Site icon Wonderful Engineering

This New AI Tool Will Allow The Detection Of Lung Cancer A Year In Advance

Technology, when incorporated in medicine, has the wondrous effects of saving lives, which is the ultimate goal of breakthroughs in medicine. New technology in Artificial Intelligence (AI) is here for early signs of lung cancer detection. Scientists say that it can detect cancer one year earlier than the regular methods of cancer detection.

This breakthrough is brought forward by new research presented at the European Respiratory Society International Congress. Lung cancer has become the most common cause of death with the disease. It destroys approximately 1.8 million lives globally every year. However, the detection of lung cancer in the body is often observed very far in the cancer stages. This means that even when detected, it is at a stage where it cannot be treated or has very slim chances of getting cured.

This is why Artificial Intelligence (AI) has brought this method. The conventional computerized tomography (CT) scans can already reveal features of lung tumors, and a post-CT biopsy or surgery can confirm the malignancy of the tumor. But every scan employs an expert radiologist, who has to look through around 300 images for key signs of lung tumors, which can be very subtle, easy to miss, and tiny.

This study that is brought to the surface now uses AI assistance in diagnoses. This was presented by Researcher Benoît Audelan of the Epione project team, at Université Côte d’Azur’s Inrea, which is France’s National Institute for Research in Digital Science and Technology. Audelan worked on this technology with colleagues from their university, along with Therpixel, which is an AI-focused software company that emphasizes medical imaging. Other contributions were also made by officials at the University Hospital of Nice.

The AI program was trained by running on CT scans taken from 888 patients who were conventionally tested already. The technology was tested on 1179 patients. From a group of 177 patients who were already diagnosed, 172 were correctly detected to have cancer. This makes a 97% accuracy rate for the AI which is very impressive. This program would only assist radiologists and not take their place.

Exit mobile version