
AI could help us more accurately screen for breast cancer, new research
10almonds is reader-supported. We may, at no cost to you, receive a portion of sales if you purchase a product through a link in this article.
At least 20,000 Australian women are diagnosed with breast cancer each year. And more than 3,300 die from the disease.
To save women’s lives, we need to detect breast cancer early. Breast screening, which halves women’s risk of dying from breast cancer, is key to that.
A new Australian study published today in The Lancet Digital Health suggests AI could help improve how we screen for breast cancer.

How do we currently screen for breast cancer?
Since 1992, Australia has offered free breast X-rays, known as mammograms, every two years to women aged between 50 and 74. Just over half of eligible women participate.
Of the women found to have cancer, about 25% are diagnosed between the biennial screens. These “interval cancers” are often aggressive and, unfortunately, more likely to be fatal.
In some cases, a more sensitive screening test may have detected them earlier.
The role of AI
Australia’s BreastScreen program was established in response to several major clinical trials conducted between the 1960s and 1980s. The screening technology used by the program has not substantially changed since then.
Researchers are now exploring risk-adjusted screening, which tailors screening to women based on their risk, as a way to detect more cancers earlier. This may include programs offering different technologies for women at higher risk of developing breast cancer.
Currently, we generally assess cancer risk via questionnaires that help identify if a woman has any risk factors associated with breast cancer.
One risk factor is breast density which refers to how much glandular tissue is in the breast. As well as being a risk factor for breast cancer, the higher a woman’s breast density, the harder it is to detect cancer on a mammogram.
We can also use one-off genetic testing to identify women with a higher lifetime risk of developing breast cancer. This involves looking for high-risk gene mutations such as BRCA1 and BRCA2, which are associated with increased breast and ovarian cancer risk. Genetic testing can also help us estimate a person’s lifetime risk of developing breast cancer.
More recently, researchers have been investigating artificial intelligence (AI) as a new approach to assess breast cancer risk. A new Australian study, published in The Lancet Digital Health today, focused on a specific AI tool known as BRAIx.
What did the study involve? And what did it find?
This study used an AI tool, known as BRAIx, trained using BreastScreen Australia data to help radiologists assess mammograms.
The study assessed how well BRAIx predicted women’s risk of developing breast cancer in the next four years, among women who had a clear mammogram.
Of the 95,823 Australian women assessed, 1.1% (1,098) had developed breast cancer in the four years after they received a clear mammogram. Of the 4,430 Swedish women assessed, 6.9% had developed breast cancer within two years of a clear screen.
The study findings show that BRAIx scores were very useful for identifying women who were more likely to develop cancer one to two years after having a clear screen. Findings from the Australian dataset suggest BRAIx scores identified cancers found three to four years later, but with less accuracy.
These findings suggest BRAIx could help identify women who might benefit from additional tests. This may include an MRI (which uses a magnetic field to produce images of organs and tissue) or contrast-enhanced mammography (which uses an iodine dye to improve the visibility of a regular mammogram).
These findings reinforce a 2024 Swedish study that used an AI-based risk assessment to select women for additional testing. The researchers referred 7% of women to have a follow-up MRI, and 6.5% of were found to have cancers missed by mammograms.
Does the study have any limitations?
As with most studies, yes. Here are two.
- it’s difficult to compare BRAIx to genetic testing. This is because BRAIx is trained to find missed or emerging cancers over a four year period. In contrast, genetic testing identifies a person’s risk of developing cancer over their lifetime
- it might not use the best breast density data. This study found BRAIx more accurately predicts breast cancer risk compared to assessments based on breast density. But this breast density data was collected using a different tool to those used by the Breastscreen program. So this finding should be interpreted carefully.
So, where to from here?
The study adds to a growing body of evidence that AI risk assessment could help breast screening programs find cancers earlier.
BRAIx is now being trialled as part of the BreastScreen Victoria program, to help read mammograms. And other states are already using and evaluating different AI tools for reading mammograms.
