Connect with us

News

AI as good as radiologists at spotting breast cancer, study finds

AI screening is as good as two radiologists working together, Swedish researchers suggest

Published

on

Mammography screening supported by artificial intelligence is a safe alternative to today’s conventional double reading by radiologists, a new study has shown.

The potential of AI to support mammography screening has attracted much attention, but how this is to be optimally conducted and what the clinical consequences will be remains unclear.

Female breast cancer has now surpassed lung cancer as the most commonly diagnosed cancer worldwide, with an estimated two million new cases registered in 2020.

The Mammography Screening with Artificial Intelligence (MASAI) trial is the first randomised controlled trial evaluating the effect of AI-supported screening.

The study, led by researchers from Lund University in Sweden, addressed the clinical safety of using AI in mammography screening and found that AI screening is as good as two radiologists working together, without increasing false positives.

“In our trial, we used AI to identify screening examinations with a high risk of breast cancer, which underwent double reading by radiologists,” said Kristina Lång, researcher and associate professor in diagnostic radiology at Lund University and consultant at Skåne University Hospital, who led the study.

“The remaining examinations were classified as low risk and were read only by one radiologist. In the screen reading, radiologists used AI as detection support, in which it highlighted suspicious findings on the images.”

The 80,033 women included in the safety analysis were randomly allocated into two groups: 40,003 women in the intervention group that underwent AI-supported screening and 40,030 in the control group that underwent standard double reading without AI support.

“We found that using AI resulted in the detection of 20 per cent more cancers compared with standard screening, without affecting false positives. A false positive in screening occurs when a woman is recalled but cleared of suspicion of cancer after workup,” Lång added.

The screen-reading workload for radiologists was reduced by 44 per cent. The number of screen readings with AI-supported screening was 46,345 compared with 83,231 with standard screening.

Lång said the time aspect is incredibly important, as one radiologist reads only an average of 50 screening examinations per hour.

“We estimated that it took approximately five months less of a radiologist’s time to read the roughly 40,000 screening examinations in the AI group,” she explained.

“However, we need to see whether these promising results hold up under other conditions, for example with other radiologists or other AI algorithms.

“There may be other ways to use AI in mammography screening, but these should preferably also need to be investigated in a prospective setting,” the researcher added.

A total of 100,000 women have now been enrolled in the MASAI trial. The research team’s next step is to investigate which cancer types that were detected with and without AI support.

The primary endpoint of the trial is interval-cancer rate. An interval cancer is a cancer diagnosed between screenings and generally have poorer prognosis than screen-detected cancers. The interval-cancer rate will be assessed after the 100,000 women in the trial have had at least a two-year follow up.

“Screening is complex,” Lång said. “The balance between benefit and harm must always be taken into account. Just because a screening method finds more cancers does not necessarily mean it’s a better method.

“What’s important is to find a method that can identify clinically significant cancers at an early stage. However, this has to be balanced with the harm of false positives and the overdiagnosis of indolent cancers.

“The results from our first analysis shows that AI-supported screening is safe since the cancer detection rate did not decline despite a substantial reduction in the screen-reading workload.

“The planned analysis of interval cancers will show whether AI-supported screening also leads to a more accurate and effective screening programme.”

Insight

Drug turns off ‘master switch’ in aggressive breast cancer

Published

on

A drug targeting a key regulator in triple-negative breast cancer reduced tumour growth and cancer stem cell viability in laboratory models.

Triple-negative breast cancer is an aggressive subtype that disproportionately affects women under 40 and accounts for about 15 to 20 per cent of breast cancers.

The disease lacks receptors for oestrogen, progesterone and the HER2 protein, which are targeted by several cancer drugs, making it particularly difficult to treat.

Researchers from the National University of Singapore’s Yong Loo Lin School of Medicine investigated mechanisms that allow triple-negative breast cancer cells to spread and resist treatment.

They examined regulators of Wnt signalling, a pathway involved in processes including cell growth and movement, and identified a master regulator called DP103.

DP103 is a gene that controls a major biological process. The researchers found it creates a cycle in which cancer cells continue to grow and spread while resisting treatment and maintaining cancer stem cells linked to disease recurrence.

The team then investigated whether a targeted drug known as Supinoxin, or RX-5902, could block DP103 and its effects in triple-negative breast cancer.

Analysis of 21 samples, including patient tumour tissue, laboratory-grown breast cancer cells and organoids derived from local cancer patients, found that the drug reduced cancer stem cell viability by 40 to 60 per cent.

Tumour growth in laboratory-grown tumour models fell by about 50 per cent.

In laboratory models, treatment also reduced tumour size by around 90 per cent while largely sparing healthy cells.

It also extended survival, with half of the treated laboratory models reaching 70 days and beyond, compared with none in the untreated group.

DP103 had previously been identified as a biomarker for triple-negative breast cancer by a team led by Alan Prem Kumar, an assistant professor with the NUS Centre for Cancer Research and principal investigator for the new study.

RX-5902 is already being studied as a treatment for breast cancer, and Kumar said the findings could help identify patients who may be more likely to benefit.

“Our findings suggest that DP103 could potentially serve as a diagnostic biomarker to identify the patients most likely to benefit from RX-5902 treatment, paving the way for a more precise, personalised approach to treating triple-negative breast cancer,” he said.

“Instead of treating all patients the same, future clinical trials could focus on those whose tumours have high levels of DP103, where the therapy is expected to have the greatest impact,” said Kumar.

