Patient-specific temperature distribution prediction in laser interstitial thermal therapy: single-irradiation data-driven method

Laser interstitial thermal therapy (LITT) is popular for treating brain tumours and epilepsy. The strict control of tissue thermal damage extent is crucial for LITT. Temperature prediction is useful for predicting thermal damage extent. Accurately predictingin vivobrain tissue temperature is challenging due to the temperature dependence and the individual variations in tissue properties. Considering these factors is essential for improving the temperature prediction accuracy.Objective. To present a method for predicting patient-specific tissue temperature distribution within a target lesion area in the brain during LITT.Approach. A magnetic resonance temperature imaging (MRTI) data-driven estimation model was constructed and combined with a modified Pennes bioheat transfer equation (PBHE) to predict patient-specific temperature distribution. In the PBHE for temperature prediction, the individual specificity and temperature dependence of thermal tissue properties and blood perfusion, as well as the individual specificity of optical tissue properties were considered. Only MRTI data during one laser irradiation were required in the method. This enables the prediction of patient-specific temperature distribution and the resulting thermal damage region for subsequent ablations.Main results. Patient-specific temperature prediction was evaluated based on clinical data acquired during LITT in the brain, using intraoperative MRTI data as the reference standard. Our method significantly improved the prediction performance of temperature distribution and thermal damage region. The average root mean square error was decreased by 69.54%, the average intraclass correlation coefficient was increased by 37.5%, the average Dice similarity coefficient was increased by 43.14% for thermal damage region prediction.Significance. The proposed method can predict temperature distribution and thermal damage region at an individual patient level during LITT, providing a promising approach to assist in patient-specific treatment planning for LITT in the brain.

A workflow for predicting radiofrequency-induced heating around bilateral deep brain stimulation electrodes in MRI

BACKGROUND

Heating around deep brain stimulation (DBS) in magnetic resonance imaging (MRI) occurs when the time-varying electromagnetic (EM) fields induce currents in the electrodes which can generate heat and potentially cause tissue damage. Predicting the heating around the electrode contacts is important to ensure the safety of patients with DBS implants undergoing an MRI scan. We previously proposed a workflow to predict heating around DBS contacts and introduced a parameter, equivalent transimpedance, that is independent of electrode trajectories, termination, and radiofrequency (RF) excitations. The workflow performance was validated in a unilateral DBS system.

PURPOSE

To predict RF heating around the contacts of bilateral (DBS) electrodes during an MRI scan in an anthropomorphic head phantom.

METHODS

Bilateral electrodes were fixed in a skull phantom filled with hydroxyethyl cellulose (HEC) gel. The electrode shafts were suspended extracranially, in a head and torso phantom filled with the same gel material. The current induced on the electrode shaft was experimentally measured using an MR-based technique 3 cm above the tip. A transimpedance value determined in a previous offline calibration was used to scale the shaft current and calculate the contact voltage. The voltage was assigned as a boundary condition on the electrical contacts of the electrode in a quasi-static (EM) simulation. The resulting specific absorption rate (SAR) distribution became the input for a transient thermal simulation and was used to predict the heating around the contacts. RF heating experiments were performed for eight different lead trajectories using circularly polarized (CP) excitation and two linear excitations for one trajectory. The measured temperatures for all experiments were compared with the simulated temperatures and the root-mean-squared errors (RMSE) were calculated.

RESULTS

The RF heating around the contacts of both bilateral electrodes was predicted with ≤ 0.29°C of RMSE for 20 heating scenarios.

CONCLUSION

The workflow successfully predicted the heating for different bilateral DBS trajectories and excitation patterns in an anthropomorphic head phantom.

