Mediaboss Marketing

The Secretary of State for Digital, Culture, Media and Sport visited the University today to hear how researchers are being trained to deploy artificial intelligence (AI) in the fight against cancer.

Baroness Nicky Morgan met PhD researchers involved increating the next generation of intelligent technology that will revolutionisehealthcare.

The University is one of 16 centres for doctoral training inAI funded by UKResearch and Innovation, the Government agency responsible forfostering research and development.

The focus of the doctoral training at Leedsis to develop researchers who can apply AIto medical diagnosisand care.

Scientists believe intelligent systems and data analyticswill result in quicker and more accurate diagnosis. Early detection is at theheart of the NHS planto transform cancer survival rates by 2028.

Baroness Morgan said: "Weare committed to being a world leader in artificial intelligence technology andthrough our investment in 16new Centres for Doctoral Training we arehelping train the next generation of researchers.

"It was inspirational to meet some of the leading experts from medicineand computer science working in the new centre at Leeds Universitytoday.They are doing fantastic work to diagnose cancer quicker whichcould save millions of lives."

Baroness Morgan spent time talking to the PhD researchers.

Professor Lisa Roberts, Deputy Vice-Chancellor: Research and Innovation with Baroness Nicky Morgan

Anna Linton is a neuroscientist accepted onto the firstcohort of the programme, which started in the autumn.

She said: The healthcare system can generate a vastquantity of information but sometimes it is assessed in isolation.

I am interested in researching AI systems that can analysemedical notes, the results of pathology tests and scans and identify patternsin that disparate information and make order of it, to give a unified pictureof a patients health status.

That information will help the GP or other healthcareprofessional make a more precise diagnosis.

Dr Emily Clarke is a hospital doctor specialising inhistopathology, the changes in tissue caused by disease. She is an associatemember of the doctoral training programme on a research scholarship from the Medical Research Council.

She wants to develop an AI system to improve the diagnosisof melanoma, a type of skin cancer whose incidence, according to CancerResearch UK, has more than doubled since the early 1990s. It has thefastest rising incidence of any cancer.

Melanoma is detected from the visual examination by ahistopathologist of tissue samples taken during a biopsy. But up to one in sixcases is initially misdiagnosed.

Dr Clarke said: I am hoping we can develop an automatedsystem that can help histopathologists identify melanoma. Diagnosing melanomacan be notoriously difficult so it is hoped that in the future AI may helpbuild a knowledge base of the types of cell changes that are suggestive ofmelanoma and provide a more accurate prediction of a patients prognosis."

Dr Emily Clarke discussing her research project

About 10 researchers will be recruited onto the training programmeeach year. When it is fully up and running, there will be 50 people studyingfor a PhD.

We cant be complacent. We need to ensure there are enough talented and creative people with the skills and knowledge to harness and develop this powerful technology.

Professor Lisa Roberts, Deputy Vice-Chancellor: Researchand Innovation, said: The research at Leeds will ensure the UK remains at theforefront of an important emerging technology that will shape healthcare forfuture generations.

There is little doubt that our researchers will becontribute to future academic and industrial breakthroughs in the field of AI,enabling industry in the UK to remain at the heart of innovation in AI.

David Hogg, Professor of Artificial Intelligence and Director of the Leeds Centre forDoctoral Training, said: The UK is a world leader in AI.

But we cant be complacent. We need to ensure there areenough talented and creative people with the skills and knowledge to harnessand develop this powerful technology.

The PhD researchers will be supervised by leading expertsin computer science and medicine from the University and Leeds TeachingHospitals NHS Trust. To harness thetechnology requires researchers with a strong understanding of medicine,biology and computing and we aim to give that to them.

The researchers joining the Leeds training programme come from a range ofbackgrounds: some are computer scientists and others are biologists orhealthcare professionals but all are able to think computationally and are able to express problems and solutions in a form that can be executed by a computer.

