Closed-loop high precision human tissue temperature measurements using a joint forward and inverse method

• Published in: Biomedical signal processing and control Vol. 93; p. 106196
• Main Authors: Liu, Jie, Cai, Xinyi, Liu, Yixuan, Sun, Zhenlin, Sun, Guangmin
• Format: Journal Article
• Language: English
• Published: Elsevier Ltd 01.07.2024
• Subjects: Four-layer tissue; High-precision; Multi-frequency bands; Opt-XGBoost; R2; SSE; Four-layer tissue; KNN; RMSE; Multi-frequency bands; PCA; FEM; MAE; High-precision; Opt-XGBoost; RF; XGBoost; MSE
• DOI: 10.1016/j.bspc.2024.106196
• ISSN: 1746-8094

•A high precision multi-frequency band inversion algorithm (Opt-XGBoost), based on an objective function correction and hyperparameter optimization, is proposed to improve the accuracy of multi-layer tissue temperature inversion.•The incoherent four-layer tissue forward model combines the Pennes heat transfer equation and the modeling method of fluid–solid coupling boundaries, and introduces random errors in this incoherent forward model.•To address the limitations of non-contact microwave precise measurements of internal tissue temperatures in the human body, we propose a closed-loop forward and backward joint multi-layer temperature prediction model. A closed-loop forward-inverse joint multi-layer temperature prediction method is introduced to overcome the limitations of non-contact microwave-based precise temperature measurements within human tissues. This approach merges an incoherent four-layer tissue forward model with a multi-frequency high-precision inversion algorithm. Random errors were incorporated into the forward model to construct a multi-layer human tissue dataset for performance validation and optimization of the inversion algorithm. The lack of precise temperature measurements in internal human tissues was addressed using an incoherent four-layer forward model that integrates the Pennes heat transfer equation with a fluid–solid coupling boundary modeling technique. Parameter differentiation analysis was conducted in the forward modeling step using incoherent electromagnetic transport equations. The proposed high-precision multi-frequency inversion process, added to the objective function, refines the XGBoost algorithm by assigning a penalty factor and adjusting for neighboring tissue temperature distributions. The Optuna framework was then utilized to optimize XGBoost hyper-parameter sets, resulting in the Opt-XGBoost inversion algorithm. This approach achieved a root mean square error of 0.033 °C and an average absolute error of 0.0256 °C in simulations involving forward modeling-generated data.