TY - JOUR
T1 - Theoretical model for laser ablation outcome predictions in brain
T2 - Calibration and validation on clinical MR thermometry images
AU - Fahrenholtz, Samuel John
AU - Madankan, Reza
AU - Danish, Shabbar
AU - Hazle, John D.
AU - Stafford, R. Jason
AU - Fuentes, David
N1 - Publisher Copyright:
© 2017 Informa UK Limited, trading as Taylor & Francis Group.
PY - 2018/5/18
Y1 - 2018/5/18
N2 - Purpose: Neurosurgical laser ablation is experiencing a renaissance. Computational tools for ablation planning aim to further improve the intervention. Here, global optimisation and inverse problems are demonstrated to train a model that predicts maximum laser ablation extent. Methods: A closed-form steady state model is trained on and then subsequently compared to N=20 retrospective clinical MR thermometry datasets. Dice similarity coefficient (DSC) is calculated to provide a measure of region overlap between the 57°C isotherms of the thermometry data and the model-predicted ablation regions; 57°C is a tissue death surrogate at thermal steady state. A global optimisation scheme samples the dominant model parameter sensitivities, blood perfusion (ω) and optical parameter (µeff) values, throughout a parameter space totalling 11 440 value-pairs. This represents a lookup table of µeff–ω pairs with the corresponding DSC value for each patient dataset. The µeff–ω pair with the maximum DSC calibrates the model parameters, maximising predictive value for each patient. Finally, leave-one-out cross-validation with global optimisation information trains the model on the entire clinical dataset, and compares against the model naïvely using literature values for ω and µeff. Results: When using naïve literature values, the model’s mean DSC is 0.67 whereas the calibrated model produces 0.82 during cross-validation, an improvement of 0.15 in overlap with the patient data. The 95% confidence interval of the mean difference is 0.083–0.23 (p<0.001). Conclusions: During cross-validation, the calibrated model is superior to the naïve model as measured by DSC, with +22% mean prediction accuracy. Calibration empowers a relatively simple model to become more predictive. Abbreviations: CEM: cumulative effective minutes; DSC: Dice similarity coefficient; MR: magnetic resonance.
AB - Purpose: Neurosurgical laser ablation is experiencing a renaissance. Computational tools for ablation planning aim to further improve the intervention. Here, global optimisation and inverse problems are demonstrated to train a model that predicts maximum laser ablation extent. Methods: A closed-form steady state model is trained on and then subsequently compared to N=20 retrospective clinical MR thermometry datasets. Dice similarity coefficient (DSC) is calculated to provide a measure of region overlap between the 57°C isotherms of the thermometry data and the model-predicted ablation regions; 57°C is a tissue death surrogate at thermal steady state. A global optimisation scheme samples the dominant model parameter sensitivities, blood perfusion (ω) and optical parameter (µeff) values, throughout a parameter space totalling 11 440 value-pairs. This represents a lookup table of µeff–ω pairs with the corresponding DSC value for each patient dataset. The µeff–ω pair with the maximum DSC calibrates the model parameters, maximising predictive value for each patient. Finally, leave-one-out cross-validation with global optimisation information trains the model on the entire clinical dataset, and compares against the model naïvely using literature values for ω and µeff. Results: When using naïve literature values, the model’s mean DSC is 0.67 whereas the calibrated model produces 0.82 during cross-validation, an improvement of 0.15 in overlap with the patient data. The 95% confidence interval of the mean difference is 0.083–0.23 (p<0.001). Conclusions: During cross-validation, the calibrated model is superior to the naïve model as measured by DSC, with +22% mean prediction accuracy. Calibration empowers a relatively simple model to become more predictive. Abbreviations: CEM: cumulative effective minutes; DSC: Dice similarity coefficient; MR: magnetic resonance.
KW - Laser tissue ablation
KW - Neoplasm metastasis
KW - Neurosurgery
UR - http://www.scopus.com/inward/record.url?scp=85019615706&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85019615706&partnerID=8YFLogxK
U2 - 10.1080/02656736.2017.1319974
DO - 10.1080/02656736.2017.1319974
M3 - Article
C2 - 28540820
AN - SCOPUS:85019615706
SN - 0265-6736
VL - 34
SP - 101
EP - 111
JO - International Journal of Hyperthermia
JF - International Journal of Hyperthermia
IS - 1
ER -