B. Al-taan, O. S. Eltweri, A. Sharpe, and D. , Prognostic value of baseline FDG uptake on PET-CT in esophageal carcinoma, World Journal of Gastrointestinal Oncology, vol.6, issue.5, pp.139-144, 2014.
DOI : 10.4251/wjgo.v6.i5.139

D. G. Altman, B. Lausen, and W. Sauerbrei, Dangers of Using "Optimal" Cutpoints in the Evaluation of Prognostic Factors, JNCI Journal of the National Cancer Institute, vol.86, issue.11, pp.829-835, 1994.
DOI : 10.1093/jnci/86.11.829

M. Amadasun and R. King, Textural features corresponding to textural properties, IEEE Transactions on Systems, Man, and Cybernetics, vol.19, issue.5, pp.1264-1273, 1989.
DOI : 10.1109/21.44046

R. Bellman and R. Bellman, Adaptive Control Processes : A Guided Tour. Princeton Legacy Library, 1961.

S. Ben-haim, P. Ell, . 18f-fdg, and P. Pet, 18F-FDG PET and PET/CT in the Evaluation of Cancer Treatment Response, Journal of Nuclear Medicine, vol.50, issue.1, pp.88-99, 2008.
DOI : 10.2967/jnumed.108.054205

T. Berghmans, M. Dusart, and M. Paesmans, Primary Tumor Standardized Uptake Value (SUVmax) Measured on Fluorodeoxyglucose Positron Emission Tomography (FDG-PET) is of Prognostic Value for Survival in Non-small Cell Lung Cancer (NSCLC): A Systematic Review and Meta-Analysis (MA) by the European Lung Cancer Working Party for the IASLC Lung Cancer Staging Project, Journal of Thoracic Oncology, vol.3, issue.1, pp.6-12, 2008.
DOI : 10.1097/JTO.0b013e31815e6d6b

R. J. Beukinga, J. B. Hulshoff, and L. V. Van-dijk, F-FDG PET/CT Imaging, Journal of Nuclear Medicine, vol.58, issue.5, pp.723-729, 2017.
DOI : 10.2967/jnumed.116.180299

R. L. Blom, I. R. Steenbakkers, and G. Lammering, PET/CT-based metabolic tumour volume for response prediction of neoadjuvant chemoradiotherapy in oesophageal carcinoma, European Journal of Nuclear Medicine and Molecular Imaging, vol.53, issue.10, pp.1500-1506, 2013.
DOI : 10.2967/jnumed.112.102749

A. L. Blum and P. Langley, Selection of relevant features and examples in machine learning, Artificial Intelligence, vol.97, issue.1-2, pp.245-27110, 1997.
DOI : 10.1016/S0004-3702(97)00063-5

R. Boellaard, Standards for PET Image Acquisition and Quantitative Data Analysis, Journal of Nuclear Medicine, vol.50, issue.Suppl_1, pp.11-20, 2009.
DOI : 10.2967/jnumed.108.057182
URL : http://jnm.snmjournals.org/content/early/2009/04/20/jnumed.108.057182.full.pdf

R. Boellaard, R. Delgado-bolton, and W. Oyen, FDG PET/CT: EANM procedure guidelines for tumour imaging: version 2.0, European Journal of Nuclear Medicine and Molecular Imaging, vol.28, issue.10, pp.328-354, 2015.
DOI : 10.1097/MNM.0b013e3282eff2d5
URL : https://link.springer.com/content/pdf/10.1007%2Fs00259-014-2961-x.pdf

R. Boellaard, N. C. Krak, and O. S. Hoekstra, Effects of Noise, Image Resolution, and ROI Definition on the Accuracy of Standard Uptake Values : A Simulation Study, J Nucl Med, vol.45, issue.9, pp.1519-1527, 2004.

R. Boellaard, W. Oyen, and C. J. Hoekstra, The Netherlands protocol for standardisation and quantification of FDG whole body PET studies in multi-centre trials, European Journal of Nuclear Medicine and Molecular Imaging, vol.177, issue.6, pp.2320-2333, 2008.
DOI : 10.1055/s-2005-858197

N. Boughattas, M. Berar, and K. Hamrouni, Brain tumor segmentation from multiple MRI sequences using multiple kernel learning, 2014 IEEE International Conference on Image Processing (ICIP), 2014.
DOI : 10.1109/ICIP.2014.7025378
URL : https://hal.archives-ouvertes.fr/hal-01144737

C. Bourgier, J. Colinge, and N. Aillères, D{é}finition et applications cliniques des radiomics, Cancer/Radiotherapie, vol.19, pp.6-7, 2015.
DOI : 10.1016/j.canrad.2015.06.008

G. Box and T. G. , Bayesian Inference in Statistical Analysis, 1973.
DOI : 10.1002/9781118033197

L. Breiman, Random Forests, Machine Learning, vol.45, issue.1, pp.5-32, 2001.
DOI : 10.1023/A:1010933404324

L. Breiman, J. Friedman, and R. Olshen, Classification and Regression Trees, 1984.

C. M. Breki, A. Dimitrakopoulou-strauss, and J. Hassel, Fractal and multifractal analysis of PET/CT images of metastatic melanoma before and after treatment with ipilimumab, EJNMMI Research, vol.29, issue.7, pp.61-71, 2016.
DOI : 10.1109/TMI.2010.2048119

F. J. Brooks and P. Grigsby, The Effect of Small Tumor Volumes on Studies of Intratumoral Heterogeneity of Tracer Uptake, Journal of Nuclear Medicine, vol.55, issue.1, pp.37-42, 2014.
DOI : 10.2967/jnumed.112.116715

A. Bryant and R. J. Cerfolio, The Maximum Standardized Uptake Values on Integrated FDG-PET/CT Is Useful in Differentiating Benign From Malignant Pulmonary Nodules, The Annals of Thoracic Surgery, vol.82, issue.3
DOI : 10.1016/j.athoracsur.2006.03.095

P. Burman, -fold cross-validation and the repeated learning-testing methods, Biometrika, vol.76, issue.3, pp.503-514, 1989.
DOI : 10.1093/biomet/76.3.503

I. Buvat, F. Orlhac, and M. Soussan, Tumor Texture Analysis in PET: Where Do We Stand?, Journal of Nuclear Medicine, vol.56, issue.11, pp.1642-1644, 2015.
DOI : 10.2967/jnumed.115.163469
URL : http://jnm.snmjournals.org/content/56/11/1642.full.pdf