So it may be time for Australia to conduct a national, independent review of these new tools. As part of a more risk-adjusted approach to breast screening, they could save lives.
Carolyn Nickson, Principal Research Fellow, Cancer Elimination Collaboration, University of Sydney; The University of Melbourne and Bruce Mann, Professor of Surgery, Specialist Breast Surgeon, The University of Melbourne
This article is republished from The Conversation under a Creative Commons license. Read the original article.
Don’t Forget…
Did you arrive here from our newsletter? Don’t forget to return to the email to continue learning!
Recommended
Learn to Age Gracefully
Join the 98k+ American women taking control of their health & aging with our 100% free (and fun!) daily emails:
-
Viruses aren’t always harmful. 6 ways they’re used in health care and pest control
10almonds is reader-supported. We may, at no cost to you, receive a portion of sales if you purchase a product through a link in this article.
We tend to just think of viruses in terms of their damaging impacts on human health and lives. The 1918 flu pandemic killed around 50 million people. Smallpox claimed 30% of those who caught it, and survivors were often scarred and blinded. More recently, we’re all too familiar with the health and economic impacts of COVID.
But viruses can also be used to benefit human health, agriculture and the environment.
Viruses are comparatively simple in structure, consisting of a piece of genetic material (RNA or DNA) enclosed in a protein coat (the capsid). Some also have an outer envelope.
Viruses get into your cells and use your cell machinery to copy themselves.
Here are six ways we’ve harnessed this for health care and pest control.1. To correct genes
Viruses are used in some gene therapies to correct malfunctioning genes. Genes are DNA sequences that code for a particular protein required for cell function.
If we remove viral genetic material from the capsid (protein coat) we can use the space to transport a “cargo” into cells. These modified viruses are called “viral vectors”.
Viruses consist of a piece of RNA or DNA enclosed in a protein coat called the capsid.
DEXiViral vectors can deliver a functional gene into someone with a genetic disorder whose own gene is not working properly.
Some genetic diseases treated this way include haemophilia, sickle cell disease and beta thalassaemia.
2. Treat cancer
Viral vectors can be used to treat cancer.
Healthy people have p53, a tumour-suppressor gene. About half of cancers are associated with the loss of p53.
Replacing the damaged p53 gene using a viral vector stops the cancerous cell from replicating and tells it to suicide (apoptosis).
Viral vectors can also be used to deliver an inactive drug to a tumour, where it is then activated to kill the tumour cell.
This targeted therapy reduces the side effects otherwise seen with cytotoxic (cell-killing) drugs.
We can also use oncolytic (cancer cell-destroying) viruses to treat some types of cancer.
Tumour cells have often lost their antiviral defences. In the case of melanoma, a modified herpes simplex virus can kill rapidly dividing melanoma cells while largely leaving non-tumour cells alone.
3. Create immune responses
Viral vectors can create a protective immune response to a particular viral antigen.
One COVID vaccine uses a modified chimp adenovirus (adenoviruses cause the common cold in humans) to transport RNA coding for the SARS-CoV-2 spike protein into human cells.
The RNA is then used to make spike protein copies, which stimulate our immune cells to replicate and “remember” the spike protein.
Then, when you are exposed to SARS-CoV-2 for real, your immune system can churn out lots of antibodies and virus-killing cells very quickly to prevent or reduce the severity of infection.
4. Act as vaccines
Viruses can be modified to act directly as vaccines themselves in several ways.
We can weaken a virus (for an attenuated virus vaccine) so it doesn’t cause infection in a healthy host but can still replicate to stimulate the immune response. The chickenpox vaccine works like this.
The Salk vaccine for polio uses a whole virus that has been inactivated (so it can’t cause disease).
Others use a small part of the virus such as a capsid protein to stimulate an immune response (subunit vaccines).
An mRNA vaccine packages up viral RNA for a specific protein that will stimulate an immune response.
5. Kill bacteria
Viruses can – in limited situations in Australia – be used to treat antibiotic-resistant bacterial infections.
