The application of deep neural networks towards solving problems in science and engineering has demonstrated encouraging results with the recent formulation of physics-informed neural networks ...(PINNs). Through the development of refined machine learning techniques, the high computational cost of obtaining numerical solutions for partial differential equations governing complicated physical systems can be mitigated. However, solutions are not guaranteed to be unique, and are subject to uncertainty caused by the choice of network model parameters. For critical systems with significant consequences for errors, assessing and quantifying this model uncertainty is essential. In this paper, an application of PINN for laser bio-effects with limited training data is provided for uncertainty quantification analysis. Additionally, an efficacy study is performed to investigate the impact of the relative weights of the loss components of the PINN and how the uncertainty in the predictions depends on these weights. Network ensembles are constructed to empirically investigate the diversity of solutions across an extensive sweep of hyper-parameters to determine the model that consistently reproduces a high-fidelity numerical simulation.
•A physics informed neural network is designed for solving the heat diffusion equation.•An ensemble method increases accuracy of predictions and quantifies uncertainty.•A weighting heuristic automatically normalizes individual components of loss function.•Equitable convergence amongst competing minimization objectives is enforced.•Network design parameters are optimized for both accuracy and reliability.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Skin injury response to near-infrared (NIR) laser radiation between the minimum visible lesion threshold and ablation onset is not well understood. This study utilizes a 1070-nm diode-pumped Yb-fiber ...laser to explore the response of excised porcine skin to high-energy exposures in the suprathreshold injury region without inducing ablation. Concurrent high-speed videography is employed to determine a dichotomous response for three progressive damage categories: observable surface distortion, surface bubble formation due to contained intracutaneous water vaporization, and surface bubble rupture during exposure. Median effective dose (ED50) values are calculated in these categories for 3- and 100-ms pulses with beam diameters (1 / e2) of 3 mm (28, 35, and 49 J / cm2) and 7 mm (96, 141, and 212 J / cm2), respectively. Double-pulse cases are secondarily investigated. Experimental data are compared with the maximum permissible exposure limits and ablation onset simulated by a one-dimensional multiphysics model. Logistic regression analysis predicted injury events with ∼90 % of accuracy. The distinction of skin response into progressive damage categories expands the current understanding of high-energy laser safety while underlining the unique biophysical effects during induced water phase change in tissue. These results prove to be useful in the diagnosis and treatment of NIR laser injuries.
Modeling of physical processes as partial differential equations (PDEs) is often carried out with computationally expensive numerical solvers. A common, and important, process to model is that of ...laser interaction with biological tissues. Physics-informed neural networks (PINNs) have been used to model many physical processes, though none have demonstrated an approximation involving a source term in a PDE, which modeling laser-tissue interactions requires. In this work, a numerical solver for simulating tissue interactions with lasers was surrogated using PINNs while testing various boundary conditions, one with a radiative source term involved. Models were tested using differing activation function combinations in their architectures for comparison. The best combinations of activation functions were different for cases with and without a source term, and R2 scores and average relative errors for the predictions of the best PINN models indicate that it is an accurate surrogate model for corresponding solvers. PINNs appear to be valid replacements for numerical solvers for one-dimensional tissue interactions with electromagnetic radiation.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
The time-temperature response of porcine tissue to laser radiation exposure is investigated as a function of wavelength. We experimentally measure the thermal response of tissue to laser radiation ...ranging in wavelength from 1100 nm to 1550 nm. The experimental data were compared to simulations performed using thermal modeling software. Based on these simulations, and the corresponding experimental data, damage thresholds as a function of wavelength were estimated. This data can be used to help optimize the design of optical imaging systems, particularly those being used for biomedical imaging.