Voice box cancer care trial uses AI

TOP medics in Newcastle are using AI to help tackle a form of cancer which can cost patients their voice or potentially their life.

Amar Rajgor - an ear, nose and throat specialist who works at Newcastle University and the Newcastle Hospitals NHS Trust - has been leading a team doing first-ofits-kind research into using artificial intelligence to improve treatment of laryngeal cancer, which affects someone’s voice box.

The idea is to use AI to analyse the images created by CT scans.

High-tech software looks at the images “pixel by pixel” to consider patterns in a tumour that can’t be seen by the naked eye. This can work as a “virtual biopsy”, experts said.

Mr Rajgor, an ear, nose and throat specialist, said: “Radiomics can be seen as a superpowered magnifying glass for medical images, like CT scans.

“It carefully examines every tiny detail, even the ones that are hard to see. By doing this, it can find patterns and irregularities that cannot be seen by a human or might otherwise be missed.”

The results can find “markers” which indicate whether a patient may be likely to die sooner due to the disease. Around 2,400 new cases of Laryngeal cancer are diagnosed each year - with half of those affected living less than three years.

Mr Rajgor’s research - published in the Journal of Laryngology & Otology - has found that looking at some of these patterns can be a better indicator for a patient’s future prognosis than traditional measures such as how old or at what stage the cancer is at.

Mr Rajgor added: “These developments are very exciting, as this research could play a big role in guiding treatment and delivering precision medicine in the future.

“It could ensure that patients get the right treatment for them, based on what their tumour looks like and how it behaves.

“I hope this will also help patients make more informed decisions about their treatment journey.

“Another positive is that this method does not change the patient pathway but enhances it, by analysing medical images in a way that cannot be done by a human.

He said the technique could “revolutionise” treatment for the cancer.