LAPSE:2020.0903
Published Article
LAPSE:2020.0903
MobileNetV2 Ensemble for Cervical Precancerous Lesions Classification
Cătălin Buiu, Vlad-Rareş Dănăilă, Cristina Nicoleta Răduţă
July 17, 2020
Women’s cancers remain a major challenge for many health systems. Between 1991 and 2017, the death rate for all major cancers fell continuously in the United States, excluding uterine cervix and uterine corpus cancers. Together with HPV (Human Papillomavirus) testing and cytology, colposcopy has played a central role in cervical cancer screening. This medical procedure allows physicians to view the cervix at a magnification of up to 10%. This paper presents an automated colposcopy image analysis framework for the classification of precancerous and cancerous lesions of the uterine cervix. This framework is based on an ensemble of MobileNetV2 networks. Our experimental results show that this method achieves accuracies of 83.33% and 91.66% on the four-class and binary classification tasks, respectively. These results are promising for the future use of automatic classification methods based on deep learning as tools to support medical doctors.
Keywords
biomedical image processing, cervical cancer, computer-aided diagnosis, deep learning, ensemble, machine learning algorithms, MobileNetV2, transfer learning
Suggested Citation
Buiu C, Dănăilă VR, Răduţă CN. MobileNetV2 Ensemble for Cervical Precancerous Lesions Classification. (2020). LAPSE:2020.0903
Author Affiliations
Buiu C: Department of Automatic Control and Systems Engineering, Politehnica University of Bucharest, 060042 Bucharest, Romania [ORCID]
Dănăilă VR: Department of Automatic Control and Systems Engineering, Politehnica University of Bucharest, 060042 Bucharest, Romania [ORCID]
Răduţă CN: Sf. Ioan Clinical Emergency Hospital, Bucur Maternity, 042122 Bucharest, Romania
Journal Name
Processes
Volume
8
Issue
5
Article Number
E595
Year
2020
Publication Date
2020-05-16
Published Version
ISSN
2227-9717
Version Comments
Original Submission
Other Meta
PII: pr8050595, Publication Type: Journal Article
Record Map
Published Article

LAPSE:2020.0903
This Record
External Link

doi:10.3390/pr8050595
Publisher Version
Download
Files
[Download 1v1.pdf] (892 kB)
Jul 17, 2020
License
CC BY 4.0
Meta
Record Statistics
Record Views
537
Version History
[v1] (Original Submission)
Jul 17, 2020
 
Verified by curator on
Jul 17, 2020
This Version Number
v1
Citations
Most Recent
This Version
URL Here
https://psecommunity.org/LAPSE:2020.0903
 
Original Submitter
Calvin Tsay
Links to Related Works
Directly Related to This Work
Publisher Version