New AI tool can help identify lung cancer accurately: study

Over the years, the AI sector has grown by leaps and bounds. Thanks to advancements in artificial intelligence (AI) and machine learning, modern automated machines are inching closer to matching the capabilities of humans.

AI has several applications in a number of fields, including healthcare and education. It is being used to address several issues related to disease detection. To address one such concern, researchers in the UK have developed an AI tool that can predict whether an abnormal growth in the body is cancerous or not.

The tool has been developed by experts at the Royal Marsden NHS Foundation Trust, the Institute of Cancer Research, London, and Imperial College London.

The findings of the study named, OCTAPUS-AI, have been published in the Lancet's eBioMedicine journal and claims that it will be able to hasten cancer diagnosis.

The researchers used 900 CT scans of people with large lung nodules to develop the algorithm that helps the AI tool make predictions related to cancerous growths in the body.

They used a technique called radiomics, an image analysis technology that can be used to detect information not spotted by the human eye. The study tried to understand and analyse if AI could help identify the risk of cancer returning in non-small cell lung cancer (NSCLC) patients.

It found that the AI model was able to identify each nodule's risk of cancer. "According to these initial results, our model appears to identify cancerous large lung nodules accurately," said Dr. Benjamin Hunter, a clinical oncology registrar at the Royal Marsden and a clinical research fellow at Imperial.

Hunter added that the researchers now plan to test the technology on patients with large lung nodules. However, the experts added that the current study is still at an early stage and more tests need to be conducted if we wish to use the technology in the future.

"In the future, we hope it will improve early detection and potentially make cancer treatment more successful by highlighting high-risk patients and fast-tracking them to earlier intervention," he added.

This is not the first time that AI tools are being developed for cancer diagnosis. Several studies are being conducted across various institutions to find out how AI can help reduce the world's disease burden.

NHS Trusts is conducting a similar study called Colo-Detect for early bowel cancer diagnosis. In fact, a woman who was part of the study, has now been declared cancer free. The woman's life was saved all thanks to the AI tech used for her cancer diagnosis.

It was able to detect an area of cancer in her body following a colonoscopy last year and the doctors then decided to conducted a surgery based on its outcomes. "I always say yes to these research projects because I know that they can make things a lot better for everybody," the woman, named Jean Tyler, told BBC. She was one of the 2,000 patients from 10 NHS trusts that were recruited for the trial.

Professor Colin Rees who led the study believes that AI is likely to become "a major tool used by medicine in the coming years." The trials in the study are still underway and it remains to be seen if doctors will be able to use it for early cancer diagnosis anytime soon.

According to NHS, Lung cancer is one of the most common and serious types of cancer and affects more than 43,000 people in the UK every year. It mainly affects older people and is rare in people younger than 40.

A report by Cancer Research UK says, every two minutes someone in the UK is diagnosed with cancer. Between 2016 and 2018, breast, prostate, lung and bowel cancers account for over half (53%) of all new cancer cases reported in the country. Bowel cancer claims around 16,800 lives a year in the UK.