(Press-News.org) UNDER EMBARGO UNTIL 00:01 UK TIME ON WEDNESDAY 12 NOVEMBER 2025
Researchers at the University of Southampton have developed an artificial intelligence (AI) tool that can spot hard-to-see objects lodged in patients’ airways better than expert radiologists.
In a study published in npj Digital Medicine, the AI model outperformed radiologists in checking CT scans for objects that don’t show up well on scans.
These accidentally inhaled objects can cause coughing, choking, difficulty breathing and sometimes lead to more serious complications if not treated properly.
The findings highlight how AI can support doctors in diagnosing complex and potentially life-threatening conditions.
The research has been led by Dr Yihua Wang, Dr Zehor Belkhatir, and Prof Rob Ewing at the University of Southampton in partnership with researchers from Wuhan, China.
“These objects can be extremely subtle and easy to miss, even for experienced clinicians,” said PhD Researcher Zhe Chen, co-first author of the study from the University of Southampton.
“Our AI model acts like a second set of eyes, helping radiologists detect these hidden cases earlier and more reliably.”
Foreign body aspiration (FBA) occurs when an object, often food or a small piece of material, becomes lodged in the airways.
When the objects, such as plant material or crayfish shells, are radiolucent (invisible on X-rays and faint even on CT scans), it can be very difficult to detect. This often leads to missed or delayed diagnoses, putting patients at risk of serious complications. Up to 75 per cent of FBA cases in adults involve radiolucent foreign bodies.
To address this challenge, the research team created a deep learning model. It combines a high-precision airway mapping technique (MedpSeg) with a neural network that analyses CT images for hidden signs of foreign bodies.
The model was trained and tested using three independent patient groups, consisting of over 400 patients, in collaboration with hospitals in China.
To put the model to the test, researchers compared its performance to that of three expert radiologists, each with over ten years of clinical experience. The task was to examine 70 CT scans, 14 of which were cases of radiolucent FBA, confirmed by bronchoscopy.
When the radiologists detected a case of radiolucent FBA, they did so with total precision – there were no false positives. In comparison, the AI model did so with 77 per cent precision, detecting some false positives.
However, the radiologists missed a large portion of FBA cases, identifying just 36 per cent of them and highlighting the difficulty humans have in spotting such cases. The AI model, on the other hand, was able to spot 71 per cent of cases, meaning far fewer FBA cases slipped through the net.
In F1 score, which balances precision and recall, the model outperformed the radiologists with a score of 74 per cent vs 53 per cent.
“The results demonstrate the real-world potential of AI in medicine, particularly for conditions that are difficult to diagnose through standard imaging,” commented Dr Yihua Wang, lead author of the study.
The researchers emphasise that the system is designed to assist, not replace, radiologists - providing an additional layer of confidence in complex or uncertain cases.
The researchers now aim to conduct multi-centre studies with larger and more diverse populations to improve the model and reduce the risk of bias.
The paper Automated Detection of Radiolucent Foreign Body Aspiration on Chest CT Using Deep Learning is published in npj Digital Medicine and is available online.
The research was supported by the UK Medical Research Council and the China Scholarship Council.
Ends
Contact
Steve Williams, Media Manager, University of Southampton, press@soton.ac.uk or 023 8059 3212.
Notes for editors
The paper Automated Detection of Radiolucent Foreign Body Aspiration on Chest CT Using Deep Learning is published in npj Digital Medicine. It is available here: https://www.nature.com/articles/s41746-025-02097-w
For interviews please contact Steve Williams, Media Manager, University of Southampton press@soton.ac.uk or 023 8059 3212.
Image available here: https://safesend.soton.ac.uk/pickup?claimID=dSBtSc7WaNWCGCJ3&claimPasscode=GXtcuVJUoJJvyjrJ
Additional information
The University of Southampton drives original thinking, turns knowledge into action and impact, and creates solutions to the world’s challenges. We are among the top 100 institutions globally (QS World University Rankings 2025). Our academics are leaders in their fields, forging links with high-profile international businesses and organisations, and inspiring a 24,000-strong community of exceptional students, from over 135 countries worldwide. Through our high-quality education, the University helps students on a journey of discovery to realise their potential and join our global network of over 300,000 alumni. www.southampton.ac.uk
www.southampton.ac.uk/news/contact-press-team.page
Follow us on X: https://twitter.com/UoSMedia
END
AI detects hidden objects on chest scans better than radiologists
2025-11-12
ELSE PRESS RELEASES FROM THIS DATE:
Breakthrough gives hope in fight against aggressive form of blood cancer
2025-11-12
Researchers at the University of Southampton have identified a new subtype of lymphoma which could pave the way to improved and more targeted treatments for some blood cancer patients.
The cancer scientists and biologists have also found that lymphoma cells of this new subtype carry a unique sugar that promotes the survival and growth of the cancer.
Lymphoma is a type of blood cancer that affects white blood cells called lymphocytes. There are many different types of lymphoma, but this latest breakthrough is in a type called diffuse large B-cell lymphoma (DLBCL), which affects our B cells. When operating ...
Experts find £90K “sweet spot” for crowdfunding success
2025-11-12
A new study led by the University of East Anglia (UEA) reveals what drives investors to put their money behind business start-ups.
