PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

AI detects the stiffness of cancer cell exosomes: DGIST develops deep learning-based lung cancer diagnostic technology

2025-07-30
(Press-News.org) □ The research team led by Senior Researchers Yoonhee Lee from the Division of Biomedical Technology and Gyogwon Koo from the Division of Intelligent Robot at DGIST (under President Kunwoo Lee) has developed a technology that distinguishes lung cancer gene mutations solely by measuring the “stiffness” of exosomes—tiny particles released from cancer cells in the bloodstream—using atomic force microscopy (AFM). Their study enables rapid and precise analysis of individual exosomes and is expected to advance into a new liquid biopsy-based diagnostic technique for lung cancer.

 

□ Non-small cell lung cancer (NSCLC) is the most common type of lung cancer, accounting for more than 85% of all cases. However, because it rarely shows noticeable symptoms in the early stages, it is often diagnosed at an advanced stage, making treatment difficult. NSCLC continues to have a high mortality rate, and developing new diagnostic technologies that enable early detection and treatment remains a significant challenge in the medical field. In particular, conventional tissue biopsies place a considerable burden on patients and have limitations in repeated testing. As such, non-invasive liquid biopsy technology utilizing blood-derived information has recently attracted attention.

 

□ The research team led by Senior Researchers Yoonhee Lee and Gyogwon Koo at DGIST isolated exosomes from NSCLC cell lines with distinct genetic mutations (A549: KRAS mutation, PC9: EGFR mutation, PC9/GR: EGFR-resistant mutation). Using AFM, the team measured nano-scale physical properties of individual exosomes at high resolution, including surface stiffness and height-to-radius ratios.

 

□ They found that the exosomes derived from A549 cells exhibited significantly higher stiffness, which indicated that alterations in the cell membrane lipids caused by KRAS mutations were also reflected in the exosomes. In contrast, exosomes derived from PC9 and PC9/GR cells showed similar properties, suggesting a correlation with their shared genetic background. These findings demonstrate that the physical properties of exosomes vary depending on the genetic mutations of the cancer cells from which they originate.

 

□ To precisely classify these nanomechanical characteristics of exosomes, the research team employed AI technology. Height and stiffness data of exosomes obtained through AFM were visualized and used to train a deep learning-based convolutional neural network (DenseNet-121) model to classify their cell lines of origin. Exosomes derived from A549 cells were distinguished with a remarkably high accuracy of 96%, and the overall average AUC reached 0.92. This demonstrates the potential of a next-generation liquid biopsy platform capable of high-precision classification based solely on the physical properties of exosomes, without the need for fluorescent labeling.

 

□ Senior Researchers Yoonhee Lee and Gyogwon Koo stated, “This study presents a new diagnostic potential to distinguish lung cancer with specific genetic mutations using only a small amount of exosome samples. We plan to actively pursue the practical application of this technology by integrating a high-speed AFM platform in clinical sample validation.”

 

□ This study was conducted with Senior Researcher Yoonhee Lee from the Division of Biomedical Technology and Gyogwon Koo from the Division of Intelligent Robot at DGIST serving as corresponding authors, and postdoctoral researcher Soohyun Park from the Division of Biomedical Technology and Dr. Youngkyu Kim from Columbia University as co-first authors. The research findings were published online in the renowned chemistry journal Analytical Chemistry on July 8, 2025. 

 

- Corresponding Author E-mail Address : yoonhee@dgist.ac.kr

END


ELSE PRESS RELEASES FROM THIS DATE:

Positive ethnic identity fosters STEM career aspirations

2025-07-30
When Black and Latino youth aspire toward careers in science and technology, their confidence in exploring career possibilities and how they think society views their ethnic-racial group can play a crucial role in whether their dreams take root. Such is a finding of a study by UC Riverside associate professor of psychology Aerika Brittian Loyd, UCR doctoral candidate Tate LeBlanc, and co-authors published in the Journal for STEM Education Research. Middle and high school students who voiced higher expectations of success in exploring different career paths — along with perceptions that their racial ...

