RESUMEN
Many biological systems have a narrow temperature range of operation, meaning high accuracy and spatial distribution level are needed to study these systems. Most temperature sensors cannot meet both the accuracy and spatial distribution required in the microfluidic systems that are often used to study these systems in isolation. This paper introduces a neural network called the Multi-Directional Fluorescent Temperature Long Short-Term Memory Network (MFTLSTM) that can accurately calculate the temperature at every pixel in a fluorescent image to improve upon the standard fitting practice and other machine learning methods use to relate fluorescent data to temperature. This network takes advantage of the nature of heat diffusion in the image to achieve an accuracy of ±0.0199 K RMSE within the temperature range of 298K to 308 K with simulated data. When applied to experimental data from a 3D printed microfluidic device with a temperature range of 290 K to 380 K, it achieved an accuracy of ±0.0684 K RMSE. These results have the potential to allow high temperature resolution in biological systems than is available in many microfluidic devices.
RESUMEN
Many biological systems have a narrow temperature range of operation, meaning high accuracy and spatial distribution level are needed to study these systems. Most temperature sensors cannot meet both the accuracy and spatial distribution required in the microfluidic systems that are often used to study these systems in isolation. This paper introduces a neural network called the Multi-Directional Fluorescent Temperature Long Short-Term Memory Network (MFTLSTM) that can accurately calculate the temperature at every pixel in a fluorescent image to improve upon the standard fitting practice and other machine learning methods use to relate fluorescent data to temperature. This network takes advantage of the nature of heat diffusion in the image to achieve an accuracy of ±0.0199 K RMSE within the temperature range of 298K to 308 K with simulated data. When applied to experimental data from a 3D printed microfluidic device with a temperature range of 290 K to 380 K, it achieved an accuracy of ±0.0684 K RMSE. These results have the potential to allow high temperature resolution in biological systems than is available in many microfluidic devices.
RESUMEN
Biological systems often have a narrow temperature range of operation, which require highly accurate spatially resolved temperature measurements, often near ±0.1 K. However, many temperature sensors cannot meet both accuracy and spatial distribution requirements, often because their accuracy is limited by data fitting and temperature reconstruction models. Machine learning algorithms have the potential to meet this need, but their usage in generating spatial distributions of temperature is severely lacking in the literature. This work presents the first instance of using neural networks to process fluorescent images to map the spatial distribution of temperature. Three standard network architectures were investigated using non-spatially resolved fluorescent thermometry (simply-connected feed-forward network) or during image or pixel identification (U-net and convolutional neural network, CNN). Simulated fluorescent images based on experimental data were generated based on known temperature distributions where Gaussian white noise with a standard deviation of ±0.1 K was added. The poor results from these standard networks motivated the creation of what is termed a moving CNN, with an RMSE error of ±0.23 K, where the elements of the matrix represent the neighboring pixels. Finally, the performance of this MCNN is investigated when trained and applied to three distinctive temperature distributions characteristic within microfluidic devices, where the fluorescent image is simulated at either three or five different wavelengths. The results demonstrate that having a minimum of 10 3.5 data points per temperature and the broadest range of temperatures during training provides temperature predictions nearest to the true temperatures of the images, with a minimum RMSE of ±0.15 K. When compared to traditional curve fitting techniques, this work demonstrates that greater accuracy when spatially mapping temperature from fluorescent images can be achieved when using convolutional neural networks.