(Press-News.org)
Melanoma remains one of the hardest skin cancers to diagnose because it often mimics harmless moles or lesions. While most artificial intelligence (AI) tools rely on dermoscopic images alone, they often overlook crucial patient information (like age, gender, or where on the body the lesion appears) that can improve diagnostic accuracy. This highlights the importance of multimodal fusion models that can enable high precision diagnosis.
To bridge that gap, Professor Gwangill Jeon from the Department of Embedded Systems Engineering, Incheon National University, South Korea, in collaboration with the University of West of England (UK), Anglia Ruskin University (UK), and the Royal Military College of Canada, created a deep learning model that integrates patient data and dermoscopic images. The study was made available online on June 06, 2025, and will be published in Volume 124 of the journal Information Fusion on December 01, 2025.
“Skin cancer, particularly melanoma, is a disease in which early detection is critically important for determining survival rates,” says Prof. Jeon. “Since melanoma is difficult to diagnose based solely on visual features, I recognized the need for AI convergence technologies that can consider both imaging data and patient information.”
Using the large-scale SIIM-ISIC melanoma dataset, which contains over 33,000 dermoscopic images paired with clinical metadata, the team trained their AI model to recognize subtle links between what appears on the skin and who the patient is. The model achieved 94.5% accuracy and an F1-score of 0.94, outperforming popular image-only models such as ResNet-50 and EfficientNet.
The researchers also performed feature importance analysis to make the system more transparent and robust. Factors like lesion size, patient age, and anatomical site were found to contribute strongly for accurate detection. These insights can help doctors understand and provide a roadmap to trust the diagnosis performed by AI.
Prof. Jeon says, “The model is not merely designed for academic purposes. It could be used as a practical tool that could transform real-world melanoma screening. This research can be directly applied to developing an AI system that analyzes both skin lesion images and basic patient information to enable early detection of melanoma.”
In the future, the model could power smartphone-based skin diagnosis applications, telemedicine systems, or AI-assisted tools in dermatology clinics, helping reduce misdiagnosis rates and improve access to care. Prof. Jeon explains, “The study represents a step forward toward personalized diagnosis and preventive medicine through AI convergence technology.”
The study highlights how multimodal AI can bridge the gap between machine learning and clinical decision-making, paving the way for more accurate, accessible, and trustworthy skin cancer diagnostics.
***
Reference
Authors: Misbah Ahmada,b, Imran Ahmedc, Abdellah Chehrid, Gwangill Jeone*
Affiliations:
aCentre for Machine Vision, Bristol Robotics Laboratory, University of West of England, UK
bDepartment of Animal and Agriculture, Hartpury University, UK
cSchool of Computing and Information Science, Anglia Ruskin University, UK
dDepartment of Mathematics and Computer Science, Royal Military College of Canada (RMC), Canada
eDepartment of Embedded Systems Engineering, Incheon National University, Republic of Korea
About Incheon National University
Incheon National University (INU) is a comprehensive, student-focused university. It was founded in 1979 and given university status in 1988. One of the largest universities in South Korea, it houses nearly 14,000 students and 500 faculty members. In 2010, INU merged with Incheon City College to expand capacity and open more curricula. With its commitment to academic excellence and an unrelenting devotion to innovative research, INU offers its students real-world internship experiences. INU not only focuses on studying and learning but also strives to provide a supportive environment for students to follow their passion, grow, and, as their slogan says, be INspired.
Website: https://www.inu.ac.kr/sites/inuengl/index.do?epTicket=LOG
About the author Professor Gwanggil Jeon
Prof. Gwanggil Jeon received his B.S., M.S., and Ph.D. (summa cum laude) degrees from the Department of Electronics and Computer Engineering at Hanyang University, Seoul, Korea, in 2003, 2005, and 2008, respectively. From 2009 to 2011, he was with the School of Information Technology and Engineering, University of Ottawa, Ottawa, ON, Canada, as a Post-doctoral Fellow. From 2011 to 2012, he served as an Assistant Professor at the Graduate School of Science and Technology at Niigata University, Japan. From 2014 to 2015 and 2015.06 to 2015.07, he remained a Visiting Scholar at Centre de Mathématiques et Leurs Applications (CMLA), École Normale Supérieure Paris-Saclay (ENS-Cachan) in France. Dr. Jeon is currently a full-time Professor at Incheon National University in Korea.
END
Glioblastoma—the most aggressive form of brain cancer—remains one of medicine’s biggest challenges. Despite surgery, radiotherapy, and chemotherapy, most patients survive only about a year after diagnosis. However, a new discovery might change how doctors understand and monitor this deadly disease. Specifically, the study focused on isocitrate dehydrogenase (IDH) wild-type glioblastoma, the most common and rapidly growing form of the tumor, known for its poor prognosis and limited treatment options.