Bacteriophages are viruses that kill bacteria. Each type of phage usually infects a particular species of bacteria.
Unlike antibiotics – which often kill “good” bacteria along with the disease-causing ones – phage therapy leaves your normal flora (useful microbes) intact.
Bacteriophages (red) are viruses that kill bacteria (green).
Shutterstock6. Target plant, fungal or animal pests
Viruses can be species-specific (infecting one species only) and even cell-specific (infecting one type of cell only).
This occurs because the proteins viruses use to attach to cells have a shape that binds to a specific type of cell receptor or molecule, like a specific key fits a lock.
The virus can enter the cells of all species with this receptor/molecule. For example, rabies virus can infect all mammals because we share the right receptor, and mammals have other characteristics that allow infection to occur whereas other non-mammal species don’t.
When the receptor is only found on one cell type, then the virus will infect that cell type, which may only be found in one or a limited number of species. Hepatitis B virus successfully infects liver cells primarily in humans and chimps.
We can use that property of specificity to target invasive plant species (reducing the need for chemical herbicides) and pest insects (reducing the need for chemical insecticides). Baculoviruses, for example, are used to control caterpillars.
Similarly, bacteriophages can be used to control bacterial tomato and grapevine diseases.
Other viruses reduce plant damage from fungal pests.
Myxoma virus and calicivirus reduce rabbit populations and their environmental impacts and improve agricultural production.
Just like humans can be protected against by vaccination, plants can be “immunised” against a disease-causing virus by being exposed to a milder version.
Thea van de Mortel, Professor, Nursing, School of Nursing and Midwifery, Griffith University
This article is republished from The Conversation under a Creative Commons license. Read the original article.
Share This Post
-
Alpha, beta, theta: what are brain states and brain waves? And can we control them?
10almonds is reader-supported. We may, at no cost to you, receive a portion of sales if you purchase a product through a link in this article.
There’s no shortage of apps and technology that claim to shift the brain into a “theta” state – said to help with relaxation, inward focus and sleep.
But what exactly does it mean to change one’s “mental state”? And is that even possible? For now, the evidence remains murky. But our understanding of the brain is growing exponentially as our methods of investigation improve.
Brain-measuring tech is evolving
Currently, no single approach to imaging or measuring brain activity gives us the whole picture. What we “see” in the brain depends on which tool we use to “look”. There are myriad ways to do this, but each one comes with trade-offs.
We learnt a lot about brain activity in the 1980s thanks to the advent of magnetic resonance imaging (MRI).
Eventually we invented “functional MRI”, which allows us to link brain activity with certain functions or behaviours in real time by measuring the brain’s use of oxygenated blood during a task.
We can also measure electrical activity using EEG (electroencephalography). This can accurately measure the timing of brain waves as they occur, but isn’t very accurate at identifying which specific areas of the brain they occur in.
Alternatively, we can measure the brain’s response to magnetic stimulation. This is very accurate in terms of area and timing, but only as long as it’s close to the surface.
What are brain states?
All of our simple and complex behaviours, as well as our cognition (thoughts) have a foundation in brain activity, or “neural activity”. Neurons – the brain’s nerve cells – communicate by a sequence of electrical impulses and chemical signals called “neurotransmitters”.
Neurons are very greedy for fuel from the blood and require a lot of support from companion cells. Hence, a lot of measurement of the site, amount and timing of brain activity is done via measuring electrical activity, neurotransmitter levels or blood flow.
We can consider this activity at three levels. The first is a single-cell level, wherein individual neurons communicate. But measurement at this level is difficult (laboratory-based) and provides a limited picture.
As such, we rely more on measurements done on a network level, where a series of neurons or networks are activated. Or, we measure whole-of-brain activity patterns which can incorporate one or more so-called “brain states”.
According to a recent definition, brain states are “recurring activity patterns distributed across the brain that emerge from physiological or cognitive processes”. These states are functionally relevant, which means they are related to behaviour.