The programme is hosted bythe Leeds Institute for Data Analytics (LIDA), establishedwithUniversityinvestmenttosupport innovation in medical bioinformatics, funded by the MedicalResearch Council, andConsumer Data, funded by the Economic and Social Research Council.

LIDA has now grown to support aportfolio in excess of 45 million of research across the University, bringingtogether over 150 researchers and data scientists. It supports the Universityspartnership withthe Alan Turing Institute, the UKs national institute for data scienceand artificial intelligence.

The University has a strong track record in applyingdigital technologies to healthcare. In partnership with Leeds TeachingHospitals NHS Trust, it is bringing together nine hospitals, seven universitiesand medical technology companies to create a digital pathology network whichwill allow medical staff to collaborate remotely and to conduct AI research. This is known as the Northern Pathology Imaging Co-operative.

Leeds Teaching Hospitals NHS Trust is a leader in usingdigital pathology for cancer diagnosis.

Main photo shows some of the PhD researchers with - front, from left - Professor David Hogg, Director of the Leeds Centre for Doctoral Training, Baroness Nicky Morgan, Secretary of State for Digital, Media, Culture and Sport, and Professor Lisa Roberts, Deputy Vice-Chancellor: Research and Innovation.

More here:
Using artificial intelligence to speed up cancer detection - University of Leeds

- Advertisement -

Abel Mocln, an archaeologist at the Centro Nacional de Investigacin sobre la Evolucin Humana (CENIEH), has led a study which combines Archaeology and Artificial Intelligence, published in the journalArchaeological and Anthropological Sciences, about the Navalmallo Rock Shelter site, situated in the locality of Pinilla de Valle in Madrid, which shows the activity by Neanderthal groups of breaking the bones of medium-sized animals such as deer, for subsequent consumption of the marrow within.

The particular feature of the study lies in its tremendous statistical potential. For the first time, Artificial Intelligence has been used to determine the agent responsible for breaking the bones at an archaeological site, with highly reliable results, which it will be possible to compare with other sites and experiments in the future.

Credit: CENIEH

We have managed to show that statistical tools based on Artificial Intelligence can be applied to studying the breaking of the fossil remains of animals which appear at sites, states Mocln.

In the work, it is not just this activity carried out by the Neanderthals which is emphasized, but also aspects of the methodology developed by the authors of the study. On this point, Mocln insists on the importance of Artificial Intelligence as this is undoubtedly the perfect line of work for the immediate future of Archaeology in general and Taphonomy in particular.

The largest Neanderthal settlement

The Navalmallo Rock Shelter, about 76,000 years old, offers one of the few large windows into Neanderthal behavior within the Iberian Meseta. With its area of over 300 m2, it may well be the largest Neanderthal camp known in the center of the Iberian Peninsula, and it has been possible to reveal different activities conducted by these hominins here, such as hunting large animals, the manufacture of stone tools and the systematic use of fire.

In this study, part of the Valle de los Neandertales project, which includes other locations in the archaeological site complex of Calvero de la Higuera, the collaborating researchers were Rosa Huguet, of the IPHES in Tarragona, Beln Mrquez and Csar Laplana, of the Museo Arqueolgico Regional in Madrid, as well as the three codirectors of the Pinilla del Valle project: Juan Luis Arsuaga, Enrique Baquedano and Alfredo Prez Gonzlez.

CENIEH

Header Image Abrigode Navalmallo Credit: CENIEH

- Advertisement -

See the rest here:
Artificial intelligence to study the behavior of Neanderthals - HeritageDaily

While Google and other technology giants have their own dynamics to keep the most detailed and up-to-date maps possible, it is an expensive and time-consuming process. And in some areas, the data is limited.

To improve this, researchers at MIT and Qatar Computing Research Institute (QCRI) have developed a new machine-learning model based on satellite images that could significantly improve digital maps for GPS navigation. The system, called RoadTagger, recognizes the types of roads and the number of lanes in satellite images, even in spite of trees or buildings that obscure the view. In the future, the system should recognize even more details, such as bike paths and parking spaces.

