#ArtificialIntelligence could help to spot breast cancer

Mammogram images

(Images: The CRUK-funded OPTIMAM database)

A computer algorithm has been shown to be as effective as human radiologists in spotting breast cancer from x-ray images.

The international team behind the study, which includes researchers from Google Health, DeepMind, Imperial College London, the NHS and Northwestern University in the US, designed and trained an artificial intelligence (AI) model on mammography images from almost 29,000 women.

The findings, published today in Nature, show the AI was able to correctly identify cancers from the images with a similar degree of accuracy to expert radiologists, and holds the potential to assist clinical staff in practice.

When tested on a large UK dataset as part of the Cancer Research UK-funded OPTIMAM project* and a smaller US dataset from Northwestern University**, the AI also reduced the proportion of screening errors – where cancer was either incorrectly identified or where it may have been missed.

Screening programmes remain one of the best tools at our disposal for catching cancer early and improving outcomes for patients, but many challenges remain – not least the current volume of images radiologists must review. Lord Ara DarziImperial College London

According to the researchers, the work demonstrates how the AI could potentially be applied in clinical settings around the world.

The team highlights that such AI tools could support clinical decision-making in the future as well as alleviate the pressure on healthcare systems internationally by supporting the workload of clinical reviewers.

Dominic King, UK Lead at Google Health, said:

“Our team is really proud of these research findings, which suggest that we are on our way to developing a tool that can help clinicians spot breast cancer with greater accuracy. Further testing, clinical validation and regulatory approvals are required before this could start making a difference for patients, but we’re committed to working with our partners towards this goal.”

Professor the Lord Ara Darzi of Denham, one of the authors of the paper and director of the Cancer Research UK Imperial Centre and the Institute of Global Health Innovation at Imperial College London, said:

“Screening programmes remain one of the best tools at our disposal for catching cancer early and improving outcomes for patients, but many challenges remain – not least the current volume of images radiologists must review.

“While these findings are not directly from the clinic, they are very encouraging, and they offer clear insights into how this valuable technology could be used in real life.

“There will of course a number of challenges to address before AI could be implemented in mammography screening programmes around the world, but the potential for improving healthcare and helping patients is enormous.”

REDUCING FALSE FINDINGS

In the UK, it’s estimated that one in eight women will be diagnosed with breast cancer in their lifetime, with the risk increasing with age. Early detection and treatment provide the best outcome for women, but accurately detecting and diagnosing breast cancer remains a significant challenge.

Women aged between 50 and 71 are invited to receive a mammogram on the NHS every three years, where an x-ray of the breast tissue is used to look for abnormal growths or changes which may be cancerous. While screening is highly effective and the majority of cancers are picked up during the process, even with significant clinical expertise human interpretation of the x-rays is open to errors.***

 

The findings showed the AI was able to correctly identify cancers from images with a similar degree of accuracy to expert radiologists, and has the potential to support decision making and workload of clinical staff. 

 

In the latest study, researchers at Google Health trained an AI model on depersonalised patient data – using mammograms from women in the UK and US where any information that could be used to identify them was removed.

The AI model reviewed tens of thousands of images, which had been previously interpreted by expert radiologists. But while the human experts had access to the patient’s history when interpreting scans, the AI had only the most recent mammogram to go on.

During the evaluation, the researchers found their AI model could predict breast cancer from scans with a similar level of accuracy overall to expert radiographers (or were shown to be ‘non-inferior’). Compared to human interpretation, the AI showed an absolute reduction in the proportion of cases where cancer was incorrectly identified (5.7%/1.2% in the UK and US data respectively), as well as cases where cancer was missed (9.4%/2.7% in UK/US data).

INCREASING EFFICIENCY

Beyond the AI model’s potential to support and improve clinical decision-making, the researchers also looked to see if their model could improve reader efficiency. While the AI did not surpass the double-reader benchmark, statistically it performed no worse than the second reader.

In a small secondary analysis, they simulated the AI’s role in the double-reading process – used by the NHS. In this process, scans are interpreted by two separate radiologists, each of whom would review the scan and recommend a follow up or no action. Any positive finding is referred for biopsy and in cases where the two readers disagree, the case goes to a third clinical reviewer for decision.

The simulation compared the AI’s decision with that of the first reader. Scans were only sent to a second reviewer if there was a disagreement between the first reader and the AI. The findings showed that using the AI in this way could reduce the workload of the second reviewer by as much as 88%, which could ultimately help to triage patients in a shorter timeframe.

According to the team, the findings are exciting and show how AI could assist healthcare screening services around the world. One such practical application could include providing automatic real-time feedback on mammography images, awarding a statistical score which could be used to triage suspected cases more quickly.

However, the researchers add that further testing in larger populations is required.

Michelle Mitchell, Cancer Research UK’s chief executive, said:

“These results highlight the significant role that AI could play in the future of cancer care. Embracing technology like this may help improve the way we diagnose cancer in the years to come.

“Screening helps diagnose breast cancer at an early stage, when treatment is more likely to be successful, ensuring more people survive the disease. But it also has harms such as diagnosing cancers that would never have gone on to cause any problems and missing some cancers.

"This is still early stage research, but it shows how AI could improve breast cancer screening and ease pressure off the NHS. And while further clinical studies are needed to see how and if this technology could work in practice, the initial results are promising.”

‘International evaluation of an artificial intelligence system to identify breast cancer in screening mammography’ by Scott Mayer McKinney et al. is published in Nature.

*The UK dataset included mammograms from 25,856 women screened on the NHS at three NHS hospital trusts as part of the Cancer Research UK-funded OPTIMAM project. Data were depersonalised, which included medical history and notes but removing any information which could be used to identify an individual.

**The US dataset captured mammograms from 3097 women at the Northwestern Medicine.

***According to a 2011 review of the national breast cancer screening programme in the UK, the service resulted in thousands of cases of overdiagnosis and false positives every year. A false positive result is where the initial scan incorrectly identifies cancer but the patient is later cleared. Overdiagnosis resulted in unnecessary treatment for cancer – including biopsy and breast tissue removal. The report suggested there may be as many as 7,000 unnecessary breast cancer diagnoses in the UK each year.

You may also be interested in these articles:

Register, Login or Login with your Social Media account:


Advertisers

Upcoming FE Events

Advertiser Skyscrapers

Latest Education News

Further Education News

The FE News Channel gives you the latest education news and updates on emerging education strategies and the #FutureofEducation and the #FutureofWork.

Providing trustworthy and positive Further Education news and views since 2003, we are a digital news channel with a mixture of written word articles, podcasts and videos. Our specialisation is providing you with a mixture of the latest education news, our stance is always positive, sector building and sharing different perspectives and views from thought leaders, to provide you with a think tank of new ideas and solutions to bring the education sector together and come up with new innovative solutions and ideas.

FE News publish exclusive peer to peer thought leadership articles from our feature writers, as well as user generated content across our network of over 3000 Newsrooms, offering multiple sources of the latest education news across the Education and Employability sectors.

FE News also broadcast live events, podcasts with leading experts and thought leaders, webinars, video interviews and Further Education news bulletins so you receive the latest developments in Skills News and across the Apprenticeship, Further Education and Employability sectors.

Every week FE News has over 200 articles and new pieces of content per week. We are a news channel providing the latest Further Education News, giving insight from multiple sources on the latest education policy developments, latest strategies, through to our thought leaders who provide blue sky thinking strategy, best practice and innovation to help look into the future developments for education and the future of work.

In May 2020, FE News had over 120,000 unique visitors according to Google Analytics and over 200 new pieces of news content every week, from thought leadership articles, to the latest education news via written word, podcasts, video to press releases from across the sector.

We thought it would be helpful to explain how we tier our latest education news content and how you can get involved and understand how you can read the latest daily Further Education news and how we structure our FE Week of content:

Main Features

Our main features are exclusive and are thought leadership articles and blue sky thinking with experts writing peer to peer news articles about the future of education and the future of work. The focus is solution led thought leadership, sharing best practice, innovation and emerging strategy. These are often articles about the future of education and the future of work, they often then create future education news articles. We limit our main features to a maximum of 20 per week, as they are often about new concepts and new thought processes. Our main features are also exclusive articles responding to the latest education news, maybe an insight from an expert into a policy announcement or response to an education think tank report or a white paper.

FE Voices

FE Voices was originally set up as a section on FE News to give a voice back to the sector. As we now have over 3,000 newsrooms and contributors, FE Voices are usually thought leadership articles, they don’t necessarily have to be exclusive, but usually are, they are slightly shorter than Main Features. FE Voices can include more mixed media with the Further Education News articles, such as embedded podcasts and videos. Our sector response articles asking for different comments and opinions to education policy announcements or responding to a report of white paper are usually held in the FE Voices section. If we have a live podcast in an evening or a radio show such as SkillsWorldLive radio show, the next morning we place the FE podcast recording in the FE Voices section.

Sector News

In sector news we have a blend of content from Press Releases, education resources, reports, education research, white papers from a range of contributors. We have a lot of positive education news articles from colleges, awarding organisations and Apprenticeship Training Providers, press releases from DfE to Think Tanks giving the overview of a report, through to helpful resources to help you with delivering education strategies to your learners and students.

Podcasts

We have a range of education podcasts on FE News, from hour long full production FE podcasts such as SkillsWorldLive in conjunction with the Federation of Awarding Bodies, to weekly podcasts from experts and thought leaders, providing advice and guidance to leaders. FE News also record podcasts at conferences and events, giving you one on one podcasts with education and skills experts on the latest strategies and developments.

We have over 150 education podcasts on FE News, ranging from EdTech podcasts with experts discussing Education 4.0 and how technology is complimenting and transforming education, to podcasts with experts discussing education research, the future of work, how to develop skills systems for jobs of the future to interviews with the Apprenticeship and Skills Minister.

We record our own exclusive FE News podcasts, work in conjunction with sector partners such as FAB to create weekly podcasts and daily education podcasts, through to working with sector leaders creating exclusive education news podcasts.

Education Video Interviews

FE News have over 700 FE Video interviews and have been recording education video interviews with experts for over 12 years. These are usually vox pop video interviews with experts across education and work, discussing blue sky thinking ideas and views about the future of education and work.

Events

FE News has a free events calendar to check out the latest conferences, webinars and events to keep up to date with the latest education news and strategies.

FE Newsrooms

The FE Newsroom is home to your content if you are a FE News contributor. It also help the audience develop relationship with either you as an individual or your organisation as they can click through and ‘box set’ consume all of your previous thought leadership articles, latest education news press releases, videos and education podcasts.

Do you want to contribute, share your ideas or vision or share a press release?

If you want to write a thought leadership article, share your ideas and vision for the future of education or the future of work, write a press release sharing the latest education news or contribute to a podcast, first of all you need to set up a FE Newsroom login (which is free): once the team have approved your newsroom (all content, newsrooms are all approved by a member of the FE News team- no robots are used in this process!), you can then start adding content (again all articles, videos and podcasts are all approved by the FE News editorial team before they go live on FE News). As all newsrooms and content are approved by the FE News team, there will be a slight delay on the team being able to review and approve content.

 RSS IconRSS Feed Selection Page