In a study published online on October 11, 2025, in Neuro-Oncology, ...
The most common technique used for closing the uterus after a cesarean delivery causes so many long-term complications that it’s time to question its use. That’s the conclusion reached by two world-renowned specialists in obstetrics and gynecology in an article published in a special issue of the American Journal of Obstetrics & Gynecology on cesarean delivery. The authors argue in favor of replacing the current approach with a closure technique that respects the natural anatomical structure of the uterus.
The authors, Dr Emmanuel Bujold, professor at Université ...
Researchers Kohki Horie, Keiichiro Toda, Takuma Nakamura, and Takuro Ideguchi of the University of Tokyo have built a microscope that can detect a signal over an intensity range fourteen times wider than conventional microscopes. Moreover, the observations are made label-free, that is, without the use of additional dyes. This means the method is gentle on cells and adequate for long-term observations, holding potential for testing and quality control applications in the pharmaceutical and biotechnology industries. The findings are published in the journal Nature Communications.
Microscopes have ...
ANN ARBOR—For a long time, evolutionary biologists have thought that the genetic mutations that drive the evolution of genes and proteins are largely neutral: they're neither good nor bad, but just ordinary enough to slip through the notice of selection.
Now, a University of Michigan study has flipped that theory on its head.
In the process of evolution, mutations occur which can then become fixed, meaning that every individual in the population carries that mutation. A longstanding theory, called the Neutral Theory of Molecular Evolution, posits that most genetic mutations that are fixed are neutral. Bad mutations ...
Tensor operations are the kind of arithmetic that form the backbone of nearly all modern technologies, especially artificial intelligence, yet they extend beyond the simple maths we’re familiar with. Imagine the mathematics behind rotating, slicing, or rearranging a Rubik’s cube along multiple dimensions. While humans and classical computers must perform these operations step by step, light can do them all at once.
Today, every task in AI, from image recognition to natural language processing, relies on tensor operations. However, the explosion of ...
Mangrove ecosystems rank among the most efficient "blue carbon" systems on Earth, capable of absorbing and storing vast quantities of atmospheric carbon dioxide (CO2). However, mangroves also release methane (CH4), a potent greenhouse gas, potentially offsetting a portion of their climate mitigation benefits. While prior research has focused primarily on methane emissions from mangrove soils and water surfaces, the role of tree stems as an emission pathway and its significance for global blue carbon accounting have remained largely unexamined.
In a new study, researchers from the South China Botanical Garden of the Chinese Academy of Sciences conducted a global-scale ...
Food brings people together. It serves as a tool to communicate political stances, to cultivate cross-cultural comprehension or, if necessary, create tensions. Menus can reflect these intentions by using food to create specific psychological effects and convey symbolic messages. But how exactly is it done?
Now, researchers in Portugal have examined menus from diplomatic dinners, state banquets, and receptions hosted over the 20th and 21st centuries to find out how meals reflected and shaped Portuguese foreign policy and ...
A research team from South China University of Technology has made progress in understanding both the unconditional global existence and the vanishing viscosity limit of parabolic-elliptic coupled systems, with findings that extend existing research. The work, led by Prof. Changjiang Zhu and Dr. Qiaolong Zhu, is published in Acta Mathematica Scientia.
The study focuses on a parabolic-elliptic coupled system, which is a simplified model critical to understanding phenomena where fluid motion interacts with heat radiation. ...
As global water, energy and food demands intensify under climate change, a scalable, round-the-clock technology that simultaneously produces fresh water, electricity and irrigation water is urgently needed. Now researchers from Harbin Institute of Technology, Wuhan University and Tsinghua University—led by Prof. Shih-Hsin Ho—have unveiled an integrated Water/Electricity-Cogeneration–Cultivation (WEC) platform that couples solar-driven desalination with salinity-gradient power generation and zero-pollution crop irrigation. The work offers a practical blueprint for advancing ...
As data theft and counterfeiting grow ever more sophisticated, cryptography demands devices that are miniature, reconfigurable and almost impossible to reverse-engineer. Now researchers from the Shenyang Institute of Automation (CAS), Shanghai University and City University of Hong Kong—led by Prof. Haibo Yu and Prof. Wen Jung Li—have created a micro-dynamic multiple encryption device (μ-DMED) built from coumarin-based metamaterials that can hide, rewrite and store multilevel information under different light fields. The work establishes a new paradigm for on-chip, high-security optical encryption.
Why μ-DMED Matters
All-Optical ...
