Combinatorial Biomarkers for Malignant Polyps and Colon Cancer Detection

ABSTRACT Technological advancements in colonoscopic and polypectomy procedures have drastically reduced both the incidence and overall mortality due to colorectal cancerCRCHowevereven with the availability of multiple screening toolsonlyof CRC are diagnosed at early stagein part due to lack of compliance with follow up colonoscopy procedurelimited access to colonoscopyThese factors contribute to inappropriate surveillance follow up as well as development of `interval cancerandaposwithinyears of a completely negative colonoscopyHistological characteristic of polypectized polypshigh risk vslow riskis among major criterion for follow up surveillance colonoscopyGiven that current surveillance recommendations depend on the histologic type of the polypthe underdiagnoses of these premalignant precursors often leads to inappropriate follow up care and therapythus contributing to CRCOur initial screening has identified that a combination of markers i eMUCMUC AC and CAthat accurately differentiate benign hyperplastic polypHPfrom pre malignant sessile serrated adenoma polypSSA Pand tubular adenomaTABased on preliminary studies and the identified gaps in diagnosiswe hypothesize that this newly identified marker panel of MUCMUC AC and CAcan accurately classify the major colorectal polyp subtypesand in conjunction with machine learning tools can provide an economical product for improved patient stratification for better surveillance and prevention of CRCTo meet these milestonestwo specific aims are proposedaimis designed to evaluate the potential of MUCMUC AC and CAfor effective stratification of benign from malignant polypsThe major milestones for this aim is the development of a MUCMUC ACand CAimmunostaining kit and to evaluate the potential of the combination for differentiating HPSSA P and TA in highly suspicious cases with documented inter observer variability amongst pathologistsFurtheraimfocuses on the development of polyp differentiation deep learning computational program based upon histologytissue markersMUCMUC AC and CApolyp sizenumberand locationthe most critical parameters for deciding the interval of surveillance colonoscopyfor accurate surveillance of CRC by colonoscopyThe major milestone is to develop and evaluate the colon cancer polyp stratification algorithm in an independent patient setOverallthe present phase I SBIR application seeks to advance the CRC field by simplifying and improving CRC precursor classificationthus improving the ease of polyp classification which can facilitate better recommendations for follow up surveillance colonoscopyThis should in turn further reduce the healthcare burden by improving patient adherence for CRC managementto reduce deaths from CRCAltogetherresults from Phasewill lead to validation in a multi center trial and validation in a clinical settingCLIA labduring phase II to form the basis to seek FDA approval of this test for use in hospital testing to provide accurate classification of premalignant polyps PROJECT NARRATIVE With onlyof patient diagnosed at an early stagecolorectal cancerCRCis the second leading cause of cancer related deathsThe present PhaseSBIR study aims to harness the diagnostic potential of a combination of biomarkersclinical characteristic of polyps and CRC as well as machine learning approaches for accurate distinction of malignant polyp tissues from benign for improving CRC detection and surveillance