MRI Texture Analysis Predicts p53 Status in Head and Neck Squamous Cell Carcinoma

BACKGROUND AND PURPOSE: Head and neck cancer is common, and understanding the prognosis is an important part of patient management. In addition to the Tumor, Node, Metastasis staging system, tumor biomarkers are becoming more useful in understanding prognosis and directing treatment. We assessed whether MR imaging texture analysis would correctly classify oropharyngeal squamous cell carcinoma according to p53 status. MATERIALS AND METHODS: A cohort of 16 patients with oropharyngeal squamous cell carcinoma was prospectively evaluated by using standard clinical, histopathologic, and imaging techniques. Tumors were stained for p53 and scored by an anatomic pathologist. Regions of interest on MR imaging were selected by a neuroradiologist and then analyzed by using our 2D fast time-frequency transform tool. The quantified textures were assessed by using the subset-size forward-selection algorithm in the Waikato Environment for Knowledge Analysis. Features found to be significant were used to create a statistical model to predict p53 status. The model was tested by using a Bayesian network classifier with 10-fold stratified cross-validation. RESULTS: Feature selection identified 7 significant texture variables that were used in a predictive model. The resulting model predicted p53 status with 81.3% accuracy (P < .05). Cross-validation showed a moderate level of agreement (κ = 0.625). CONCLUSIONS: This study shows that MR imaging texture analysis correctly predicts p53 status in oropharyngeal squamous cell carcinoma with ∼80% accuracy. As our knowledge of and dependence on tumor biomarkers expand, MR imaging texture analysis warrants further study in oropharyngeal squamous cell carcinoma and other head and neck tumors.

[1]  E. Sturgis,et al.  Human papillomavirus as a marker of the natural history and response to therapy of head and neck squamous cell carcinoma. , 2012, Seminars in radiation oncology.

[2]  Thierry Soussi,et al.  Assessing TP53 status in human tumours to evaluate clinical outcome , 2001, Nature Reviews Cancer.

[3]  P. Parizel,et al.  Accuracy of MRI in characterization of soft tissue tumors and tumor-like lesions. A prospective study in 548 patients , 2004, European Radiology.

[4]  Eibe Frank,et al.  Large-scale attribute selection using wrappers , 2009, 2009 IEEE Symposium on Computational Intelligence and Data Mining.

[5]  Qiang Li,et al.  P53 and vascular endothelial growth factor expressions are two important indices for prognosis in gastric carcinoma. , 2008, The West Indian medical journal.

[6]  Ying Pan,et al.  Towards MIB-1 and p53 detection in glioma magnetic resonance image: a novel computational image analysis method. , 2012, Physics in medicine and biology.

[7]  D. Lane,et al.  The p53 tumour suppressor gene , 1998, The British journal of surgery.

[8]  N. Jović,et al.  p53 mutations and human papillomavirus infection in oral squamous cell carcinomas: correlation with overall survival. , 2005, Journal of cranio-maxillo-facial surgery : official publication of the European Association for Cranio-Maxillo-Facial Surgery.

[9]  K. Hörmann,et al.  Vascular Endothelial Growth Factor Expression Correlates with p53 Mutation and Angiogenesis in Squamous Cell Carcinoma of the Head and Neck , 2000, Acta oto-laryngologica.

[10]  Y. Shimada,et al.  In oesophageal squamous cell carcinoma vascular endothelial growth factor is associated with p53 mutation, advanced stage and poor prognosis. , 1998, British Journal of Cancer.

[11]  Yunyan Zhang,et al.  MRI Texture Analysis in Multiple Sclerosis , 2011, Int. J. Biomed. Imaging.

[12]  Sylvia Drabycz,et al.  Predicting MGMT Methylation Status of Glioblastomas from MRI Texture , 2009, MICCAI.

[13]  D. Lane,et al.  p53, guardian of the genome , 1992, Nature.

[14]  Ian H. Witten,et al.  Data mining in bioinformatics using Weka , 2004, Bioinform..

[15]  D. Lane,et al.  Cancer. p53, guardian of the genome. , 1992, Nature.

[16]  Joseph Ross Mitchell,et al.  Approach for fast time-frequency analysis , 2014, IET Signal Process..

[17]  B. Vogelstein.  A deadly inheritance , 1990, Nature.

[18]  C. Chung,et al.  New promising molecular targets in head and neck squamous cell carcinoma , 2012, Current opinion in oncology.

[19]  B. Vogelstein,et al.  p53 mutations in human cancers. , 1991, Science.

[20]  A. Jemal,et al.  Global cancer statistics , 2011, CA: a cancer journal for clinicians.

[21]  S. Edge.  AJCC Cancer Staging Handbook: From the AJCC Cancer Staging Manual , 2002 .

[22]  Chunshui Yu,et al.  3D texture analysis on MRI images of Alzheimer’s disease , 2011, Brain Imaging and Behavior.

[23]  Peter Gibbs,et al.  Texture analysis in assessment and prediction of chemotherapy response in breast cancer , 2013, Journal of magnetic resonance imaging : JMRI.

[24]  Estevam R. Hruschka,et al.  Bayesian networks for imputation in classification problems , 2007, Journal of Intelligent Information Systems.

[25]  Grégoire Toussaint,et al.  Three dimensional texture analysis in MRI: a preliminary evaluation in gliomas. , 2003, Magnetic resonance imaging.

[26]  David Heckerman,et al.  Bayesian Networks for Data Mining , 2004, Data Mining and Knowledge Discovery.

[27]  Huan Yu,et al.  Coregistered FDG PET/CT-Based Textural Characterization of Head and Neck Cancer for Radiation Treatment Planning , 2009, IEEE Transactions on Medical Imaging.

[28]  Sylvia Drabycz,et al.  Image Texture Characterization Using the Discrete Orthonormal S-Transform , 2008, Journal of Digital Imaging.

[29]  A. D. De Schepper,et al.  Magnetic resonance imaging of soft tissue tumors , 2000, European Radiology.

[30]  B. Vogelstein.  Cancer. A deadly inheritance. , 1990, Nature.

[31]  K. Ang,et al.  TP53 Disruptive Mutations Lead to Head and Neck Cancer Treatment Failure through Inhibition of Radiation-Induced Senescence , 2011, Clinical Cancer Research.

[32]  Chien-Chang Ho,et al.  ADHD classification by a texture analysis of anatomical brain MRI data , 2012, Front. Syst. Neurosci..

[33]  J. Manola,et al.  TP53 mutations and survival in squamous-cell carcinoma of the head and neck. , 2007, The New England journal of medicine.

[34]  J. Ferlay,et al.  Global Cancer Statistics, 2002 , 2005, CA: a cancer journal for clinicians.

[35]  L. Miroslaw,et al.  Towards rapid cervical cancer diagnosis: automated detection and classification of pathologic cells in phase-contrast images , 2006, International Journal of Gynecologic Cancer.

[36]  B Weyn,et al.  Automated breast tumor diagnosis and grading based on wavelet chromatin texture description. , 1998, Cytometry.

[37]  A. Levine,et al.  The 1993 Walter Hubert Lecture: the role of the p53 tumour-suppressor gene in tumorigenesis. , 1994, British Journal of Cancer.

[38]  L. Turek,et al.  Association between p53 and Human Papillomavirus in Head and Neck Cancer Survival , 2008, Cancer Epidemiology Biomarkers & Prevention.

[39]  M. Sundaram,et al.  Magnetic resonance imaging of soft tissue masses: an evaluation of fifty-three histologically proven tumors. , 1988, Magnetic resonance imaging.

[40]  Maria Grazia Bruzzone,et al.  Methylation of O6-Methylguanine DNA Methyltransferase and Loss of Heterozygosity on 19q and/or 17p Are Overlapping Features of Secondary Glioblastomas with Prolonged Survival , 2007, Clinical Cancer Research.

[41]  S. Nemec,et al.  Texture‐based and diffusion‐weighted discrimination of parotid gland lesions on MR images at 3.0 Tesla , 2013, NMR in biomedicine.

[42]  F. Greene,et al.  AJCC cancer staging handbook : from the AJCC cancer staging manual , 2002 .

[43]  M. Kransdorf,et al.  Radiologic evaluation of soft-tissue masses: a current perspective. , 2000, AJR. American journal of roentgenology.

[44]  D. Demetrick,et al.  The Use of Magnetic Resonance Imaging to Noninvasively Detect Genetic Signatures in Oligodendroglioma , 2008, Clinical Cancer Research.

[45]  Siegfried Trattnig,et al.  Texture‐based classification of focal liver lesions on MRI at 3.0 Tesla: A feasibility study in cysts and hemangiomas , 2010, Journal of magnetic resonance imaging : JMRI.

[46]  A. Jemal,et al.  Global Cancer Statistics , 2011 .

[47]  Zhengrong Liang,et al.  Characterization of texture features of bladder carcinoma and the bladder wall on MRI: initial experience. , 2013, Academic radiology.