Talpur, Dhani Bux and Rang, Ali Raza and Khowaja, Ashfaque and Shah, Asadullah (2024) DeepCervixNet: an advanced deep learning approach for cervical cancer classification in Pap smear images. VAWKUM Transactions on Computer Sciences, 12 (1). pp. 136-148. ISSN 2411-6335 E-ISSN 2308-8168
|
PDF
- Published Version
Download (4MB) | Preview |
Abstract
Cervical cancer is among the leading causes of female mortality, emphasizing the significance of early detection and treatment to prevent its spread. While Pap smear images are widely used for cervical cancer screening, the manual diagnostic method is timeconsuming and prone to error. The research article introduces DeepCervixNet, an innovative automated computerized approach designed for detecting cervical cancer in Pap smear images. In this study, we enhance ResNet101 and DenseNet169, state-of-the-art Convolutional Neural Network (CNN) architectures, by integrating the sequence and excitation (SE) blocks. Subsequently, Ensemble learning is employed to utilize the extracted features and classify the final output. The Harlev dataset was employed to test our model, with Gaussian smoothing and median filtering applied for image enhancement. This resulted in an overall improvement in the performance of the model. DeepCervixNet had an accuracy of 99.89% in cervical cells. The study’s findings validate our model’s robustness and efficacy, proving its superiority over a majority of current state-of-the-art models used to classify cervical cells, including standard ResNet and DenseNet architectures without SE blocks
| Item Type: | Article (Journal) |
|---|---|
| Uncontrolled Keywords: | Cervical Cancer, Deep Learning, CNN, DenseNet, ResNet, Ensemble Learning |
| Subjects: | T Technology > T Technology (General) > T10.5 Communication of technical information T Technology > T Technology (General) > T11.95 Industrial directories |
| Kulliyyahs/Centres/Divisions/Institutes (Can select more than one option. Press CONTROL button): | Kulliyyah of Information and Communication Technology > Department of Information System Kulliyyah of Information and Communication Technology > Department of Information System |
| Depositing User: | Prof Asadullah Shah |
| Date Deposited: | 13 Feb 2025 16:08 |
| Last Modified: | 13 Feb 2025 16:08 |
| URI: | http://irep.iium.edu.my/id/eprint/119348 |
Actions (login required)
 |
View Item |
Download Statistics
Download Statistics