Connect with us

Cancer

AI could help improve early detection of interval breast cancer

Published

on

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.”

Cancer

Common cholesterol drug shows ovarian cancer promise

Published

on

A common cholesterol drug could help weaken a fluid shield that helps ovarian cancer tumours survive, early lab findings suggest.

The findings do not show the drug treats ovarian cancer. But they suggest changing the environment the cancer depends on could make it more vulnerable to existing treatment.

A federally funded study at Duke University School of Medicine found that ascites, a build-up of fluid in the abdomen, may do more than cause discomfort.

Doctors can drain ascites to ease pain, improve mobility and make breathing easier, but the fluid may also help cancer cells survive and spread. It occurs in 90 per cent of people with advanced ovarian cancer.

According to the study, ascites acts as a shield, helping cancer cells evade ferroptosis, a form of cell death.

Ferroptosis is a kind of cellular rusting. It happens when iron inside a cell reacts with certain fats, causing the cell membrane to break apart.

Many metastatic cancer cells, meaning cells that float freely through the abdomen looking for new places to grow, are naturally vulnerable to this kind of damage.

“Doctors have mostly viewed ascites as a symptom rather than an active driver of disease,” said Jen-Tsan Chi, professor in the department of molecular genetics and microbiology and co-leader of the Cancer Biology Program at the Duke Cancer Institute.

“We’ve learned it gives cancer a survival advantage, which fills a major gap in understanding how ovarian cancer spreads.”

Scientists bathed cancer cell lines and patient-derived tumour cells in ascites collected from patients and watched how they responded to ferroptosis triggers.

The fluid protected cancer cells by changing how they store fats and control iron levels, effectively blocking cell death.

The protection required only trace amounts, with as little as 2 per cent immersion shielding cancer cells from destruction.

“What surprised us was how selective this effect was,” said Yasaman Setayeshpour, first author and graduate student in molecular genetics and microbiology at Duke School of Medicine.

“Ascites didn’t protect the cancer cells from other well-known types of cell death, like apoptosis or necrosis, it only blocked ferroptosis.

“To figure out why, we broke ascites down into major parts, like lipids, proteins, and small molecules, and tested what happened when each was removed.

“When we took the lipids out, the protective effect disappeared. That told us lipids are the key reason ascites helps these cancer cells survive.”

But researchers found an unexpected helper in bezafibrate, an older cholesterol drug used to lower triglycerides by altering how the body processes fats.

The cholesterol drug restored sensitivity to ferroptosis, but only when ascites was present. On its own, the drug did not trigger cell death or slow tumour growth in mice.

The drug’s impact depended on the cancer’s surroundings, in this case the fat-rich fluid bathing the tumour. Researchers found that targeting this environment, using repurposed drugs like bezafibrate, could leave cancer cells more exposed to existing cancer treatments.

Chi said the finding could have implications beyond ovarian cancer. Other cancers, including colorectal and pancreatic cancers, can also spread within the abdominal cavity.

“This work shows how much the environment around a tumour matters,” Chi said.

“Biological fluids like ascites don’t just give cancer cells a place to move. They actively help drive how cancer spreads.”

Continue Reading

Diagnosis

Artera receives FDA Clearance for breast cancer platform

Published

on

Artera has won FDA clearance for ArteraAI Breast, its breast cancer platform for patients with early-stage HR-positive, HER2-negative invasive breast cancer.

ArteraAI Breast is the first and only FDA-cleared digital pathology-based risk stratification tool for breast cancer.

These FDA milestones come alongside recent CE marking for both the ArteraAI Prostate Biopsy Assay and the ArteraAI Breast Cancer Assay in the US and Europe.

“FDA clearance for ArteraAI Breast represents a significant expansion of our FDA-cleared AI platform in oncology,” said Andre Esteva, chief executive and co-founder of Artera.