Real-Time Temperature Prediction of Power Devices Using an Improved Thermal Equivalent Circuit Model and Application in Power Electronics

As a core component of photovoltaic power generation systems, insulated gate bipolar transistor (IGBT) modules continually suffer from severe temperature swings due to complex operation conditions and various environmental conditions, resulting in fatigue failure. The junction temperature prediction guarantees that the IGBT module operates within the safety threshold. The thermal equivalent circuit model is a common approach to predicting junction temperature. However, the model parameters are easily affected by the solder aging. An accurate temperature prediction by the model is impossible during service. This paper proposes an improved thermal equivalent circuit model that can remove the effect of solder aging. Firstly, the solder aging process is monitored in real-time based on the case temperatures. Secondly, the model parameters are corrected by the thermal impedance from chip to baseplate based on the linear thermal characteristic. The simulation and experimental results show that the proposed model can reduce the temperature prediction error by more than 90% under the same aging condition. The proposed method only depends on the case temperatures to correct the model parameters, which is more economical. In addition, the experimental and simulation analysis in this work can help students of power electronics courses have an in-depth knowledge of power devices' mechanical structure, heat dissipation principles, temperature distribution, junction temperature monitoring, and so on.

Informer-Based Temperature Prediction Using Observed and Numerical Weather Prediction Data

This paper proposes an Informer-based temperature prediction model to leverage data from an automatic weather station (AWS) and a local data assimilation and prediction system (LDAPS), where the Informer as a variant of a Transformer was developed to better deal with time series data. Recently, deep-learning-based temperature prediction models have been proposed, demonstrating successful performances, such as conventional neural network (CNN)-based models, bi-directional long short-term memory (BLSTM)-based models, and a combination of both neural networks, CNN-BLSTM. However, these models have encountered issues due to the lack of time data integration during the training phase, which also lead to the persistence of a long-term dependency problem in the LSTM models. These limitations have culminated in a performance deterioration when the prediction time length was extended. To overcome these issues, the proposed model first incorporates time-periodic information into the learning process by generating time-periodic information and inputting it into the model. Second, the proposed model replaces the LSTM with an Informer as an alternative to mitigating the long-term dependency problem. Third, a series of fusion operations between AWS and LDAPS data are executed to examine the effect of each dataset on the temperature prediction performance. The performance of the proposed temperature prediction model is evaluated via objective measures, including the root-mean-square error (RMSE) and mean absolute error (MAE) over different timeframes, ranging from 6 to 336 h. The experiments showed that the proposed model relatively reduced the average RMSE and MAE by 0.25 °C and 0.203 °C, respectively, compared with the results of the CNN-BLSTM-based model.

Frost prediction using machine learning and deep neural network models

This study describes accurate, computationally efficient models that can be implemented for practical use in predicting frost events for point-scale agricultural applications. Frost damage in agriculture is a costly burden to farmers and global food security alike. Timely prediction of frost events is important to reduce the cost of agricultural frost damage and traditional numerical weather forecasts are often inaccurate at the field-scale in complex terrain. In this paper, we developed machine learning (ML) algorithms for the prediction of such frost events near Alcalde, NM at the point-scale. ML algorithms investigated include deep neural network, convolution neural networks, and random forest models at lead-times of 6-48 h. Our results show promising accuracy (6-h prediction RMSE = 1.53-1.72°C) for use in frost and minimum temperature prediction applications. Seasonal differences in model predictions resulted in a slight negative bias during Spring and Summer months and a positive bias in Fall and Winter months. Additionally, we tested the model transferability by continuing training and testing using data from sensors at a nearby farm. We calculated the feature importance of the random forest models and were able to determine which parameters provided the models with the most useful information for predictions. We determined that soil temperature is a key parameter in longer term predictions (>24 h), while other temperature related parameters provide the majority of information for shorter term predictions. The model error compared favorable to previous ML based frost studies and outperformed the physically based High Resolution Rapid Refresh forecasting system making our ML-models attractive for deployment toward real-time monitoring of frost events and damage at commercial farming operations.

Temperature Prediction of Seasonal Frozen Subgrades Based on CEEMDAN-LSTM Hybrid Model

Improving the temperature prediction accuracy for subgrades in seasonally frozen regions will greatly help improve the understanding of subgrades' thermal states. Due to the nonlinearity and non-stationarity of the temperature time series of subgrades, it is difficult for a single general neural network to accurately capture these two characteristics. Many hybrid models have been proposed to more accurately forecast the temperature time series. Among these hybrid models, the CEEMDAN-LSTM model is promising, thanks to the advantages of the long short-term memory (LSTM) artificial neural network, which is good at handling complex time series data, and its combination with the broad applicability of the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) in the field of signal decomposition. In this study, by performing empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and CEEMDAN on temperature time series, respectively, a hybrid dataset is formed with the corresponding time series of volumetric water content and frost heave, and finally, the CEEMDAN-LSTM model is created for prediction purposes. The results of the performance comparisons between multiple models show that the CEEMDAN-LSTM model has the best prediction performance compared to other decomposed LSTM models because the composition of the hybrid dataset improves predictive ability, and thus, it can better handle the nonlinearity and non-stationarity of the temperature time series data.

