An AI tool has identified microscopic breast cancer patterns that could help medical professionals better forecast disease progression.

The tool, called CenSegNet, was developed to analyse hundreds of thousands of cells in tumour samples and detect abnormalities in structures known as centrosomes.

Centrosomes are small structures inside cells that ensure DNA is divided equally during cell replication. Researchers say abnormalities in these structures have been considered a hallmark of cancer for more than a century.

In cancerous tissue, centrosomes can replicate excessively, driving the progression of the disease.

Scientists at the University of Southampton used the system to study tissue from 127 breast cancer patients being treated at University Hospital Southampton.

More than 330,000 centrosomes were analysed, revealing two distinct abnormalities that had previously been considered part of the same process.

One involved cells developing too many centrosomes, while the other involved centrosomes becoming abnormally enlarged.

Researchers found the two defects behaved independently and could occur in different areas of the same tumour.

Dr Salah Elias, of the University of Southampton’s school of biological sciences and institute for life sciences, said: “For more than a century, centrosome abnormalities have been recognised as a hallmark of cancer, but studying them in patient tissues has been extremely challenging.

“CenSegNet allows us to analyse these defects at single-cell resolution across entire tumours and uncover patterns that were previously impossible to see.

“Rather than viewing centrosome abnormalities as a single phenomenon, our study shows that they have distinct biological states with different spatial distributions and clinical associations.”

The platform also helped uncover a link between different centrosome abnormalities and features of cancer.

Tumours with high levels of enlarged centrosomes were more aggressive, while patients whose cells had lower levels had a better chance of survival.

Dr Elias said: “Specific combinations of defects may influence how a tumour grows, invades surrounding tissues and responds to treatment.

This opens the door to developing new biomarkers and, ultimately, more personalised treatment strategies.”

Researchers hope AI could eventually be used to track disease by analysing the behaviour of cell structures.

The team also plans to combine CenSegNet with more data to explore whether it could help guide treatment decisions.

Glaucoma drugs could potentially be repurposed to treat aggressive breast cancer after researchers identified markers linked to response.

Scientists found that several cancers, including breast cancer, melanoma and a type of blood cancer, rely on the same molecule to become aggressive and spread.

Drugs that block the molecule are already used to treat glaucoma and may therefore have potential as cancer treatments.

Researchers also identified markers that could help indicate which patients may respond well to the drugs.

Experts said the findings could help establish which patients may benefit from existing treatments.

Repurposing medicines already shown to be safe could also allow treatments to reach patients faster.

Lead author Victoria Sanz Moreno, professor of cancer cell and metastasis biology at The Institute of Cancer Research in London, said: “Some cancers are particularly aggressive, and once they spread they become very hard to treat.

“Catching these aggressive cancers and preventing their ability to move around the body is really crucial to our mission to keep more people living well with cancer.

“Our research has identified a shared weakness of aggressive cancer cells that could be targeted across many cancer types, wherever they originate in the body.

“We confirmed our findings in aggressive cancers such as breast cancer, melanoma, and a type of blood cancer called acute myeloid leukaemia, but we believe this molecular fingerprint of cancer cells likely to die after treatment applies to many more cancer types.

“It’s reassuring to know that a treatment already exists – a drug currently being used safely in some patients could be adapted to treat these cancers.”

Researchers set out to find markers that could identify which cancers would respond well to drugs blocking ROCK, also known as Rho kinase.

Aggressive cancer cells rely on ROCK as they spread around the body and cause advanced disease that is harder to treat.

The molecule keeps the scaffolding inside cells tense, causing them to contract and become round and generating enough force for cancer cells to squeeze through tissue.

The team, working in the Breast Cancer Now Toby Robins Research Centre at The Institute of Cancer Research, examined data from a drug-sensitivity database to identify which cancer cells responded to ROCK inhibitors.

Breast cancer cells that responded to ROCK inhibitors had a particular gene called E-Cadherin that was not working properly.

In melanoma, responsive cells tended to have a more rounded shape and high activity in a signalling pathway called NFKB.

Acute myeloid leukaemia cells that responded well to ROCK inhibitors had a specific subset of genetic alterations.

Researchers then tested the findings in laboratory tumour samples and mouse studies.

They hope tumour biopsies showing these markers could eventually help identify patients who may respond well to ROCK inhibitors.

Dr Simon Vincent, chief scientific officer at Breast Cancer Now, said: “With around 11,500 women tragically dying from breast cancer every year in the UK, research like this is vital to finding more effective treatment options.

“This study helps to lay the foundation for understanding who among those with certain cancers, including breast cancer, might benefit most from existing drugs. Finding new uses for existing treatments, which we know people can safely take, is easier and faster than developing new cancer drugs from scratch.

“It’s encouraging that these drugs may be especially effective in targeting cancer cells that are more likely to spread and resist treatment.

