Improving CT prediction of treatment response in patients with metastatic colorectal carcinoma using statistical learning theory
AffiliationDepartment of Bioengineering, Binghamton University, Binghamton, NY, 13903-6000, USA
Department of Radiology, University of Arizona, Tucson, AZ 85724, USA
Center for Research in Biological Systems, University of California at San Diego, La Jolla, California 92093-0043 USA
Department of Radiation Oncology, Massachusetts General Hospital Cancer Center and Harvard Medical School, Boston, Massachusetts 02114 USA
MetadataShow full item record
CitationLand et al. BMC Genomics 2010, 11(Suppl 3):S15 http://www.biomedcentral.com/1471-2164/11/S3/S15
Rights© 2010 Land et al; licensee BioMed Central Ltd. This is an open access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/2.0)
Collection InformationThis item is part of the UA Faculty Publications collection. For more information this item or other items in the UA Campus Repository, contact the University of Arizona Libraries at email@example.com.
AbstractBACKGROUND:Significant 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.RESULTS:Predictions 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.CONCLUSIONS:This 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.
VersionFinal published version