Researchers in Portugal develop an image analysis AI platform to boost worldwide research

DL4MicEverywhere empowers life scientists to harness cutting-edge deep learning techniques for biomedical research

2024-05-17

(Press-News.org) A team of researchers from the Instituto Gulbenkian de Ciência (IGC) in Portugal, together with Åbo Akademi University in Finland, the AI4Life consortium, and other collaborators, have developed an innovative open-source platform called DL4MicEverywhere published today in the journal Nature Methods*. This platform provides life scientists with easy access to advanced artificial intelligence (AI) for the analysis of microscopy images. Itenables other researchers, regardless of their computational expertise, to easily train and use deep learning models on their own data.

Deep learning, a subfield of AI, has revolutionised the analysis of large and complex microscopy datasets, allowing scientists to automatically identify, track and analyse cells and subcellular structures. However, the lack of computing resources and AI expertise prevents some researchers in life-sciences from taking advantage of these powerful techniques in their own work. DL4MicEverywhere addresses these challenges by providing an intuitive interface for researchers to use deep learning models on any experiment that requires image analysis and in diverse computing infrastructures, from simple laptops to high-performance clusters.

"Our platform establishes a bridge between AI technological advances and biomedical research", said Ivan Hidalgo-Cenamor, first author of the study and researcher at IGC. “With it, regardless of their expertise in AI, researchers gain access to cutting-edge microscopymethods, enabling them to automatically analyse their results and potentially discover new biological insights”.

The DL4MicEverywhere platform builds upon the team's previous work, ZeroCostDL4Mic, to allow the training and use of models across various computational environments. The platform also includes a user-friendly interface and expands the collection of available methodologies that users can apply to common microscopy image analysis tasks.

"DL4MicEverywhere aims to democratise AI for microscopy by promoting community contributions and adhering to FAIR principles for scientific research software - making resources findable, accessible, interoperable and reusable", explained Dr. Estibaliz Gómez-de-Mariscal, co-lead of the study and researcher at IGC. "We hope this platform will empower researchers worldwide to harness these powerful techniques in their work, regardless of their resources or expertise".

The development of DL4MicEverywhere is a great example of the collaborative environment in science. First, it was developed with the purpose of allowing any researcher worldwide to take advantage of the most advanced technologies in microscopy, contributing to accelerate scientific discoveries. Second, it was made possible only through an international collaboration of experts in computer science, image analysis, and microscopy, with key contributions from the AI4Life consortium. The project was co-led by Ricardo Henriques at IGC and Guillaume Jacquemet at Åbo Akademi University.

"This work represents an important milestone in making AI more accessible and reusable for the microscopy community", said Professor Jacquemet. "By enabling researchers to share their models and analysis pipelines easily, we can accelerate discoveries and enhance reproducibility in biomedical research".

"DL4MicEverywhere has the potential to be transformative for the life sciences," added Professor Henriques. "It aligns with our vision in AI4Life to develop sustainable AI solutions that empower researchers and drive innovation in healthcare and beyond".

The DL4MicEverywhere platform is freely available as an open-source resource, reflecting the teams' commitment to open science and reproducibility. The researchers believe that by lowering the barriers to advanced microscopy image analysis, DL4MicEverywhere will enable breakthrough discoveries in fields ranging from basic cell biology to drug discovery and personalised medicine.

*Iván Hidalgo-Cenalmor, Joanna W Pylvänäinen, Mariana G Ferreira, Craig T Russell, Ignacio Arganda-Carreras, AI4Life Consortium, Guillaume Jacquemet, Ricardo Henriques, Estibaliz Gómez-de-Mariscal (2024) DL4MicEverywhere: Deep learning for microscopy made flexible, shareable, and reproducible. Nature Methods. DOI: 10.1038/s41592-024-02295-6

END

[Attachments] See images for this press release:

Researchers in Portugal develop an image analysis AI platform to boost worldwide research 2

Researchers in Portugal develop an image analysis AI platform to boost worldwide research 3

ELSE PRESS RELEASES FROM THIS DATE:

A devastating fire 2,200 years ago preserved a moment of life and war in Iron Age Spain — right down to a single gold earring

2024-05-17

A ruined building in the middle of the Pyrenees records a tragedy for the people who lived there — a devastating fire which burned a settlement to the ground, destroying everything down to a hidden gold earring. Now archaeologists’ excavation of Building G, in the strategically placed Iron Age site of Tossal de Baltarga, reveals a way of life derailed by violence: potentially, a forgotten episode of the war between Carthage and Rome. “The destruction was dated around the end of the third century BCE, the moment where the Pyrenees were involved in the Second Punic War and the passage of Hannibal’s troops,” ...

