Sheila Tooth, 68, is now back home in Littlehampton and recovering from breast cancer surgery – thanks to the power of AI to spot cancers which may be invisible to the human eye.
Sheila said: “It’s extraordinary and I’m amazed. When I talk to friends, we just can’t believe this AI can detect what the human eye can’t always see. I just feel so lucky.”
University Hospitals Sussex is one of 15 trusts across the country that participated in a project that looked at the effectiveness of using an AI system to analyse mammograms – an X-ray of the breast to help detect cancers – to see if it could improve the early detection of breast cancer by seeing tiny signs of cancer that can be missed at this stage.
AI technology is being used to see if it can improve breast cancer screening by spotting cancer that human ‘readers’ might miss.
The project tested an AI system developed by Kheiron Medical Technologies called Mammography Intelligent Assessment (Mia) at Worthing Hospital, and Park Centre in Brighton, and was funded by the NIHR and NHS England ‘Artificial Intelligence in Health and Care Award,’ which supports promising AI technologies for health and social care.
After the scan is taken, the mammogram is typically reviewed by two highly skilled radiologists or film readers, who look for any signs of cancer. Upon review, they then decide if the scan is ‘normal’ without signs of cancer or if further investigation is needed.
Over the course of the two-month project, more than 12,000 mammograms considered as ‘normal’ were reviewed using the AI system which acts as an extra ‘reader’ alongside radiologists, to flag any scans it thinks needs to be looked at again.
The AI system suggested that just under 10% of those mammograms should be re-read by a clinical panel to identify any potential cancers that were not detected in the initial screening.
Upon further review, 11 women were asked to come back for investigation and five were found to have breast cancer.
Sheila, a retired nurse, and counsellor of almost 40 years, had previously been diagnosed with a non-invasive early breast cancer 15 years ago and underwent a lumpectomy.
Following her most recent mammogram, when she was experiencing no symptoms, Sheila’s scan was flagged by the AI system and was investigated further, leading to her cancer being discovered.
Sheila said: “I remember the shock of the letter, having had cancer before I was very frightened. But I knew that whatever they could see on my scan must have been incredibly small if it wasn’t picked up the first time.”
The mother-of-one was diagnosed with the same early non-invasive breast cancer as before but because it was found so early, Sheila was able to have a lumpectomy and didn’t need any further treatment.
Sheila credits the AI system for helping detect her cancer early. She said: “Being 68, this may have been my last mammogram, so my early cancer might have developed into invasive cancer in my 70s. So, I’m deeply grateful for it to have been caught so early. It’s just fantastic and all the staff were amazing, so kind and lovely and very reassuring.”
Sheila is now recovering well following her operation and having caught and treated her cancer early, has meant she could get back to her normal activities.
Dr Olga Strukowska, Consultant Radiologist and Director of Breast Screening West Sussex Breast Screening Programme explains: “We are still in early stages of AI evaluation in clinical scenarios but based on current trials and research projects, AI should find its place within the breast screening programme. The earlier and more accurately we detect cancer, the better the chance our patients will have a positive outcome.
“That’s why this is so exciting. Using AI increases accuracy while reducing the number of missed cancers and lowering false positives. It empowers screening services to deliver confident, accurate, timely results through deep learning technology that works with radiologists and promotes high-quality standards of care for our patients.”
Steve Dixon, Senior AI Project Lead for Breast Services, said: “I feel privileged to have been part of the UHSussex breast screening teams in this groundbreaking evaluation project to demonstrate one of the potential uses of AI within the NHS breast screening programme. I have no doubt that, in time, integrating AI with clinicians’ expertise will enhance the effectiveness of patient care, improving both outcomes and the quality of service for patients.”
In Sussex, around 650 women every year are diagnosed with breast cancer following their screening. The programme invites women aged 50-71 for a screening every three years.
The Trust is now planning to take part in a national randomised controlled trial, as part of the next phase of introducing AI into breast screening.
Dr Sameer Gangoli, Consultant Radiologist and Clinical and Governance Lead for AI for UHSussex praised the breast screening team for their efforts in improving the care of patients like Sheila.
He said: “This project has been a trailblazer in the Trust for a comprehensive, ambitious, and exciting AI programme which we have established. We are looking forward to seeing how these projects can revolutionise patient care and enhance outcomes in healthcare in the very near future.”