First author Cai Wanpei said RX-5902 could prevent beta-catenin, a protein whose mutation is associated with various cancers, from entering the nucleus of human cells and switching off genes that drive cancer growth and spread.

“This slows tumour progression and triggers apoptosis – the natural death of cancer cells,” said Cai, who was a PhD student at the NUS Centre for Cancer Research and NUS Medicine’s pharmacology department during the research.

Study co-author Celestial T. Yap said triple-negative breast cancer remains particularly difficult to treat because conventional treatments such as surgery, chemotherapy and immunotherapy may not work for all patients.

She said DP103 could represent a “biological vulnerability” in the disease.

“This discovery offers new insights that could support more precise patient selection and open the door to better targeted strategies for durable disease control and improved clinical outcomes,” said Yap, an associate professor with the NUS Centre for Cancer Research and NUS Medicine’s physiology department.

The researchers said abnormal Wnt signalling also drives several other cancers, meaning the findings could offer avenues for treating other aggressive cancers.

Their next steps include validating DP103 as a predictive biomarker in larger patient groups and further developing therapies targeting the regulator for clinical testing.

The team will also investigate combining RX-5902 with existing therapies to further improve treatment outcomes.

Continue Reading

Cancer

Federal gov should fund drug to treat breast cancer and endometriosis, Aus committee says

Published

on

Australia’s drug advisory committee has recommended wider funding of triptorelin for women with breast cancer or endometriosis.

The recommendation comes after AstraZeneca announced plans to remove Zoladex from the market, risking leaving more than 7,500 women with breast cancer without an alternative treatment.

Both medicines block the release of oestrogen and testosterone and can be used as part of treatment, or for fertility preservation, in some forms of cancer.

The Pharmaceutical Benefits Advisory Committee met urgently in July and recommended making triptorelin unrestricted under the Pharmaceutical Benefits Scheme (PBS), which would mean it was funded for all uses.

The drug has been listed on the PBS for prostate cancer since 2006.

Triptorelin and Zoladex can also be used to treat endometriosis and to block puberty for either precocious puberty or gender-affirming care.

Vicki Durston, director of policy and advocacy at Breast Cancer Network Australia, described the recommendation as “a significant step forward” and said access to the medicine could mean the difference between life and death for some patients.

She said some women had already chosen to have their ovaries removed because of uncertainty over Zoladex supplies.

Marilla Druitt, Victorian state chair of the Royal Australian and New Zealand College of Obstetricians and Gynaecologists, said it remained unclear whether triptorelin would work exactly the same way as Zoladex, but the recommendation was likely to be positive for patients with endometriosis and pelvic pain.

She said: “I’m glad we’ve got an alternative.”

“That’s fantastic, and it remains to be seen whether or not it will be as good, but pain is so complex, pain is a really hard thing to study because it’s got so many contributors.”

Druitt said further research would be needed after the medicine was introduced.

If accepted by the federal government, the recommendation would also allow PBS funding of triptorelin for puberty suppression in precocious puberty and gender-affirming care.

This would make gender-affirming care federally funded through the PBS for the first time and would remove a financial barrier for transgender children in Queensland and the Northern Territory.

Stuart Aitken, medical director of Gender Health Australia, said the recommendation had sparked “absolute joy” among his patients.

He said: “It takes away a huge barrier to accessing evidence-based care.”

“It means that the ban has a very limited effect.”

Continue Reading

Insight

Benchmarking 2027: Shifting priorities in US health infrastructure

Published

on

By Women’s HealthX

As healthcare organisations navigate tightening compliance mandates, evolving reimbursement frameworks, and shifting health economics, the single most critical asset for leadership is operational visibility into what their industry counterparts are executing right now.

Ahead of the Women’s HealthX marketplace in Boston this December, a cross-functional steering committee of health plans, hospital networks, biopharma innovators, and enterprise employers has launched the definitive 2026 U.S. Health Infrastructure Survey.

The objective of this brief, multi-state index is to bypass abstract market fluff and map out exactly how the country’s elite healthcare stakeholders are practically structuring their 2027 budgets, clinical protocols, and technology procurement guidelines.

Some of the questions we are asking:

  • Health Plans & Payers “What is the biggest operational barrier to expanding women’s health coverage?”
  • Health Systems & Providers “What is the biggest women’s health priority for health systems over the next 24 months?”
  • Pharma & Life Sciences “What is the biggest commercial hurdle facing women’s health innovation?”
  • Employers & Benefits Leaders “Which women’s health challenge creates the greatest workforce impact?”

By contributing just 60 seconds of your operational insight to the index, you will ensure your specific sector’s parameters are accurately represented.

In return for your participation, you will secure a priority, pre-ordered copy of the completed 30-page intelligence report when the final data drops this September!

See where your direct peer groups are drawing their line in the sand for the upcoming fiscal year.

Contribute 60 seconds and pre-order your national benchmark report

Women’s HealthX 2026 | From Rhetoric to Results

Encore Boston Harbor | December 3-4 2026

Bypass abstract market rhetoric to evaluate real-world health economics, regulatory compliance mandates, and care delivery systems.

Join the region’s foremost health plan medical directors, hospital COOs, biopharma innovators, and enterprise benefits buyers anchoring our 2026 tracks.

Review full agenda

Meet confirmed speakers

Secure your pass

Continue Reading

Trending

Copyright © 2025 Aspect Health Media Ltd. All Rights Reserved.