Brain states involve the synchronisation of different brain regions, something that’s been most readily observed in animal models, usually rodents. Only now are we starting to see some evidence in human studies.
Various kinds of states
The most commonly-studied brain states in both rodents and humans are states of “arousal” and “resting”. You can picture these as various levels of alertness.
Studies show environmental factors and activity influence our brain states. Activities or environments with high cognitive demands drive “attentional” brain states (so-called task-induced brain states) with increased connectivity. Examples of task-induced brain states include complex behaviours such as reward anticipation, mood, hunger and so on.
In contrast, a brain state such as “mind-wandering” seems to be divorced from one’s environment and tasks. Dropping into daydreaming is, by definition, without connection to the real world.
We can’t currently disentangle multiple “states” that exist in the brain at any given time and place. As mentioned earlier, this is because of the trade-offs that come with recording spatial (brain region) versus temporal (timing) brain activity.
Brain states vs brain waves
Brain state work can be couched in terms such as alpha, delta and so forth. However, this is actually referring to brain waves which specifically come from measuring brain activity using EEG.
EEG picks up on changing electrical activity in the brain, which can be sorted into different frequencies (based on wavelength). Classically, these frequencies have had specific associations:
- gamma is linked with states or tasks that require more focused concentration
- beta is linked with higher anxiety and more active states, with attention often directed externally
- alpha is linked with being very relaxed, and passive attention (such as listening quietly but not engaging)
- theta is linked with deep relaxation and inward focus
- and delta is linked with deep sleep.
Brain wave patterns are used a lot to monitor sleep stages. When we fall asleep we go from drowsy, light attention that’s easily roused (alpha), to being relaxed and no longer alert (theta), to being deeply asleep (delta).
Can we control our brain states?
The question on many people’s minds is: can we judiciously and intentionally influence our brain states?
For now, it’s likely too simplistic to suggest we can do this, as the actual mechanisms that influence brain states remain hard to detangle. Nonetheless, researchers are investigating everything from the use of drugs, to environmental cues, to practising mindfulness, meditation and sensory manipulation.
Controversially, brain wave patterns are used in something called “neurofeedback” therapy. In these treatments, people are given feedback (such as visual or auditory) based on their brain wave activity and are then tasked with trying to maintain or change it. To stay in a required state they may be encouraged to control their thoughts, relax, or breathe in certain ways.
The applications of this work are predominantly around mental health, including for individuals who have experienced trauma, or who have difficulty self-regulating – which may manifest as poor attention or emotional turbulence.
However, although these techniques have intuitive appeal, they don’t account for the issue of multiple brain states being present at any given time. Overall, clinical studies have been largely inconclusive, and proponents of neurofeedback therapy remain frustrated by a lack of orthodox support.
Other forms of neurofeedback are delivered by MRI-generated data. Participants engaging in mental tasks are given signals based on their neural activity, which they use to try and “up-regulate” (activate) regions of the brain involved in positive emotions. This could, for instance, be useful for helping people with depression.
Another potential method claimed to purportedly change brain states involves different sensory inputs. Binaural beats are perhaps the most popular example, wherein two different wavelengths of sound are played in each ear. But the evidence for such techniques is similarly mixed.
Treatments such as neurofeedback therapy are often very costly, and their success likely relies as much on the therapeutic relationship than the actual therapy.
On the bright side, there’s no evidence these treatment do any harm – other than potentially delaying treatments which have been proven to be beneficial.
Susan Hillier, Professor: Neuroscience and Rehabilitation, University of South Australia
This article is republished from The Conversation under a Creative Commons license. Read the original article.
Share This Post
-
Broccoli vs Cauliflower – Which is Healthier?
10almonds is reader-supported. We may, at no cost to you, receive a portion of sales if you purchase a product through a link in this article.
Our Verdict
When comparing broccoli to cauliflower, we picked the broccoli.
Why?
This one is quite straightforward. Superficially, they’re very similar:
Both are great cruciferous vegetables with many health benefits to offer. Even for those keen to avoid oxalates, which cruciferous vegetables in general can be high in, these ones are quite low.
