
Right now, the NHS breast cancer screening programme saves around 1,300 lives in the UK each year.
But there are severe NHS staff shortages, particularly in the teams that help diagnose cancer, with some reports suggesting that up to 1 in 10 diagnostic posts are currently vacant. Throw in rising demand to the mix , and the future of these services could be in trouble.
But new technology could help ease the situation. We’ve partnered with Google Health on research to develop artificial intelligence that not only has the potential to change the way we detect breast cancer but could also save the NHS time and money.
Helping to train a computer
Our scientists have created a database of anonymised breast cancer scans (mammograms) that have come from breast screening appointments at a number of NHS breast screening centres around the UK, to be used for research.
Containing over 2.5 million images, this database is the largest and most dynamic of its kind in the world. And it’s available for academic and commercial partners to use, if they have a smart and scientifically sound research proposal that will benefit patients. But before they get access, their proposal is scrutinized by a group of experts, including people affected by cancer.
That’s where Google Health comes in. Five years ago, Google and researchers from Imperial College London approached our team with a belief that a fancy computer programme could be developed and trained to spot cancer on mammograms.
“Basically, they were trying to teach a machine to read images and it takes an awful lot of images for it to learn so it can get really good at picking up cancer,” says Helen, a member of the group Independent Cancer Patients’ Voice, that brings together patient advocates to help with medical research. She reviewed Google Health’s application to access the database.
Computers with AI capabilities are only as good as the data they’ve been trained on, so for her, our mammogram collection and Google’s technology prowess were a winning combination.
Results from this mighty research collaboration, published in Nature, show that the learning paid off. The AI software was able to correctly identify cancers in screening images with a similar degree of accuracy as the experts. The computer programme also reduced the number of errors, including cases where cancer is flagged incorrectly or those that are missed altogether.
Currently, 2 experts review breast screening scans. But the system isn’t perfect, as screening can miss some cancers and pick up ones that wouldn’t have gone on to cause problems.
“It now looks from this research that having the combination of a human eye and a machine eye over the images could actually give more accurate results,” says Helen. She is referring to the study’s finding that AI reduced false positive results. These are ‘false alarms’ that can occur when someone gets an abnormal result, but they don’t have cancer.
“That will reduce loads of anxiety for women,” says Helen, who was diagnosed with breast cancer in 2004 and finished reconstruction surgery in 2014. It will also save the NHS time and money by reducing the number of patients who are called back for further tests.
Artificial intelligence in a real scenario
Professor Ken Young works for the NHS and manages our mammogram collection. He and his colleagues helped Google Health analyse the data and design the trial to make it the most realistic AI study in breast cancer detection to date.
“What I think is most interesting about this study is its realism,” says Young. “What’s unusual is that it compares the algorithm to a totally realistic clinical scenario.”
Past studies have used specially selected mammograms that were analysed in a somewhat artificial setting. For example, some other programmes have been tested on a set of images that have more cancer cases than would be found in the general population.
But in the latest study, researchers compared real decisions made by radiologists analysing the scans of people attending the NHS breast screening programme.
“We have a sample that is representative of all the women that might come through breast screening,” says Young. “It includes easy cases, difficult cases and everything in between.”
And thanks to this collaboration, the data set is even richer than it was before. Around 100,000 more normal cases have been added to the database, which are now available to other researchers using the scan collection.
Giving the gift of time
NHS staff could also benefit from the partnership. A recent review suggested that this kind of tech will give radiologists ‘the gift of time’, instead of replacing them.
“All the radiologists I know aren’t worried about AI at all,” says Young. “I think they’d be delighted to have some of the quite monotonous work of reading mammograms done for them, so they’re freed up to do other things.”
Keeping patient data safe
The other concern when it comes to developing AI software is data protection, something that Young, Helen and the team have carefully thought through.
“One of the concerns that comes through is patient confidentiality,” says Helen, who has taken part in trials herself. “It’s very important that I sit there on the lay side to make certain that everything is anonymised, and the ethics are checked.”
Before images enter the database, they’re immediately de-identified so there is no way that a researcher can find out who the mammograms belong to. The scans don’t include any personal information, which is “stripped out before we add the image to the database and share it with researchers,” says Young.
And research groups who are granted access to the images also have to agree to certain conditions, like keeping the patient data confidential and not using it for any other purpose than the development of AI screening algorithms.
