Leontiou Theodoros, Frixou Anna, Charalambides Marios, Stiliaris Efstathios, Papanicolas Costas N, Nikolaidou Sofia, Papadakis Antonis
Department of Mechanical Engineering, Frederick University, Nicosia 1036, Cyprus.
Computation-Based Science and Technology Research Center (CaSToRC), The Cyprus Institute, 20 Kavafi Street, Nicosia 2121, Cyprus.
Tomography. 2024 Nov 30;10(12):1930-1946. doi: 10.3390/tomography10120140.
: Accurate reconstruction of internal temperature fields from surface temperature data is critical for applications such as non-invasive thermal imaging, particularly in scenarios involving small temperature gradients, like those in the human body. : In this study, we employed 3D convolutional neural networks (CNNs) to predict internal temperature fields. The network's performance was evaluated under both ideal and non-ideal conditions, incorporating noise and background temperature variations. A physics-informed loss function embedding the heat equation was used in conjunction with statistical uncertainty during training to simulate realistic scenarios. : The CNN achieved high accuracy for small phantoms (e.g., 10 cm in diameter). However, under non-ideal conditions, the network's predictive capacity diminished in larger domains, particularly in regions distant from the surface. The introduction of physical constraints in the training processes improved the model's robustness in noisy environments, enabling accurate reconstruction of hot-spots in deeper regions where traditional CNNs struggled. : Combining deep learning with physical constraints provides a robust framework for non-invasive thermal imaging and other applications requiring high-precision temperature field reconstruction, particularly under non-ideal conditions.
从表面温度数据准确重建内部温度场对于诸如非侵入性热成像等应用至关重要，特别是在涉及小温度梯度的场景中，如人体中的情况。在本研究中，我们采用三维卷积神经网络（CNN）来预测内部温度场。在理想和非理想条件下对网络性能进行了评估，其中纳入了噪声和背景温度变化。在训练期间，使用嵌入热方程的物理信息损失函数并结合统计不确定性来模拟现实场景。该CNN对小尺寸模型（例如直径为10厘米）实现了高精度。然而，在非理想条件下，网络在较大区域的预测能力下降，特别是在远离表面的区域。在训练过程中引入物理约束提高了模型在噪声环境中的鲁棒性，能够在传统CNN难以处理的较深区域准确重建热点。将深度学习与物理约束相结合为非侵入性热成像和其他需要高精度温度场重建的应用提供了一个强大的框架，特别是在非理想条件下。
