artificial intelligence can detect the first signs of the disease

⁇ [VIDÉO] You may also like this partner content (after the ad)

Pancreatic cancer is still one of the most difficult to treat. In fact, the diagnosis of pancreatic duct adenocarcinoma is delayed by the absence of specific diagnostic symptoms and biomarkers. Developed by Cedars-Sinai researchers, an artificial intelligence tool was trained with CT images taken months or even years before the diagnosis of pancreatic cancer. Thus, he was able to predict with 86% accuracy which people would develop cancer based on the appearance of the images.

Pancreatic duct adenocarcinoma is a malignant tumor that accounts for more than 90% of pancreatic cancer cases. Currently the fourth leading cause of cancer death, less than 10% of patients live more than five years after being diagnosed or starting treatment. However, it is possible to increase the survival rate by up to 50% when the diagnosis is early and when complete removal of the tumor is possible, according to recent studies.

The main problem is that there is no easy way to detect pancreatic duct adenocarcinoma in an early stage, as the disease is asymptomatic at onset. Therefore, 80% of patients are already in an advanced stage of cancer when diagnosed.

Early diagnosis of pancreatic duct adenocarcinoma is very rare

Although people with this type of cancer may experience unexplained abdominal pain or weight loss, these symptoms do not alert them to the onset of cancer, as they are common in other diseases. ” No single symptoms for early diagnosis of pancreatic duct adenocarcinoma Stephen J. Pandol, director of basic and translational research on the pancreas at Cedars-Sinai Medical Center (Los Angeles) and co-author of the study, said in a press release.

Most patients with digestive disorders undergo an abdominal CT scan where a radiologist’s evaluation considers them “negative,” although some of these patients eventually develop pancreatic cancer. American researchers write. In fact, it is very difficult to identify “naked eye” pancreatic abnormalities in these images. ” Artificial intelligence is the first choice to carry out the modeling of the prediction of various cancers “, the authors add.

AI training can detect the first signs of cancer

By reviewing patients’ electronic medical records, the team selected 36 people who met the criteria they were looking for: having been diagnosed with pancreatic duct adenocarcinoma in the last 15 years and having a computed tomography (or CT scan). computed) with the “negative” result six months to three years before diagnosis (prediagnosis). CT images of 36 people who did not develop cancer were also used as a control.

Data design proposed for the study, with three types of abdominal CT scan: Health Control, Prediagnosis and Diagnosis. Prediagnostic and diagnostic scans were obtained from the same patient. © Pandol, Li et al (2022)

The artificial intelligence (AI) tool developed by the researchers was trained to detect variations in the surface of the pancreas in pre-diagnostic CT images, compared to control images. The researchers used Bayes’ naive sorting algorithm to automatically classify CT scan images according to the probability of cancer occurrence, knowing that they were especially targeted at high risk. In the end, the tool achieved an average rating accuracy of 86% across the data set.

This AI tool was able to capture and quantify very subtle early signs of pancreatic duct adenocarcinoma in CT scans, years before the onset of the disease. “welcomes Debiao Li, a professor of biomedical and image sciences at Cedars-Sinai and lead author of the study.

On the other hand, researchers regret the small amount of data, due to the fact that pre-diagnostic scans are rarely available. They hope that the AI ​​will reduce the time for diagnosis and thus promote the complete removal of the tumor through surgery. With these encouraging results, they are now working to replicate the model in a larger amount of data, in order to validate it.

Source: Biomarkers of cancer

Leave a Comment