A comparative study of 3 deep learning models for Pap smear screening

Simple item page
dc.contributor.authorPromworn, Yuttachon
dc.contributor.authorPintavirooj, C.
dc.contributor.authorPiyawattanametha, Wibool
dc.date.accessioned2026-08-06T10:23:56Z
dc.date.available2026-08-06T10:23:56Z
dc.date.issued2019-01-10
dc.description.abstractThis work presents a comparative study of automated screening procedure for Pap smear with deep learning technology. Three convolution neural network models (AlexNet, densenet161 and resnet101) were employed for detecting the presence of cervical precancerous or cancerous cells from Pap smear database. The study compares accuracy, sensitivity, specificity, and computation time for each deep learning model. The best model is the densenet161 due to its high sensitivity and accuracy which are key factors in an automated Pap smear screening procedure to offer the best early detection of cervical cancer to better treatment outcomes.
dc.identifier.citationBmeicon 2018 11th Biomedical Engineering International Conference, 2019
dc.identifier.doi10.1109/BMEiCON.2018.8609945
dc.identifier.other2-s2.0-85062056796
dc.identifier.urihttps://dspace.kmitl.ac.th/handle/123456789/9697
dc.sourceBmeicon 2018 11th Biomedical Engineering International Conference
dc.subjectAlexNet
dc.subjectCervical cancer
dc.subjectDeep learning
dc.subjectDensenet161
dc.subjectPap smear
dc.subjectResnet101
dc.titleA comparative study of 3 deep learning models for Pap smear screening
dc.typeConference Paper

Files

Collections

Research