A workflow for predicting temperature increase at the electrical contacts of deep brain stimulation electrodes undergoing MRI

Purpose

The purpose of this study is to present a workflow for predicting the radiofrequency (RF) heating around the contacts of a deep brain stimulation (DBS) lead during an MRI scan.

Methods

The induced RF current on the DBS lead accumulates electric charge on the metallic contacts, which may cause a high local specific absorption rate (SAR), and therefore, heating. The accumulated charge was modeled by imposing a voltage boundary condition on the contacts in a quasi‐static electromagnetic (EM) simulation allowing thermal simulations to be performed with the resulting SAR distributions. Estimating SAR and temperature increases from a lead in vivo through EM simulation is not practical given anatomic differences and variations in lead geometry. To overcome this limitation, a new parameter, transimpedance, was defined to characterize a given lead. By combining the transimpedance, which can be measured in a single calibration scan, along with MR‐based current measurements of the lead in a unique orientation and anatomy, local heating can be estimated. Heating determined with this approach was compared with results from heating studies of a commercial DBS electrode in a gel phantom with different lead configurations to validate the proposed method.

Results

Using data from a single calibration experiment, the transimpedance of a commercial DBS electrode (directional lead, Infinity DBS system, Abbott Laboratories, Chicago, IL) was determined to be 88 Ω. Heating predictions using the DBS transimpedance and rapidly acquired MR‐based current measurements in 26 different lead configurations resulted in a <23% (on average 11.3%) normalized root‐mean‐square error compared to experimental heating measurements during RF scans.

Conclusion

In this study, a workflow consisting of an MR‐based current measurement on the DBS lead and simple quasi‐static EM/thermal simulations to predict the temperature increase around a DBS electrode undergoing an MRI scan is proposed and validated using a commercial DBS electrode.

Click here for author‐reader discussions

Diffuse Reflection Infrared Fourier Transform Spectroscopy and Partial Least Squares Regression Analysis for Temperature Prediction of Irreversible Thermochromic Paints

Temperature measurement of internal components of a jet engine is a crucial control parameter to ensure its component life and efficiency. Particularly for thermal analysis of internal components of jet engines, irreversible thermochromic paints (TPs) have been developed at Rolls-Royce plc to evaluate the surface temperature of engine components where it is otherwise impossible. Thermochromic paints change color with respect to an increased temperature whereby the resulting change in the TP color corresponds to the maximum temperature experienced by the surface of engine components during testing. To improve the reliability and reproducibility of the temperature measurement by TPs, this work explored the potential use of diffuse reflection Fourier transform infrared spectroscopy (DRIFTS) combined with partial least squares regression (PLSR) analysis. The outcome of the prediction of the raw and pre-processed datasets was compared and discussed. The major contributors to the prediction models were the change in the property of the surface M-OH bonds, the structural change of the inorganic pigments and fillers, and their solid-state reaction at a higher temperature. The result showed improved reliability of the prediction model after the combined pre-process treatments with reported RMSEC of 4.5 °C and RMSECV of 13.0 °C using three latent variables.

