Show simple item record

dc.contributor.authorMenon, Sumeet
dc.contributor.authorMangalagiri, Jayalakshmi
dc.contributor.authorGalita, Josh
dc.contributor.authorMorris, Michael
dc.contributor.authorSaboury, Babak
dc.contributor.authorYesha, Yaacov
dc.contributor.authorYesha, Yelena
dc.contributor.authorNguyen, Phuong
dc.contributor.authorGangopadhyay, Aryya
dc.contributor.authorChapman, David
dcterms.creatorhttps://orcid.org/0000-0002-8632-6292en_US
dc.date.accessioned2022-09-22T16:26:53Z
dc.date.available2022-09-22T16:26:53Z
dc.date.issued2021-10-01
dc.description.abstractWe present a novel algorithm that is able to classify COVID-19 pneumonia from CT Scan slices using a very small sample of training images exhibiting COVID19 pneumonia in tandem with a larger number of normal images. This algorithm is able to achieve high classification accuracy using as few as 10 positive training slices (from 10 positive cases), which to the best of our knowledge is one order of magnitude fewer than the next closest published work at the time of writing. Deep learning with extremely small positive training volumes is a very difficult problem and has been an important topic during the COVID19 pandemic, because for quite some time it was difficult to obtain large volumes of COVID-19 positive images for training. Algorithms that can learn to screen for diseases using few examples are an important area of research. We present the Cycle Consistent Segmentation Generative Adversarial Network (CCS-GAN). CCS-GAN combines style transfer with pulmonary segmentation and relevant transfer learning from negative images in order to create a larger volume of synthetic positive images for the purposes of improving diagnostic classification performance. The performance of a VGG-19 classifier plus CCS-GAN was trained using a small sample of positive image slices ranging from at most 50 down to as few as 10 COVID-19 positive CT-scan images. CCS-GAN achieves high accuracy with few positive images and thereby greatly reduces the barrier of acquiring large training volumes in order to train a diagnostic classifier for COVID-19.en_US
dc.description.sponsorshipThis research was supported by NSF award titled RAPID: Deep Learning Models for Early Screening of COVID-19 using CT Images, award # 2027628. This work was also supported in part by the NSF IUCRC program as part of the Center for Advanced Real Time Analytics (CARTA) Research Experience for Undergraduates (REU).en_US
dc.description.urihttps://arxiv.org/abs/2110.01605en_US
dc.format.extent10 pagesen_US
dc.genrejournal articlesen_US
dc.genrepostprintsen_US
dc.identifierdoi:10.13016/m2n14i-dyan
dc.identifier.citation"Menon, Sumeet, et al. CCS-GAN: COVID-19 CT-scan classification with very few positive training images. IEEE TRANSACTIONS ON MEDICAL IMAGING. In Press. "en_US
dc.identifier.urihttps://doi.org/10.48550/arXiv.2110.01605
dc.identifier.urihttp://hdl.handle.net/11603/25790
dc.language.isoen_USen_US
dc.publisherIEEEen_US
dc.relation.isAvailableAtThe University of Maryland, Baltimore County (UMBC)
dc.relation.ispartofUMBC Computer Science and Electrical Engineering Department Collection
dc.relation.ispartofUMBC Information Systems Department
dc.relation.ispartofUMBC Faculty Collection
dc.relation.ispartofUMBC Student Collection
dc.rights© 2021 IEEE.  Personal use of this material is permitted.  Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.en_US
dc.titleCCS-GAN: COVID-19 CT-scan classification with very few positive training imagesen_US
dc.typeTexten_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record