J. Calais, S. Thureau, and B. Dubray, Areas of High 18F-FDG Uptake on Preradiotherapy PET/CT Identify Preferential Sites of Local Relapse After Chemoradiotherapy for Non-Small Cell Lung Cancer, Journal of Nuclear Medicine, vol.56, issue.2, pp.196-203, 2015.
DOI : 10.2967/jnumed.114.144253
URL : https://hal.archives-ouvertes.fr/hal-01117241

A. Chalkidou, O. Doherty, M. J. Marsden, and P. , False Discovery Rates in PET and CT Studies with Texture Features: A Systematic Review, PLOS ONE, vol.158, issue.Suppl 1, pp.1-18, 2015.
DOI : 10.1371/journal.pone.0124165.s004

G. Chandrashekar and F. Sahin, A survey on feature selection methods, Computers & Electrical Engineering, vol.40, issue.1, pp.16-28, 2014.
DOI : 10.1016/j.compeleceng.2013.11.024

C. Chang, W. Liu, and H. Zhang, Image retrieval based on region shape similarity, pp.31-38, 2001.

H. Chen, B. F. Lee, and W. C. Su, The increment in standardized uptake value determined using dual-phase 18F-FDG PET is a promising prognostic factor in non-small-cell lung cancer, European Journal of Nuclear Medicine and Molecular Imaging, vol.28, issue.10, pp.1478-1485, 2013.
DOI : 10.1007/s002590100537

X. Chen and M. Wasikowski, FAST, Proceeding of the 14th ACM SIGKDD international conference on Knowledge discovery and data mining, KDD 08, pp.124-132, 2008.
DOI : 10.1145/1401890.1401910
URL : https://hal.archives-ouvertes.fr/hal-00995911

G. Cook, C. Yip, and M. Siddique, Are Pretreatment 18F-FDG PET Tumor Textural Features in Non-Small Cell Lung Cancer Associated with Response and Survival After Chemoradiotherapy?, Journal of Nuclear Medicine, vol.54, issue.1, pp.19-26, 2013.
DOI : 10.2967/jnumed.112.107375

D. R. Cox and D. Oakes, Analysis of Survival Data, 1984.

B. K. Das and B. Das, Positron Emission Tomography-A Guide for Clinicians, 2015.

A. J. De-langen, A. Vincent, and L. M. Velasquez, Repeatability of 18F-FDG Uptake Measurements in Tumors: A Metaanalysis, Journal of Nuclear Medicine, vol.53, issue.5, pp.701-708, 2012.
DOI : 10.2967/jnumed.111.095299

A. P. Dempster, N. M. Laird, and D. Rubin, Maximum likelihood from incomplete data via the EM algorithm, J R Stat Soc Ser B Methodol, vol.39, issue.1, pp.1-38, 1977.

J. Dem?ar, Statistical Comparisons of Classifiers over Multiple Data Sets, J Mach Learn Res, vol.7, 2006.

P. Desbordes, S. Ruan, and R. Modzelewski, Feature selection for outcome prediction in oesophageal cancer using genetic algorithm and random forest classifier, Comput Med Imaging Graph, 2016.

P. Desbordes, S. Ruan, and R. Modzelewski, Predictive value of initial FDG-PET features for treatment response and survival in esophageal cancer patients treated with chemoradiation therapy using a random forest classifier, PLoS One, vol.12, issue.3, 2017.
URL : https://hal.archives-ouvertes.fr/hal-01637198

D. Fiore, A. Lecleire, S. Gangloff, and A. , Impact of nutritional parameter variations during definitive chemoradiotherapy in locally advanced oesophageal cancer, Digestive and Liver Disease, vol.46, issue.3, pp.270-275, 2014.
DOI : 10.1016/j.dld.2013.10.016

M. Diehn, C. Nardini, and D. S. Wang, Identification of noninvasive imaging surrogates for brain tumor gene-expression modules, Proceedings of the National Academy of Sciences, vol.63, issue.7, pp.5213-5218, 2008.
DOI : 10.1093/jnen/63.7.700

X. Dong, L. Xing, and P. Wu, Three-dimensional positron emission tomography image texture analysis of esophageal squamous cell carcinoma, Nuclear Medicine Communications, vol.34, issue.1, pp.40-46, 2013.
DOI : 10.1097/MNM.0b013e32835ae50c

G. Doumou, M. Siddique, and C. Tsoumpas, The precision of textural analysis in 18F-FDG-PET scans of oesophageal cancer, European Radiology, vol.55, issue.9, pp.2805-2812, 2015.
DOI : 10.2967/jnumed.112.116715

D. Bois, D. , D. Bois, and E. , A Formula To Estimate The Approximate Surface Area If Height And Weight be Known, Arch Intern Med, 1916.

W. Dubitzky, M. Granzow, and D. Berrar, Fundamentals of data mining in genomics and proteomics, 2007.
DOI : 10.1007/978-0-387-47509-7

J. Dunn, Well-Separated Clusters and Optimal Fuzzy Partitions, Journal of Cybernetics, vol.4, issue.1, pp.95-104, 1974.
DOI : 10.1080/01969727408546059

E. A. Eisenhauer, P. Therasse, and J. Bogaerts, New response evaluation criteria in solid tumours: Revised RECIST guideline (version 1.1), European Journal of Cancer, vol.45, issue.2, pp.228-247, 2009.
DOI : 10.1016/j.ejca.2008.10.026

E. Naqa, I. Grigsby, P. W. Apte, and A. , Exploring feature-based approaches in PET images for predicting cancer treatment outcomes, Pattern Recognition, vol.42, issue.6, pp.1162-1171, 2009.
DOI : 10.1016/j.patcog.2008.08.011

T. Erselcan, B. Turgut, and D. Dogan, Lean body mass-based standardized uptake value, derived from a predictive equation, might be misleading in PET studies, European Journal of Nuclear Medicine and Molecular Imaging, vol.29, issue.12, pp.1630-1638, 2002.
DOI : 10.1007/s00259-002-0974-3

X. Fave, M. Cook, and A. Frederick, Preliminary investigation into sources of uncertainty in quantitative imaging features, Computerized Medical Imaging and Graphics, vol.44, pp.54-61, 2015.
DOI : 10.1016/j.compmedimag.2015.04.006

M. Fernández-delgado, E. Cernadas, and S. Barro, Do we Need Hundreds of Classifiers to Solve Real World Classification Problems ?, J Mach Learn Res, vol.15, pp.3133-3181, 2014.

J. Fledelius, A. Winther-larsen, and A. A. Khalil, 18)F-FDG-PET/CT for very early response evaluation predicts CT response in Erlotinib treated NSCLC patients -A comparison of assessment methods, J Nucl Med, 2017.