Wildlife show wide range of responses to human presence in U.S. national parks

2025-07-30
The presence of humans and human infrastructure in U.S. national parks has lasting effects on the behaviours of the large animals that call them home, according to a new study. “Wildlife all around the world fear people and avoid areas of high human activity, but it was surprising to see that this holds true even in more remote protected areas,” said Dr. Kaitlyn Gaynor, a zoologist at the University of British Columbia and lead author of the paper published today in the Proceedings of the Royal Society B. Researchers tracked 229 animals from 10 species across 14 national parks and protected areas using GPS collar data from 2019 to 2020, ...

Great Tits show early signs of splitting up: Oxford researchers uncover social clues to bird 'divorce'

2025-07-30
In a discovery that deepens our understanding of animal social bonds, a study led by University of Oxford researchers in collaboration with the University of Leeds has demonstrated that wild great tits exhibit clear behaviours signalling ‘divorce’ long before the breeding season. The findings, published today (30 July) in Proceedings of the Royal Society B, provide valuable new insights into how animals navigate complex social decisions. provide valuable new insights into how animals navigate complex social decisions. For monogamous birds that only bond with one partner at a time, ...

From the lab to the hand: nanodevice brings personalized genomics closer to reality

2025-07-30
Osaka, Japan – DNA holds the instructions that make us who we are. If we want to read those instructions, say to understand our predisposition to genetic disorders, we need to carefully ‘unzip’ DNA’s iconic double-helix structure. This is neither easy nor fast, and the process involves intense heating and chemicals that can damage the DNA. Now, in a new study published in ACS Nano, a research team led by The University of Osaka has developed a novel technology for making the unzipping process much easier. Their invention uses a miniature heater to precisely and gently unzip the DNA double helix. The device uses a nano-sized platinum coil. As the DNA strand reaches ...

Women politicians receive more identity-based attacks on social media than men, study finds

2025-07-30
Women politicians in Europe receive uncivil tweets regardless of how known they are – and woman also receive more identity-based attacks than other politicians, revealed a new study in Politics & Gender, published on behalf of the American Political Science Association by Cambridge University Press.  This study used a machine learning approach to analyse over 23 million tweets addressed to politicians in Germany, Spain, the United Kingdom, and the United States, to determine the degree of incivility that female politicians face. Women in politics frequently report serious online harassment, yet the extent of this harassment and how it compares ...

Idaho National Laboratory accelerates nuclear energy projects with Amazon Web Services cloud and AI technologies

2025-07-29
(IDAHO FALLS, Idaho) — The Idaho National Laboratory (INL) and Amazon Web Services (AWS) will collaborate to use AWS’s advanced capabilities and cloud infrastructure to develop artificial intelligence (AI) tools for nuclear energy projects. INL leads the nation in adapting AI for the nuclear energy industry. The laboratory is developing a suite of technologies that use AI to reduce the costs and timeframes of designing, licensing, building and operating nuclear facilities. Ultimately, the tools could be used for safe and reliable autonomous operation of nuclear reactors and accelerating deployment of new advanced reactors. AWS’s advanced computing power and AI foundation ...

Kavraki elected to European Academy of Sciences

2025-07-29
Lydia Kavraki, a pioneering researcher in robotics, computational biomedicine and artificial intelligence (AI) at Rice University, has been elected to the European Academy of Sciences. This prestigious organization recognizes excellence in scientific advancement and innovation.  The honor will be conferred in Geneva in December, placing Kavraki among an elite group of scientists whose work drives progress in both academia and applied technology. Kavraki, the Kenneth and Audrey Kennedy Professor of Computing, holds multiple appointments across engineering ...

