Deep Learning-Driven Computational Imaging for Noninvasive Monitoring System of Brain Temperature and Metabolism: A Hypothermia Validation for Acute Ischemic Stroke

Abstract

Brain temperature (BT) is a critical physiological indicator closely associated with neurological function and disease progression. However, real-time, noninvasive monitoring of BT remains a challenge due to the limitations of current technologies. Here, we present a novel multimodal framework combining bioheat transfer modeling, deep learning, and computational thermography for accurate BT prediction and imaging. A one-dimensional convolutional neural network was trained on multimodal clinical data, integrating cerebral blood flow, tissue oxygen saturation, and intracranial pressure, achieving a mean absolute error of 0.31°C in BT prediction. The framework incorporates finite element analysis to generate 3D thermographic maps of brain tissue with a spatial resolution of 0.4 mm, validated using MRI-derived data. This approach demonstrated robust performance in predicting localized temperature variations in acute ischemic stroke patients undergoing therapeutic hypothermia, with deviations below 0.45°C. Our findings highlight the potential of this system to enable precise BT monitoring, bridging the gap between computational modeling and clinical neuro-thermometry, and paving the way for advanced diagnostic and therapeutic interventions.

Keywords

brain temperature imaging / deep learning / hemodynamics / hypothermia neuroprotection / metabolism thermodynamics

References

[1] N. M. Rzechorzek, M. J. Thrippleton, F. M. Chappell, et al., “A Daily Temperature Rhythm in the human Brain Predicts Survival After Brain Injury,” Brain 145, no. 6 (2022): 2031–2048.

[2] D. Sung, A. Rejimon, J. W. Allen, A. G. Fedorov, and C. C. Fleischer, “Predicting Brain Temperature in Humans Using Bioheat Models: Progress and Outlook,” Journal of Cerebral Blood Flow & Metabolism 43, no. 6 (2023): 833–842.

[3] B. Yulug, H. A. Velioglu, D. Sayman, S. Cankaya, and L. Hanoglu, “Brain Temperature in Healthy and Diseased Conditions: A Review on the Special Implications of MRS for Monitoring Brain Temperature,” Biomedicine & Pharmacotherapy 160 (2023): 114287.

[4] S. Mrozek, F. Vardon, and T. Geeraerts, “Brain Temperature: Physiology and Pathophysiology After Brain Injury,” Anesthesiology Research and Practice 2012 (2012): 989487.

[5] J. Soukup, A. Zauner, E. M. Doppenberg, et al., “The Importance of Brain Temperature in Patients After Severe Head Injury: Relationship to Intracranial Pressure, Cerebral Perfusion Pressure, Cerebral Blood Flow, and Outcome,” Journal of Neurotrauma 19, no. 5 (2002): 559–571.

[6] C. Childs, “Human Brain Temperature: Regulation, Measurement and Relationship With Cerebral Trauma: Part 1,” British Journal of Nneurosurgery 22, no. 4 (2008): 486–496.

[7] K. N. Fountas, E. Z. Kapsalaki, C. H. Feltes, et al., “Disassociation Between Intracranial and Systemic Temperatures as an Early Sign of Brain Death,” Journal of Neurosurgical Anesthesiology 15, no. 2 (2003): 87–89.

[8] C. Stroud, J. P. Onnela, and H. Manji, “Harnessing Digital Technology to Predict, Diagnose, Monitor, and Develop Treatments for Brain Disorders,” NPJ Digital Medicine 2 (2019): 44.

[9] T. Ishida, T. Inoue, T. Inoue, et al., “Brain Temperature Measured by Magnetic Resonance Spectroscopy to Predict Clinical Outcome in Patients With Infarction,” Sensors (Basel, Switzerland) 21, no. 2 (2021): 490.

[10] Y. W. Wu, B. A. Comstock, F. F. Gonzalez, et al., “Trial of Erythropoietin for Hypoxic-Ischemic Encephalopathy in Newborns,” New England Journal of Medicine 387, no. 2 (2022): 148–159.

[11] D. Schrag and E. Basch, “Hypothermia After Traumatic Brain Injury,” Jama 320, no. 21 (2018): 2204–2206.

