<![CDATA[Cervical cancer ranks among the top causes of cancer-related deaths in women globally. Early detection is vital for improving patient survival rates. The multiclass classification of cervical cell images presents challenges primarily due to the notable variations in cell sizes across different classes. Conventional AI methods for diagnosing cervical cancer often rely on image-resizing techniques that overlook crucial features like relative cell dimensions, which impairs the models' ability to distinguish between classes effectively. This paper presents a novel AI-driven approach that employs constant padding to maintain the natural size differences among cells. Our method utilizes deep learning for both feature extraction and multiclass classification. We assessed the method using the publicly accessible SIPaKMeD dataset. Experimental findings indicate that our approach surpasses traditional image-resizing methods, especially in classes that are more challenging to predict. This strategy highlights AI's potential to improve cervical cancer diagnosis, offering a more precise and dependable tool for early detection. A reliable and precise AI model for diagnosing cervical cancer is crucial for promoting widespread screening and ensuring timely and effective treatment, which can ultimately lower mortality rates. By aiding early and accurate diagnosis, this approach aligns with global health efforts to alleviate the burden of cancer and other diseases, especially in areas with limited access to advanced healthcare services facilities.]]>
Copyrights © 2025
