AI System can diagnose lung cancer up to a year earlier

A new artificial intelligence (AI System) project developed by scientists in France can detect early signs of lung cancer on chest scans even a year before the disease can be diagnosed with existing methods to date.

Lung cancer is the most common cause of cancer death worldwide with approximately 1.8 million deaths each year. It is often diagnosed at an advanced stage, when the possibility of effective treatment is limited. Scientists hope that the use of “smart” medical technology will make the diagnosis faster, thus increasing the chances of treating the disease.

Read more: Experimental mRNA vaccine for HIV by Moderna

Today’s computed tomography detects traces of cancer in the lungs and is followed by a biopsy or surgery to confirm that the tumor is malignant. However, it is not always easy for the radiologist or other doctor who “reads” the imaging tests to “catch” the very small traces of cancer.

Researchers from the National Institute for Research in Digital Science and Technology (Inria) of the University of the Côte d’Azur, the University Hospital of Nice and the software company Therapixel, led by Benoit Odelan, who made the relevant announcement at the international conference of the European Society of Pulmonology, trained an artificial intelligence algorithm, feeding it with scans of 888 patients who had already done imaging tests for a suspect th tumors.

The system was then tested on 1,179 patients who had done lung scans in the last two years, including 177 who had already been diagnosed through a biopsy with lung cancer. The artificial intelligence program identified 172 of the 177 cancers (97% accuracy). The five tumors he “lost” were located in the center of the breast, where it is more difficult to distinguish a cancer from the healthy parts of the body.

Moreover, the researchers, who were also funded by the French government, tested the system on scans that had been done a year before the tumors were diagnosed and confirmed through a biopsy in the same 1,179 patients and managed to detect 152 suspicious areas, which were later diagnosed as cancerous tumors. On the other hand, so far the program detects many suspicious areas that are not cancer (false positive diagnoses), so it will need improvement before it is used clinically, so as not to lead to unnecessary biopsies.

“Screening for lung cancer means that there are many more scans to be done, but we don’t have enough radiologists to analyze all these tests. That is why we need to develop computer programs, which can help us. Our study shows that this program is able to find possible traces of lung cancer up to a year earlier. Our goal is not to replace radiologists, but to help them by giving them a tool that can identify the earliest traces of lung cancer,” said Odelan.

source: ΑΠΕ-ΜΠΕ

Spread the love

Leave a Reply

Your email address will not be published. Required fields are marked *