Screening for skin disease on your laptop
New artificial neural network design can differentiate between healthy and diseased skin
(Press-News.org) The founding chair of the Biomedical Engineering Department at the University of Houston is reporting a new deep neural network architecture that provides early diagnosis of systemic sclerosis (SSc), a rare autoimmune disease marked by hardened or fibrous skin and internal organs. The proposed network, implemented using a standard laptop computer (2.5 GHz Intel Core i7), can immediately differentiate between images of healthy skin and skin with systemic sclerosis.
"Our preliminary study, intended to show the efficacy of the proposed network architecture, holds promise in the characterization of SSc," reports Metin Akay, John S. Dunn Endowed Chair Professor of biomedical engineering. The work is published in the IEEE Open Journal of Engineering in Medicine and Biology.
"We believe that the proposed network architecture could easily be implemented in a clinical setting, providing a simple, inexpensive and accurate screening tool for SSc."
For patients with SSc, early diagnosis is critical, but often elusive. Several studies have shown that organ involvement could occur far earlier than expected in the early phase of the disease, but early diagnosis and determining the extent of disease progression pose significant challenge for physicians, even at expert centers, resulting in delays in therapy and management.
In artificial intelligence, deep learning organizes algorithms into layers (the artificial neural network) that can make its own intelligent decisions. To speed up the learning process, the new network was trained using the parameters of MobileNetV2, a mobile vision application, pre-trained on the ImageNet dataset with 1.4M images.
"By scanning the images, the network learns from the existing images and decides which new image is normal or in an early or late stage of disease," said Akay.
Among several deep learning networks, Convolutional Neural Networks (CNNs) are most commonly used in engineering, medicine and biology, but their success in biomedical applications has been limited due to the size of the available training sets and networks.
To overcome these difficulties, Akay and partner Yasemin Akay combined the UNet, a modified CNN architecture, with added layers, and they developed a mobile training module. The results showed that the proposed deep learning architecture is superior and better than CNNs for classification of SSc images.
"After fine tuning, our results showed the proposed network reached 100% accuracy on the training image set, 96.8% accuracy on the validation image set, and 95.2% on the testing image set," said Yasmin Akay, UH instructional associate professor of biomedical engineering.
The training time was less than five hours.
Joining Metin Akay and Yasemin Akay, the paper was co-authored by Yong Du, Cheryl Shersen, Ting Chen and Chandra Mohan, all of University of Houston; and Minghua Wu and Shervin Assassi of the University of Texas Health Science Center (UT Health).
[Attachments] See images for this press release:
ELSE PRESS RELEASES FROM THIS DATE:
WASHINGTON--Raindrops on other planets and moons are close to the size of raindrops on Earth despite having different chemical compositions and falling through vastly different atmospheres, a new study finds. The results suggest raindrops falling from clouds are surprisingly similar across a wide range of planetary conditions, which could help scientists better understand the climates and precipitation cycles of other worlds, according to the researchers.
Raindrops on Earth are made of water, but other worlds in our solar system have precipitation made of more unusual stuff. On Venus, ...
As part of an international collaboration, researchers from ELTE Eötvös Loránd University developed a new animal model to study a rare genetic disease that can lead to blindness at the age of 40-50. The new model could open up new perspectives in our understanding of this metabolic disease and will also help to identify new potential drug candidates, according to the recent study published in Frontiers in Cell and Developmental Biology.
Pseudoxanthoma elasticum (PXE) is a rare genetic disease with symptoms that usually manifest in adolescence or in early adulthood. The symptoms are caused by the appearance of hydroxyapatite crystal deposits in the subcutaneous connective tissue and retina ...
The universe is expanding at an ever-increasing rate, and while no one is sure why, researchers with the Dark Energy Survey (DES) at least had a strategy for figuring it out: They would combine measurements of the distribution of matter, galaxies and galaxy clusters to better understand what's going on.
Reaching that goal turned out to be pretty tricky, but now a team led by researchers at the Department of Energy's SLAC National Accelerator Laboratory, Stanford University and the University of Arizona have come up with a solution. Their analysis, published April 6 in Physical Review ...
