Date of Publication :15th January 2025

Abstract: Pancreatic cancer, particularly pancreatic ductal adenocarcinoma (PDAC), is among the deadliest cancers due to its asymptomatic early stages, often leading to late diagnoses and poor prognoses. Traditional di agnostic methods, including computed tomography (CT) and endoscopic ultrasound (EUS), frequently fail to detect the disease at an early stage, resulting in delaye d interventions. Recent advancements in machine learning (ML) and deep learning (DL) technique s, notably convolutional neural networks (CNNs) and object detection models like You Only Look Once (YOLO), are significantly enhancing tumor detection and the simulation of tumor growth. This review aims to explore these advanced AI strategies in medical imaging diagnostics, emphasizing their potential to identify early-stage pancreatic cancer and predict tumor progression. Additionally, it examines innovative imaging techniques, emerging biomarkers, and liquid biopsy technologies, along with mathematical models for assessing cancer risk. By integrating these tools, the review underscores the potential for improved screening and treatment approaches that can enhance patient outcomes.

Reference :