“This milestone reflects the growing role of our technology across multiple cancer types. Breast cancer care is highly nuanced, with treatment decisions that depend on individualised risk.

“Our goal remains consistent across prostate and breast cancer, and beyond: to help clinicians translate complex data into more precise, personalised treatment decisions across the cancer journey.”

ArteraAI Breast generates an AI-derived risk score showing the likelihood of distant metastasis, meaning cancer spreading to another part of the body, in patients with early-stage HR-positive, HER2-negative breast cancer.

Using digitised histopathology images, which are scanned tissue sample images, alongside patient clinical variables, the model sorts patients into low-risk and high-risk groups based on a predefined risk score cut-off.

In early-stage HR-positive, HER2-negative breast cancer, deciding the right intensity of treatment can be complex because clinical and pathological factors vary. Artera said the tool is designed to support clinicians within established decision-making frameworks.

Data presented at the 2025 San Antonio Breast Cancer Symposium evaluated the model in early-stage breast cancer and demonstrated the potential to inform chemotherapy benefit in certain patient populations.

“This clearance represents an important advance on the road to personalising treatments for patients with early-stage breast cancer,” said Eric Winer, medical oncologist and director of the Yale Cancer Center.

“Using AI and digital pathology has the potential to streamline operational workflows, while creating a strong interdisciplinary linkage between oncology and pathology. This approach may further improve the clinicians’ ability to help patients make the best treatment decisions.”

ArteraAI Breast is designed to integrate directly into standard pathology workflows using routine surgical resection samples, without requiring additional tissue or separate specimen collection.

This approach allows the software to provide same-day results, enabling pathology laboratories to give clinicians patient-specific prognostic risk information alongside standard histopathology reports.

Continue Reading

Diagnosis

Nurse celebrates role in trial that enhanced breast cancer surgery outcomes

Published

on

A nurse who works with breast cancer patients has spoken of her pride after joining a trial that improved breast cancer surgery after her own diagnosis.

Heidi Jones, a 53-year-old staff nurse on the surgical day unit at Basildon Hospital, is a mother of two from Corringham in Essex and works with breast cancer patients daily.

She was diagnosed with breast cancer in 2025, the day after her birthday. She told ITV News Anglia that she had jumped at the opportunity to take part in the trial.

“I said yes because we need to get out there about the advancements in treatment and in surgery and medicines,” she said.

“Cancer is a big thing, so whatever you can do to improve the treatment of the cancer, I was all for it.”

Mid and South Essex NHS Foundation Trust was one of two UK centres taking part in the trial, alongside 21 others across the US, Canada and Austria.

The trial involved using a breast cancer locator, or BCL, a customised 3D mould matched to the unique dimensions of the patient’s tumour and breast.

The BCL is then placed over the patient during surgery, giving teams more detailed guidance on the tumour’s shape, size and location.

Results found a 34 per cent reduction in the number of second surgeries needed, and a 32 per cent reduction in cases where cancer remained after surgery.

Surgeon Wayne Chicken said the new technique could have a big impact on some patients.

“I’ve been working in breast surgery for 25 years, and breast surgery has changed radically in those 25 years,” he said.

“Now we’re trying to do less and less, the minimum necessary to control the disease, rather than big procedures and potentially over-treat cancers. This is doing the minimum necessary to treat the cancer.”

This actually uses the information from the MRI scans to plan, so the impact is less surgery and more likely to get it right in a single operation.

Using the BCL system, Jones’s breast cancer surgery was a success, with the tumour removed completely.

“I do talk about things quite openly, and I use it now when the ladies are coming in. I’ll tell them I’ve gone through it,” she said.

“It just gives them that little bit more to let them know someone else has come through [treatment] and has come through the other side.

“I feel proud that I actually took part in it. I feel privileged to have taken part in it and been asked to do it.

“I’m extremely glad it’s been really successful as well. I was lucky, I class myself lucky.”

Continue Reading

Trending

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