Spatiotemporal estimations of temperature rise during electroporation treatments using a deep neural network. Jacobs, E. J. t., Campelo, S. N., Aycock, K. N., Yao, D., & Davalos, R. V. Comput Biol Med, 161:107019, 2023. 1879-0534 Jacobs, Edward J 4th Campelo, Sabrina N Aycock, Kenneth N Yao, Danfeng Davalos, Rafael V Journal Article Research Support, N.I.H., Extramural United States 2023/05/24 Comput Biol Med. 2023 Jul;161:107019. doi: 10.1016/j.compbiomed.2023.107019. Epub 2023 May 16.doi abstract bibtex The nonthermal mechanism for irreversible electroporation has been paramount for treating tumors and cardiac tissue in anatomically sensitive areas, where there is concern about damage to nearby bowels, ducts, blood vessels, or nerves. However, Joule heating still occurs as a secondary effect of applying current through a resistive tissue and must be minimized to maintain the benefits of electroporation at high voltages. Numerous thermal mitigation protocols have been proposed to minimize temperature rise, but intraoperative temperature monitoring is still needed. We show that an accurate and robust temperature prediction AI model can be developed using estimated tissue properties (bulk and dynamic conductivity), known geometric properties (probe spacing), and easily measurable treatment parameters (applied voltage, current, and pulse number). We develop the 2-layer neural network on realistic 2D finite element model simulations with conditions encompassing most electroporation applications. Calculating feature contributions, we found that temperature prediction is mostly dependent on current and pulse number and show that the model remains accurate when incorrect tissue properties are intentionally used as input parameters. Lastly, we show that the model can predict temperature rise within ex vivo perfused porcine livers, with error <0.5 °C. This model, using easily acquired parameters, is shown to predict temperature rise in over 1000 unique test conditions with <1 °C error and no observable outliers. We believe the use of simple, readily available input parameters would allow this model to be incorporated in many already available electroporation systems for real-time temperature estimations.
@article{RN93,
author = {Jacobs, E. J. th and Campelo, S. N. and Aycock, K. N. and Yao, D. and Davalos, R. V.},
title = {Spatiotemporal estimations of temperature rise during electroporation treatments using a deep neural network},
journal = {Comput Biol Med},
volume = {161},
pages = {107019},
note = {1879-0534
Jacobs, Edward J 4th
Campelo, Sabrina N
Aycock, Kenneth N
Yao, Danfeng
Davalos, Rafael V
Journal Article
Research Support, N.I.H., Extramural
United States
2023/05/24
Comput Biol Med. 2023 Jul;161:107019. doi: 10.1016/j.compbiomed.2023.107019. Epub 2023 May 16.},
abstract = {The nonthermal mechanism for irreversible electroporation has been paramount for treating tumors and cardiac tissue in anatomically sensitive areas, where there is concern about damage to nearby bowels, ducts, blood vessels, or nerves. However, Joule heating still occurs as a secondary effect of applying current through a resistive tissue and must be minimized to maintain the benefits of electroporation at high voltages. Numerous thermal mitigation protocols have been proposed to minimize temperature rise, but intraoperative temperature monitoring is still needed. We show that an accurate and robust temperature prediction AI model can be developed using estimated tissue properties (bulk and dynamic conductivity), known geometric properties (probe spacing), and easily measurable treatment parameters (applied voltage, current, and pulse number). We develop the 2-layer neural network on realistic 2D finite element model simulations with conditions encompassing most electroporation applications. Calculating feature contributions, we found that temperature prediction is mostly dependent on current and pulse number and show that the model remains accurate when incorrect tissue properties are intentionally used as input parameters. Lastly, we show that the model can predict temperature rise within ex vivo perfused porcine livers, with error <0.5 °C. This model, using easily acquired parameters, is shown to predict temperature rise in over 1000 unique test conditions with <1 °C error and no observable outliers. We believe the use of simple, readily available input parameters would allow this model to be incorporated in many already available electroporation systems for real-time temperature estimations.},
