This appeared last week:
AI increasing accuracy and efficiency in cancer screening
By Velvet-Belle Templeman on May 12, 2022 7:00AM
Dr Helen Frazer is leading
the research at St Vincent’s Hospital in Melbourne using AI to improve the
accuracy of breast cancer screening and shorten the time to return results to
patients.
St Vincent’s Hospital in Melbourne has partnered with BreastScreen Victoria, St
Vincent’s Institute of Medical Research, the Australian Institute of Machine
Learning at the University of Adelaide and the University of Melbourne to
support the research program, and its being overseen by Aikenhead Centre for
Medical Discovery.
Despite the screening program being largely considered as a successful public
health initiative over its 30 year term, Frazer believes that AI can not only
save lives in this space, but improve the experience for women.
“We're now working with five of our top performing algorithms and their
ensemble and the exciting thing is that we've moved into this real world
setting. So we've been testing and validating our models in a real-world
retrospective cohort of women of over half a million women,” she said.
“We’re also working in a digital twin environment where we're prospectively
testing those models in real time as women come into the screening pathway.”
Frazer said that the research program is focusing on data central and model
centric development to train and test the models.
“We have over 4.2 million mammogram images and the associated non-image data
for that image. So we know that the words age, whether she has a family
history, has she had hormone replacement therapy? We also know whether the
mammogram was abnormal, whether the woman came back to assessment, a biopsy
performed, a cancer diagnosed, the cancer removed and the surgical
histopathology,” said Frazer.
The biggest challenge that they are facing is generalisability she said.
https://www.itnews.com.au/digitalnation/video/ai-increasing-accuracy-and-efficiency-in-cancer-screening-579869
There is also coverage here ( with some other AI successes)
AI driving solutions in healthcare, gender equality and wildlife conservation
By Velvet-Belle Templeman on May 10, 2022 7:00AM
Artificial intelligence
(AI) and machine learning (ML) are making significant inroads in solving
intractable problems in healthcare, gender inequality and wildlife
conservation.
The Women in AI Awards Australia and New Zealand 2022 awards the
top-performing female leaders and innovators using AI to drive impact in their
sectors and who are also providing a social good.
Digital Nation Australia spoke to the winners and runner-ups of the most
prestigious award of the night, the Innovator of the Year award, as well as the
winner of the WAI Trailblazer. Between them, the four winners shared a prize
pool of $30,000.
AI in breast cancer screening
Dr Helen Frazer, radiologist, breast cancer clinician and clinical director at
BreastScreen at St Vincent’s Hospital in Melbourne, won the WAI Innovator of
the Year award, for her work in transforming women’s experience in breast
cancer screening, and saving lives.
“We have curated a very large, globally unique data set for breast cancer AI
research,” said Frazer.
“We've been testing and validating our models in a real-world retrospective
cohort of over half a million women, and we're also working in a digital twin
environment where we're prospectively testing those models in real-time, as
women come into the screening pathway.”
The outcomes include higher test accuracy, due to specificity and sensitivity,
as well as shortening the timeframe for women to wait for their screening
results.
“An algorithm will actually pass through a mammogram almost instantaneously.
Whereas for someone like me, a radiologist to read the mammogram, it takes a
lot longer,” she said.
“Currently women wait up to 14 days for an all-clear result from their
mammogram and 95 percent of our work in population screening of well women is
normal. So there's a lot of anxiety as women wait that period to get their
result.”
Frazer said she is working to implement AI to more rapidly assess images to
make that turn-around the same day or within just a few days.
Radiologist talent shortages are a key challenge facing the health sector, and
Frazer believes that AI can help to meet this need.
On winning the award, Frazer said she hopes that it can encourage more women
and girls to work in STEM.
“We know that female participation [in STEM] is low and global figures will say
25 percent or less proportion of women are in STEM-related roles. We know also
that women in artificial intelligence is even less again, and probably at best
around about 15 percent,” she said.
“There are ethical, legal and social implications of machines actually making
medical decisions or used to support or augment medical decisions. I believe it
is so important to hear all voices, for everyone to have a seat at the table
and that includes women.”
More here:
This seems to really be a win-win with diagnosis quicker and more accurate and the patient not having a long wait for most results.
Also the rare radiologists can look more carefully at the hard images where the outcome is unclear and human judgement is useful!
Good stuff.
David.
No comments:
Post a Comment