Exploration of polymer cononsolvency mechanism through soft X-ray absorption spectroscopy

2024-05-17

This study investigates the cononsolvency mechanism of poly(N-isopropylacrylamide) (PNIPAM), which is soluble in pure methanol (MeOH) and water but insoluble in aqueous MeOH solutions. Combining oxygen K-edge X-ray absorption spectroscopy (XAS) with theoretical calculations executed in molecular dynamics (MD) simulations and inner-shell calculations, it was found that hydrophobic interactions between PNIPAM and MeOH clusters play a key role in PNIPAM aggregation and cononsolvency emergence. PNIPAM is ...

Researchers use machine-learning modeling tools to improve zinc-finger nuclease editing technology

2024-05-17

Genome editing is making inroads into biomedical research and medicine. By employing biomolecule modeling tools, a Japanese research team is accelerating the pace and cutting the cost of zinc finger nuclease (ZFN) technology, a primary gene editing tool. In a recently published study, researchers from Hiroshima University and the Japanese National Institute of Advanced Industrial Science and Technology demonstrated how machine learning-driven modular assembly systems can improve gene editing. The study was published on April 10 in the journal Advanced Science. “Genome editing is ...

USC researcher awarded $3.1 million to study early brain development of babies born to mothers with diabetes in pregnancy

2024-05-17

It has long been understood that pregnant women with diabetes are more likely to have children with obesity than women who do not have diabetes during pregnancy. But scientists have not fully understood the cause or why babies born to mothers with diabetes are also more likely to develop obesity and associated metabolic disorders later in life. To help find answers, Keck School of Medicine of USC researcher Shan Luo, PhD, has been awarded $3.1 million in funding from the National Institutes of Health and the National Institute of Diabetes ...

Men at greater risk of major health effects of diabetes than women

2024-05-17

Men are at greater risk than women of the major health effects of diabetes (types 1 and 2), suggests a long term study published online in the Journal of Epidemiology & Community Health. Rates of cardiovascular disease, leg, foot, and kidney complications, and the sight-threatening eye disease diabetic retinopathy are all higher in men, regardless of whether they had diabetes for more or less than 10 years, the findings show. The global prevalence of diabetes is similar in men and women, and is projected to rise to 783 million by 2045, note the researchers. But ...

Likelihood of kids and young people smoking and vaping linked to social media use

2024-05-17

The more time spent on social media, the greater the likelihood that children and young people will both smoke and/or vape, suggests research published online in the respiratory journal Thorax. Clocking up a weekday tally of 7 or more hours was associated with a more than a doubling in risk among 10 to 25 year olds, the findings indicate, reinforcing concerns about the marketing clout of these platforms, say the researchers. The existing body of research on social media use and smoking and ...

Global life expectancy to increase by nearly 5 years by 2050 despite geopolitical, metabolic, and environmental threats, reports new global study

2024-05-17

**Embargo: 23.30 [UK time], 6:30 p.m. [EDT] May 16, 2024** Global Burden of Disease The latest findings from the Global Burden of Disease Study (GBD) 2021, published today in The Lancet, forecast that global life expectancy will increase by 4.9 years in males and 4.2 years in females between 2022 and 2050. Increases are expected to be largest in countries where life expectancy is lower, contributing to a convergence of increased life expectancy across geographies. The trend is largely driven by public health measures that ...

High primary health coverage significantly reduces child mortality in Latin America

2024-05-17

The implementation of primary health care (PHC) over the last two decades has prevented more than 300,000 child deaths in four Latin American countries, and could prevent more than 140,000 by 2030 in a scenario of economic crisis. This is the main conclusion of a study coordinated by the Barcelona Institute for Global Health (ISGlobal), a centre supported by “la Caixa” Foundation, published in The Lancet Global Health. The 2018 Astana Declaration highlighted the critical role of PHC in ensuring that everyone enjoys the highest possible standard of health, and in achieving universal health coverage. The Declaration also stressed the ...

Ubiquitin trailblazer elected Fellow of prestigious Royal Society

2024-05-17

WEHI division head and pioneer of ubiquitination Professor David Komander has been elected a Fellow of the esteemed Royal Society, the UK’s national science academy. Prof Komander was recognised for his significant research contributions towards understanding ubiquitin, the ‘kiss of death’ protein which tells our cells which proteins to break down or recycle – a vital process that helps cells stay healthy and function correctly. Prof Komander’s work has helped unravel the ‘ubiquitin code’ that enables ubiquitin to perform many ...

A new ‘rule of biology’ may have come to light, expanding insight into evolution and aging

2024-05-17

By Darrin S. Joy A molecular biologist at the USC Dornsife College of Letters, Arts and Sciences may have found a new “rule of biology.” A rule of biology, sometimes called a biological law, describes a recognized pattern or truism among living organisms. Allen’s rule, for example, states that among warm-blooded animals, those found in colder areas have shorter, thicker limbs (to conserve body heat) than those in hotter regions, which need more body surface area to dissipate heat. Zoologist Joel Allen formulated this idea in 1877, and though he wasn’t the first or the last to present a rule of biology, his ...