Algorithm to quantify nuclear features and confidence intervals for classification of oral neoplasia from high-resolution optical images

Simple item page
dc.citation.articleNumber54502en_US
dc.citation.issueNumber5en_US
dc.citation.journalTitleJournal of Medical Imagingen_US
dc.citation.volumeNumber7en_US
dc.contributor.authorYang, Eric C.en_US
dc.contributor.authorBrenes, David R.en_US
dc.contributor.authorVohra, Imran S.en_US
dc.contributor.authorSchwarz, Richard A.en_US
dc.contributor.authorWilliams, Michelle D.en_US
dc.contributor.authorVigneswaran, Nadarajahen_US
dc.contributor.authorGillenwater, Ann M.en_US
dc.contributor.authorRichards-Kortum, Rebecca R.en_US
dc.contributor.orgBioengineeringen_US
dc.date.accessioned2020-12-16T19:47:14Zen_US
dc.date.available2020-12-16T19:47:14Zen_US
dc.date.issued2020en_US
dc.description.abstractPurpose:In vivo optical imaging technologies like high-resolution microendoscopy (HRME) can image nuclei of the oral epithelium. In principle, automated algorithms can then calculate nuclear features to distinguish neoplastic from benign tissue. However, images frequently contain regions without visible nuclei, due to biological and technical factors, decreasing the data available to and accuracy of image analysis algorithms. Approach: We developed the nuclear density-confidence interval (ND-CI) algorithm to determine if an HRME image contains sufficient nuclei for classification, or if a better image is required. The algorithm uses a convolutional neural network to exclude image regions without visible nuclei. Then the remaining regions are used to estimate a confidence interval (CI) for the number of abnormal nuclei per mm2, a feature used by a previously developed algorithm (called the ND algorithm), to classify images as benign or neoplastic. The range of the CI determines whether the ND-CI algorithm can classify an image with confidence, and if so, the predicted category. The ND and ND-CI algorithm were compared by calculating their positive predictive value (PPV) and negative predictive value (NPV) on 82 oral biopsies with histopathologically confirmed diagnoses. Results: After excluding the images that could not be classified with confidence, the ND-CI algorithm had higher PPV (65% versus 59%) and NPV (78% versus 75%) than the ND algorithm. Conclusions: The ND-CI algorithm could improve the real-time classification of HRME images of the oral epithelium by informing the user if an improved image is required for diagnosis.en_US
dc.identifier.citationYang, Eric C., Brenes, David R., Vohra, Imran S., et al.. "Algorithm to quantify nuclear features and confidence intervals for classification of oral neoplasia from high-resolution optical images." <i>Journal of Medical Imaging,</i> 7, no. 5 (2020) SPIE: https://doi.org/10.1117/1.JMI.7.5.054502.en_US
dc.identifier.digital054502_1en_US
dc.identifier.doihttps://doi.org/10.1117/1.JMI.7.5.054502en_US
dc.identifier.urihttps://hdl.handle.net/1911/109719en_US
dc.language.isoengen_US
dc.publisherSPIEen_US
dc.rightsPublished by SPIE under a Creative Commons Attribution 4.0 Unported License. Distribution or reproduction of this work in whole or in part requires full attribution of the original publication, including its DOI.en_US
dc.rights.urihttps://creativecommons.org/licenses/by/4.0/en_US
dc.titleAlgorithm to quantify nuclear features and confidence intervals for classification of oral neoplasia from high-resolution optical imagesen_US
dc.typeJournal articleen_US
dc.type.dcmiTexten_US
dc.type.publicationpublisher versionen_US
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
054502_1.pdf
Size:
2.77 MB
Format:
Adobe Portable Document Format
Download
Collections
Faculty Publications