RoadTagger relies on a novel combination of a convolutional neural network (CNN) and a graph neural network (GNN) to automatically predict the number of lanes and road types (residential or highway) behind obstructions.

Simply put, this model is fed only raw data and automatically produces output without human intervention. Following this dynamic, you can predict, for example, the type of road or if there are several lanes behind a grove, according to the analyzed characteristics of the satellite images.

The researcher team has already tested RoadTagger using real data, covering an area of 688 square kilometers of maps of 20 U.S. cities, and achieved 93% accuracy in the detection of road types and 77% in the number of lanes.

Maintaining this degree of accuracy on digital maps would not only save time and avoid many headaches for drivers but could also prevent accidents. And of course, it would be vital information in case of emergency or disasters.

The researchers now want to further improve the system and also record additional properties, including bike paths, parking bays, and the road surface after all, it makes a difference for drivers whether a former gravel track is now paved somewhere in the hinterland.

Read more from the original source:
Artificial intelligence to update digital maps and improve GPS navigation - Inceptive Mind

The Evolution of Artificial Intelligence as a System | 2020-01-09 | Security Magazine This website requires certain cookies to work and uses other cookies to help you have the best experience. By visiting this website, certain cookies have already been set, which you may delete and block. By closing this message or continuing to use our site, you agree to the use of cookies. Visit our updated privacy and cookie policy to learn more. This Website Uses CookiesBy closing this message or continuing to use our site, you agree to our cookie policy. Learn MoreThis website requires certain cookies to work and uses other cookies to help you have the best experience. By visiting this website, certain cookies have already been set, which you may delete and block. By closing this message or continuing to use our site, you agree to the use of cookies. Visit our updated privacy and cookie policy to learn more.

Here is the original post:
The Evolution of Artificial Intelligence as a System - Security Magazine

Artificial intelligence and machine learning promises to revolutionize healthcare.

Proponents say it will help diagnose ailments more quickly and more accurately, as well as help monitor peoples health and take over a swath of doctors paperwork so they can see more patients.

At least, thats the promise.

Theres been an exponential increase in approvals from the Food and Drug Administration (FDA) for these type of health products as well as projections that artificial intelligence (AI) will become an $8 billion industry by 2022.

However, many experts are urging to pump the brakes on the AI craze.

[AI] has the potential to democratize healthcare in ways we can only dream of by allowing equal care for all. However, it is still in its infancy and it needs to mature, Jos Morey, MD, a physician, AI expert, and former associate chief health officer for IBM Watson, told Healthline.

Consumers should be wary of rushing to a new facility simply because they may be providing a new AI tool, especially if it is for diagnostics, he said. There are really just a handful of physicians across the world that are practicing that understand the strengths and benefits of what is currently available.

But what exactly is artificial intelligence in medical context?

It starts with machine learning, which are algorithms that enable a computer program to learn by incorporating increasing large and dynamic amounts of data, according to Wired magazine.

The terms machine learning and AI are often used interchangeably.

To understand machine learning, imagine a given set of data say a set of X-rays that do or do not show a broken bone and having a program try to guess which ones show breaks.

The program will likely get most of the diagnoses wrong at first, but then you give it the correct answers and the machine learns from its mistakes and starts to improve its accuracy.

Rinse and repeat this process hundreds or thousands (or millions) of times and, theoretically, the machine will be able to accurately model, select, or predict for a given goal.

So its easy to see how in healthcare a field that deals with massive amounts of patient data machine learning could be a powerful tool.

One of the key areas where AI is showing promise is in diagnostic analysis, where the AI system will collect and analyze data sets on symptoms to diagnose the potential issue and offer treatment solutions, John Bailey, director of sales for the healthcare technology company Chetu Inc., told Healthline.

