CUST: CNN for Ultrasound Thermal Image Reconstruction Using Sparse Time-of-Flight Information

Kim, Younsu; Audigier, Chloé; Anas, Emran Mohammad Abu; Ziegle, Jens; Friebe, Michael; Boctor, Emad M.

doi:10.1007/978-3-030-01045-4_4

Cited by 4 publications

(4 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One-dimensional studies include atmospheric temperature profiles as functions of altitude (a feedforward neural network, FFNN, with a root mean squared error (RMSE) between ±0.4-1 K [26] and ±1.61 K [27]), temperature and concentration profiles of gases during a combustion reaction (multilayer perceptron (MLP) network with an RMSE between 1.2-8.1% [28]), and a 1D convolutional neural network (CNN) for optical IR thermometer in molten metals [29]. For two-dimensional studies, hyperspectral imaging (RMSE of ±1.14 K [30]), time-of-flight for ultrasonic waves (a mean error near ±0.12 K [31]), 2D flame surface and temperature by CNN [32] (with an unreported RMSE), and flame spectral absorption images (RMSE of ±13.5K [33]) were used to determine temperature. The hyperspectral study developed a surface temperature-deep convolutional neural network (ST-DCNN) but trained it on data only at a single position rather than the full temperature distribution of the surface [30].…”

Section: Neural Network Approaches To Temperature Analysismentioning

confidence: 99%

Demonstration of Neural Networks to Reconstruct Temperatures from Simulated Fluorescent Data towards use in Bio-Microfluidics

Kullberg

Colton

Gregory

et al. 2022

Preprint

View full text Add to dashboard Cite

Biological systems often have a narrow temperature range of operation, which require highly accurate spatially resolved temperature measurements, often near ±0.1K. 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 103.5 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.

show abstract

Section: Neural Network Approaches To Temperature Analysismentioning

confidence: 99%

Demonstration of Neural Networks to Reconstruct Temperatures from Simulated Fluorescent Data towards use in Bio-Microfluidics

Kullberg

Colton

Gregory

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…This hypothesis is based on planar temperature reconstruction from a series of images taken using thermochromic liquid crystals (TLC), where a pixel-topixel based simply connected feedforward network (P2P-SCFFNN) achieved a mean absolute deviation near ±0.1 K over a 4.4 K range from 291.1 to 295.5 K [14]. NNs have been used to recreate temperature from other signals as well, such as IR thermometry of a point [15], atmospheric temperature at varying altitudes [16], flame temperature and composition [17][18][19], and time-of-flight for ultrasonic waves [20]. Previous works' fundamental limitations are that they cannot create a 2D image or have not been applied to fluorescence thermometry.…”

Section: Introductionmentioning

confidence: 99%

Using Recurrent Neural Networks to Reconstruct Temperatures from Simulated Fluorescent Data for use in Bio-Microfluidics

Kullberg,

Sanchez,

Mitchell

et al. 2023

Preprint

View full text Add to dashboard Cite

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.

show abstract

“…These include measuring atmospheric temperatures as a function of altitude, 20 determining temperature during combustion, 21 hyperspectral imaging trained on temperature at a single point, 22 and determining temperature distributions based on time-of-flight of ultrasound through tissue. 23 Based on these few instances with temperature and other sensors benefiting from machine learning use, 24 there is the potential to improve temperature sensing in biological system through the use of neural networks to interpret temperature sensitive signals.…”

Section: ■ Introductionmentioning

confidence: 99%

“…Previously, the focus of machine learning via neural networks for thermal application has historically been on image recognition in thermal images. − A limited number of studies have used feed forward or convolution neural networks to predict temperature based on another signal. These include measuring atmospheric temperatures as a function of altitude, determining temperature during combustion, hyperspectral imaging trained on temperature at a single point, and determining temperature distributions based on time-of-flight of ultrasound through tissue . Based on these few instances with temperature and other sensors benefiting from machine learning use, there is the potential to improve temperature sensing in biological system through the use of neural networks to interpret temperature sensitive signals.…”

Section: Introductionmentioning

confidence: 99%

Use of Machine Learning with Temporal Photoluminescence Signals from CdTe Quantum Dots for Temperature Measurement in Microfluidic Devices

Lewis

Erikson

Sanchez

et al. 2020

ACS Appl. Nano Mater.

View full text Add to dashboard Cite

Because of the vital role of temperature in many biological processes studied in microfluidic devices, there is a need to develop improved temperature sensors and data analysis algorithms. The photoluminescence (PL) of nanocrystals (quantum dots) has been successfully used in microfluidic temperature devices, but the accuracy of the reconstructed temperature has been limited to about 1 K over a temperature range of tens of degrees. A machine learning algorithm consisting of a fully connected network of seven layers with decreasing numbers of nodes was developed and applied to a combination of normalized spectral and time-resolved PL data of CdTe quantum dot emission in a microfluidic device. The data used by the algorithm were collected over two temperature ranges: 10–300 K and 298–319 K. The accuracy of each neural network was assessed via a mean absolute error of a holdout set of data. For the low-temperature regime, the accuracy was 7.7 K, or 0.4 K when the holdout set is restricted to temperatures above 100 K. For the high-temperature regime, the accuracy was 0.1 K. This method provides demonstrates a potential machine learning approach to accurately sense temperature in microfluidic (and potentially nanofluidic) devices when the data analysis is based on normalized PL data when it is stable over time.

show abstract

CUST: CNN for Ultrasound Thermal Image Reconstruction Using Sparse Time-of-Flight Information

Cited by 4 publications

References 12 publications

Demonstration of Neural Networks to Reconstruct Temperatures from Simulated Fluorescent Data towards use in Bio-Microfluidics

Demonstration of Neural Networks to Reconstruct Temperatures from Simulated Fluorescent Data towards use in Bio-Microfluidics

Using Recurrent Neural Networks to Reconstruct Temperatures from Simulated Fluorescent Data for use in Bio-Microfluidics

Use of Machine Learning with Temporal Photoluminescence Signals from CdTe Quantum Dots for Temperature Measurement in Microfluidic Devices

Contact Info

Product

Resources

About