[12] C. Wu, W. Zhao, H. An, et al., “Safety, Feasibility, and Potential Efficacy of Intraarterial Selective Cooling Infusion for Stroke Patients Treated With Mechanical Thrombectomy,” Journal of Cerebral Blood flow and Metabolism 38, no. 12 (2018): 2251–2260.

[13] R. Kollmar, E. Juettler, H. B. Huttner, et al., “Cooling in Intracerebral Hemorrhage (CINCH) Trial: Protocol of a Randomized German-Austrian Clinical Trial,” International Journal of Stroke 7, no. 2 (2012): 168–172.

[14] S. Singh, L. Bianchi, S. Korganbayev, P. Namakshenas, R. Melnik, and P. Saccomandi, “Non-Fourier Bioheat Transfer Analysis in Brain Tissue during Interstitial Laser Ablation: Analysis of Multiple Influential Factors,” Annals of Biomedical Engineering (2024): 967–981.

[15] P. M. Kochanek and T. C. Jackson, “The Brain and Hypothermia-From Aristotle to Targeted Temperature Management,” Critical Care Medicine 45, no. 2 (2017): 305–310.

[16] M. Horn, W. K. Diprose, S. Pichardo, A. Demchuk, and M. Almekhlafi, “Non-invasive Brain Temperature Measurement in Acute Ischemic Stroke,” Frontiers in Neurology 13 (2022): 889214.

[17] D. Sung, P. A. Kottke, B. B. Risk, et al., “Personalized Predictions and Non-invasive Imaging of human Brain Temperature,” Communications Physics 4, no. 1 (2021): 68.

[18] P. HH, “Analysis of Tissue and Arterial Blood Temperatures in the Resting human Forearm,” Journal of Applied Physiology 1, no. 2 (1948): 93–122.

[19] H. B. S. Atigh, S. A. Abdollahi, H. S. Sarkesh, F. Talati, and S. Faramarzi, “Numerical Study of Thermal Protection for Healthy Tissue Using Phase Change Materials in Microwave Ablation With Coaxial Slot Antennas,” Results in Engineering 25 (2025): 104473.

[20] D. Kim and H. Kim, “Analysis of Optimal Treatment Starting Time for Photothermal Therapy through Analysis of Diffusion Behavior of Gold Nanoparticles,” International Journal of Nanomedicine 19 (2024): 3167–3186.

[21] F. Rezaei, W. Dai, S. Davani, and A. Bora, “A Physics-informed Neural Network Method for Thermal Analysis in Laser-irradiated 3D Skin Tissues With Embedded Vasculature, Tumor and Gold Nanorods,” International Journal of Heat and Mass Transfer 245 (2025): 126980.

[22] A. Dagro and J. Wilkerson, “A Computational Investigation of Strain Concentration in the Brain in Response to a Rapid Temperature Rise,” Journal of the Mechanical Behavior of Biomedical Materials 115 (2021): 104228.

[23] A.-A. Konstas, M. A. Neimark, A. F. Laine, and J. Pile-Spellman, “A Theoretical Model of Selective Cooling Using Intracarotid Cold Saline Infusion in the human Brain,” Journal of Applied Physiology 102, no. 4 (2007): 1329–1340.

[24] Y. Lutz, A. Loewe, S. Meckel, O. Dössel, and G. Cattaneo, “Combined Local Hypothermia and Recanalization Therapy for Acute Ischemic Stroke: Estimation of Brain and Systemic Temperature Using an Energetic Numerical Model,” Journal of Thermal Biology 84 (2019): 316–322.

[25] Y. Lutz, T. Meiner, L. Krames, et al., “Selective Brain Hypothermia for Ischemic MCA-M1 Stroke: Influence of Cerebral Arterial Circulation in a 3D Brain Temperature Model,” IEEE Transactions on Biomedical Engineering 68, no. 2 (2021): 404–415.

[26] A. Bousselham, O. Bouattane, M. Youssfi, and A. Raihani, “3D brain Tumor Localization and Parameter Estimation Using Thermographic Approach on GPU,” Journal of Thermal Biology 71 (2018): 52–61.

[27] A. Habib, C. Karmakar, and J. Yearwood, “Interpretability and Optimisation of Convolutional Neural Networks Based on Sinc-Convolution,” IEEE Journal of Biomedical and Health Informatics 27, no. 4 (2023): 1758–1769.

