breast cancer lumps
Artificial Intelligence is faster and 99% more accurate. Is it the next big step in the medical field?
Researchers have developed machine learning software that can accurately diagnose a patient’s breast cancer risk 30 times faster than doctors, based on mammogram results and personal medical history.
The system could help doctors give better diagnoses the first time around – which means fewer mammogram callbacks and false positives.
“This software intelligently reviews millions of records in a short amount of time, enabling us to determine breast cancer risk more efficiently using a patient’s mammogram,” said one of the researchers, Stephen Wong, from Houston Methodist Research Institute. “This has the potential to decrease unnecessary biopsies.”
A mammogram is a breast X-ray that aims to spot any potentially cancerous cells before symptoms arise.
In many countries, women over the age of 50 are advised to get a precautionary screening every two years, but as good as that system is, 50 percent of the tests in the US yield false positive results. In other words, one in two healthy women are wrongly being told they might have cancer.
On top of that, there’s a big grey area of ‘suspicious’ mammograms, which fall anywhere between a 3 and 95 percent cancer risk, and these patients are recommended to have follow-up biopsies.
Right now, about 20 percent of biopsies in the US are unnecessarily performed, according to the researchers, and the new AI has been designed to greatly reduce that number by making a more accurate diagnosis the first time.
Computer software is already used to help doctors analyse mammogram images themselves, but this system takes things one step further, by looking at the doctors’ reports on these scans, as well as a patient’s full medical history, to more accurately determine breast cancer risk
In the most recent demonstration, the researchers tested the AI on 500 breast cancer patients’ mammogram results and pathology reports.
Within a few hours, the software had come back with diagnostic information – specifically, it identified the breast cancer subtype each patient had.
The researchers then double checked the AI diagnoses with clinical results, and showed that the software was 99 percent accurate. The same analysis would have taken doctors more than 500 hours.
“Accurate review of this many charts would be practically impossible without AI,” said Wong.
To be clear, the AI so far hasn’t been tested in a real-world setting – the results analysed in this study were from existing breast cancer patients – but the researchers have now provided enough evidence to warrant follow-up trials.
It also won’t be able to prevent all false positives or suspicious mammogram results – sometimes there’s just not enough information available to make a diagnosis. But it should help doctors make a more accurate conclusion.
We’re looking forward to seeing how this software could make breast cancer diagnosis – as well as other cancers – faster and more accurate, and save people the time and stress of unnecessary further testing.
An existing osteoporosis drug has been found to halt the growth of breast cancer cells, and researchers are now investigating its potential as a new treatment for high-risk women.
The drug, called denosumab, could one day be prescribed as a preventative breast cancer treatment for women with mutations in the BRCA1 gene – which famously gave Angelina Jolie an estimated 87 percent risk of breast cancer and a 50 percent risk of ovarian cancer.
In a healthy state, the genes BRCA1 and BRCA2 produce tumour suppressor proteins that help repair damaged DNA, and ensure the stability of the cell’s genetic material.
But if these genes are mutated and not functioning properly – something that can be passed down by a person’s mother or father – they can produce faulty proteins, and will be unable to repair DNA damage.
This can lead to new cells developing further mutations that make them a whole lot more susceptible to breast and ovarian cancer growth. “About half of women who inherit a harmful mutation in BRCA1 or BRCA2 will develop breast cancer by the age of 70,” Ian Sample reports for The Guardian.
If a woman tests positive for these types of mutations, there are a number of precautionary measures she can take to mitigate the risk of either developing cancer, or not detecting it fast enough for effective treatment.
The US National Cancer Institute lists enhanced screening, prophylactic (risk-reducing) surgery, and chemoprevention as the main ones. But a new study suggests that there might be another option – taking the osteoporosis drug denosumab in pill-form to keep the harmful effects of these genetic mutations at bay.
Nolan and her colleagues analysed breast tissue from a woman with BRCA1 mutations to discover a group of cells that grew so rapidly, they appeared to be precursors of breast cancer.
Inside these cells, the team found a protein called the RANK receptor, which signals to breast cells when they need to grow, particularly during pregnancy and menstruation. If this protein is deregulated – say, in women with a malfunctioning BRCA1 gene – breast cells can start dividing and multiplying uncontrollably, resulting in breast cancer.
This discovery, reported by the team earlier this year, was exciting in itself, because it gave scientists a clear, single target on which to test new treatments. Even more exciting was the fact that the RANK receptor protein was already targeted by denosumab to combat bone weakness in osteoporosis patients, or in patients where breast cancer has spread to the bone.
When the team tested ree on mice engineered to developed breast cancer and in isolated human breast cancer cells, it was found to prevent or delay the development of tumours.
“We are very excited by these findings because it means we’ve found a strategy that might be useful to prevent breast cancer in very high risk women, particularly BRCA1 mutation carriers,” said one of the team, Geoff Lindeman, a medical oncologist at the Royal Melbourne Hospital.
The team is remaining cautious about the results, published in Nature Medicine, because until they’re replicated in actual, living humans – instead of mice or isolated breast tissue – they’re nothing more than a jumping off point. A major clinical study is now underway with at-risk volunteers, and it’s expected to span two years.
With a London-based group reporting earlier this year that they managed to shrink breast cancer tumours in just 11 days using combination drug therapy, and a silicon ‘nano-balls’ treatment rendering up to 50 percent of mouse breast cancer subjects “functionally cured”, real developments are being made in this space. Let’s just hope the clinical trials give us more positive news.