K. Fukushima and . Neocognitron, Neocognitron: A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position, Biological Cybernetics, vol.40, issue.4, pp.193-202, 1980.
DOI : 10.1007/BF00344251

P. E. Galavis, C. Hollensen, and N. Jallow, Variability of textural features in FDG PET images due to different acquisition modes and reconstruction parameters, Acta Oncologica, vol.45, issue.9, pp.1012-1016, 2010.
DOI : 10.1016/j.patcog.2008.08.011

M. Galloway, Texture analysis using gray level run lengths, Computer Graphics and Image Processing, vol.4, issue.2, pp.172-179, 1975.
DOI : 10.1016/S0146-664X(75)80008-6

X. Gao, C. Chu, and Y. Li, The method and efficacy of support vector machine classifiers based on texture features and multi-resolution histogram from 18F-FDG PET-CT images for the evaluation of mediastinal lymph nodes in patients with lung cancer, European Journal of Radiology, vol.84, issue.2, pp.312-317, 2015.
DOI : 10.1016/j.ejrad.2014.11.006

R. Genuer, For{ê}ts al{é}atoires : aspects th{é}oriques, s{é}lection de variables et applications, 2010.

P. Geurts, D. Ernst, and L. Wehenkel, Extremely randomized trees, Machine Learning, vol.63, issue.1, pp.3-4210, 2006.
DOI : 10.1007/s10994-006-6226-1
URL : https://hal.archives-ouvertes.fr/hal-00341932

R. Gilad-bachrach, A. Navot, and N. Tishby, Margin based feature selection - theory and algorithms, Twenty-first international conference on Machine learning , ICML '04, 2004.
DOI : 10.1145/1015330.1015352
URL : http://www.aicml.cs.ualberta.ca/banff04/icml/pages/papers/100.pdf

C. Gini, Measurement of Inequality of Incomes, The Economic Journal, vol.31, issue.121, pp.124-126, 1921.
DOI : 10.2307/2223319

I. Guyon and A. Elisseef, An Introduction to Variable and Feature Selection Isabelle, J ofMachine Learn Res, vol.3, pp.1157-1182, 2003.

I. Guyon, J. Weston, and S. Barnhill, Gene Selection for Cancer Classification using Support Vector Machines, Machine Learning, vol.46, issue.1/3, pp.389-422, 2002.
DOI : 10.1023/A:1012487302797

R. M. Haralick, K. Shanmugam, and I. Dinstein, Textural Features for Image Classification, IEEE Transactions on Systems, Man, and Cybernetics, vol.3, issue.6, 1973.
DOI : 10.1109/TSMC.1973.4309314
URL : http://www.cis.rit.edu/~cnspci/references/dip/segmentation/haralick1973.pdf

T. Hastie, R. Tibshirani, and J. Friedman, The Elements of Statistical Learning : Data Mining, Inference, and Prediction, 2009.

M. Hatt, C. Le-rest, C. Albarghach, and N. , PET functional volume delineation: a robustness and repeatability study, European Journal of Nuclear Medicine and Molecular Imaging, vol.97, issue.12, pp.663-672, 2011.
DOI : 10.1109/JPROC.2009.2027925
URL : https://hal.archives-ouvertes.fr/inserm-00574273

M. Hatt, D. Groheux, and A. Martineau, Comparison Between 18F-FDG PET Image-Derived Indices for Early Prediction of Response to Neoadjuvant Chemotherapy in Breast Cancer, Journal of Nuclear Medicine, vol.54, issue.3, pp.341-349, 2013.
DOI : 10.2967/jnumed.112.108837
URL : https://hal.archives-ouvertes.fr/hal-00748923

M. Hatt, M. Majdoub, and M. Vallières, 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, Journal of Nuclear Medicine, vol.56, issue.1, pp.38-44, 2015.
DOI : 10.2967/jnumed.114.144055

M. Hatt, D. Visvikis, and N. M. Albarghach, Prognostic value of 18F-FDG PET image-based parameters in oesophageal cancer and impact of tumour delineation methodology, European Journal of Nuclear Medicine and Molecular Imaging, vol.51, issue.9, pp.1191-1202, 2011.
DOI : 10.2967/jnumed.110.078501
URL : https://hal.archives-ouvertes.fr/inserm-00574267

M. Hatt, D. Visvikis, and O. Pradier, Baseline 18F-FDG PET image-derived parameters for therapy response prediction in oesophageal cancer, European Journal of Nuclear Medicine and Molecular Imaging, vol.17, issue.1, pp.1595-1606, 2011.
DOI : 10.1245/s10434-009-0719-7
URL : https://hal.archives-ouvertes.fr/inserm-00595534

S. Herlidou, Y. Rolland, and J. Y. Bansard, Comparison of automated and visual texture analysis in MRI: Characterization of normal and diseased skeletal muscle, Magnetic Resonance Imaging, vol.17, issue.9, pp.1393-1397, 1999.
DOI : 10.1016/S0730-725X(99)00066-1

A. Herskovic, K. Martz, and M. Sarraf, Combined Chemotherapy and Radiotherapy Compared with Radiotherapy Alone in Patients with Cancer of the Esophagus, New England Journal of Medicine, vol.326, issue.24, pp.1593-1598, 1992.
DOI : 10.1056/NEJM199206113262403

S. G. Hilsenbeck, G. M. Clark, and W. Mcguire, Why do so many prognostic factors fail to pan out?, Breast Cancer Research and Treatment, vol.27, issue.3, pp.197-206, 1992.
DOI : 10.1038/bjc.1990.380

Y. Hochberg and Y. Benjamin, More powerful procedures for multiple significance testing, Statistics in Medicine, vol.63, issue.7, pp.811-818, 1990.
DOI : 10.1093/biomet/69.3.493

F. Hofheinz, A. Lougovski, and K. Zöphel, Increased evidence for the prognostic value of primary tumor asphericity in pretherapeutic FDG PET for risk stratification in patients with head and neck cancer, European Journal of Nuclear Medicine and Molecular Imaging, vol.37, issue.1, pp.429-437, 2014.
DOI : 10.1007/s00259-009-1297-4

J. Holland, Adaptation in Natural and Artificial Systems : An Introductory Analysis with Applications to Biology, Control and Artificial Intelligence, 1992.

D. Hosmer and S. Lemeshow, Applied logistic regression, 2000.
DOI : 10.1002/0471722146

C. W. Hsu and C. Lin, A Comparison of Methods for Multiclass Support Vector Machines, IEEE Trans Neural Networks, vol.13, issue.2, pp.415-425, 2002.

