Cancer
AI could help improve early detection of interval breast cancer
A new study suggests that AI could help detect interval breast cancer — those that develop between routine screenings — before they become more advanced and harder to treat. This could potentially lead to better screening practices, earlier treatment and improved patient outcomes.
The study, led by investigators at the UCLA Health Jonsson Comprehensive Cancer Center and published in the Journal of the National Cancer Institute, found that AI was able to identify “mammographically-visible” types of interval cancers earlier by flagging them at the time of screening.
These include tumours that are visible on mammograms but not detected by radiologists, or have very subtle signs on mammography that are easy to miss because the signs were faint or arguably below the level of detection by the human eye.
Researchers estimate that incorporating AI into screening could help reduce the number of interval breast cancers by 30 per cent.
“This finding is important because these interval cancer types could be caught earlier when the cancer is easier to treat,” said Dr. Tiffany Yu, assistant professor of Radiology at the David Geffen School of Medicine at UCLA and first author of the study.
“For patients, catching cancer early can make all the difference. It can lead to less aggressive treatment and improve the chances of a better outcome.”
While similar research has been conducted in Europe, this study is among the first to explore the use of AI to detect interval breast cancers in the United States. Researchers point out that there are key differences between the US and European screening practices.
In the US, most mammograms are performed using digital breast tomosynthesis (DBT), often called 3D mammography, and patients are typically screened every year. In contrast, European programmes usually use digital mammography (DM), often called 2D mammography, and screen patients every two to three years.
The retrospective study analysed data from nearly 185,000 past mammograms from 2010 to 2019 that included both DM and DBT. From the data, the team looked at 148 cases where a woman was diagnosed with interval breast cancer.
Radiologists then reviewed these cases to determine why the cancer wasn’t spotted earlier. The new study adapted a European classification system to categorize the interval cancers. They include: Missed reading error, minimal signs–actionable, minimal signs–non–actionable, true interval cancer, occult (which is truly invisible on mammogram), and missed due to a technical error.
Researchers then applied a commercially available AI software called Transpara to the initial screening mammograms performed before the cancer diagnosis to determine if it could detect subtle signs of cancer that were missed by radiologists during initial screenings, or at least flag them as suspicious. The tool scored each mammogram from 1 to 10 for cancer risk. A score of 8 or higher was considered flagged as potentially concerning.
The team found that the AI flagged 76 per cent of the mammograms that had been originally read as normal but were later linked to an interval breast cancer. It flagged 90 per cent of missed reading error cases where the cancer had been visible on the mammogram but missed or misinterpreted by the radiologist.
It caught 89 per cent of minimal-signs-actionable cancers that showed very subtle signs and could reasonably have been acted upon, as well as 72 per cent of those with minimal-signs-non-actionable that were likely too subtle to prompt action.
For cancers that were occult or completely invisible on the mammogram, the AI flagged 69 per cent of cases.
It was somewhat less effective at identifying true interval cancers, those that were not present at the time of screening but developed later, flagging 50 per cent.
“While we had some exciting results, we also uncovered a lot of AI inaccuracy and issues that need to be further explored in real-world settings,” said Dr. Hannah Milch, assistant professor of Radiology at the David Geffen School of Medicine and senior author of the study.
“For example, despite being invisible on mammography, the AI tool still flagged 69 per cent of the screening mammograms that had occult cancers. However, when we looked at the specific areas on the images that the AI marked as suspicious, the AI did not do as good of a job and only marked the actual cancer 22 per cent of the time.”
Larger prospective studies are needed to understand how radiologists would use AI in practice and address key questions, such as how to handle cases where AI flags areas as suspicious that aren’t visible to the human eye, especially when the AI isn’t always accurate in pinpointing the exact location of cancer.
“While AI isn’t perfect and shouldn’t be used on its own, these findings support the idea that AI could help shift interval breast cancers toward mostly true interval cancers,” Yu added.
“It shows potential to serve as a valuable second set of eyes, especially for the types of cancers that are the hardest to catch early. This is about giving radiologists better tools and giving patients the best chance at catching cancer early, which could lead to more lives saved.”
Diagnosis
Lung cancer drug shows breast cancer potential
Ovarian cancer cells quickly activate survival responses after PARP inhibitor treatment, and a lung cancer drug could help block this, research suggests.
PARP inhibitors are a common treatment for ovarian cancer, particularly in tumours with faulty DNA repair. They stop cancer cells fixing DNA damage, which leads to cell death, but many tumours later stop responding.
Researchers identified a way cancer cells may survive PARP inhibitor treatment from the outset, pointing to a potential way to block that response. A Mayo Clinic team found ovarian cancer cells rapidly switch on a pro-survival programme after exposure to PARP inhibitors. A key driver is FRA1, a transcription factor (a protein that turns genes on and off) that helps cancer cells adapt and avoid death.
The team then tested whether brigatinib, a drug approved for certain lung cancers, could block this response and boost the effect of PARP inhibitors. Brigatinib was chosen because it inhibits multiple signalling pathways involved in cancer cell survival.
In laboratory studies, combining brigatinib with a PARP inhibitor was more effective than either treatment alone. Notably, the effect was seen in cancer cells but not normal cells, suggesting a more targeted approach.
Brigatinib also appeared to act in an unexpected way. Rather than working through the usual DNA repair routes, it shut down two signalling molecules, FAK and EPHA2, that aggressive ovarian cancer cells rely on. FAK and EPHA2 are proteins that relay survival signals inside cells. Blocking both at once weakened the cells’ ability to adapt and resist treatment, making them more vulnerable to PARP inhibitors.
