2023-11-21 00:10:26
All types of cancer cause around 10 million deaths annually on the planet.
A new algorithm makes it possible to identify this tumor when it is imperceptible to the eye to offer a healing alternative to patients.
40% of small pancreatic cancer cases elude detection by CT scans.
He pancreatic cancer It remains one of the deadliest on the planet. One of the main reasons is because most cases are identified in advanced stages. When this occurs, the chances of cure are lower and that is why the most important part, in addition to prevention, is timely detection.
Why is pancreatic cancer so difficult to identify?
To date, it is estimated that 70 percent of patients die within a year after diagnosis. Unfortunately, 40 percent of cases of small pancreatic cancer They evade detection by computed tomography (CT) scans until they have advanced to a stage where they are incurable.
This creates a critical late-stage barrier to early detection measures. In most patients, including high-risk people undergoing screening, imaging detects the tumor at a stage where a cure is unlikely.
New advances against pancreatic cancer
In a recent advance, researchers at Mayo Clinic Comprehensive Cancer Center used the world’s most extensive image data set to develop a Artificial Intelligence (AI) model versatile that has demonstrated the potential for autonomous detection of pancreatic cancer on standard CT when surgical intervention may still promise a cure.
“This is where the study emerges as a ray of hope. It addresses the late-stage challenge: detecting cancer at a stage where it is even beyond the reach of experts,” says Ajit H. Goenka, MD, a Mayo Clinic radiologist.
The group developed a high-precision AI model, trained on the largest (3,000+ patients) and most diverse CT data set, for fully automated cancer detection, including small and difficult-to-detect tumors.
The work was published in Gastroenterologythe magazine of the American Gastroenterological Association. The study not only builds on the group’s recent work on radiomics-based early detection models, but also underscores Mayo Clinic’s position as a model of innovation in AI healthcare solutions.
Most importantly, the model could detect visually invisible cancer in normal-appearing pancreas from pre-diagnostic CT images (i.e., those obtained between three and 36 months before clinical diagnosis) at a considerably early stage. (a median of 438 days) before clinical diagnosis.
“These findings suggest that AI has the potential to detect cases of occult cancer in asymptomatic people, allowing surgical treatment at a stage when a cure is still possible.”
Finally, the model remained reliable and accurate across diverse patient groups and variations in scanning equipment and imaging techniques. This resilience is crucial to the model’s usefulness in a wide range of real-world medical scenarios.
Also read:
This IMSS hospital is a pioneer in pancreas, heart and kidney transplants
Pancreatic cancer, one of the deadliest due to its difficulty in detecting it
Celebrities diagnosed with pancreatic cancer: From businessmen to singers
#Pancreatic #cancer #detected