C. J. Huang, D. X. Yang, and Y. Chuang, Application of wrapper approach and composite classifier to the stock trend prediction, Expert Systems with Applications, vol.34, issue.4, pp.2870-2878, 2008.
DOI : 10.1016/j.eswa.2007.05.035

S. H. Hyun, J. Y. Choi, and Y. M. Shim, Prognostic Value of Metabolic Tumor Volume Measured by 18F-Fluorodeoxyglucose Positron Emission Tomography in Patients with Esophageal Carcinoma, Annals of Surgical Oncology, vol.34, issue.1, pp.115-122, 2010.
DOI : 10.2214/ajr.185.2.01850436

J. Ioannidis, Why most published research findings are false, PLoS Med, vol.2, issue.8, pp.696-701, 2005.

A. Jackson, J. O-'connor, and G. Parker, Imaging Tumor Vascular Heterogeneity and Angiogenesis using Dynamic Contrast-Enhanced Magnetic Resonance Imaging, Clinical Cancer Research, vol.13, issue.12, pp.3449-3459, 2007.
DOI : 10.1158/1078-0432.CCR-07-0238
URL : http://clincancerres.aacrjournals.org/content/clincanres/13/12/3449.full.pdf

P. Jayachandran, R. K. Pai, and A. Quon, Postchemoradiotherapy Positron Emission Tomography Predicts Pathologic Response and Survival in Patients With Esophageal Cancer, International Journal of Radiation Oncology*Biology*Physics, vol.84, issue.2
DOI : 10.1016/j.ijrobp.2011.12.029

K. Jayasurya, G. Fung, and S. Yu, Comparison of Bayesian network and support vector machine models for two-year survival prediction in lung cancer patients treated with radiotherapy, Medical Physics, vol.55, issue.4, pp.1401-1407, 2010.
DOI : 10.1016/S0925-2312(03)00379-5

G. H. John, R. Kohavi, and K. Pfleger, Irrelevant Features and the Subset Selection Problem, Proc. Elev. Int. al Conf, pp.121-129, 1994.
DOI : 10.1016/B978-1-55860-335-6.50023-4
URL : ftp://robotics.stanford.edu/pub/gjohn/papers/relevance.ps

V. Kalff, C. Duong, and E. G. Drummond, Findings on 18F-FDG PET scans after neoadjuvant chemoradiation provides prognostic stratification in patients with locally advanced rectal carcinoma subsequently treated by radical surgery, J Nucl Med, vol.47, issue.1, pp.14-22, 2006.

B. Kaplan and P. Meier, Nonparametric Estimation from Incomplete Observations, Journal of the American Statistical Association, vol.37, issue.282, pp.457-481, 1958.
DOI : 10.1214/aoms/1177731566

D. Karnofsky and J. Burchenal, The Clinical Evaluation of Chemotherapeutic Agents in Cancer, Eval. Chemother. Agents, p.196, 1949.

H. Kato, M. Fukuchi, and T. Miyazaki, Prediction of response to definitive chemoradiotherapy in esophageal cancer using positron emission tomography, Anticancer Res, vol.27, issue.4, pp.2627-2633, 2007.

J. M. Kenney, L. D. Marinelli, and H. Woodard, Tracer Studies with Radioactive Phosphorus in Malignant Neoplastic Disease1, Radiology, vol.37, issue.6, 1941.

A. Kerhet, C. Small, and H. Quon, Segmentation of Lung Tumours in Positron Emission Tomography Scans: A Machine Learning Approach, Artif Intell Med, vol.45, issue.2, pp.146-155, 2009.
DOI : 10.1118/1.2712043

A. Kerhet, C. Small, and H. Quon, 186 APPLICATION OF MACHINE LEARNING METHODOLOGY FOR PETBASED DEFINITION OF LUNG CANCER, Radiotherapy and Oncology, vol.92, issue.1, pp.41-47, 2010.
DOI : 10.1016/S0167-8140(12)72573-2

H. Kiers and A. Smilde, A comparison of various methods for multivariate regression with highly collinear variables, Statistical Methods and Applications, vol.5, issue.2, pp.193-228, 2007.
DOI : 10.1007/978-0-387-21606-5

K. Kim, S. J. Kim, and I. J. Kim, Prognostic value of volumetric parameters measured by F-18 FDG PET/CT in surgically resected non-small-cell lung cancer, Nuclear Medicine Communications, vol.33, issue.6, pp.613-620, 2012.
DOI : 10.1097/MNM.0b013e328351d4f5

K. Kira and L. A. Rendell, The feature selection problem : Traditional methods and a new algorithm, AAAI-92 Proc. 1992, pp.129-13410

R. Kohavi and G. John, Wrappers for feature subset selection, Artificial Intelligence, vol.97, issue.1-2, pp.273-324, 1997.
DOI : 10.1016/S0004-3702(97)00043-X
URL : https://doi.org/10.1016/s0004-3702(97)00043-x

W. H. Kruskal and W. Wallis, Use of Ranks in One-Criterion Variance Analysis, Journal of the American Statistical Association, vol.3, issue.260, pp.583-621, 1952.
DOI : 10.2307/3001946

P. Lambin, E. Rios-velazquez, and R. Leijenaar, Radiomics: Extracting more information from medical images using advanced feature analysis, European Journal of Cancer, vol.48, issue.4, pp.441-446, 2012.
DOI : 10.1016/j.ejca.2011.11.036
URL : https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4533986/pdf

S. Larson, Y. Erdi, and T. Akhurst, 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, Clinical Positron Imaging, vol.2, issue.3, pp.159-171, 1999.
DOI : 10.1016/S1095-0397(99)00016-3

Y. Lecun, L. Bottou, and Y. Bengio, Gradient-based learning applied to document recognition, Proceedings of the IEEE, vol.86, issue.11, pp.2278-2323, 1998.
DOI : 10.1109/5.726791

P. Lee, J. G. Bazan, and P. W. Lavori, Metabolic Tumor Volume is an Independent Prognostic Factor in Patients Treated Definitively for Non???Small-Cell Lung Cancer, Clinical Lung Cancer, vol.13, issue.1, pp.52-58, 2012.
DOI : 10.1016/j.cllc.2011.05.001

R. Leijenaar, S. Carvalho, and E. R. Velazquez, Stability of FDG-PET Radiomics features: An integrated analysis of test-retest and inter-observer variability, Acta Oncologica, vol.4, issue.7, pp.1391-1397, 2013.
DOI : 10.1080/10543400701329422

R. Leijenaar, G. Nalbantov, and S. Carvalho, The effect of SUV discretization in quantitative FDG-PET Radiomics: the need for standardized methodology in tumor texture analysis, Scientific Reports, vol.14, issue.1, 2015.
DOI : 10.1186/1471-2407-14-130