[28] H. C. Kuo, Y. P. Hsieh, H. H. Tseng, C. T. Wang, S. H. Fang, and Y. Tsao, “Toward Real-World Voice Disorder Classification,” IEEE Transactions on Bio-Medical Engineering 70, no. 10 (2023): 2922–2932.

[29] H. P. Chan, R. K. Samala, L. M. Hadjiiski, and C. Zhou, “Deep Learning in Medical Image Analysis,” Advances in Experimental Medicine and Biology 1213 (2020): 3–21.

[30] J. Cosentino, B. Behsaz, B. Alipanahi, et al., “Inference of Chronic Obstructive Pulmonary Disease With Deep Learning on Raw Spirograms Identifies New Genetic Loci and Improves Risk Models,” Nature Genetics 55, no. 5 (2023): 787–795.

[31] F. Zhuang, Z. Qi, K. Duan, et al., “A Comprehensive Survey on Transfer Learning,” Proceedings of the IEEE 109, no. 1 (2021): 43–76.

[32] P. Dhal, B. Pradhan, U. Fiore, S. A. J. Francis, and D. S. Roy, “A Clinical Diabetes Prediction Based Support System Based on the Multi-objective Metaheuristic Inspired Fine Tuning Deep Network,” Information Fusion 122 (2025): 103188.

[33] M. Kolossváry, V. K. Raghu, J. T. Nagurney, U. Hoffmann, and M. T. Lu, “Deep Learning Analysis of Chest Radiographs to Triage Patients With Acute Chest Pain Syndrome,” Radiology 306, no. 2 (2023): e221926.

[34] T. Kousar, M. S. M. Rahim, S. Iqbal, F. Yousaf, and M. Sanaullah, “Applications of Deep Learning Algorithms in Ischemic Stroke Detection, Segmentation, and Classification,” Artificial Intelligence Review 58, no. 5 (2025): 149.

[35] S. J. Fahrenholtz, R. Madankan, S. Danish, J. D. Hazle, R. J. Stafford, and D. Fuentes, “Theoretical Model for Laser Ablation Outcome Predictions in Brain: Calibration and Validation on Clinical MR Thermometry Images,” International Journal of Hyperthermia 34, no. 1 (2018): 101–111.

[36] Y. Zadka, O. Doron, G. Rosenthal, and O. Barnea, “Mechanisms of Reduced Cerebral Blood Flow in Cerebral Edema and Elevated Intracranial Pressure,” Journal of Applied Physiology (Bethesda, Md: 1985) 134, no. 2 (2023): 444–454.

[37] M. Jiang, F. Cao, Q. Zhang, et al., “Model-predicted Brain Temperature Computational Imaging by Multimodal Noninvasive Functional Neuromonitoring of Cerebral Oxygen Metabolism and Hemodynamics: MRI-derived and Clinical Validation,” Journal of Cerebral Blood Flow and Metabolism 45, no. 2 (2025): 275–291.

[38] S. Shahdadian, X. Wang, S. Kang, C. Carter, and H. Liu, “Site-specific Effects of 800- and 850-nm Forehead Transcranial Photobiomodulation on Prefrontal Bilateral Connectivity and Unilateral Coupling in Young Adults,” Neurophotonics 10, no. 2 (2023): 025012.

[39] Y. Zhao, P. M. Vanhoutte, and S. W. Leung, “Vascular Nitric Oxide: Beyond eNOS,” Journal of Pharmacological Sciences 129, no. 2 (2015): 83–94.

[40] J. Si, M. Li, X. Zhang, R. Han, X. Ji, and T. Jiang, “Cerebral Tissue Oximeter Suitable for Real-time Regional Oxygen Saturation Monitoring in Multiple Clinical Settings,” Cognitive Neurodynamics 17, no. 3 (2022): 563–574.

[41] A. L. Sukstanskii and D. A. Yablonskiy, “Theoretical Model of Temperature Regulation in the Brain During Changes in Functional Activity,” Proceedings of the National Academy of Sciences of the United States of America 103, no. 32 (2006): 12144–12149.

