Deep neural network provides robust detection of disease biomarkers in real time – ScienceDaily

Sophisticated systems for detecting biomarkers, such as DNA or proteins that indicate the presence of a disease, are essential for real-time diagnostics and disease monitoring devices.

Holger Schmidt, UC Santa Cruz emeritus professor of electrical and computer engineering, and his group have long focused on developing unique, highly sensitive devices called optofluidic chips to detect biomarkers.

Schmidt graduate student Vahid Ganjalizadeh led the effort to use machine learning to improve their systems, improving its ability to accurately classify biomarkers. The deep neural network he developed classifies particle signals with 99.8 percent accuracy in real time, on a system that is relatively inexpensive and portable for point-of-care applications, as shown in a new paper. Nature Science Reports.

When biomarker detectors are taken into the field or to a point of care such as a health clinic, the signals received by the sensors may not be as high quality as in a laboratory or controlled environment. This can be due to a number of factors, such as the need to use cheaper chips to reduce costs, or environmental characteristics such as temperature and humidity.

To address the challenges of a weak signal, Schmidt and his team developed a deep neural network that can identify the source of that weak signal with high confidence. The researchers trained the neural network with known training signals, teaching it to recognize the possible variations it could see so that it could recognize patterns and identify new signals with very high accuracy.

First, a parallel cluster wavelet analysis (PCWA) approach developed in Schmidt’s lab detects the presence of a signal. The neural network then processes the potentially weak or noisy signal to identify its source. This system works in real time, so users can get results in a fraction of a second.

“It’s all about making the most of the low-quality signals possible and doing it really quickly and efficiently,” Schmidt said.

A smaller version of the neural network model can run on mobile devices. In the paper, the researchers run the system on a Google Coral Dev board, a relatively inexpensive device for accelerated execution of artificial intelligence algorithms. This means that the system also requires less energy to run the processing compared to other techniques.

“Unlike some research that requires supercomputers to perform high-precision detection, we’ve proven that even a compact, portable, relatively inexpensive device can do the work for us,” Ganjalizadeh said. “That makes it accessible, feasible and portable for point-of-care applications.”

The entire system is designed for completely local use, which means that data processing can take place without Internet access, unlike other systems that rely on cloud computing. This also provides a data security advantage as results can be obtained without the need to share data with a cloud server provider.

It is also designed to deliver results on a mobile device, eliminating the need to bring a laptop into the field.

“You can build a more robust system that you can move to under-resourced or less developed regions and it still works,” Schmidt said.

This improved system will work for any other biomarkers that the Schmidt lab’s systems have been used to detect in the past, such as COVID-19, Ebola, influenza and cancer biomarkers. Although they are currently focused on medical applications, the system can be adapted to detect any type of signal.

To push the technology even further, Schmidt and members of his lab plan to add even more dynamic signal processing capabilities to their devices. This will simplify the system and combine the processing methods needed to detect signals at low and high concentrations of molecules. The team is also working to integrate individual parts of the setup into an integrated optofluidic chip design.

Source link