“While this research is still at an early stage and clinical trials are needed, it’s an important step towards more personalised breast cancer treatments in the future.”

First author Jaume Barcelo, formerly a postdoctoral research fellow at The Institute of Cancer Research in London and now based at Barts Cancer Institute at Queen Mary University of London, said: “Our study has identified a specific pattern of features that is consistent across many cancer types, and that can be used to match the right patients to this treatment.

“The next stage for this research will be to test how these drugs that inhibit ROCK work in combination with other treatments, to maximise the benefit for patients.

“As ROCK inhibitors are already approved to treat glaucoma, I hope that our findings can be used to progress the drugs into clinical trials to treat cancer in the near future.”

The research was funded by The Institute of Cancer Research, Breast Cancer Now, Barts Cancer Charity, Cancer Research UK, Worldwide Cancer Research and UK Research and Innovation.

Susanna Daniels, chief executive officer of Melanoma Focus, said: “Despite major advances in melanoma treatment over the past decade, too many people still die from the disease each year, and not every patient responds to the treatments currently available.

“Every new discovery improves our understanding of how melanoma grows and survives, bringing us closer to treatments that are more effective, more targeted and have the potential to improve survival.

“While these findings are still at an early stage and will need to be tested in clinical trials, they offer an encouraging direction for future melanoma research and the development of more personalised treatments.”

Women living in socially vulnerable neighbourhoods had a 20 per cent higher risk of death after an ovarian cancer diagnosis, a study found.

Black women also faced a 45 per cent higher risk of death than white women.

Researchers said the combination of being Black and living in a highly vulnerable neighbourhood was linked to a greater risk of death than would be expected from either factor alone.

Francesmary Modugno, professor in the Department of Obstetrics, Gynecology and Reproductive Sciences at the University of Pittsburgh and senior author, said: “We expected residential context to influence outcomes, but what surprised us was how much stronger the impact was for Black women.

“Our findings suggest that it’s not simply where someone lives. The interaction between a woman’s lived experience and her residential environment may be helping drive these persistent disparities.”

Modugno is part of the Women’s Cancer Research Center, a collaboration between UPMC Hillman Cancer Center and Magee-Womens Research Institute.

Epithelial ovarian cancer is the deadliest form of gynaecological cancer, with around half of patients surviving for five years after diagnosis.

Survival is lower among Black women, with fewer than 40 per cent alive five years after diagnosis.

Differences including age at diagnosis, cancer stage and tumour type explain some of the survival gap, but researchers said a substantial proportion remains unexplained.

Researchers examined whether social determinants of health, including conditions in the communities where patients live, could help explain the remaining difference in outcomes.

The study, carried out with researchers at the University of Alabama at Birmingham, analysed data from 2,544 women diagnosed with epithelial ovarian cancer and treated at the O’Neal Comprehensive Cancer Center.

The group included 509 Black women and 2,035 white women.

Researchers linked patients’ residential census tracts to the US Centers for Disease Control and Prevention’s Social Vulnerability Index.

The index measures neighbourhood factors including poverty, housing conditions, transport access, educational attainment and other socioeconomic challenges.

Black women in the study were more likely to live in highly vulnerable neighbourhoods.

However, where women lived did not fully explain the racial difference in survival.

Black women had poorer survival than white women even when they lived in similarly advantaged communities, while being Black and living in a highly vulnerable neighbourhood together was associated with a greater risk of death than expected from either factor alone.

Researchers said the findings could help health systems and cancer services identify women at greater risk and provide additional support.

Possible measures include patient navigation programmes, transport assistance, childcare support and survivorship services to help patients complete treatment and manage the challenges of cancer care.

Rebecca Arend, associate professor of gynaecology oncology at the University of Alabama at Birmingham, said: “Our findings reinforce that we must better understand and address the barriers patients face in their communities and ensure that every woman has equitable access to high-quality care.”

Arend, who is also associate director of clinical research at the O’Neal Comprehensive Cancer Center, added: “Translating research into meaningful improvements in cancer outcomes is only possible through strong collaborations among academic medical centres, researchers and community partners.”

The study builds on research published in 2025 led by Modugno and University of Pittsburgh colleagues using data from UPMC Hillman Cancer Center in western Pennsylvania.

That research also found an association between social vulnerability and ovarian cancer survival.

The latest analysis included a substantially larger group of Black women and examined more closely how residential conditions might contribute to racial inequalities in outcomes.

Researchers said the findings need to be replicated in other parts of the US and among additional racial and ethnic groups to determine how widely they apply.

Future work will examine other social and environmental factors that could affect ovarian cancer survival, including neighbourhood pollution, access to food and community resources.

Researchers hope the findings could lead health systems to develop more targeted support for patients at greatest risk of poor outcomes.

Adding neighbourhood measures such as the Social Vulnerability Index to cancer care planning could help health systems identify women facing barriers to care and connect them with support during treatment.