C. Lemarignier, D. Fiore, F. Marre, and C. , Pretreatment metabolic tumour volume is predictive of disease-free survival and overall survival in patients with oesophageal squamous cell carcinoma, European Journal of Nuclear Medicine and Molecular Imaging, vol.40, issue.11, pp.2008-2016, 2014.
DOI : 10.1007/s00259-013-2465-0
URL : https://hal.archives-ouvertes.fr/hal-01120600

E. Levine, M. R. Farmer, and P. Clark, Predictive Value of 18-Fluoro-Deoxy-Glucose-Positron Emission Tomography (18F-FDG-PET) in the Identification of Responders to Chemoradiation Therapy for the Treatment of Locally Advanced Esophageal Cancer, Annals of Surgery, vol.243, issue.4
DOI : 10.1097/01.sla.0000208430.07050.61

Y. Li and L. Guo, TCM-KNN scheme for network anomaly detection using feature-based optimizations, Proceedings of the 2008 ACM symposium on Applied computing , SAC '08, p.2103, 2008.
DOI : 10.1145/1363686.1364194

C. Lian, S. Ruan, and T. Denoeux, Selecting radiomic features from FDG-PET images for cancer treatment outcome prediction, Medical Image Analysis, vol.32, pp.257-268, 2016.
DOI : 10.1016/j.media.2016.05.007
URL : https://hal.archives-ouvertes.fr/hal-01324553

V. J. Lowe, J. W. Fletcher, and L. Gobar, Prospective investigation of positron emission tomography in lung nodules., Journal of Clinical Oncology, vol.16, issue.3, pp.1075-1084, 1998.
DOI : 10.1200/JCO.1998.16.3.1075

J. Macqueen, Some methods for classification and analysis of multivariate observations, Proc Fifth Berkeley Symp Math Stat Probab, vol.1, issue.233, pp.281-297, 1967.

B. Mandelbrot, A Fractal???s Lacunarity, and how it can be Tuned and Measured, Fractals Biol Med, 1994.
DOI : 10.1007/978-3-0348-8501-0_2

N. Mantel, Evaluation of survival data and two new rank order statistics arising in its consideration, Cancer Chemother Rep, vol.50, issue.3, pp.163-170, 1966.

A. Marusyk, V. Almendro, and K. Polyak, Intra-tumour heterogeneity: a looking glass for cancer?, Nature Reviews Cancer, vol.139, issue.5, pp.323-334, 2012.
DOI : 10.1016/j.cell.2009.11.025

W. S. Mcculloch and W. Pitts, A logical calculus of the ideas immanent in nervous activity, The Bulletin of Mathematical Biophysics, vol.5, issue.4, pp.115-133, 1943.
DOI : 10.1007/BF02478259

H. Mi, C. Petitjean, and B. Dubray, Robust feature selection to predict tumor treatment outcome, Artificial Intelligence in Medicine, vol.64, issue.3, pp.195-204, 2015.
DOI : 10.1016/j.artmed.2015.07.002
URL : https://hal.archives-ouvertes.fr/hal-01153463

Z. Michalewicz, Genetic Algorithms + Data Structures = Evolution Programs, 1996.

B. Miller-a, B. Hoogstraten, B. Staquet, and M. , Reporting results of cancer treatment, 1<207:: AID-CNCR2820470134>3.0.CO, pp.207-214, 1981.
DOI : 10.1002/1097-0142(19810101)47:1<207::AID-CNCR2820470134>3.0.CO;2-6

T. R. Miller, E. Pinkus, and F. Dehdashti, Improved prognostic value of 18F-FDG PET using a simple visual analysis of tumor characteristics in patients with cervical cancer, J Nucl Med, vol.44, issue.2, pp.192-197, 2003.

K. Miwa, M. Inubushi, and K. Wagatsuma, FDG uptake heterogeneity evaluated by fractal analysis improves the differential diagnosis of pulmonary nodules, European Journal of Radiology, vol.83, issue.4, pp.715-719, 2014.
DOI : 10.1016/j.ejrad.2013.12.020

M. Mohri, A. Rostamizadeh, and A. Talwalkar, Foundations of Machine Learning, 2012.

W. Mu, Z. Chen, and Y. Liang, Staging of cervical cancer based on tumor heterogeneity characterized by texture features on (18)F-FDG PET images, Phys Med Biol, vol.6060135123, issue.13, pp.5123-5139, 2015.

M. Nakajo, M. Jinguji, and Y. Nakabeppu, Texture analysis of 18F-FDG PET/CT to predict tumour response and prognosis of patients with esophageal cancer treated by chemoradiotherapy, European Journal of Nuclear Medicine and Molecular Imaging, vol.17, issue.2, pp.206-214, 2017.
DOI : 10.1245/s10434-009-0719-7

U. Nestle, S. Kremp, and A. Schaefer-schuler, Comparison of different methods for delineation of {<}sup{>}18{<}/sup{>}F-FDG PET-positive tissue for target volume definition in radiotherapy of patients with non-Small cell lung cancer, J Nucl Med, vol.468, issue.8, pp.1342-1348, 2005.

F. Ng, R. Kozarski, and B. Ganeshan, Assessment of tumor heterogeneity by CT texture analysis: Can the largest cross-sectional area be used as an alternative to whole tumor analysis?, European Journal of Radiology, vol.82, issue.2, pp.342-348, 2013.
DOI : 10.1016/j.ejrad.2012.10.023

M. Oken, R. Creech, and D. Tormey, Toxicity and response criteria of the Eastern Cooperative Oncology Group, AMERICAN JOURNAL OF CLINICAL ONCOLOGY, vol.5, issue.6, 1982.
DOI : 10.1097/00000421-198212000-00014

D. P. Onoma, I. Gardin, and R. Modzelewski, Segmentation des tumeurs en imagerie m{é}dicale TEP bas{é}e sur la marche al{é}atoire 3D, RFIA, vol.2012, pp.978-980, 2012.
DOI : 10.1016/j.mednuc.2013.03.033

F. Orlhac, C. Nioche, and M. Soussan, Understanding Changes in Tumor Texture Indices in PET: A Comparison Between Visual Assessment and Index Values in Simulated and Patient Data, Journal of Nuclear Medicine, vol.58, issue.3, pp.387-392, 2017.
DOI : 10.2967/jnumed.116.181859

F. Orlhac, M. Soussan, and K. Chouahnia, 18F-FDG PET-Derived Textural Indices Reflect Tissue-Specific Uptake Pattern in Non-Small Cell Lung Cancer, PLOS ONE, vol.30, issue.9, pp.1-16, 2015.
DOI : 10.1371/journal.pone.0145063.s005
URL : https://doi.org/10.1371/journal.pone.0145063