[42] H. Demirel, H. H. Göktaş, B. Erkal, and B. Ciylan, “Prediction of the Brain Temperature From Other Body Temperatures in Hypothermia Induced Rats by Using Artificial Neural Networks,” Computers in Biology and Medicine 42, no. 7 (2012): 772–777.

[43] L. Cai, E. Zhao, H. Niu, et al., “A Machine Learning Approach to Predict Cerebral Perfusion Status Based on Internal Carotid Artery Blood Flow,” Computers in Biology and Medicine 164 (2023): 107264.

[44] M. Jiang, M. Li, Y. Gao, et al., “The Intra-arterial Selective Cooling Infusion System: A Mathematical Temperature Analysis and in Vitro Experiments for Acute Ischemic Stroke Therapy,” Cns Neuroscience & Therapeutics 28, no. 9 (2022): 1303–1314.

[45] T. S. Baker, A. L. Zannou, D. Cruz, et al., “Development and Clinical Validation of a Finite Element Method Model Mapping Focal Intracranial Cooling,” IEEE Transactions on Neural Systems and Rehabilitation Engineering 30 (2022): 2168–2174.

[46] D. Sung, A. Rejimon, J. W. Allen, A. G. Fedorov, and C. C. Fleischer, “Predicting Brain Temperature in Humans Using Bioheat Models: Progress and Outlook,” Journal of Cerebral Blood Flow and Metabolism 43, no. 6 (2023): 833–842.

[47] G. Zhao, F. Panhwar, and Z. Chen, “Modeling Combined Cryosurgery and Hyperthermia with Thermally Significant Blood Vessels,” Theory and Applications of Heat Transfer in Humans 2 (2018): 669–685.

[48] A. M. VanHook, “Hypothermia-induced Neuroprotection,” Science Signaling 10, no. 470 (2017): eaan1410.

[49] S. Kuttner, K. K. Wickstrøm, M. Lubberink, et al., “Cerebral Blood Flow Measurements With (15)O-water PET Using a Non-invasive Machine-learning-derived Arterial Input Function,” Journal of Cerebral Blood Flow and Metabolism 41, no. 9 (2021): 2229–2241.

[50] R. N. D'Souza, P. Y. Huang, and F. C. Yeh, “Structural Analysis and Optimization of Convolutional Neural Networks With a Small Sample Size,” Scientific Reports 10, no. 1 (2020): 834.

[51] G. Varoquaux, “Cross-validation Failure: Small Sample Sizes Lead to Large Error Bars,” Neuroimage 180, no. Pt A (2018): 68–77.

[52] J. A. Barbero-Aparicio, A. Olivares-Gil, J. J. Rodríguez, C. García-Osorio, and J. F. Díez-Pastor, “Addressing Data Scarcity in Protein Fitness Landscape Analysis: A Study on Semi-supervised and Deep Transfer Learning Techniques,” Information Fusion 102 (2024): 102035.

[53] D. Li and H. J. Zhang, “Improved Regularization and Robustness for Fine-tuning in Neural Networks,” Advances in Neural Information Processing Systems 34 (2021): 27249–27262.

[54] Y. Lu, M. Shen, H. Wang, et al., “Machine Learning for Synthetic Data Generation: A Review,” arXiv 34 (2023): 27249–27262.

[55] T. S. Ko, C. D. Mavroudis, W. B. Baker, et al., “Non-invasive Optical Neuromonitoring of the Temperature-dependence of Cerebral Oxygen Metabolism During Deep Hypothermic Cardiopulmonary Bypass in Neonatal Swine,” Journal of Cerebral Blood Flow & Metabolism 40, no. 1 (2018): 187–203.

[56] S. S. Kety and C. F. Schmidt, “The Nitrous Oxide Method for THE Quantitative Determination of Cerebral Blood Flow in Man: Theory, Procedure and Normal Values,” The Journal of Clinical Investigation 27, no. 4 (1948): 476–483.

[57] J. Larimer, “Hemoglobin Concentration and Oxygen Capacity of Mammalian Blood,” Journal of the Elisha Mitchell Scientific Society 75, no. 2 (1959): 174–177.

Rights & permissions

2026 The Author(s). MedComm published by Sichuan International Medical Exchange & Promotion Association (SCIMEA) and John Wiley & Sons Australia, Ltd.