Researchers analysed more than a thousand successful crowdfunding campaigns on the platform Seedrs.
They found that setting a £90K “sweet spot” target, having around 19 team members, and using certain phrases including “health” and “organic” in campaign pitches all helped attract investors.
Offering a high equity percentage in return for investment was also found to be crucial – with low equity ratios putting investors off.
The researchers hope their work could help entrepreneurs fine-tune ...
Tough little wallaby sets the scene for kangaroo bounding success
2025-11-12
Flinders University fossil experts have unearthed more clues about why kangaroos and wallabies have endured to become one of the continent’s most prolific marsupial groups.
They have analysed the powerful limbs of Australia’s earliest ‘true’ kangaroo – the shared ancestor of modern-day kangaroos and wallabies.
The palaeontologists focused on the limb bones of the extinct Dorcopsoides fossilis, found only in the rich Alcoota fossil field in the southern Northern Territory.
Lead investigator Dr Isaac Kerr says these hardy hopping marsupials, which lived around 7 million years ago in a period called the Late Miocene, are ...
Scientists develop low-cost sensor to safeguard water from fireworks pollution
2025-11-11
A team of researchers from Nanjing University and Nanjing Normal University has designed a new, affordable sensor to detect toxic perchlorate in water, paving the way for better environmental monitoring and healthier communities. The sensor, inspired by porphyrin molecules and costing less than two US dollars, offers rapid and highly accurate detection of perchlorate, a harmful pollutant that often escapes into rivers and drinking water through fireworks manufacturing and industrial operations.
Perchlorate is a persistent pollutant known for its mobility, water solubility, and stability. While perchlorate can occur naturally, ...
Researchers aim to disrupt breast cancer line of communication and prevent spread
2025-11-11
Cancer Center at Illinois (CCIL) Program Leader Erik Nelson’s lab made an important discovery about the relationship between cholesterol and breast cancer progression with crucial implications for breast cancer therapeutics.
Breast cancer is the second leading cause of cancer-related death for American women, and more than 90% of breast cancer deaths are caused by metastatic spread of the disease. While breast cancer therapies have improved significantly in recent years, scientists do not yet understand the totality of molecular mechanisms involved in breast cancer progression and treatment ...
A sit-stand ratio ‘sweet spot’ may boost office productivity
2025-11-11
New research has found a simple sit-stand routine at work significantly reduces lower back pain, offering a high-impact solution for employees in sedentary work environments.
While the Griffith University-led study focused on individuals with recent lower back pain, the recommended ratio of 30 minutes sitting followed by 15 minutes standing (30:15) could benefit all desk-based workers by improving focus, reducing stress, and encouraging regular movement patterns throughout the day.
In collaboration with co-authors ...
New computational process could help condense decades of disease biology research into days
2025-11-11
At 10 one-millionths of a meter wide, a single human cell is tiny. But something even smaller exerts an enormous influence on everything a cell does: proton concentration, or pH. On the microscopic level, pH-dependent structures regulate cell movement and division. Altered pH response can accelerate the development of cancers and neurodegenerative diseases such as Alzheimer’s and Huntington’s.
Researchers hope that pinpointing pH-sensitive structures in proteins would help them determine how proteins respond to pH changes in normal and diseased cells alike and, ultimately, to ...
UTIA soil scientist receives Women in Science National Mentoring Award
2025-11-11
As a mentor, Sindhu Jagadamma, associate professor of soil science at the University of Tennessee Institute of Agriculture, helps her students increase their self-confidence and push themselves to persevere through adversity, traits she learned to improve in herself as a young girl from a small town in India.
Former mentees who worked with Jagadamma in the Sustainable Soil Management Lab nominated her for the Women in Science Mentoring Award, given by the American Society of Agronomy, Crop Science Society of America and Soil Science Society of America. She received the award at ...
New study finds generative AI can brainstorm objectives but needs human expertise for decision quality
2025-11-11
CATONSVILLE, Md., Nov. 11, 2025 – A new peer-reviewed study in the INFORMS journal Decision Analysis finds that while generative AI (GenAI) can help define viable objectives for organizational and policy decision-making, the overall quality of those objectives falls short unless humans intervene.
In the field of decision analysis, defining objectives is a foundational step. Before you can evaluate options, allocate resources or design policies, you need to identify what you’re trying to achieve.
The research underscores that AI tools are valuable brainstorming partners, but sound decision analysis still requires a “human ...
New analysis yields clearer picture of toxin-producing blue-green algae blooms
2025-11-11
CORVALLIS, Ore. – A long-term analysis shows that a major Oregon reservoir abruptly swapped one type of toxic algae for another midway through the 12-year study period, absent any obvious cause.
The project provides a novel look at harmful algal blooms, or HABs, which pose multiple health risks to people and animals worldwide.
Harmful algal blooms in lakes and reservoirs are explosions of cyanobacteria, often referred to as blue-green algae. Microscopic organisms ubiquitous in all types of water around the globe, cyanobacteria use sunlight to make their own food and in warm, nutrient-rich environments can quickly multiply, resulting in blooms that spread across ...