck Cancer
Seng Chuan Ong (2008)
10.2967/jnumed.115.167684
18F-FDG PET/CT of Non–Small Cell Lung Carcinoma Under Neoadjuvant Chemotherapy: Background-Based Adaptive-Volume Metrics Outperform TLG and MTV in Predicting Histopathologic Response
Irene A. Burger (2016)
10.1016/j.ijrobp.2010.11.050
Analysis of pretreatment FDG-PET SUV parameters in head-and-neck cancer: tumor SUVmean has superior prognostic value.
Kristin Higgins (2012)
10.1593/NEO.131400
Tumor evolution and intratumor heterogeneity of an oropharyngeal squamous cell carcinoma revealed by whole-genome sequencing.
Xinyi Cindy Zhang (2013)
10.1016/j.ijrobp.2009.04.043
Automated radiation targeting in head-and-neck cancer using region-based texture analysis of PET and CT images.
Huan Yu (2009)
10.2967/jnumed.111.099531
18F-FDG Metabolic Tumor Volume and Total Glycolytic Activity of Oral Cavity and Oropharyngeal Squamous Cell Cancer: Adding Value to Clinical Staging
Elizabeth H Dibble (2012)
10.1002/SIM.5511
Contrasting treatment‐specific survival using double‐robust estimators
KyungMann Kim (2012)
10.1007/s00330-014-3269-8
Asphericity of pretherapeutic tumour FDG uptake provides independent prognostic value in head-and-neck cancer
Ivayla Apostolova (2014)
10.1073/pnas.0610117104
Identification of a subpopulation of cells with cancer stem cell properties in head and neck squamous cell carcinoma
M E Prince (2007)
10.1007/978-1-4612-4380-9_25
Nonparametric Estimation from Incomplete Observations
E. L. Kaplan (1958)
10.2967/jnumed.111.101402
18F-FDG PET/CT Metabolic Tumor Volume and Total Lesion Glycolysis Predict Outcome in Oropharyngeal Squamous Cell Carcinoma
Remy Lim (2012)
10.1371/journal.pone.0084999
Correlations between Functional Imaging Markers Derived from PET/CT and Diffusion-Weighted MRI in Diffuse Large B-Cell Lymphoma and Follicular Lymphoma
Xingchen Wu (2014)
10.1007/s13566-012-0065-4
Prognostic value of 18F-FDG PET metabolic parameters in oropharyngeal squamous cell carcinoma
Adam A. Garsa (2012)
10.1016/j.oraloncology.2012.09.005
Total lesion glycolysis: a possible new prognostic parameter in oral cavity squamous cell carcinoma.
Yasser G Abd El-Hafez (2013)
10.1002/jso.23703
Prognostic significance of the intratumoral heterogeneity of (18) F-FDG uptake in oral cavity cancer.
Soo Hyun Kwon (2014)
10.1118/1.1568978
CERR: a computational environment for radiotherapy research.
Joseph O. Deasy (2003)
10.1016/S0360-3016(02)02705-0
Measurement of tumor volume by PET to evaluate prognosis in patients with advanced cervical cancer treated by radiation therapy.
Tom R. Miller (2002)
10.1080/01621459.1999.10474144
A Proportional Hazards Model for the Subdistribution of a Competing Risk
Jason Peter Fine (1999)
10.2967/jnumed.114.141424
Molecular Imaging to Plan Radiotherapy and Evaluate Its Efficacy
Robert Jeraj (2015)
10.1109/TSMC.1973.4309314
Textural Features for Image Classification
Robert M. Haralick (1973)
10.1186/2191-219X-2-56
Assessment of tumour size in PET/CT lung cancer studies: PET- and CT-based methods compared to pathology
Patsuree Cheebsumon (2012)
10.1200/JCO.20.5.1398
Standardized uptake value of 2-[(18)F] fluoro-2-deoxy-D-glucose in predicting outcome in head and neck carcinomas treated by radiotherapy with or without chemotherapy.
Abdelkarim Said Allal (2002)
Tumor radiocurability: relationship to intrinsic tumor heterogeneity and to the tumor bed effect.
John T. Leith (1990)
10.1097/COC.0b013e318162f150
PET-CT in Radiation Oncology: The Impact on Diagnosis, Treatment Planning, and Assessment of Treatment Response
Dwight E Heron (2008)
10.3109/0284186X.2013.812798
Stability of FDG-PET Radiomics features: An integrated analysis of test-retest and inter-observer variability
Ralph T. H. Leijenaar (2013)
10.1002/(SICI)1097-0142(19971215)80:12+<2505::AID-CNCR24>3.0.CO;2-F
Segmentation of lung lesion volume by adaptive positron emission tomography image thresholding.
Yusuf E. Erdi (1997)
2-Deoxy-2-[18F] fluoro-D-glucose uptake and correlation to intratumoral heterogeneity.
