Ninepoint Medical, Inc. — Department of Health and Human Services SBIR Phase I: 102

Description

ABSTRACT The goal of this project is to develop a based computer aided diagnosisCADalgorithm for identification of regions at risk for developing esophageal adenocarcinomaEACin optical coherence tomographyOCTscans of the esophagusEAC is one of the deadliest cancers with ayear survival rate of less thanyet the standard of care for detecting precursors to EAC is widely recognized to be inadequateJust recentlya study found thatof patients who underwent a standard endoscopic surveillance exam which was found to beclearthen went on and progressed to EAC within one yearClearly today s approach is not working and a significant percentage of disease is being missedWhile comprehensive esophageal OCT imaging has shown great potential in addressing this unmet clinical needone of the main limiters to wider adoption and impact of this technology is the challenge of interpreting the large volume of high resolution images in real timeA CAD algorithm would allow OCT to realize its promise in this field and significantly improve the standard of careHere we propose the development of a deep learning CAD algorithm which will operate on a full patient level volumetric dataset with awareness of the anatomyrobust against image quality and motion artifactsand trained and validated against a large datasetandgtpatientsWe will aim to reach a sensitivity and specificity ofbased on a threshold set by the American Society for GastroenterologyASGEfor the performance of advanced imaging in the detection of high grade dysplasia in BE PROJECT NARRATIVE The goal of this project is to develop a computer aided diagnosisCADalgorithm for use with the NinePoint Medical OCT imaging system and provide early detection of pre cancerous lesionsEarlier detection leads to earlier treatmentmore positive health outcomes for patients and lower healthcare system costs