F. Orlhac, M. Soussan, and J. A. Maisonobe, Tumor Texture Analysis in 18F-FDG PET: Relationships Between Texture Parameters, Histogram Indices, Standardized Uptake Values, Metabolic Volumes, and Total Lesion Glycolysis, Journal of Nuclear Medicine, vol.55, issue.3, pp.414-422, 2014.
DOI : 10.2967/jnumed.113.129858

O. Palie, P. Michel, and J. F. Ménard, The predictive value of treatment response using FDG PET performed on day 21 of chemoradiotherapy in patients with oesophageal squamous cell carcinoma. A prospective, multicentre study (RTEP3), European Journal of Nuclear Medicine and Molecular Imaging, vol.38, issue.7, pp.1345-1355, 2013.
DOI : 10.1007/s00259-011-1755-7

I. Petkovska, S. K. Shah, and M. F. Mcnitt-gray, Pulmonary nodule characterization: A comparison of conventional with quantitative and visual semi-quantitative analyses using contrast enhancement maps, European Journal of Radiology, vol.59, issue.2, pp.244-252, 2006.
DOI : 10.1016/j.ejrad.2006.03.005

P. Pudil, J. Novovieova, and J. Kittler, Floating search methods in feature selection, Pattern Recognition Letters, vol.15, issue.11, pp.1119-1125, 1993.
DOI : 10.1016/0167-8655(94)90127-9

T. Pyka, R. A. Bundschuh, and N. Andratschke, Textural features in pre-treatment [F18]-FDG-PET/CT are correlated with risk of local recurrence and disease-specific survival in early stage NSCLC patients receiving primary stereotactic radiation therapy, Radiation Oncology, vol.25, issue.2, pp.100-110, 2015.
DOI : 10.1007/s12149-010-0442-2

A. Rakotomamonjy, Variable Selection Using SVM-based Criteria, J ofMachine Learn Res, vol.3, pp.1357-1370, 2003.

N. P. Rizk, L. Tang, and P. S. Adusumilli, Predictive Value of Initial PET-SUVmax in Patients with Locally Advanced Esophageal and Gastroesophageal Junction Adenocarcinoma, Journal of Thoracic Oncology, vol.4, issue.7, pp.875-879, 2009.
DOI : 10.1097/JTO.0b013e3181a8cebf

J. Roehrig and R. A. Castellino, The promise of computer aided detection in digital mammography, European Journal of Radiology, vol.31, issue.1, pp.35-3900067, 1999.
DOI : 10.1016/S0720-048X(99)00067-4

G. Roman-jimenez, O. Acosta, and J. Leseur, Random forests to predict tumor recurrence following cervical cancer therapy using pre-and per-treatment 18 F-FDG PET parameters, pp.2444-2447, 2016.
DOI : 10.1109/embc.2016.7591224
URL : https://hal.archives-ouvertes.fr/hal-01484704

E. Segal, C. B. Sirlin, and C. Ooi, Decoding global gene expression programs in liver cancer by noninvasive imaging, Nature Biotechnology, vol.101, issue.6, pp.675-680, 2007.
DOI : 10.3748/wjg.v8.i3.385

G. Shafer, A Mathematical Theory of Evidence, 1976.

J. Shawe-taylor and N. Cristianini, Kernel Methods for Pattern Analysis, 2004.
DOI : 10.1017/CBO9780511809682

M. Soussan, K. Chouahnia, and J. A. Maisonobe, Prognostic implications of volume-based measurements on FDG PET/CT in stage III non-small-cell lung cancer after induction chemotherapy, European Journal of Nuclear Medicine and Molecular Imaging, vol.47, issue.5, pp.668-676, 2013.
DOI : 10.1159/000134474

C. Spearman, The Proof and Measurement of Association between Two Things, The American Journal of Psychology, vol.15, issue.1, pp.72-101, 1904.
DOI : 10.2307/1412159

D. Specht, A general regression neural network, IEEE Transactions on Neural Networks, vol.2, issue.6, pp.568-576, 1991.
DOI : 10.1109/72.97934

B. Srivastava, N. Hinton, G. Krizhevsky, and A. , Dropout : A Simple Way to Prevent Neural Networks from Overfitting, J Mach Learn Res, vol.15, pp.1929-1958, 2014.

S. G. Swisher, E. J. Maish, and M. , 2-Fluoro-2-deoxy-D-glucose positron emission tomography imaging is predictive of pathologic response and survival after preoperative chemoradiation in patients with esophageal carcinoma, Cancer, vol.101, issue.8, pp.1776-1785, 2004.
DOI : 10.1002/cncr.20585

A. Tabesh, M. Teverovskiy, and H. Y. Pang, Multifeature Prostate Cancer Diagnosis and Gleason Grading of Histological Images, IEEE Transactions on Medical Imaging, vol.26, issue.10, pp.1366-1378, 2007.
DOI : 10.1109/TMI.2007.898536

T. Takeshita, K. Morita, and Y. Tsutsui, The influence of respiratory motion on the cumulative SUV-volume histogram and fractal analyses of intratumoral heterogeneity in PET/CT imaging, Annals of Nuclear Medicine, vol.48, issue.6, pp.393-399, 2016.
DOI : 10.2967/jnumed.106.035774

S. Tan, S. Kligerman, and W. Chen, Spatial-Temporal [18F]FDG-PET Features for Predicting Pathologic Response of Esophageal Cancer to Neoadjuvant Chemoradiation Therapy, International Journal of Radiation Oncology*Biology*Physics, vol.85, issue.5, pp.1375-1382, 2013.
DOI : 10.1016/j.ijrobp.2012.10.017

S. Tan, H. Zhang, and Y. Zhang, Predicting pathologic tumor response to chemoradiotherapy with histogram distances characterizing longitudinal changes in 18F-FDG uptake patterns, Med Phys, vol.40, issue.10, 2013.

P. Teyton, J. P. Metges, J. Tallec, and V. , Valeur pronostique de la TEP au FDG dans le bilan initial du cancer de l?????sophage, M??decine Nucl??aire, vol.32, issue.6, pp.323-331, 2008.
DOI : 10.1016/j.mednuc.2008.02.013

S. Theodoridis and K. Koutroumbas, Introduction to Pattern Recognition : A Matlab Approach, 2010.

P. Therasse, S. G. Arbuck, and E. A. Eisenhauer, New Guidelines to Evaluate the Response to Treatment in Solid Tumors, Clin Trials, vol.12, issue.3, pp.16-27, 2005.

