• Hajmal Hasan A
• Mrs.S.Nithyabharathi

The primary method of preventing cancer is screening the transition zones. There are three types of cervical precancerous phases, and they can all progress to cancer. In order to determine whether a cervix is in a normal (healthy) or precancerous stage, it is imperative to carefully screen for cervical abnormalities and have a reliable method in place. When applied to biological challenges, such as medical image analysis, disease prediction, and picture segmentation, deep learning demonstrated remarkable potential. Therefore, very deep residual learning based networks are built for cervical cancer detection in this paper. Furthermore, we emphasize in this work the significance of the activation functions on the performance of a residual network (ResNet). As a result, three residual networks with various activation functions are constructed using the same topology. The models in use undergo training and testing on a collection of cervical colposcopy pictures. The latest advancements in deep learning for the segmentation and classification of cervical cytology pictures are then thoroughly reviewed. Lastly, we look into the best practices for the analysis of cervical cancer as well as the current approach. Deep convolutional neural networks (DCNNs) have demonstrated impressive results recently in a number of medical applications, including cancer detection and diagnosis, medical picture categorization, and medical image interpretation and comprehension [6]. Over time, these networks have experienced substantial enhancements and modifications. The primary focus of this upgrade was on depth and performance, and it was discovered that CNN performance varies in direct proportion to matching depth.

Cervical Cancer, ResNet, Colposcopy dataset.

"Enhancement of Cervical Cancer Diagnosis using ResNet-Based Deep Learning Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 1, page no.e148-e153, January-2024, Available :http://www.jetir.org/papers/JETIR2401418.pdf

"Enhancement of Cervical Cancer Diagnosis using ResNet-Based Deep Learning Models", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 1, page no. ppe148-e153, January-2024, Available at : http://www.jetir.org/papers/JETIR2401418.pdf