keywords = {Swine
Animals
Temperature
*Electroporation/methods
*Electroporation Therapies
Electric Conductivity
Neural Networks, Computer
Artificial intelligence
Electroporation
Pulsed electric field
Thermal heating
Tissue ablations},
ISSN = {0010-4825},
DOI = {10.1016/j.compbiomed.2023.107019},
year = {2023},
type = {Journal Article}
}
Downloads: 0
{"_id":"ZvQAXTvvtKa7cZp39","bibbaseid":"jacobs-campelo-aycock-yao-davalos-spatiotemporalestimationsoftemperatureriseduringelectroporationtreatmentsusingadeepneuralnetwork-2023","author_short":["Jacobs, E. J. t.","Campelo, S. N.","Aycock, K. N.","Yao, D.","Davalos, R. V."],"bibdata":{"bibtype":"article","type":"Journal Article","author":[{"propositions":[],"lastnames":["Jacobs"],"firstnames":["E.","J.","th"],"suffixes":[]},{"propositions":[],"lastnames":["Campelo"],"firstnames":["S.","N."],"suffixes":[]},{"propositions":[],"lastnames":["Aycock"],"firstnames":["K.","N."],"suffixes":[]},{"propositions":[],"lastnames":["Yao"],"firstnames":["D."],"suffixes":[]},{"propositions":[],"lastnames":["Davalos"],"firstnames":["R.","V."],"suffixes":[]}],"title":"Spatiotemporal estimations of temperature rise during electroporation treatments using a deep neural network","journal":"Comput Biol Med","volume":"161","pages":"107019","note":"1879-0534 Jacobs, Edward J 4th Campelo, Sabrina N Aycock, Kenneth N Yao, Danfeng Davalos, Rafael V Journal Article Research Support, N.I.H., Extramural United States 2023/05/24 Comput Biol Med. 2023 Jul;161:107019. doi: 10.1016/j.compbiomed.2023.107019. Epub 2023 May 16.","abstract":"The nonthermal mechanism for irreversible electroporation has been paramount for treating tumors and cardiac tissue in anatomically sensitive areas, where there is concern about damage to nearby bowels, ducts, blood vessels, or nerves. However, Joule heating still occurs as a secondary effect of applying current through a resistive tissue and must be minimized to maintain the benefits of electroporation at high voltages. Numerous thermal mitigation protocols have been proposed to minimize temperature rise, but intraoperative temperature monitoring is still needed. We show that an accurate and robust temperature prediction AI model can be developed using estimated tissue properties (bulk and dynamic conductivity), known geometric properties (probe spacing), and easily measurable treatment parameters (applied voltage, current, and pulse number). We develop the 2-layer neural network on realistic 2D finite element model simulations with conditions encompassing most electroporation applications. Calculating feature contributions, we found that temperature prediction is mostly dependent on current and pulse number and show that the model remains accurate when incorrect tissue properties are intentionally used as input parameters. Lastly, we show that the model can predict temperature rise within ex vivo perfused porcine livers, with error <0.5 °C. This model, using easily acquired parameters, is shown to predict temperature rise in over 1000 unique test conditions with <1 °C error and no observable outliers. We believe the use of simple, readily available input parameters would allow this model to be incorporated in many already available electroporation systems for real-time temperature estimations.","keywords":"Swine Animals Temperature *Electroporation/methods *Electroporation Therapies Electric Conductivity Neural Networks, Computer Artificial intelligence Electroporation Pulsed electric field Thermal heating Tissue ablations","issn":"0010-4825","doi":"10.1016/j.compbiomed.2023.107019","year":"2023","bibtex":"@article{RN93,\n author = {Jacobs, E. J. th and Campelo, S. N. and Aycock, K. N. and Yao, D. and Davalos, R. V.