Adam Pine cone optimization with Deep learning for cervical cancer detection using pap smear image
V T Ram Pavan Kumar, P.L. Ramesh, M Arulselvi · 2024
Cervical cancer is the main reason of mortality in females worldwide. The Human Papillomavirus (HPV) is the major reasonfor cervical cancer in female patients. The virus first infects cells in the cervix of female patients and spreads throughout the cervix. This cancer is curable if diagnosed early and treated on time. Here, this paper presents an innovative method based on Deep Learning (DL) for detecting cervical cancer. Initially, the input pap smear image is considered as inputand is forwarded to the preprocessing step in which the noise contained in the pap smear image is eradicated utilizing an adaptive bilateral filter. Next, Utilizing a Mask Regional Convolutional Neural Network (Mask-RCNN) the affected region is segmented and shape features are mined from the segmented image. Then, cervical cancer detection is effectuated by exploiting the Deep Maxout Network (DMN) model, which is structurally optimizedbythe designed Adam Pine Cone Optimization Algorithm (APCOA). Furthermore, the performance of APCOA_DMN is assessed using several metrics and it obtained anaccuracyof $\mathrm{9 1. 2 8 4 \%}$, a True Negative Rate (TNR) of $91.315 \%$, and a True Positive Rate (TPR) of $\mathrm{9 1. 9 7 9 \%}$.