Diagnostic Accuracy of Radiomics in the Early Detection of Pancreatic Cancer: A Systematic Review and Qualitative Assessment Using the Methodological Radiomics Score (METRICS)

Abstract

Pancreatic ductal adenocarcinoma is highly aggressive and usually deadly because is detected too late for effective treatment. Radiomics, a technique that uses patterns invisible to the human eye extracted from diagnostic imaging, could help identify early signs of this disease. The aim of this systematic review was to assess the application of radiomics to identify early indicators of pancreatic ductal adenocarcinoma. A review of ten studies explored how radiomics, particularly through CT, is being used to develop machine learning models to differentiate between healthy and cancerous pancreatic tissue. While promising, the studies showed mixed results due to heterogeneous findings and the methodological nature of the studies, highlighting the need for further research.