This type of functionality can further assist doctors in determining the illness or condition and allow for better, more responsive care, he said. Since AIs key benefit is in pattern detection, it can also be leveraged in identifying, and assist in containing, illness outbreaks and antibiotic resistance.

That all sounds great. So whats the hitch?

The problem lies in lack of reproducibility in real-world settings, Morey said. If you dont test on large robust datasets that are being just one facility or one machine, then you potentially develop bias into the algorithm that will ultimately only work in one very specific setting but wont be compatible for large scale roll-out.

He added, The lack of reproducibility is something that affects a lot of science but AI in healthcare in particular.

For instance, a study in the journal Science found that even when AI is tested in a clinical setting, its often only tested in a single hospital and risks failing when moved to another clinic.

Then theres the issue of the data itself.

Machine learning is only as good as the data sets the machines are working with, said Ray Walsh, a digital privacy expert at ProPrivacy.

A lack of diversity in the datasets used to train up medical AI could lead to algorithms unfairly discriminating against under-represented demographics, Walsh told Healthline.

This can create AI that is prejudiced against certain people, he continued. As a result, AI could lead to prejudice against particular demographics based on things like high body mass index (BMI), race, ethnicity, or gender.

Meanwhile, the FDA has fast-tracked approval of AI-driven products, from approving just 1 in 2014 to 23 in 2018.

Many of these products havent been subjected to clinical trials since they utilize the FDAs 510(k) approval path, which allows companies to market products without clinical trials as long as they are at least as safe and effective, that is, substantially equivalent, to a legally marketed device.

This process has made many in the AI health industry happy. This includes Elad Walach the co-founder and chief executive officer of Aidoc, a startup focused on eliminating bottlenecks in medical image diagnosis.

The FDA 510(k) process has been very effective, Walach told Healthline. The key steps include clinical trials applicable to the product and a robust submission process with various types of documentation addressing the key aspects of the claim and potential risks.

The challenge the FDA is facing is dealing with the increasing pace of innovation coming from AI vendors, he added. Having said that, in the past year they progressed significantly on this topic and created new processes to deal with the increase in AI submissions.

But not everyone is convinced.

The FDA has a deeply flawed approval process for existing types of medical devices and the introduction of additional technological complexity further exposes those regulatory inadequacies. In some instances, it might also raise the level of risk, said David Pring-Mill, a consultant to tech startups and opinion columnist at TechHQ.

New AI products have a dynamic relationship with data. To borrow a medical term, they arent quarantined. The idea is that they are always learning, but perhaps its worth challenging the assumption that a change in outputs always represents an improved product, he said.

The fundamental problem, Pring-Mill told Healthline, is that the 510(k) pathway allows medical device manufacturers to leapfrog ahead without really proving the merits of their products.

One way or another, machine learning and AI integration into the medical field is here to stay.

Therefore, the implementation will be key.

Even if AI takes on the data processing role, physicians may get no relief. Well be swamped with input from these systems, queried incessantly for additional input to rule in or out possible diagnoses, and presented with varying degrees of pertinent information, Christopher Maiona, MD, SFHM, the chief medical officer at PatientKeeper Inc., which specializes in optimizing electronic health records, told Healthline.

Amidst such a barrage, the systems user interface will be critical in determining how information is prioritized and presented so as to make it clinically meaningful and practical to the physician, he added.

And AIs success in medicine both now and in the future may ultimately still rely on the experience and intuition of human beings.

A computer program cannot detect the subtle nuances that comes with years of caring for patients as a human, David Gregg, MD, chief medical officer for StayWell, a healthcare innovation company, told Healthline.

Providers can detect certain cues, connect information and tone and inflection when interacting with patients that allow them to create a relationship and provide more personalized care, he said. AI simply delivers a response to data, but cannot address the emotional aspects or react to the unknown.

Follow this link:
Don't Put Your Health in the Hands of Artificial Intelligence Just Yet - Healthline