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

Persistent Link:
http://hdl.handle.net/10150/610011
Title:
Improving CT prediction of treatment response in patients with metastatic colorectal carcinoma using statistical learning theory
Author:
Land, Walker; Margolis, Dan; Gottlieb, Ronald; Krupinski, Elizabeth; Yang, Jack
Affiliation:
Department 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
Issue Date:
2010
Publisher:
BioMed Central
Citation:
Land et al. BMC Genomics 2010, 11(Suppl 3):S15 http://www.biomedcentral.com/1471-2164/11/S3/S15
Journal:
BMC Genomics
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 Information:
This 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 repository@u.library.arizona.edu.
Abstract:
BACKGROUND: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.
EISSN:
1471-2164
DOI:
10.1186/1471-2164-11-S3-S15
Version:
Final published version
Additional Links:
http://www.biomedcentral.com/1471-2164/11/S3/S15

Full metadata record

DC FieldValue Language
dc.contributor.authorLand, Walkeren
dc.contributor.authorMargolis, Danen
dc.contributor.authorGottlieb, Ronalden
dc.contributor.authorKrupinski, Elizabethen
dc.contributor.authorYang, Jacken
dc.date.accessioned2016-05-20T08:56:25Z-
dc.date.available2016-05-20T08:56:25Z-
dc.date.issued2010en
dc.identifier.citationLand et al. BMC Genomics 2010, 11(Suppl 3):S15 http://www.biomedcentral.com/1471-2164/11/S3/S15en
dc.identifier.doi10.1186/1471-2164-11-S3-S15en
dc.identifier.urihttp://hdl.handle.net/10150/610011-
dc.description.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.en
dc.language.isoenen
dc.publisherBioMed Centralen
dc.relation.urlhttp://www.biomedcentral.com/1471-2164/11/S3/S15en
dc.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)en
dc.titleImproving CT prediction of treatment response in patients with metastatic colorectal carcinoma using statistical learning theoryen
dc.typeArticleen
dc.identifier.eissn1471-2164en
dc.contributor.departmentDepartment of Bioengineering, Binghamton University, Binghamton, NY, 13903-6000, USAen
dc.contributor.departmentDepartment of Radiology, University of Arizona, Tucson, AZ 85724, USAen
dc.contributor.departmentCenter for Research in Biological Systems, University of California at San Diego, La Jolla, California 92093-0043 USAen
dc.contributor.departmentDepartment of Radiation Oncology, Massachusetts General Hospital Cancer Center and Harvard Medical School, Boston, Massachusetts 02114 USAen
dc.identifier.journalBMC Genomicsen
dc.description.collectioninformationThis 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 repository@u.library.arizona.edu.en
dc.eprint.versionFinal published versionen
All Items in UA Campus Repository are protected by copyright, with all rights reserved, unless otherwise indicated.