Eva Henriksson (2007)
10.1016/j.ijrobp.2003.12.039
Prediction of outcome in head-and-neck cancer patients using the standardized uptake value of 2-[18F]fluoro-2-deoxy-D-glucose.
Abdelkarim Said Allal (2004)
NCCN Practice Guidelines for Head and Neck Cancers.
David G. Pfister (2000)
10.1148/radiol.14132807
Repeatability of metabolically active tumor volume measurements with FDG PET/CT in advanced gastrointestinal malignancies: a multicenter study.
Virginie Frings (2014)
10.1016/j.ijrobp.2011.10.023
Validation that metabolic tumor volume predicts outcome in head-and-neck cancer.
Chad Tang (2012)



This paper is referenced by
10.1007/s11864-018-0585-2
Big Data in Head and Neck Cancer
Carlo Resteghini (2018)
10.1080/0284186X.2019.1629013
Perfusion CT radiomics as potential prognostic biomarker in head and neck squamous cell carcinoma
Marta Bogowicz (2019)
10.1007/s13139-019-00571-4
Radiomics in Oncological PET/CT: a Methodological Overview
Seunggyun Ha (2019)
10.1186/s13550-019-0563-0
Association of metabolic and genetic heterogeneity in head and neck squamous cell carcinoma with prognostic implications: integration of FDG PET and genomic analysis
Jinyeong Choi (2019)
10.1007/s40336-018-0299-2
Heterogeneity analysis of 18F-FDG PET imaging in oncology: clinical indications and perspectives
Pierre Lovinfosse (2018)
10.1016/j.oraloncology.2018.01.030
Heterogeneity and irregularity of pretreatment 18F-fluorodeoxyglucose positron emission tomography improved prognostic stratification of p16-negative high-risk squamous cell carcinoma of the oropharynx.
Nai-Ming Cheng (2018)
10.1007/s40336-018-0292-9
FDG PET radiomics: a review of the methodological aspects
Pierre Lovinfosse (2018)
10.1002/hed.26025
A critical appraisal of the clinical applicability and risk of bias of the predictive models for mortality and recurrence in patients with oropharyngeal cancer: Systematic review.
Antonio Palazón-Bru (2019)
10.23736/S1824-4785.19.03192-3
CT radiomics and PET radiomics: ready for clinical implementation?
Marta Bogowicz (2019)
10.1371/journal.pone.0222509
Radiomics features of the primary tumor fail to improve prediction of overall survival in large cohorts of CT- and PET-imaged head and neck cancer patients
Rachel B. Ger (2019)
10.1186/s13550-019-0555-0
Texture analysis of pretreatment [18F]FDG PET/CT for the prognostic prediction of locally advanced salivary gland carcinoma treated with interstitial brachytherapy
Wen-jie Wu (2019)
10.1055/s-0043-121964
Radiomics: Big Data Instead of Biopsies in the Future?
Kathrin Scheckenbach (2018)
10.1007/s13139-017-0500-y
Radiomics in Oncological PET/CT: Clinical Applications
Jeong Won Lee (2017)
10.1016/j.compbiomed.2020.103731
Kernel Wasserstein Distance
Jung Hun Oh (2019)
10.1259/bjr.20170926
A review on radiomics and the future of theranostics for patient selection in precision medicine.
Simon A Keek (2018)
QUANTITATIVE IMAGING FOR PRECISION MEDICINE IN HEAD AND NECK CANCER PATIENTS
Rachel Ger (2019)
10.1101/773168
Reproducibility test of radiomics using network analysis and Wasserstein K-means algorithm
Jung Hun Oh (2019)
10.1007/s00586-018-05877-z
A prediction model of surgical site infection after instrumented thoracolumbar spine surgery in adults
Daniël M C Janssen (2018)
10.1186/s41199-020-00053-7
Applications of radiomics in precision diagnosis, prognostication and treatment planning of head and neck squamous cell carcinomas
Stefan P. Haider (2020)
10.1016/j.compbiomed.2020.103731
A novel kernel Wasserstein distance on Gaussian measures: An application of identifying dental artifacts in head and neck computed tomography
Jung Hun Oh (2020)
10.1002/hed.25337
Pretreatment metabolic tumor volume as a prognostic factor in HPV‐associated oropharyngeal cancer in the context of AJCC 8th edition staging
John M Floberg (2018)
10.33612/diss.111448998
The prognostic value of CT radiomic features from primary tumours and pathological lymph nodes in head and neck cancer patients
T. Zhai (2020)
10.1016/j.jacr.2019.05.045
Feeding the Data Monster: Data Science in Head and Neck Cancer for Personalized Therapy.
Loredana G. Marcu (2019)
10.1055/S-0043-121964
Radiomics: Big Data statt Biopsie in der Zukunft?
Kathrin Scheckenbach (2018)
Semantic Scholar Logo Some data provided by SemanticScholar