Abstract: Cervical cancer represents a significant global health challenge, particularly in underserved regions where access to conventional screening methodologies is limited. In this study, we investigated the efficacy of deep learning models, including Densenet 201, Vgg16, and Vgg19, trained on the International Agency for Research on Cancer (IARC) Colposcopy Image Bank dataset. The dataset was partitioned into training and validation subsets, and the performance of each model was evaluated on the validation data. Our findings reveal that Densenet201 exhibits superior validation accuracy compared to Vgg16 and Vgg19. The primary objective of this research is to develop a robust and accessible tool for early detection and intervention, with the ultimate aim of alleviating the burden of cervical cancer screening in resource-constrained settings.

Keywords: Colposcopy, Cervical cancer screening, Deep learning.

Cite:
Karthik Pai, Athmika C Jain, Chirag, Greeshma Jain, Maryjo M George*, "Cervical Abnormality Detection with Deep Learning Powered Colposcopy Analysis", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 3, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13332.


PDF | DOI: 10.17148/IJARCCE.2024.13332

Open chat
Chat with IJARCCE