However, if you have IBS, you might want to avoid both, for their raffinose content that may cause problems for you.
For pretty much everyone else, unless you have a special reason why it’s not the case for you, both are a good source of abundant vitamins and minerals, and yet…
Anything cauliflower can do, broccoli can do better!
Broccoli contains more of the vitamins they both contain, and more of the minerals they both contain.
Broccoli also beats cauliflower on amino acids (except lysine), and contains a lot more lutein and zeaxanthin, carotenoids important for healthy eyes and brain.
So by all means enjoy both, but if you’re going to pick one, pick broccoli!
Want to know more?
Check out: Brain Food? The Eyes Have It!
Enjoy!
Share This Post
Related Posts
-
Ayurveda’s Contributions To Science
10almonds is reader-supported. We may, at no cost to you, receive a portion of sales if you purchase a product through a link in this article.
Ayurveda’s Contributions To Science (Without Being Itself Rooted in Scientific Method)
Yesterday, we asked you for your opinions on ayurveda, and got the above-depicted, below-described, set of responses. Of those who responded…
- A little over 41% said “I don’t know what ayurveda is without looking it up”
- A little over 37% said “It is a fine branch of health science with millennia of evidence”
- A little over 16% said “It gets some things right, but not by actual science”
- A little over 4% said “It is a potentially dangerous pseudoscience”
So, what does the science say?
Ayurveda is scientific: True or False?
False, simply. Let’s just rip the band-aid off in this case. That doesn’t mean it’s necessarily without merit, though!
Let’s put it this way:
- If you drink coffee to feel more awake because scientific method has discerned that caffeine has vasoconstrictive and adenosine-blocking effects while also promoting dopaminergic activity, then your consumption of coffee is evidence-based and scientific. Great!
- If you drink coffee to feel more awake because somebody told you that that somebody told them that it energizes you by balancing the elements fire (the heat of the coffee), air (the little bubbles on top), earth (the coffee grinds), water (the water), and ether (steam), then that is neither evidence-based nor scientific, but it will still work exactly the same.
Ayurveda is a little like that. It’s an ancient traditional Indian medicine, based on a combination of anecdotal evidence and supposition.
- The anecdotal evidence from ayurveda has often resulted in herbal remedies that, in modern scientific trials, have been found to have merit.
- Ayurvedic meditative practices also have a large overlap with modern mindfulness practices, and have also been found to have merit
- Ayurveda also promotes the practice of yoga, which is indeed a very healthful activity
- The supposition from ayurveda is based largely in those five elements we mentioned above, as well as a “balancing of humors” comparable to medieval European medicine, and from a scientific perspective, is simply a hypothesis with no evidence to support it.
Note: while ayurveda is commonly described as a science by its practitioners in the modern age, it did not originally claim to be scientific, but rather, wisdom handed down directly by the god Dhanvantari.
Ayurveda gets some things right: True or False?
True! Indeed, we covered some before in 10almonds; you may remember:
Bacopa Monnieri: A Well-Evidenced Cognitive Enhancer
(Bacopa monnieri is also known by its name in ayurveda, brahmi)
There are many other herbs that have made their way from ayurveda into modern science, but the above is a stand-out example. Others include:
- Ashwagandha: The Root of All Even-Mindedness?
- Boswellia serrata (Frankincense) Against Pain and Depression/Anxiety
Yoga and meditation are also great, and not only that, but great by science, for example:
- NCCIH | Yoga for Health: Clinical Guidelines, Scientific Literature, Info for Patients
- The Neuroscience of Mindfulness: How Mindfulness Alters the Brain and Facilitates Emotion Regulation
Ayurveda is a potentially dangerous pseudoscience: True or False?
Also True! We covered why it’s a pseudoscience above, but that doesn’t make it potentially dangerous, per se (you’ll remember our coffee example).
