Artificial intelligence has successfully detected a woman’s breast cancer, after a routine exam assessed by humans was found to be ‘normal’.
Sheila Tooth received the all-clear after her most recent mammogram was reviewed by two experienced radiologists who determined there were no signs of cancer. However, Sussex University Hospital, where she had her appointment, was participating in research to see if AI could improve early detection.
The technology made it possible to detect cancer cells that were undetectable to the human eye, allowing Sheila, who was diagnosed with early breast cancer 15 years ago, to receive minimal treatment as early as possible.
“It’s extraordinary and I’m amazed,” said the retired nurse from West Sussex, England. “I knew that whatever they could see on my scanner must have been incredibly small if it hadn’t been detected the first time.”
The mother-of-one was diagnosed with the same early, non-invasive breast cancer as before, but because it was detected so early, she was able to have a lumpectomy and did not need any further treatment.
Now that she is recovering from the surgery, she says she is very grateful for AI technology.
“When I talk to friends, we just can’t believe that this AI can detect what the human eye can’t always see. I feel so lucky.
“At 68, this may have been my last mammogram, so my early cancer could have developed into invasive cancer at 70, so I am deeply grateful that it was detected so early.”
EXCITING NEWS: Manuka honey reduces breast cancer cell growth by 84% in human cells and mice
Five “normal” screenings out of 12,000 were canceled
Sussex University Hospitals is one of 15 trusts across the UK that took part in the project to test whether AI can detect cancers that humans might miss. The project used an AI system developed by Kheiron Medical Technologies called Mammography Intelligent Assessment, and was funded by the NIHR and NHS England.
Throughout the two-month project, more than 12,000 mammograms deemed normal by radiologists were reviewed using the AI system, suggesting that just under 10% of these films would need to be re-read by a clinical panel to identify any potential cancer that may have been detected. was not detected during initial screening.
After further examination, 11 women were invited back for investigation. Five of them suffered from breast cancer.
Dr Olga Strukowska, consultant radiologist and director of the West Sussex Breast Screening Program, said we are still in the early stages of evaluating AI in clinical scenarios, but based on the trials and research underway, AI will surely find its place in screening programs.
INCREDIBLE AI: New AI smartphone app accurately diagnoses ear infections and prevents unnecessary antibiotic use
“The earlier and more accurately we detect cancer, the greater the chance that our patients will have a positive outcome. That’s why it’s so exciting.
“It enables screening services to provide reliable, accurate and 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 Manager for Breast Services, said: “I have no doubt that over time, the integration of AI with clinicians’ expertise will improve the effectiveness of patient care, improving both outcomes and quality of service for patients. »
Sussex University Hospitals is now considering taking part in a national randomized controlled trial involving AI – part of the next phase of introducing the technology into breast cancer screening.
MORE BREAKTHROUGHS: Portable breast cancer test uses your saliva and gives accurate readings in 5 seconds
Patients who undergo a mammogram must be registered with a doctor to be invited for additional breast cancer screening, but Sheila now recommends the technology to everyone, saying: “It’s just fantastic!
SPREAD THE GOOD NEWS By sharing on social networks…