Nursing mothers who receive a COVID-19 vaccine may pass protective antibodies to their babies through breast milk for at least 80 days following vaccination, suggests new research from Washington University School of Medicine in St. Louis.
"Our study showed a huge boost in antibodies against the COVID-19 virus in breast milk starting two weeks after the first shot, and this response was sustained for the course of our study, which was almost three months long," said first author Jeannie Kelly, MD, assistant professor of obstetrics and gynecology. "The antibodies levels were still high at the end of our study, so the protection likely extends even longer."
Cells from individuals with Major Depressive Disorder (MDD) were found to have higher than expected rates of methylation at specific sites on their DNA, when compared to cells from healthy individuals without MDD, according to a study by a multidisciplinary team of UC San Francisco scientists, in collaboration with others. Methylation is a process by which DNA is chemically modified at specific sites, resulting in changes in the expression of certain genes. Methylation of particular sets of genes, called "DNA methylation clocks," typically change in predictable ways as people ...
During the early phase of the pandemic, approximately 40% of the COVID-19 literature was shared as preprints - freely available manuscripts that are shared prior to peer-review. In a new study publishing in the open access journal PLOS Biology, researchers led by Dr Jonathon Coates (Queen Mary University of London), Dr Nicholas Fraser (Leibniz Information Centre for Economics, Germany) and Dr Liam Brierley (University of Liverpool) explore the crucial role of preprint servers in hosting COVID-19 related science and how these preprints have been used to disseminate knowledge of COVID-19, leading to cultural shifts in journalistic and policy practices.
There has been a rapid and incredible scientific response to the COVID-19 pandemic, with research ...
Innovation and advances in technology have facilitated agricultural activity in recent years, as traditional irrigation techniques have been supplanted by pressure-basedones, improving water efficiency but increasing energy dependence. This drives up the Agriculture sector's energy costs, some of the highest in the European Union.
With the aim of increasing the energy efficiency of irrigation, researchers at the Hydraulics and Irrigation Group with the María de Maeztu Unit of Excellence,at the Department of Agronomy of the University of Cordoba (DAUCO), Juan Antonio Rodríguez Díaz and Jorge García Morillo, have field-tested a low-cost technology that takes advantage of the excess pressure on the grid to generate energy. This ...
It is difficult to imagine our daily life without lithium-ion batteries. They dominate the small format battery market for portable electronic devices, and are also commonly used in electric vehicles. At the same time, lithium-ion batteries have a number of serious issues, including: a potential fire hazard and performance loss at cold temperatures; as well as a considerable environmental impact of spent battery disposal.
According to the leader of the team of researchers, Professor in the Department of Electrochemistry at St Petersburg University END ...
Ambient air pollution is a global public health crisis, causing more than 4.9 million premature deaths per year around the world. In Africa, it has surpassed AIDS as the leading cause of premature death. According to one study, air pollution--specifically, fine particulate matter (PM2.5)--may cause at least as many as 780,000 premature deaths annually in Africa and worsen a significant number of diseases, including asthma, lung cancer, and chronic obstructive pulmonary disease.
Kinshasa, capital of the Democratic Republic of the Congo, and Brazzaville, capital of the Republic of Congo, are both large metropolises. However, neither Kinshasa (population 14. 3 million) nor Brazzaville (population 2.4 million) have had comprehensive air quality monitoring programs. ...
Scientists at UCL have used artificial intelligence (AI) to identify three new multiple sclerosis (MS) subtypes. Researchers say the groundbreaking findings will help identify those people more likely to have disease progression and help target treatments more effectively.
MS affects over 2.8 million people globally and 130,000 in the UK, and is classified into four* 'courses' (groups), which are defined as either relapsing or progressive. Patients are categorised by a mixture of clinical observations, assisted by MRI brain images, and patients' symptoms. These observations guide the timing and choice of treatment.
For this study, published in Nature Communications, researchers wanted to find out if there were any - as yet unidentified - patterns ...
LAST 30 PRESS RELEASES:
[Press-News.org] Screening for skin disease on your laptop
New artificial neural network design can differentiate between healthy and diseased skin