},\n title = {Spatiotemporal estimations of temperature rise during electroporation treatments using a deep neural network},\n journal = {Comput Biol Med},\n volume = {161},\n pages = {107019},\n note = {1879-0534\nJacobs, Edward J 4th\nCampelo, Sabrina N\nAycock, Kenneth N\nYao, Danfeng\nDavalos, Rafael V\nJournal Article\nResearch Support, N.I.H., Extramural\nUnited States\n2023/05/24\nComput Biol Med. 2023 Jul;161:107019. doi: 10.1016/j.compbiomed.2023.107019. Epub 2023 May 16.},\n abstract = {The nonthermal mechanism for irreversible electroporation has been paramount for treating tumors and cardiac tissue in anatomically sensitive areas, where there is concern about damage to nearby bowels, ducts, blood vessels, or nerves. However, Joule heating still occurs as a secondary effect of applying current through a resistive tissue and must be minimized to maintain the benefits of electroporation at high voltages. Numerous thermal mitigation protocols have been proposed to minimize temperature rise, but intraoperative temperature monitoring is still needed. We show that an accurate and robust temperature prediction AI model can be developed using estimated tissue properties (bulk and dynamic conductivity), known geometric properties (probe spacing), and easily measurable treatment parameters (applied voltage, current, and pulse number). We develop the 2-layer neural network on realistic 2D finite element model simulations with conditions encompassing most electroporation applications. Calculating feature contributions, we found that temperature prediction is mostly dependent on current and pulse number and show that the model remains accurate when incorrect tissue properties are intentionally used as input parameters. Lastly, we show that the model can predict temperature rise within ex vivo perfused porcine livers, with error <0.5 °C. This model, using easily acquired parameters, is shown to predict temperature rise in over 1000 unique test conditions with <1 °C error and no observable outliers. We believe the use of simple, readily available input parameters would allow this model to be incorporated in many already available electroporation systems for real-time temperature estimations.},\n keywords = {Swine\nAnimals\nTemperature\n*Electroporation/methods\n*Electroporation Therapies\nElectric Conductivity\nNeural Networks, Computer\nArtificial intelligence\nElectroporation\nPulsed electric field\nThermal heating\nTissue ablations},\n ISSN = {0010-4825},\n DOI = {10.1016/j.compbiomed.2023.107019},\n year = {2023},\n type = {Journal Article}\n}\n\n","author_short":["Jacobs, E. J. t.","Campelo, S. N.","Aycock, K. N.","Yao, D.","Davalos, R. V."],"key":"RN93","id":"RN93","bibbaseid":"jacobs-campelo-aycock-yao-davalos-spatiotemporalestimationsoftemperatureriseduringelectroporationtreatmentsusingadeepneuralnetwork-2023","role":"author","urls":{},"keyword":["Swine Animals Temperature *Electroporation/methods *Electroporation Therapies Electric Conductivity Neural Networks","Computer Artificial intelligence Electroporation Pulsed electric field Thermal heating Tissue ablations"],"metadata":{"authorlinks":{}}},"bibtype":"article","biburl":"https://bibbase.org/network/files/bdNBTZRXTsoHCgpbh","dataSources":["D4zENc4BfFNBwSYYJ","ZPLjameRikygaiM9B","3XfNmZkLe6o8CvECW","fJQsxtBoqymHQG6tL","LzxgEApraxMPkLTMn","Z2THpXfLYEJf3CB8p"],"keywords":["swine animals temperature *electroporation/methods *electroporation therapies electric conductivity neural networks","computer artificial intelligence electroporation pulsed electric field thermal heating tissue ablations"],"search_terms":["spatiotemporal","estimations","temperature","rise","during","electroporation","treatments","using","deep","neural","network","jacobs","campelo","aycock","yao","davalos"],"title":"Spatiotemporal estimations of temperature rise during electroporation treatments using a deep neural network","year":2023}