A Guide for Water Bolus Temperature Selection for Semi-Deep Head and Neck Hyperthermia Treatments Using the HYPERcollar3D Applicator

During hyperthermia cancer treatments, especially in semi-deep hyperthermia in the head and neck (H&N) region, the induced temperature pattern is the result of a complex interplay between energy delivery and tissue cooling. The purpose of this study was to establish a water bolus temperature guide for the HYPERcollar3D H&N applicator. First, we measured the HYPERcollar3D water bolus heat-transfer coefficient. Then, for 20 H&N patients and phase/amplitude settings of 93 treatments we predict the T50 for nine heat-transfer coefficients and ten water bolus temperatures ranging from 20-42.5 °C. Total power was always tuned to obtain a maximum of 44 °C in healthy tissue in all simulations. As a sensitivity study we used constant and temperature-dependent tissue cooling properties. We measured a mean heat-transfer coefficient of h = 292 W m^-2K^-1 for the HYPERcollar3D water bolus. The predicted T50 shows that temperature coverage is more sensitive to the water bolus temperature than to the heat-transfer coefficient. We propose changing the water bolus temperature from 30 °C to 35 °C which leads to a predicted T50 increase of +0.17/+0.55 °C (constant/temperature-dependent) for targets with a median depth < 20 mm from the skin surface. For deeper targets, maintaining a water bolus temperature at 30 °C is proposed.

Analysis of the Temperature Distribution in a Refrigerated Truck Body Depending on the Box Loading Patterns

The main purpose of cold chain is to keep the temperature of products constant during transportation. The internal temperature of refrigerated truck body is mainly measured with a temperature sensor installed at the hottest point on the body. Hence, the measured temperature cannot represent the overall temperature values of transported products in the body. Moreover, the airflow pattern in the refrigerated body can vary depending on the arrangement of loaded logistics, resulting temperature differences between the transported products. In this study, the airflow and temperature change in the refrigerated body depending on the loading patterns of box were analyzed using experimental and numerical analysis methods. Ten different box loading patterns were applied to the body of 0.5 ton refrigerated truck. The temperatures inside boxes were measured depending on the loading patterns. CFD modeling with two different turbulence models (k-ε and SST k-ω) was developed using COMSOL Multiphysics for predicting the temperatures inside boxes loaded with different patterns, and the predicted data were compared to the experimental data. The k-ε turbulence model showed a higher temperature error than the SST k-ω model; however, the highest temperature point inside the boxes was almost accurately predicted. The developed model derived an approximate temperature distribution in the boxes loaded in the refrigerated body.

Temperature Prediction Using Multivariate Time Series Deep Learning in the Lining of an Electric Arc Furnace for Ferronickel Production

The analysis of data from sensors in structures subjected to extreme conditions such as the ones used in smelting processes is a great decision tool that allows knowing the behavior of the structure under different operational conditions. In this industry, the furnaces and the different elements are fully instrumented, including sensors to measure variables such as temperature, pressure, level, flow, power, electrode positions, among others. From the point of view of engineering and data analytics, this quantity of data presents an opportunity to understand the operation of the system under normal conditions or to explore new ways of operation by using information from models provided by using deep learning approaches. Although some approaches have been developed with application to this industry, it is still an open research area. As a contribution, this paper presents an applied deep learning temperature prediction model for a 75 MW electric arc furnace, which is used for ferronickel production. In general, the methodology proposed considers two steps: first, a data cleaning process to increase the quality of the data, eliminating both redundant information as well as atypical and unusual data, and second, a multivariate time series deep learning model to predict the temperatures in the furnace lining. The developed deep learning model is a sequential one based on GRU (gated recurrent unit) layer plus a dense layer. The GRU + Dense model achieved an average root mean square error (RMSE) of 1.19 °C in the test set of 16 different thermocouples radially distributed on the furnace.

Exploring the Predictability of Temperatures in a Scaled Model of a Smarthome

In modern smarthomes, temperature regulation is achieved through a mix of traditional and emergent technologies including air conditioning, heating, intelligent utilization of the effects of sun, wind, and shade as well as using stored heat and cold. To achieve the desired comfort for the inhabitants while minimizing environmental impact and cost, the home controller must predict how its actions will impact the temperature and other environmental factors in various parts of the home. The question we are investigating in this paper is whether the temperature values in different rooms in a home are predictable based on readings from sensors in the home. We are also interested in whether increased accuracy can be achieved by adding sensors to capture the state of doors and windows of the given room and/or the whole home, and what type of machine learning algorithms can take advantage of the additional information. As experimentation on real-world homes is highly expensive, we use ScaledHome, a 1:12 scale, IoT-enabled model of a smart home for data acquisition. Our experiments show that while additional data can improve the accuracy of the prediction, the type of machine learning models needs to be carefully adapted to the number of data features available.

