Year: 2025
Type: article
Abstract: Pancreatic cancer is one of the most lethal malignancies, often diagnosed at advanced stages due to lack of early symptoms and reliable screening methods.Early detection and accurate classification are critical to improve survival rates.Traditional approaches using biomarkers and imaging modalities suffer from poor sensitivity and limited predictive power.To address these challenges, this work presents a deep learning-based framework for pancreatic cancer classification using Convolutional Neural Networks (CNN), Random Forest (RF), and Naïve Bayes classifiers.The CNN model is applied for automatic feature extraction from CT images, while RF and Naïve Bayes enhance classification accuracy and interpretability.Experimental evaluation on benchmark datasets demonstrates high accuracy in distinguishing normal and cancerous cases.The proposed system integrates imaging and numerical data, providing a robust and scalable solution for real-time clinical decision support.
Language: English
Topic: AI in cancer detection
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: hybrid
OpenAlex ID: W4413879804