Kullberg Jacob, Colton Jacob, Gregory C Tolex, Bay Austin, Munro Troy
Computer Science Department, Brigham Young University, 3361 TMCB, Provo, 84602, UT, USA.
Mechanical Engineering department, Brigham Young University, 3361 TMCB, Provo, 84602, UT, USA.
Int J Thermophys. 2022 Nov;43(11). doi: 10.1007/s10765-022-03102-0. Epub 2022 Sep 25.
Biological systems often have a narrow temperature range of operation, which require highly accurate spatially resolved temperature measurements, often near ± 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 ± 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 ± 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 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 ± 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.
生物系统通常具有较窄的工作温度范围，这就需要进行高精度的空间分辨温度测量，测量精度通常要达到±K左右。然而，许多温度传感器无法同时满足精度和空间分布要求，这往往是因为它们的精度受到数据拟合和温度重建模型的限制。机器学习算法有潜力满足这一需求，但在文献中，它们在生成温度空间分布方面的应用严重不足。这项工作首次展示了使用神经网络处理荧光图像来绘制温度空间分布的实例。研究了三种标准网络架构，一种是使用非空间分辨荧光测温法（简单连接前馈网络），另外两种是在图像或像素识别过程中使用（U-net和卷积神经网络，即CNN）。基于已知温度分布生成了基于实验数据的模拟荧光图像，并添加了标准差为±K的高斯白噪声。这些标准网络的结果不佳促使创建了所谓的移动CNN，其均方根误差为±K，其中矩阵元素代表相邻像素。最后，当将这种移动CNN训练并应用于微流控设备内三种独特的特征温度分布时，研究了其性能，其中荧光图像是在三个或五个不同波长下模拟的。结果表明，在训练期间每个温度至少有 个数据点以及最宽的温度范围，能够提供最接近图像真实温度的温度预测，最小均方根误差为±K。与传统曲线拟合技术相比，这项工作表明，使用卷积神经网络在从荧光图像进行温度空间映射时可以实现更高的精度。
