Several techniques exist for the measurement of tissue oxygenation, but they all have some limitations. For instance, pulse oximetry is robust and low-cost but cannot provide a localized measure of oxygenation. Near-infrared spectroscopy, on the other hand, is prone to noisy measurements due to pressure-sensitive contact probes. Spatial frequency domain imaging (SFDI) has emerged as a promising noncontact technique that maps tissue oxygen concentrations over a wide field of view. While simple to implement, SFDI has its own limitations: it requires a sequence of several images for its predictions to be accurate and is prone to errors when working with single snapshots.
In a new study published in the Journal of Biomedical Optics, researchers from Johns Hopkins University, Mason T. Chen and Nicholas J. Durr, have proposed an end-to-end technique for accurate calculation of tissue oxygenation from single snapshots, called OxyGAN. They developed this approach using a class of machine-learning framework called a conditional generative adversarial network (cGAN), which utilizes two neural networks -- a generator and a discriminator -- simultaneously on the same input data. The generator learns to produce realistic output images, while the discriminator learns to determine whether a given image pair forms a correct reconstruction for a given input.
Using conventional SDFI, the researchers obtained oxygenation maps for the human esophagus (ex vivo), hands and feet (in vivo), and a pig colon (in vivo) under illumination with two different wavelengths (659 and 851 nm). They trained OxyGAN with the feet and esophagus samples and saved the hand and colon samples to later test its performance. Further, they compared its performance with a single-snapshot technique based on a physical model and a two-step hybrid technique that consisted of a deep-learning model to predict optical properties and a physical model to calculate tissue oxygenation.
The researchers found that OxyGAN could measure oxygenation accurately, not only for the samples it had seen during training (human feet), but also for the samples it had not seen (human hand and pig colon), demonstrating the robustness of the model. It performed better than both the single-snapshot model and the hybrid model by 24.9% and 24.7%, respectively. Moreover, the scientists optimized OxyGAN to compute ~10 times faster than the hybrid model, enabling real-time mapping at a rate of 25 Hz. Frédéric Leblond, Associate Editor for the Journal of Biomedical Optics, comments, "Not only does this paper represent significant advances that can contribute to the practical clinical implementation of spatial frequency domain imaging, but it will also be part of a relatively small (although rapidly increasing in size) pool of robust published work using AI-type methods to deal with real biomedical optics data."
While the algorithm of OxyGAN could be optimized further, this approach holds promise as a novel technique to measure tissue oxygenation.
"Currently, we are experiencing a once-in-a-century life-changing event," said Alafeef. "We are responding to this global need from a holistic approach by developing multidisciplinary tools for early detection and diagnosis and treatment for SARS-CoV-2."
There are two broad categories of COVID-19 tests on the market. The first category uses reverse transcriptase real-time polymerase chain reaction (RT-PCR) and nucleic acid hybridization strategies to identify viral RNA. Current FDA-approved diagnostic tests use this technique. Some drawbacks include the amount of time it takes to complete the test, the need for specialized personnel and the availability of equipment and reagents.
The second category of tests focuses on the detection of antibodies. However, there could be a delay of a few days to a few weeks after a person has been exposed to the virus for them to produce detectable antibodies.
In recent years, researchers have had some success with creating point-of-care biosensors using 2D nanomaterials such as graphene to detect diseases. The main advantages of graphene-based biosensors are their sensitivity, low cost of production and rapid detection turnaround. "The discovery of graphene opened up a new era of sensor development due to its properties. Graphene exhibits unique mechanical and electrochemical properties that make it ideal for the development of sensitive electrochemical sensors," said Alafeef. The team created a graphene-based electrochemical biosensor with an electrical read-out setup to selectively detect the presence of SARS-CoV-2 genetic material.
There are two components to this biosensor: a platform to measure an electrical read-out and probes to detect the presence of viral RNA. To create the platform, researchers first coated filter paper with a layer of graphene nanoplatelets to create a conductive film. Then, they placed a gold electrode with a predefined design on top of the graphene as a contact pad for electrical readout. Both gold and graphene have high sensitivity and conductivity which makes this platform ultrasensitive to detect changes in electrical signals.
Current RNA-based COVID-19 tests screen for the presence of the N-gene (nucleocapsid phosphoprotein) on the SARS-CoV-2 virus. In this research, the team designed antisense oligonucleotide (ASOs) probes to target two regions of the N-gene. Targeting two regions ensures the reliability of the senor in case one region undergoes gene mutation. Furthermore, gold nanoparticles (AuNP) are capped with these single-stranded nucleic acids (ssDNA), which represents an ultra-sensitive sensing probe for the SARS-CoV-2 RNA.
The researchers previously showed the sensitivity of the developed sensing probes in their earlier work published in ACS Nano. The hybridization of the viral RNA with these probes causes a change in the sensor electrical response. The AuNP caps accelerate the electron transfer and when broadcasted over the sensing platform, results in an increase in the output signal and indicates the presence of the virus.
The team tested the performance of this sensor by using COVID-19 positive and negative samples. The sensor showed a significant increase in the voltage of positive samples compared to the negative ones and confirmed the presence of viral genetic material in less than five minutes. Furthermore, the sensor was able to differentiate viral RNA loads in these samples. Viral load is an important quantitative indicator of the progress of infection and a challenge to measure using existing diagnostic methods.
This platform has far-reaching applications due to its portability and low cost. The sensor, when integrated with microcontrollers and LED screens or with a smartphone via Bluetooth or wifi, could be used at the point-of-care in a doctor's office or even at home. Beyond COVID-19, the research team also foresees the system to be adaptable for the detection of many different diseases.
COMPAMED-tradefair.com; Source: University of Illinois Grainger College of Engineering
