My watch list


Artificial intelligence improves biomedical imaging

ETH Zürich / Daniel Razansky

Optoacoustic imaging is particularly good at visualizing blood vessels.

01-Oct-2019: ETH researchers use artificial intelligence to improve quality of images recorded by a relatively new biomedical imaging method. This paves the way towards more accurate diagnosis and cost-effective devices.

Scientists at ETH Zurich and the University of Zurich have used machine learning methods to improve optoacoustic imaging. This relatively young medical imaging technique can be used for applications such as visualizing blood vessels, studying brain activity, characterizing skin lesions and diagnosing breast cancer. However, quality of the rendered images is very dependent on the number and distribution of sensors used by the device: the more of them, the better the image quality. The new approach developed by the ETH researchers allows for substantial reduction of the number of sensors without giving up on the resulting image quality. This makes it possible to reduce the device cost, increase imaging speed or improve diagnosis.

Optoacoustics is similar in some respects to ultrasound imaging. In the latter, a probe sends ultrasonic waves into the body, which are reflected by the tissue. Sensors in the probe detect the returning sound waves and a picture of the inside of the body is subsequently generated. In optoacoustic imaging, very short laser pulses are instead sent into the tissue, where they are absorbed and converted into ultrasonic waves. Similarly to ultrasound imaging, the waves are detected and converted into images.

Correcting for image distortions

The team led by Daniel Razansky, Professor of Biomedical Imaging at ETH Zurich and the University of Zurich, searched for a way to enhance image quality of low-cost optoacoustic devices that possess only a small number of ultrasonic sensors.

To do this, they started off by using a self-developed high-end optoacoustic scanner having 512 sensors, which delivered superior-quality images. They had these pictures analysed by an artificial neural network, which was able to learn the features of the high-quality images.

Next, the researchers discarded the majority of the sensors, so that only 128 or 32 sensors remained, with a detrimental effect on the image quality. Due to the lack of data, distortions known as streak type artefacts appeared in the images. It turned out, however, that the previously trained neural network was able to largely correct for these distortions, thus bringing the image quality closer to the measurements obtained with all the 512 sensors.

In optoacoustics, the image quality increases not only with the number of sensors used, but also when the information is captured from as many directions as possible: the larger the sector in which the sensors are arranged around the object, the better the quality. The developed machine learning algorithm was also successful in improving quality of images that were recorded from just a narrowly circumscribed sector. “This is particularly important for clinical applications, as the laser pulses cannot penetrate the entire human body, hence the imaged region is normally only accessible from one direction,” according to Razansky.

Facilitating clinical decision making

The scientists stress that their approach is not limited to optoacoustic imaging. Because the method operates on the reconstructed images, not the raw recorded data, it is also applicable to other imaging techniques. “You can basically use the same methodology to produce high-quality images from any sort of sparse data,” Razansky says. He explains that physicians are often confronted with the challenge of interpreting poor quality images from patients. “We show that such images can be improved with AI methods, making it easier to attain more accurate diagnosis.”

For Razansky, this research work is a good example of what existing methods of artificial intelligence can be used for. “Many people think that AI could replace human intelligence. This is probably exaggerated, at least for the currently available AI technology,” he says. “It can’t replace human creativity, yet may release us from some laborious, repetitive tasks.”

In their current research, the scientists used an optoacoustic tomography device customised for small animals, and trained the machine learning algorithms with images from mice. The next step will be to apply the method to optoacoustic images from human patients, Razansky says.

Original publication:
Davoudi N, Deán-Ben XL, Razansky D; "Deep learning optoacoustic tomography with sparse data, Nature Machine Intelligence"; 16. September 2019

Facts, background information, dossiers

  • artificial intelligence
  • imaging
  • diagnosis
  • machine-learning
  • optoacoustics
  • artificial neural networks

More about ETH Zürich

  • News

    Using electrical stimulus to regulate genes

    A team of researchers led by ETH professor Martin Fussenegger has succeeded in using an electric current to directly control gene expression for the first time. Their work provides the basis for medical implants that can be switched on and off using electronic devices outside the body. This ... more

    Lighting the path for cells

    ETH researchers have developed a new method in which they use light to draw patterns of molecules that guide living cells. The approach allows for a closer look at the development of multicellular organisms – and in the future may even play a part in novel therapies.  Highly complex organis ... more

    A new biosensor for the COVID-19 virus

    A team of researchers from Empa, ETH Zurich and Zurich University Hospital has succeeded in developing a novel sensor for detecting the new coronavirus. In future it could be used to measure the concentration of the virus in the environment - for example in places where there are many peopl ... more

  • q&more articles

    Analysis in picoliter volumes

    Reducing time, costs and human resources: many basic as well as applied analytical and diagnostic challenges can be performed on lab-on-a-chip systems. They enable sample quantities to be reduced, work steps to be automated and completed in parallel, and are ideal for combination with highl ... more

    Investment for the Future

    This is a very particular concern and at the same time the demand placed annually on Dr. Irmgard Werner, who, as a lecturer at the ETH Zurich, supports around 65 pharmacy students in the 5th semester practical training in “pharmaceutical analysis”. With joy and enthusiasm for her subject sh ... more

  • Authors

    Prof. Dr. Petra S. Dittrich

    Petra Dittrich is an Associate Professor in the Department of Biosystems Science and Engineering at ETH Zurich (Switzerland). She studied chemistry at Bielefeld University and the University of Salamanca (Spain). After completing her doctoral studies at the Max Planck Institute for Biophysi ... more

    Dr. Felix Kurth

    Felix Kurth studied bioengineering at the Technical University Dortmund (Germany) and at the Royal Institute of Technology in Stockholm (Sweden). During his PhD studies at ETH Zurich (Switzerland), which he completed in 2015, he developed lab-on-a-chip systems and methods for quantifying me ... more

    Lucas Armbrecht

    Lucas Armbrecht studied microsystems technology at the University of Freiburg (Breisgau, Germany). During his master’s, he focused on sensors & actuators and lab-on-a-chip systems. Since June 2015, he is PhD student in the Bioanalytics Group at ETH Zurich (Switzerland). In his doctoral stud ... more

q&more – the networking platform for quality excellence in lab and process

The q&more concept is to increase the visibility of recent research and innovative solutions, and support the exchange of knowledge. In the broad spectrum of subjects covered, the focus is on achieving maximum quality in highly innovative sectors. As a modern knowledge platform, q&more offers market participants one-of-a-kind networking opportunities. Cutting-edge research is presented by authors of international repute. Attractively presented in a high-quality context, and published in German and English, the original articles introduce new concepts and highlight unconventional solution strategies.

> more about q&more

q&more is supported by:


Your browser is not current. Microsoft Internet Explorer 6.0 does not support some functions on Chemie.DE