Tumours with higher levels of FAK and EPHA2 responded better to the drug combination. Other data link high levels of these molecules to more aggressive disease, pointing to potential benefit in harder-to-treat cases.
Arun Kanakkanthara, an oncology investigator at Mayo Clinic and a senior author of the study, said: “This work shows that drug resistance does not always emerge slowly over time; cancer cells can activate survival programmes very early after treatment begins.”
John Weroha, a medical oncologist at Mayo Clinic and a senior author of the study, said: “From a clinical perspective, resistance remains one of the biggest challenges in treating ovarian cancer. By combining mechanistic insights from Dr Kanakkanthara’s laboratory with my clinical experience, this preclinical work supports the strategy of targeting resistance early, before it has a chance to take hold. This strategy could improve patient outcomes.”
Insight
FDA approves Agilent test for ovarian cancer
Agilent has FDA approval for a test to identify ovarian cancer patients who may be eligible for immunotherapy.
Agilent’s PD-L1 IHC 22C3 pharmDx is the only FDA-approved companion diagnostic to help identify patients with epithelial ovarian, fallopian tube or primary peritoneal carcinoma whose tumours express PD-L1 and who may be eligible for treatment with KEYTRUDA, Merck’s anti-PD-1 therapy.
A companion diagnostic is a test used alongside a specific treatment to show whether a patient is suitable for that therapy. PD-L1 is a protein on some cancer cells that helps tumours evade the immune system.
These cancers affect the reproductive system and the lining of the abdominal cavity.
The test enables pathologists to assess PD-L1 expression at diagnosis to support treatment decisions in a disease where options remain limited for many.
This is the seventh FDA-approved companion diagnostic indication for PD-L1 IHC 22C3 pharmDx for use with KEYTRUDA.
Nina Green, vice president and general manager of Agilent’s clinical diagnostics division, said: “Delivering effective precision oncology requires close collaboration between diagnostics and therapeutics, and this FDA approval reflects Agilent’s long-standing industry partnership in companion diagnostics.
“We are proud to enable pathologists to identify patients with EOC who may benefit from immunotherapy.
“As the first immuno-oncology approval for this disease, this milestone underscores our commitment to advancing precision medicine and expanding access to innovative cancer treatments worldwide.”
PD-L1 expression with this test was evaluated in the KEYNOTE-B96 clinical trial supporting its use to identify patients who may benefit from KEYTRUDA.
In the US, ovarian cancer caused approximately 12,730 deaths in 2025 and the five-year survival rate was 51.6 per cent between 2015 and 2021.
In addition to these cancer types, the test is indicated in the US to help identify patients with non-small cell lung cancer, oesophageal squamous cell carcinoma, cervical cancer, head and neck squamous cell carcinoma, triple-negative breast cancer and gastric or gastro-oesophageal junction adenocarcinoma who may benefit from treatment with KEYTRUDA.
The test was developed by Agilent with Merck as a companion diagnostic for KEYTRUDA.
Cancer
Why this is your year to enter the Women’s Cancer Innovation award
Breakthroughs in cancer care don’t only come from large institutions or fully funded labs.
They also come from determined individuals, small teams, early-stage founders, clinicians with an idea, researchers testing a new approach, technologists building smarter tools and advocates redesigning how care is delivered.
If you’re building something that could change how we prevent, detect, treat, manage or live with cancer, the Women’s Cancer Innovation award sponsored by Endomag is for you.
This award is designed to spotlight organisations, technologies and individuals who are moving cancer innovation forward at any meaningful stage.
Innovation doesn’t have to fit one mold
When people hear “cancer innovation,” they often picture a new drug or medical device.
But meaningful progress happens across many areas, including digital health tools, diagnostics and early detection approaches, AI and data platforms, care delivery models, patient support solutions and more.
If your work addresses a real cancer challenge in a new or more effective way, it counts.
And you don’t need to be “finished.” Many companies delay applying for awards until everything feels polished and complete.
But the Femtech World Awards are as much about recognising momentum and potential as they are celebrating outcomes.
Judges and reviewers understand innovation journeys. They are often more interested in clarity of problem, strength of insight, and thoughtful design than in perfect execution.
Progress matters. Direction matters. Impact potential matters.
And finally, if you’re wondering “Is this good enough?” – apply.
Many strong applicants almost don’t apply. The most common hesitation isn’t lack of innovation – it’s self-doubt.
If you’re asking yourself whether your project is too early, your team too small, your work innovative enough, or whether it counts if you’re not a startup, those questions are normal.
They’re also often the very reason you should submit.
These awards exist because great work is sometimes overlooked, underfunded, or under-recognised.
The goal is to surface promising solutions and support the people building them.
Find out more about the Femtech World Awards and enter for free here.
-
Insight4 weeks agoDesigner perfumes recalled over banned chemical posing fertility risk
-
Insight2 weeks agoParents sue IVF clinic after delivering someone else’s baby
-
Insight3 weeks agoWomen’s health could unlock US$100bn by 2030
-
Insight4 weeks agoChina’s birth rate hits record low despite government fertility efforts
-
Menopause3 weeks agoHRT linked to greater weight loss on tirzepatide
-
Entrepreneur5 days agoUS startup builds wearable hormone tracker
-
Menopause2 weeks agoFlo Health and Mayo Clinic publish global perimenopause awareness study
-
Wellness4 weeks agoVerdane invest in Clue to accelerate the future of women’s health






1 Comment