AI ‘can accurately spot cancer’: Algorithm better at spotting cancerous nodules than other methods

New AI ‘can accurately spot cancer’: Algorithm is better at identifying cancerous nodules than existing methods, study claims

  • The tool can tell if abnormal growths found on CT scans are cancerous
  • The algorithm performs more efficiently and effectively than current methods

A new artificial intelligence tool can accurately identify cancer in a development that doctors and scientists said could speed up diagnosis of the disease.

The algorithm performs more effectively than current methods, according to a study.

It can identify whether abnormal growths found on CT scans are cancerous.

The AI ​​tool, designed by experts from the Royal Marsden NHS Foundation Trust, the Institute of Cancer Research, London and Imperial College London, could guide patients to treatment faster.

Cancer causes about 10 million deaths each year — nearly one in six deaths worldwide, according to the World Health Organization.

A new artificial intelligence tool can accurately identify cancer in a development that doctors and scientists said could speed up diagnosis of the disease. [File image]

Dr. Benjamin Hunter, a clinical oncology registrar at the Royal Marsden, said: ‘We hope that in the future it will improve early detection and potentially make cancer treatment more successful by highlighting patients at risk and getting them to intervene more quickly .’

The team used CT scans of about 500 patients with large lung nodules to develop an AI algorithm using radiomics, according to a report from The protector.

The technique can extract important information from medical images that cannot be easily spotted by the human eye.

The model was then tested to determine whether it could accurately identify cancerous nodules.

The study used a measure called area under the curve (AUC) to see how effective the model was at anticipating cancer.

The algorithm performs more efficiently and effectively than current methods, according to a study. [File image]

The algorithm performs more efficiently and effectively than current methods, according to a study. [File image]

According to The Guardian, an AUC of 1 indicates a perfect model, while 0.5 would be expected if the model is guessing at random.

The results showed that the AI ​​model was able to recognize the cancer risk of each nodule with an AUC of 0.87. Performance improved on the Brock score, a test used in the clinic, which scored 0.67.

“Through this work, we hope to push boundaries to accelerate the detection of the disease using innovative technologies such as AI,” said the Libra study’s principal investigator, Dr. Richard Lee.

It comes after AI developed a treatment for an aggressive cancer in just 30 days and showed it can predict a patient’s chance of survival using doctor’s notes.

The breakthroughs were achieved by separate systems, but show how the use of the powerful technology goes far beyond image and text generation.

Researchers at the University of Toronto teamed up with Insilico Medicine to develop a potential treatment for hepatocellular carcinoma (HCC) using an AI drug discovery platform called Pharma.

HCC is a form of liver cancer, but the AI ​​discovered a previously unknown treatment route and designed a “new hit molecule” that could bind to that target.