AI still has a lot to learn
This well-trained algorithm is still in its early stages, but now has a firm foundation of knowledge to build on. Next the team need to test on a wider population and to see how radiologists can benefit from using the algorithm in the clinic.
“I genuinely think the potential here is enormous,” says Young. “Breast cancer screening has a number of problems that could be tackled by the introduction of artificial intelligence.”
“These early studies using AI are the beginning of something quite big that will revolutionise medicine, this is just one of the first examples.”
Gabi
Comments
Kim Hogan May 6, 2020
If it helps with getting a better results
I had a lump and thought it was because I had lost weight then put a bit back on I had lost a lot of breast with weight loss but was called for a routine mammogram after the test come back clear I just thought it was fat so thought nothing about it. But when the lump seem to be still there I thought it best to go to the doctors to get it checked out and it was cancer so if I’d had the test done by computer maybe It would have picked it up
Gloria ortiz April 4, 2020
Bery good. God bless
Tracey Hicks April 3, 2020
Our mum died at 58 so I have done the race for life several times, so as long as it’s done properly I’m all for it
Jill Sykes April 3, 2020
Very informative – good
Sharon Hall March 16, 2020
Good
Irene Coyle March 7, 2020
I did race for life life last year with my sister & friend. Have done for many yrs off and on .but last got no letter saying thanks for support .my 2 sisters have had lung cancer 1 survived.my dad mum cousin have also passed to this disease
I found amount I’d raised in a spam folder .which caused me a lot of annoyance.as you can imagine. My sister and friend received no contact as well .l know in scheme of things this
All sounds pretty.but my work friends had also donated to help make target
So I’m dissatisfied. Sorry for rant
Sharyn Tulloch March 4, 2020
If this method of screening proves useful and sucessful in saving the lives of more women, then I strongly support the research and its findings. Lets hope for government funding to continue to pilot this work.
Dave Richards March 3, 2020
I think what your planning /doing is superb. However I am a pensioner and already pay out a monthly sum to Hospice. That along with grand children leaves little to take on further tasks. First class, I also agree it’s a way forward. Keep going. Dave
Heather Appleyard March 3, 2020
I think this will benefit a lot of people and to save life’s will be amazing
Ari Aziz March 2, 2020
Great news
Maureen George March 2, 2020
I’m 73 now and have had cancer twice. Bowel and thyroid. I’m fit as a flea. And I intend to live a very long time 👍
Taiwo Ogunbiyi March 2, 2020
This will improve quality of life. Also will save lives. My Husband died of Brain Cancer and this happened very fast. Over 3 y ears. and I can never get over it
Natasha Morey March 2, 2020
How old u got be to be tested for breast cancer cause my fiance got stage 3 lung cancer tumour on his lung
Susan Barrett March 2, 2020
Think it sounds a really good idea hopefully it won’t be to long before it’s in operation having been through this 5 years ago anything that can free staff to do more important work is brilliant they do an amazing job
Cherie March 2, 2020
Sounds fantastic spotting things early saves lives as we know do good luck with technology if you need volunteers I think a lot of people would offer their breast to help you test x
Harvi March 2, 2020
Great news , it will save life lives.
I have lost 2 friends , and have another one suffering from cancer .
Amazing work by CRUK
Kay Harcourt March 2, 2020
Brilliant news as any help to early detection can only be positive
Carole Gammans March 2, 2020
Great anything that can help amazing
Kay Silvester March 2, 2020
I think Ai will be amazing. As long as all the rules and regulations are abided by and aĺ info kept secure.
Linda A Holland March 2, 2020
If this computer truly helps to aid human diagnostic then it could be good. I have just had my mammogram and is reported as normal.
Janet heath March 2, 2020
Great news we needed more accurate results
You’re doing a great job
Saf March 2, 2020
I think it’s absolutly amazing the intelligence to do this and I hope everyone dealing with cancer carry’s on trying and pushing because everything is possible and this will be possible
Jean Bender March 2, 2020
Good work ,keep it up.
Jean March 2, 2020
Keep it up !!
Jenny Fray June 3, 2020
That’s amazing. I am having surgery tomorrow for Ductal Carcinoma In Situ picked up at routine screening. Fabulous news that this can be caught at the right time.