Temperature Prediction Based on Bidirectional Long Short-Term Memory and Convolutional Neural Network Combining Observed and Numerical Forecast Data

Weather is affected by a complex interplay of factors, including topography, location, and time. For the prediction of temperature in Korea, it is necessary to use data from multiple regions. To this end, we investigate the use of deep neural-network-based temperature prediction model time-series weather data obtained from an automatic weather station and image data from a regional data assimilation and prediction system (RDAPS). To accommodate such different types of data into a single model, a bidirectional long short-term memory (BLSTM) model and a convolutional neural network (CNN) model are chosen to represent the features from the time-series observed data and the RDAPS image data. The two types of features are combined to produce temperature predictions for up to 14 days in the future. The performance of the proposed temperature prediction model is evaluated by objective measures, including the root mean squared error and mean bias error. The experiments demonstrated that the proposed model combining both the observed and RDAPS image data is better in all performance measures for all prediction periods compared with the BLSTM-based model using observed data and the CNN-BLSTM-based model using RDAPS image data alone.

Chaotic Ensemble of Online Recurrent Extreme Learning Machine for Temperature Prediction of Control Moment Gyroscopes

Control moment gyroscopes (CMG) are crucial components in spacecrafts. Since the anomaly of bearing temperature of the CMG shows apparent correlation with nearly all critical fault modes, temperature prediction is of great importance for health management of CMGs. However, due to the complicity of thermal environment on orbit, the temperature signal of the CMG has strong intrinsic nonlinearity and chaotic characteristics. Therefore, it is crucial to study temperature prediction under the framework of chaos time series theory. There are also several other challenges including poor data quality, large individual differences and difficulty in processing streaming data. To overcome these issues, we propose a new method named Chaotic Ensemble of Online Recurrent Extreme Learning Machine (CE-ORELM) for temperature prediction of control moment gyroscopes. By means of the CE-ORELM model, this proposed method is capable of dynamic prediction of temperature. The performance of the method was tested by real temperature data acquired from actual CMGs. Experimental results show that this method has high prediction accuracy and strong adaptability to the on-orbital temperature data with sudden variations. These superiorities indicate that the proposed method can be used for temperature prediction of control moment gyroscopes.

Computational analysis of temperature distribution in microwave-heated potatoes

This research article reports the computational analysis of temperature distribution in microwave-heated convenience food such as potato. The detailed study of temperature (because temperature is a function of bacterial inactivation) and microwave powers along with drying time for the preservation of food material has been presented. Therefore, a mathematical model for potato sample is developed to predict the behavior of temperature distribution at each possible point and different shapes (slab, cylindrical, and spherical) of food material. The developed mathematical model is programmed by MATLAB software. Another parameter, microwave power is also a function of temperature. The ranging values of various microwave powers (125 W, 375 W, 625 W, 875 W, and 1250 W) along with different values of drying time (0 to 10 minutes) have been used for computation. The obtained results show the uniformity of temperature distribution throughout the whole product in the form of a three-dimensional structure. The model provides the minimum and maximum temperature ranges in specimens without performing an experiment which depicts the condition of bacterial inactivation.

Abundant Inverse Regression using Sufficient Reduction and its Applications

Statistical models such as linear regression drive numerous applications in computer vision and machine learning. The landscape of practical deployments of these formulations is dominated by forward regression models that estimate the parameters of a function mapping a set of p covariates, x , to a response variable, y. The less known alternative, Inverse Regression, offers various benefits that are much less explored in vision problems. The goal of this paper is to show how Inverse Regression in the "abundant" feature setting (i.e., many subsets of features are associated with the target label or response, as is the case for images), together with a statistical construction called Sufficient Reduction, yields highly flexible models that are a natural fit for model estimation tasks in vision. Specifically, we obtain formulations that provide relevance of individual covariates used in prediction, at the level of specific examples/samples - in a sense, explaining why a particular prediction was made. With no compromise in performance relative to other methods, an ability to interpret why a learning algorithm is behaving in a specific way for each prediction, adds significant value in numerous applications. We illustrate these properties and the benefits of Abundant Inverse Regression (AIR) on three distinct applications.