Feb 28, 2017 | By David

The technique of machine learning, where an algorithm makes predictions based on the data it processes without being explicitly programmed, is an important and wide-reaching area of computing. So the prospect of merging machine learning with 3D printing, as can be seen in a new project by researchers at UCLA, is definitely an exciting one. Using a 3D printed prototype detector with a sensor that can be modified by machine learning techniques, the researchers have demonstrated a new, more efficient way to detect tiny items such as cancer biomarkers, viruses, and proteins. This could improve the treatment and diagnosis of serious infections and diseases.

Plasmonic sensing has been used in medical research for years, in order to gather information about the composition of things at a sub-microscopic level. The process involves shining light onto metal nanostructures, which amplifies the local electric field. Interactions between this field and the particular molecule that researchers are interested in can be measured, and this allows them to learn valuable things about molecular concentration and kinetics.

However, usage of plasmonic sensing outside a laboratory setting has been limited due to the cost and bulkiness of the instruments involved. The team at UCLA, led by Aydogan Ozcan, Professor of Electrical Engineering and Bioengineering and Associate Director of the California NanoSystems Institute, has now developed a prototype for a mobile, inexpensive plasmonic reader that is also much more accurate than conventional sensor designs.

The prototype makes use of machine learning in order to decide what type of light source should be used in the plasmonic sensing process, as the technique allows a particular algorithm to adapt to the data it is presented with and to "train" itself to make decisions. It has a wide range of applications in other fields, one of the more notable being in Optical Character Recognition. Google’s map software can learn to read numbers and letters on houses and streets accurately, a task for which pre-programming an algorithm would be infeasible.

(Image: Advanced Science News)

In the case of the plasmonic sensing prototype, there are thousands of different types of LED that can be used for the sensor, so machine learning allows the four most suitable ones for a particular situation to be determined much more efficiently and accurately. The sensor can thus be easily modified according to which bio-target it is supposed to capture.

The reader consists of these four differently coloured LEDs, a camera, and 3D printed plastic housing. To use the device, a specimen is applied to the sensor, which is subsequently fitted into a cartridge that is placed inside the reader to be automatically measured and analysed. 3D printing technology allows the prototype to be made cheaply but to still be durable and appropriately designed to adapt to different situations.  

Ozcan and his team hope that their work can be used as a design tool for other researchers and scientists in the field to improve their own plasmonic reader devices. They reported that such an indispensable medical device could even be designed as a smartphone attachment. This would further drive down production costs, as well as making use of cloud connectivity and the computational power of the phones.

Once again, we can see the ease with which 3D printing can be implemented to make designs that are much cheaper and efficient than conventional solutions, as well as being more adaptable. This unlimited adaptability is something that machine learning also shares. We hope to see more multi-disciplinary combinations of these breakthroughs in future projects, particularly ones that are not only innovative but also have the potential to save lives.



Posted in 3D Printing Application



Maybe you also like:


Leave a comment:

Your Name:


Subscribe us to

3ders.org Feeds 3ders.org twitter 3ders.org facebook   

About 3Ders.org

3Ders.org provides the latest news about 3D printing technology and 3D printers. We are now seven years old and have around 1.5 million unique visitors per month.

News Archive