Dr. Dipali Shende,Parth Dange,Bhairavi Adchule,Unmesh Chaudhari,

Pancreatic cancer is one of the deadliest forms of cancer, with a low survival rate due to late diagnosis. Early detection and precise staging are crucial for improving treatment outcomes and patient survival. This paper presents a comprehensive review of a deep learning-based solution that integrates Convolutional Neural Networks (CNNs) for pancreatic tumor detection and cancer probability prediction. The proposed system leverages Endoscopic Ultrasound (EUS) imaging datasets to train a binary classification model for tumor detection and a multi-output model for predicting the probability of early-stage cancer progression. The system aims to assist healthcare providers in identifying high-risk patients, enabling timely intervention and personalized treatment planning.

https://doi.org/10.58357/jedcs.2025.v4.i1.5