UK teens who currently vape as likely to start smoking as their peers in the 1970s

2025-07-29
UK teens who currently vape are as likely to take up smoking as their peers in the 1970s,  despite a substantial fall in the prevalence of teenage smoking over the past 50 years, suggests a long term intergenerational study published online in the journal Tobacco Control. The likelihood of starting to smoke among teens who don’t vape was around 1.5%, but 33% among those who do, the findings indicate. It’s not entirely clear if the rise in popularity of e-cigarettes (vapes) among teens threatens the steady decline in the prevalence of cigarette smoking in this age group, say the researchers, as the ...

Higher ultra processed food intake linked to increased lung cancer risk

2025-07-29
A higher intake of ultra processed food (UPF) is linked to an increased risk of lung cancer, suggests research published online in the respiratory journal Thorax. Further research is warranted in different population groups, but limiting consumption of these foods may help curb the global toll of the disease, say the researchers. Lung cancer is the most common cancer in the world. And in 2020 alone there were an estimated 2.2 million new cases and 1.8 million deaths from the disease worldwide, they note. UPF typically undergo multiple processing steps, contain long lists of additives and preservatives, and are ready-to-eat or heat. High consumption has been linked to a heightened risk of ...

Exercise rehab lessens severity, frequency + recurrence of irregular heart rhythm (AF)

2025-07-29
Exercise-based cardiac rehabilitation lessens the severity, frequency, and recurrence of the most common form of irregular heart rhythm, atrial fibrillation, or AF for short, finds a pooled data analysis of the available research, published online in the British Journal of Sports Medicine. It also improves general exercise capacity and mental health, without incurring any serious side effects, the findings show. AF occurs when the heart's upper chambers (atria) don’t contract properly and instead twitch, disrupting the electrical signals to the lower chambers (ventricles). Symptoms can include palpitations, ...

LAST 30 PRESS RELEASES:

We might inhale 68,000 lung-penetrating microplastics daily in our homes and cars – 100x previous estimates

Indian adults who move to cities are significantly more likely to become obese than their rural counterparts - and the longer they stay, the greater the risk

Instagram images could influence public opinion on certain major events

Different dimensions of psychopathy might be associated with different physiological underpinnings of facial emotion recognition - and oxytocin could affect this skill - per scoping review of 66 studi

How cumulative heat exposure affects students

An international survey of over 300 adults reveals that males born in summer are potentially more prone to depression than those born in other seasons

The unusual head of a fish and the puzzle of its genes

How does metformin lower blood sugar?

Increasing solar power could lead to significant cuts in CO2 emissions

Black Death offers window into how childhood malnutrition affects adult health

Clinical trial finds safe, effective treatment for children with severe post-Covid syndrome

Researchers map where solar energy delivers the biggest climate payoff

Carbon fiber boosts dry-processed battery performance

Influenza-associated acute necrotizing encephalopathy in US children

Rainy tropics could face unprecedented droughts as an Atlantic current slows

‘One and done’: A single shot at birth may shield children from HIV for years, study finds

New method for detecting neutrinos

Respiratory viruses can wake up breast cancer cells in lungs

Stroke center certification and within-hospital racial disparities in treatment

Mortality among surgeons in the United States

Carbon 'offsets' aren't working. Here's a way to improve nature-based climate solutions

Preserving and promoting clinical trial representativeness

Study reveals mixed impact of state e-cigarette flavor bans on tobacco use

McMaster research offers promising new treatment for liver cancer

Most US adults have hearts older than their actual age. How old is yours?

JMIR Biomedical engineering invites submissions on voice phenotyping and vocal biomarkers

The metabolic dialogue between intratumoral microbes and cancer: implications for immunotherapy

Demographic data supporting FDA authorization of AI devices for Alzheimer disease and related dementias

How the common fungus Candida albicans colonizes the gut

How are coastal New Jersey communities communicating hazards of climate change?

[Press-News.org] AI detects the stiffness of cancer cell exosomes: DGIST develops deep learning-based lung cancer diagnostic technology