G. Thibault, B. Fertil, and C. Navarro, Texture Indexes and Gray Level Size Zone Matrix Application to Cell Nuclei Classification, Pattern Recognit Inf Process, pp.140-145, 2009.
URL : https://hal.archives-ouvertes.fr/hal-01499715

F. Tixier, C. Rest, C. Hatt, and M. , Intratumor Heterogeneity Characterized by Textural Features on Baseline 18F-FDG PET Images Predicts Response to Concomitant Radiochemotherapy in Esophageal Cancer, Journal of Nuclear Medicine, vol.52, issue.3, pp.369-378, 2011.
DOI : 10.2967/jnumed.110.082404
URL : https://hal.archives-ouvertes.fr/inserm-00574272

F. Tixier, M. Hatt, C. Rest, and C. , Reproducibility of Tumor Uptake Heterogeneity Characterization Through Textural Feature Analysis in 18F-FDG PET, Journal of Nuclear Medicine, vol.53, issue.5, pp.693-700, 2012.
DOI : 10.2967/jnumed.111.099127
URL : https://hal.archives-ouvertes.fr/inserm-00721377

L. Toney and H. J. Vesselle, Neural Networks for Nodal Staging of Non???Small Cell Lung Cancer with FDG PET and CT: Importance of Combining Uptake Values and Sizes of Nodes and Primary Tumor, Radiology, vol.270, issue.1, pp.91-98, 2014.
DOI : 10.1148/radiol.13122427

C. Van-de-wiele, V. Kruse, and P. Smeets, Predictive and prognostic value of metabolic tumour volume and total lesion glycolysis in solid tumours, European Journal of Nuclear Medicine and Molecular Imaging, vol.23, issue.5 Suppl, pp.290-301, 2013.
DOI : 10.1016/S0969-8051(96)00134-5

F. Van-velden, G. M. Kramer, and V. Frings, Repeatability of Radiomic Features in Non-Small-Cell Lung Cancer [18F]FDG-PET/CT Studies: Impact of Reconstruction and Delineation, Molecular Imaging and Biology, vol.85, issue.5, pp.788-795, 2016.
DOI : 10.1259/bjr/76424694

S. Vauclin, K. Doyeux, and S. Hapdey, Development of a generic thresholding algorithm for the delineation of 18FDG-PET-positive tissue : application to the comparison of three thresholding models, Phys Med Biol, vol.5422, issue.54, pp.6901-6916, 2009.
URL : https://hal.archives-ouvertes.fr/inserm-00467195

P. Vera, S. Mezzani-saillard, and A. Edet-sanson, FDG PET during radiochemotherapy is predictive of outcome at 1 year in non-small-cell lung cancer patients: a prospective multicentre study (RTEP2), European Journal of Nuclear Medicine and Molecular Imaging, vol.22, issue.2, pp.1057-1065, 2014.
DOI : 10.1016/0360-3016(92)90039-K

R. L. Wahl, H. Jacene, and Y. Kasamon, From RECIST to PERCIST: Evolving Considerations for PET Response Criteria in Solid Tumors, Journal of Nuclear Medicine, vol.50, issue.Suppl_1, pp.122-50, 2009.
DOI : 10.2967/jnumed.108.057307

H. Wang, Z. Zhou, and Y. Li, Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non-small cell lung cancer from 18F-FDG PET/CT images, EJNMMI Research, vol.35, issue.1, pp.11-21, 2017.
DOI : 10.1109/TMI.2016.2535302

L. Wang, Feature Selection with Kernel Class Separability, IEEE Transactions on Pattern Analysis and Machine Intelligence, vol.30, issue.9, pp.1534-1546, 2008.
DOI : 10.1109/TPAMI.2007.70799

W. Weber, Quantitative analysis of PET studies, Radiotherapy and Oncology, vol.96, issue.3, pp.308-310, 2010.
DOI : 10.1016/j.radonc.2010.07.004

A. Whitney, A Direct Method of Nonparametric Measurement Selection, IEEE Transactions on Computers, vol.20, issue.9, pp.201100-1103, 1971.
DOI : 10.1109/T-C.1971.223410

F. Wilcoxon, Individual Comparisons by Ranking Methods, Biometrics Bulletin, vol.1, issue.6, pp.80-83, 1945.
DOI : 10.2307/3001968

J. Willaime, F. E. Turkheimer, and L. M. Kenny, Quantification of intra-tumour cell proliferation heterogeneity using imaging descriptors of 18F fluorothymidine-positron emission tomography, Physics in Medicine and Biology, vol.58, issue.2, pp.187-203, 2013.
DOI : 10.1088/0031-9155/58/2/187

R. Xu, S. Kido, and K. Suga, Texture analysis on 18F-FDG PET/CT images to differentiate malignant and benign bone and soft-tissue lesions, Annals of Nuclear Medicine, vol.55, issue.379???423, pp.926-935, 2014.
DOI : 10.1016/S0925-2312(03)00431-4

H. Yan, R. Wang, and F. Zhao, Measurement of tumor volume by PET to evaluate prognosis in patients with advanced non-small cell lung cancer treated by non-surgical therapy, Acta Radiologica, vol.45, issue.6, pp.646-650, 2011.
DOI : 10.1007/s00259-006-0224-1

J. Yan, J. L. Chu-shern, and H. Y. Loi, Impact of Image Reconstruction Settings on Texture Features in 18F-FDG PET, Journal of Nuclear Medicine, vol.56, issue.11, pp.1667-1673, 2015.
DOI : 10.2967/jnumed.115.156927

S. Yip and H. Aerts, Applications and limitations of radiomics, Physics in Medicine and Biology, vol.61, issue.13, pp.150-166, 2016.
DOI : 10.1088/0031-9155/61/13/R150
URL : http://iopscience.iop.org/article/10.1088/0031-9155/61/13/R150/pdf

P. P. Ypsilantis, M. Siddique, and H. M. Sohn, Predicting Response to Neoadjuvant Chemotherapy with PET Imaging Using Convolutional Neural Networks, PLOS ONE, vol.102, issue.2, 2015.
DOI : 10.1371/journal.pone.0137036.t002
URL : https://doi.org/10.1371/journal.pone.0137036

C. Yu, Resampling methods : concepts, applications, and justification, Pract Assessment, Res Eval, vol.8, p.1, 2003.

H. Zaidi, E. Naqa, and I. , PET-guided delineation of radiation therapy treatment volumes: a survey of image segmentation techniques, European Journal of Nuclear Medicine and Molecular Imaging, vol.3, issue.Suppl 2, pp.2165-2187, 2010.
DOI : 10.1016/j.ijrobp.2007.04.053