What does, however, make it potentially dangerous (dose-dependent) is its use of heavy metals such as lead, mercury, and arsenic:
Heavy Metal Content of Ayurvedic Herbal Medicine Products
Some final thoughts…
Want to learn more about the sometimes beneficial, sometimes uneasy relationship between ayurveda and modern science?
A lot of scholarly articles trying to bridge (or further separate) the two were very biased one way or the other.
Instead, here’s one that’s reasonably optimistic with regard to ayurveda’s potential for good, while being realistic about how it currently stands:
Development of Ayurveda—Tradition to trend
Take care!
Don’t Forget…
Did you arrive here from our newsletter? Don’t forget to return to the email to continue learning!
Learn to Age Gracefully
Join the 98k+ American women taking control of their health & aging with our 100% free (and fun!) daily emails:
-
Most People Do Seated Forward Fold Incorrectly (Do This Instead)
10almonds is reader-supported. We may, at no cost to you, receive a portion of sales if you purchase a product through a link in this article.
This makes quite a difference:
Into the fold
What most people get wrong: focusing on touching their toes!
The reason is because this often shifts the stretch into your back, instead of your hamstrings.
Instead, here’s what to do, step by step:
- Sit down, bend your knees, and bring your belly towards your thighs, while keeping your spine straight
- Hold your toes, knees, or behind your thighs, to maintain a strong belly-to-thigh connection
- Slowly slide your feet forwards one at a time while keeping your spine straight and your belly connected to your thighs
- Stop sliding when you feel the tension in your hamstrings rather than your back
- Optimize the stretch by sending your tailbone backwards, which lengthens your hamstrings
- Inhale, then exhale and relax deeper into the stretch, using each exhale to slide slightly further forwards each time
- Make sure you don’t force your legs straight; instead, stay within your current limit and let breathing gradually increase your range!
Remember: bent knees allow you to tilt your pelvis correctly, so your hamstrings actually lengthen instead of your spine rounding. If nothing else, understand this 🙂
For more on all of this plus visual demonstrations, enjoy:
Click Here If The Embedded Video Doesn’t Load Automatically!
Want to learn more?
You might also like:
Tight Hamstrings? Here’s A Test To Know If It’s Actually Your Sciatic Nerve
Take care!
Don’t Forget…
Did you arrive here from our newsletter? Don’t forget to return to the email to continue learning!
Learn to Age Gracefully
Join the 98k+ American women taking control of their health & aging with our 100% free (and fun!) daily emails:
-
The Twenty-Four Hour Mind – by Dr. Rosalind Cartwright
10almonds is reader-supported. We may, at no cost to you, receive a portion of sales if you purchase a product through a link in this article.
We’ve reviewed books about sleep before, and even about dreaming, so what does this one have to offer that’s new?
Quite a lot, actually! Before Dr. Cartwright, there were mainly two models of sleep and dreaming:
- The “top-down” model of psychoanalysts: our minds shape our dreams which in turn reveal things about us as people
- The “bottom-up” model of neuroscientists: our brains need to go through regular maintaince cycles, of which vivid hallucinations are a quirky side-effect.
And now, as Dr. Cartwright puts it:
❝I will lay out a new [horizontal] psychological model of the twenty-four hour mind; that is, how the predominantly conscious (waking) and unconscious (sleeping) forms of mental behavior interact through the brain’s regular, but differently organized, states of waking, sleeping, and dreaming.❞
This she does in the exploratory style of a 224-page lecture, which sounds like it might be tedious, but is actually attention-grabbing and engaging throughout. This book is more of a page-turner than soporific bedtime reading!
Bottom line: if you’d like to know more about the effect your waking and sleeping brain have on each other (to include getting in between those and making adjutments as appropriate), this is very much an elucidating read!
Click here to check out The Twenty-Four Hour Mind, and learn more about yours!
Don’t Forget…
Did you arrive here from our newsletter? Don’t forget to return to the email to continue learning!
Learn to Age Gracefully
Join the 98k+ American women taking control of their health & aging with our 100% free (and fun!) daily emails:










