Improving CT prediction of treatment response in patients with metastatic colorectal carcinoma using statistical learning theory

BackgroundSignificant interest exists in establishing radiologic imaging as a valid biomarker for assessing the response of cancer to a variety of treatments. To address this problem, we have chosen to study patients with metastatic colorectal carcinoma to learn whether statistical learning theory can improve the performance of radiologists using CT in predicting patient treatment response to therapy compared with the more traditional RECIST (Response Evaluation Criteria in Solid Tumors) standard.ResultsPredictions of survival after 8 months in 38 patients with metastatic colorectal carcinoma using the Support Vector Machine (SVM) technique improved 30% when using additional information compared to WHO (World Health Organization) or RECIST measurements alone. With both Logistic Regression (LR) and SVM, there was no significant difference in performance between WHO and RECIST. The SVM and LR techniques also demonstrated that one radiologist consistently outperformed another.ConclusionsThis preliminary research study has demonstrated that SLT algorithms, properly used in a clinical setting, have the potential to address questions and criticisms associated with both RECIST and WHO scoring methods. We also propose that tumor heterogeneity, shape, etc. obtained from CT and/or MRI scans be added to the SLT feature vector for processing.

[1]  L. Lesko,et al.  Use of biomarkers and surrogate endpoints in drug development and regulatory decision making: criteria, validation, strategies. , 2001, Annual review of pharmacology and toxicology.

[2]  S. Larson,et al.  The Progress and Promise of Molecular Imaging Probes in Oncologic Drug Development , 2005, Clinical Cancer Research.

[3]  James H Thrall,et al.  Biomarkers in imaging: realizing radiology's future. , 2003, Radiology.

[4]  Nello Cristianini,et al.  Kernel Methods for Pattern Analysis , 2003, ICTAI.

[5]  Daniel C Sullivan,et al.  Functional imaging in lung cancer. , 2005, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[6]  R. F. Wagner,et al.  Assessment methodologies and statistical issues for computer-aided diagnosis of lung nodules in computed tomography: contemporary research topics relevant to the lung image database consortium. , 2004, Academic radiology.

[7]  A. Miller,et al.  Reporting results of cancer treatment , 1981, Cancer.

[8]  N. Obuchowski How many observers are needed in clinical studies of medical imaging? , 2004, AJR. American journal of roentgenology.

[9]  A. Satterfield,et al.  TREATMENT , 1924, California and western medicine.

[10]  R. Brereton,et al.  Support vector machines for classification and regression. , 2010, The Analyst.

[11]  M. Okada,et al.  [New response evaluation criteria in solid tumours-revised RECIST guideline (version 1.1)]. , 2009, Gan to kagaku ryoho. Cancer & chemotherapy.

[12]  E. Boyko,et al.  The use of risk factors in medical diagnosis: opportunities and cautions. , 1990, Journal of clinical epidemiology.

[13]  A. Padhani,et al.  The RECIST criteria: implications for diagnostic radiologists , 2001 .

[14]  L. Schwartz,et al.  New response evaluation criteria in solid tumours: revised RECIST guideline (version 1.1). , 2009, European journal of cancer.

[15]  May,et al.  [Wiley Series in Probability and Statistics] Applied Survival Analysis (Regression Modeling of Time-to-Event Data) || Extensions of the Proportional Hazards Model , 2008 .

[16]  Wafik S El-Deiry,et al.  Imaging and oncologic drug development. , 2006, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[17]  W. Heindel,et al.  Volumetric measurements of pulmonary nodules at multi-row detector CT: in vivo reproducibility , 2003, European Radiology.

[18]  R. D. Hunter,et al.  WHO Handbook for Reporting Results of Cancer Treatment , 1980 .

[19]  V. Goh,et al.  Quantitative assessment of tissue perfusion using MDCT: comparison of colorectal cancer and skeletal muscle measurement reproducibility. , 2006, AJR. American journal of roentgenology.

[20]  L. Schwartz,et al.  Lung cancer: computerized quantification of tumor response--initial results. , 2006, Radiology.

[21]  Jack Y. Yang,et al.  New statistical learning theory paradigms adapted to breast cancer diagnosis/classification using image and non-image clinical data , 2008, Int. J. Funct. Informatics Pers. Medicine.

[22]  M. Pepe,et al.  Limitations of the odds ratio in gauging the performance of a diagnostic, prognostic, or screening marker. , 2004, American journal of epidemiology.

[23]  Richard Pazdur,et al.  End points and United States Food and Drug Administration approval of oncology drugs. , 2003, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[24]  T E Walsh,et al.  Reporting results. , 1969, Archives of otolaryngology.

[25]  E. Halpern,et al.  CT tumor measurement for therapeutic response assessment: comparison of unidimensional, bidimensional, and volumetric techniques initial observations. , 2002, Radiology.

[26]  Mark J. Ratain,et al.  Measuring response in a post-RECIST world: from black and white to shades of grey , 2006, Nature Reviews Cancer.

[27]  G. Chatellier,et al.  Pulmonary nodules: preliminary experience with three-dimensional evaluation. , 2004, Radiology.

[28]  Rabiya S Tuma,et al.  Sometimes size doesn't matter: reevaluating RECIST and tumor response rate endpoints. , 2006, Journal of the National Cancer Institute.

[29]  R. Munden,et al.  Imaging of the patient with non-small cell lung cancer. , 2005, Radiology.

[30]  L. Schwartz,et al.  Imaging response assessment in oncology , 2006, Cancer imaging : the official publication of the International Cancer Imaging Society.

[31]  S Saini,et al.  Tumour size measurement in an oncology clinical trial: comparison between off-site and on-site measurements. , 2003, Clinical radiology.

[32]  J E Husband,et al.  Evaluation of the response to treatment of solid tumours – a consensus statement of the International Cancer Imaging Society , 2004, British Journal of Cancer.

[33]  M. Christian,et al.  [New guidelines to evaluate the response to treatment in solid tumors]. , 2000, Bulletin du cancer.

[34]  James H Thrall,et al.  Using imaging biomarkers to accelerate drug development and clinical trials. , 2005, Drug discovery today.

[35]  C. Jaffe Measures of response: RECIST, WHO, and new alternatives. , 2006, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[36]  M. Rosen,et al.  Primer on imaging technologies for cancer. , 2006, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[37]  Bruce D Cheson,et al.  Progress and Promise of FDG-PET Imaging for Cancer Patient Management and Oncologic Drug Development , 2005, Clinical Cancer Research.

[38]  P. Therasse Erratum to ''Measuring the clinical response. What does it mean?'' (European Journal of Cancer, 38 (2002) 1817-1823) § , 2003 .

[39]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[40]  M. Christian,et al.  Measuring response in solid tumors: unidimensional versus bidimensional measurement. , 1999, Journal of the National Cancer Institute.

[41]  Dansheng Song,et al.  A kernelised fuzzy-Support Vector Machine CAD system for the diagnosis of lung cancer from tissue images , 2008, Int. J. Funct. Informatics Pers. Medicine.

[42]  Curtis P Langlotz,et al.  Automatic structuring of radiology reports: harbinger of a second information revolution in radiology. , 2002, Radiology.

[43]  Elizabeth A. Krupinski,et al.  Improving CT prediction of treatment response in patients with metastatic colorectal carcinoma using statistical learning , 2010, Int. J. Comput. Biol. Drug Des..

[44]  P. Therasse Measuring the clinical response. What does it mean? , 2001, European journal of cancer.

[45]  L. Washington,et al.  Inherent variability of CT lung nodule measurements in vivo using semiautomated volumetric measurements. , 2006, AJR. American journal of roentgenology.