Pancreatic ductal adenocarcinoma (PDAC) is not only the most common form of pancreatic cancer, but it is also the most lethal. However, early-stage diagnosis is challenging because there are no specific diagnostic biomarkers.
This study used electronic medical records from 36 PDAC patients diagnosed with cancer in the past 15 years who underwent CT scans six months to three years before their diagnosis. These CT images were considered normal at the time they were taken.
The AI tool was trained to analyze these prediagnostic CT images and compare them to CT images of 36 people who had not developed cancer. The researchers reported that the model identified, with 86% accuracy, the people who were eventually diagnosed with pancreatic cancer and those who were not.
The AI model detected differences on the surface of the pancreas between people with cancer and healthy controls. These texture differences could be the result of molecular changes that occur when pancreatic cancer develops.
Accordingly, the method could enable early detection of PDAC, giving more people the opportunity to have their tumor completely removed by surgery.
Predicting pancreatic ductal adenocarcinoma using artificial intelligence analysis of pre-diagnostic computed tomography images
The IE from MS no longer understands current scripting languages, the latest main version (version 11) is from 2013 and has not been further developed since 2015.
Our recommendation: Use only the latest versions of modern browsers, for example Google Chrome, Mozilla Firefox or Microsofrt Edge, because only this guarantees you sufficient protection against infections and the correct display of websites!