Forum for Science, Industry and Business

Sponsored by:     3M 
Search our Site:

 

Training artificial intelligence with artificial X-rays

09.07.2018

New research could help AI identify rare conditions in medical images by augmenting existing datasets

Artificial intelligence (AI) holds real potential for improving both the speed and accuracy of medical diagnostics. But before clinicians can harness the power of AI to identify conditions in images such as X-rays, they have to 'teach' the algorithms what to look for.


On the left of each quadrant is a real X-ray image of a patient's chest and beside it, the syntheisized X-ray formulated by the DCGAN. Under the X-ray images are corresponding heatmaps, which is how the machine learning system sees the images.

Credit: Hojjat Salehinejad/MIMLab

Identifying rare pathologies in medical images has presented a persistent challenge for researchers, because of the scarcity of images that can be used to train AI systems in a supervised learning setting.

Professor Shahrokh Valaee and his team have designed a new approach: using machine learning to create computer generated X-rays to augment AI training sets.

"In a sense, we are using machine learning to do machine learning," says Valaee, a professor in The Edward S. Rogers Sr. Department of Electrical & Computer Engineering (ECE) at the University of Toronto. "We are creating simulated X-rays that reflect certain rare conditions so that we can combine them with real X-rays to have a sufficiently large database to train the neural networks to identify these conditions in other X-rays."

Valaee is a member of the Machine Intelligence in Medicine Lab (MIMLab), a group of physicians, scientists and engineering researchers who are combining their expertise in image processing, artificial intelligence and medicine to solve medical challenges. "AI has the potential to help in a myriad of ways in the field of medicine," says Valaee. "But to do this we need a lot of data -- the thousands of labelled images we need to make these systems work just don't exist for some rare conditions."

To create these artificial X-rays, the team uses an AI technique called a deep convolutional generative adversarial network (DCGAN) to generate and continually improve the simulated images. GANs are a type of algorithm made up of two networks: one that generates the images and the other that tries to discriminate synthetic images from real images. The two networks are trained to the point that the discriminator cannot differentiate real images from synthesized ones. Once a sufficient number of artificial X-rays are created, they are combined with real X-rays to train a deep convolutional neural network, which then classifies the images as either normal or identifies a number of conditions.

"We've been able to show that artificial data generated by a deep convolutional GANs can be used to augment real datasets," says Valaee. "This provides a greater quantity of data for training and improves the performance of these systems in identifying rare conditions."

The MIMLab compared the accuracy of their augmented dataset to the original dataset when fed through their AI system and found that classification accuracy improved by 20 per cent for common conditions. For some rare conditions, accuracy improved up to about 40 per cent -- and because the synthesized X-rays are not from real individuals the dataset can be readily available to researchers outside the hospital premises without violating privacy concerns.

"It's exciting because we've been able to overcome a hurdle in applying artificial intelligence to medicine by showing that these augmented datasets help to improve classification accuracy," says Valaee. "Deep learning only works if the volume of training data is large enough and this is one way to ensure we have neural networks that can classify images with high precision."

Marit Mitchell | EurekAlert!
Further information:
http://news.engineering.utoronto.ca/training-artificial-intelligence-with-artificial-x-rays/

Further reports about: X-rays artificial dataset image processing medical diagnostics

More articles from Power and Electrical Engineering:

nachricht A miniature stretchable pump for the next generation of soft robots
15.08.2019 | Ecole Polytechnique Fédérale de Lausanne

nachricht Vehicle Emissions: New sensor technology to improve air quality in cities
13.08.2019 | Technische Universität Graz

All articles from Power and Electrical Engineering >>>

The most recent press releases about innovation >>>

Die letzten 5 Focus-News des innovations-reports im Überblick:

Im Focus: A miniature stretchable pump for the next generation of soft robots

Soft robots have a distinct advantage over their rigid forebears: they can adapt to complex environments, handle fragile objects and interact safely with humans. Made from silicone, rubber or other stretchable polymers, they are ideal for use in rehabilitation exoskeletons and robotic clothing. Soft bio-inspired robots could one day be deployed to explore remote or dangerous environments.

Most soft robots are actuated by rigid, noisy pumps that push fluids into the machines' moving parts. Because they are connected to these bulky pumps by tubes,...

Im Focus: Vehicle Emissions: New sensor technology to improve air quality in cities

Researchers at TU Graz are working together with European partners on new possibilities of measuring vehicle emissions.

Today, air pollution is one of the biggest challenges facing European cities. As part of the Horizon 2020 research project CARES (City Air Remote Emission...

Im Focus: Self healing robots that "feel pain"

Over the next three years, researchers from the Vrije Universiteit Brussel, University of Cambridge, École Supérieure de Physique et de Chimie Industrielles de la ville de Paris (ESPCI-Paris) and Empa will be working together with the Dutch Polymer manufacturer SupraPolix on the next generation of robots: (soft) robots that ‘feel pain’ and heal themselves. The partners can count on 3 million Euro in support from the European Commission.

Soon robots will not only be found in factories and laboratories, but will be assisting us in our immediate environment. They will help us in the household, to...

Im Focus: Scientists create the world's thinnest gold

Scientists at the University of Leeds have created a new form of gold which is just two atoms thick - the thinnest unsupported gold ever created.

The researchers measured the thickness of the gold to be 0.47 nanometres - that is one million times thinner than a human finger nail. The material is regarded...

Im Focus: Study on attosecond timescale casts new light on electron dynamics in transition metals

An international team of scientists involving the Max Planck Institute for the Structure and Dynamics of Matter (MPSD) in Hamburg has unraveled the light-induced electron-localization dynamics in transition metals at the attosecond timescale. The team investigated for the first time the many-body electron dynamics in transition metals before thermalization sets in. Their work has now appeared in Nature Physics.

The researchers from ETH Zurich (Switzerland), the MPSD (Germany), the Center for Computational Sciences of University of Tsukuba (Japan) and the Center for...

All Focus news of the innovation-report >>>

Anzeige

Anzeige

VideoLinks
Industry & Economy
Event News

The power of thought – the key to success: CYBATHLON BCI Series 2019

16.08.2019 | Event News

4th Hybrid Materials and Structures 2020 28 - 29 April 2020, Karlsruhe, Germany

14.08.2019 | Event News

What will the digital city of the future look like? City Science Summit on 1st and 2nd October 2019 in Hamburg

12.08.2019 | Event News

 
Latest News

Stanford builds a heat shield just 10 atoms thick to protect electronic devices

19.08.2019 | Information Technology

Researchers demonstrate three-dimensional quantum hall effect for the first time

19.08.2019 | Physics and Astronomy

Catalysts for climate protection

19.08.2019 | Life Sciences

VideoLinks
Science & Research
Overview of more VideoLinks >>>