H. Zhang, K. Wroblewski, and D. Appelbaum, Independent prognostic value of whole-body metabolic tumor burden from FDG-PET in non-small cell lung cancer, International Journal of Computer Assisted Radiology and Surgery, vol.44, issue.3, pp.181-191, 2013.
DOI : 10.1016/j.lungcan.2009.08.008

N. Zhang, S. Ruan, and S. Lebonvallet, Kernel feature selection to fuse multi-spectral MRI images for brain tumor segmentation, Computer Vision and Image Understanding, vol.115, issue.2, pp.256-269, 2011.
DOI : 10.1016/j.cviu.2010.09.007
URL : https://hal.archives-ouvertes.fr/hal-00673444

W. Zhu, L. Xing, and J. Yue, Prognostic significance of SUV on PET/CT in patients with localised oesophagogastric junction cancer receiving neoadjuvant chemotherapy/chemoradiation: a systematic review and meta-analysis, The British Journal of Radiology, vol.45, issue.1017, pp.694-701, 1017.
DOI : 10.1007/s00259-004-1626-6

.. Après-une-courte-distance, le positon e + obtenu par émission ? + est annihilé avec un électron e ? donnant naissance à deux photons ? émis dans une même direction, en sens opposé à 180° l'un de l'autre et avec une énergie de 511 keV chacun, p.11

T. Coupe-transverse, F. Au, and .. , MIP d'un patient présentant une tumeur de l'oesophage. La tumeur apparait colorée sur le MIP. Les autres organes présentant également une fixation normale du FDG sont le cerveau et le coeur dû à leur activé permanente, les reins et la vessie pour leur rôle de filtration, p.14

T. Coupe-sagittale and . Tdm, une tumeur pulmonaire segmentée en bleu (a) et histogramme associé des SUV (b) d'après [Tan et al, p.26, 2013.

R. Courbes and S. , le SUV peak , l'homogénéité, l'entropie , GLNUz et ZLNU (a) des répondeurs complets et (b) des répondeurs partiels ou non-répondeurs d'après, p.33

]. Principe-de-la-radiomique-et-de-l, extraction de caractéristiques de l'image tumorale d'après, p.39, 2016.

.. Principe-de-base-de-l-'apprentissage-automatique, Après création d'une base de données, un modèle est généré par apprentissage automatique à partir de l'échantillon d'apprentissage D app Ce modèle permet de prédire un label y pred d'une observation étudiée x, p.63

A. , S. , R. Adaboost, T. , A. et al., basés sur les AUC et les taux de bonne classification moyens après validation croisée kFCV (k = 10) Les barres d'erreur indiquent un intervalle de confiance de 95 %. La valeur de p entre les différents ensembles de caractéristiques est tracée en tant que pont et étoiles, où deux étoiles signifie p < 0, 05 après corrections de Bonferroni et FDR ("False Discovery Rate"), et une étoile signifie p < 0, 05 uniquement après correction de FDR, Comparaison des résultats obtenus avec 4 méthodes de classifieurs, p.88

R. Les, Processus de l'approche GARF de sélection de caractéristiques basée sur l'algorithme génétique, p.109

R. Résultats-de-la-classification-par, AUC RF et 1-RF err ) en fonction des différents types de ré-échantillonnage utilisés pour (a) l'étude prédictive et (b) l'étude pronostique, p.135

R. Résultats-de-la-classification-par, AUC RF et 1-RF err ) en fonction des différents nombres d'arbres T en abscisse et de la méthode de calcul de f en ordonnée pour nos méthodes de sélection FIC et GARF concernant l'étude prédictive. La première ligne correspond à l'inverse de l'erreur de classification (1-RF err ) et la deuxième ligne à l', p.137

R. Résultats-de-la-classification-par, AUC RF et 1-RF err ) en fonction des différents nombres d'arbres T en abscisse et de la méthode de calcul de f en ordonnée pour nos méthodes de sélection FIC et GARF concernant l'étude pronostique. La première ligne correspond à l'inverse de l'erreur de classification (1-RF err ) et la deuxième ligne à l', p.138

. Courbes-de-survie-de-kaplan, Meier réalisées à partir des labels estimés obtenus après (a) la méthode de sélection FIC et (b) la méthode GARF, p.147

.. De-texture, 174 A.2 Illustration de la construction par étape d'une matrice de cooccurrence en fonction d'un couple ? = 0 et d = 1, A.1 Illustration 2D de la notion de couple distance, p.177

A. , S. , *. *. Mtv-tlg, and T. , er et 2 ème ordres) extraites d'un examen TEP initial au FDG chez des patients présentant un cancer du poumon non à petites cellules, Liste des tableaux 1.1 Études prédictives et pronostiques utilisant des statistiques classiques des caractéristiques images

+. Sp, . Fic, +. Sp, U. Garf-)-ainsi-que-le-test, and .. De-mann-whitney, ) des patients atteints d'un cancer de l'oesophage. Les courbes ROC ont été créées pour obtenir une sensibilité (Se), une spécificité (Sp), une AUC et les valeurs de seuil, Résultats de l'étude prédictive utilisant nos méthodes de sélection, p.152

F. , G. Sffs, H. , R. , and L. , Les moyennes et les écarts-types des indices de performances obtenus par validation sont indiqués. F sel est la taille des sous-ensembles de caractéristiques sélectionnées par les méthodes. En gras sont présentés les meilleurs résultats, Résultats des études prédictives et pronostiques utilisant plusieurs méthodes de sélection de caractéristiques, p.154

F. , G. Sffs, H. , R. , and L. , Les moyennes et les écarts-types des indices de performance obtenus par validation sont indiqués. F sel est la taille des sous-ensembles de caractéristiques sélectionnées par les méthodes, Résultats des études prédictives sans et avec différentes méthodes de sélection de caractéristiques, p.156

A. Réseaux-de-neurones-artificiels-ou, Artificial Neural Network, pp.87-89

C. Aide-aux-diagnostics-ou, Computed Aided Diagnosis, p.83

. Glnur, Gray Level Non-Uniformity, p.106

. Glnuz, Gray Level Non-Uniformity, p.197

. Lpocv, Leave-p-out Cross-Validation, p.77

O. Glossaire, Overall Survival" ou survie globale, p.150

C. Rc-réponse, Response Evaluation Criteria in Solid TumorsRELevance In Estimating Features, pp.84-86

R. Forêts and A. Ou, Random Forest, pp.87-91

. Rpr, Run Percentage, p.106

S. Bw, Standardized Uptake Value Body Weight, p.16

S. Séparateur-À-vaste-marge-ou, Support Vector Machine, pp.85-89