A Force For Good? Latest AI Development Could Help Cancer Diagnosis 

The global public is stuck in a tumultuous debate over the rapid developments in artificial intelligence (AI): is this a force for good, or will it drag us to an apocalyptic end? There’s credence to both sides. But researchers at Cardiff University have made a breakthrough that, if successful, will certainly back the former.

Researchers at Cardiff University have developed an AI system that may help doctors to detect cancer. The system is aimed at supporting radiologists’ decision-making, head researcher at the university Hantao Liu explained. 

If successful, Mr Liu’s system may help improve the accuracy of medical diagnostics and lead to earlier breast cancer detection. 

The AI Solution To Cancer Diagnosis 

Mr Liu reads computer science and informatics at Cardiff University. He and his team have been working alongside radiologists in NHS hospitals across England and Wales to develop a system that may help the medical diagnosis of cancer. 

“We want to develop the systems radiologists can work with and trust,” Mr Liu explained. 

Mr Liu’s team is working on a system that can record the eye movement of a radiologist reading medical images. This data is then fed into an AI system to learn the gaze of a radiologist. 

After training, the system will be able to identify on a scan the regions where radiologists are most likely to look when preparing a diagnosis, Mr Liu said.

Impacting The Medical Scene: A “Phenomenal” Breakthrough

In a post-Covid landscape, the NHS is under more pressure than ever before to deal with waiting lists. Consequently, scientists are turning to AI answers to medical questions

“With all of the challenges facing the NHS, it is important that we look to data science and AI for possible solutions,” Mr Liu said.

Mr Liu is just one of the many supporters of the increased involvement of AI in the medical scene. Judi Rhys, chief executive of cancer charity Tenovus, also agrees that despite AI having “something of a bad name”, we ought to welcome it into research. 

“Its [AI’s] potential use in diagnosing cancers early is phenomenal,” she said.

“It’s not about replacing the radiologists but it is about making them able to be much more responsive,” Ms Rhys added.

The AI system currently being produced by Mr Liu and his team will help to spot particularly worrying scans, helping radiologists’ diagnosis to become quicker and more effective. This more responsive technique will help get the people that need help most accelerated through the system. 

In regards to Mr Liu’s system, Ms Rhys stressed how this will ease NHS waiting queues, particularly because of how remarkably accurate studies are showing the technology to be.

“The other thing about artificial intelligence is it doesn’t actually need a break. It can get through a phenomenal number of scans and support the radiologists therefore to tackle the ‘sticky’ ones,” she said.

Whilst it is still important to look at the workforce, she said, especially given the 30% shortage of radiology consultants across the UK, “tools like this can really help them and support them in their work and that’s got to be a good thing for patients,” Ms Rhys finished.

Cancer charity Tenovus has called the potential of this AI system in diagnosing cancers early a “phenomenal” development. And this isn’t the only area of medical research where AI is in development to ease NHS pressures. 

Elsewhere In The NHS

Elsewhere, a new type of AI technology that cuts the time cancer patients must wait before starting radiotherapy is soon to be offered at cost price to all NHS trusts in England.

The technology will help doctors to calculate where to direct the therapeutic radiation beams, to kill cancerous cells while sparing as many healthy ones as possible.

To put its response into perspective: for each NHS patient, doctors typically spend between 25 minutes and two hours working through about 100 scan cross-sections, carefully “contouring” or outlining bones and organs. This AI program works two and a half times quicker. 

Indeed, this year, the government has been investing in AI projects all across the NHS. 

AI technology has the capability to speed up the diagnostic process, help doctors to catch diseases earlier and give patients the best possible chance of recovery. 

In order to deal with the current strain on its workforce and resources, it seems that the NHS will need to depend both on highly trained and skilled professionals as well as AI despite personal opinions regarding the technology.