Our paper entitled “AI-based isotherm prediction for focal cryoablation of prostate cancer” has been published in Academic Radiology. This is part of our effort to develop software/hardware infrastructures for the focal treatment of prostate cancer under MRI guidance.
In this study, we investigated a new AI model to predict the growth of cryoablation iceball to assist a physician in planning the treatment. Specifically, we tested a convolutional neural network model based on 3D-Unet to predict the frozen isotherm boundaries (iceball) resultant from a given cryo-needle placement. Intraprocedural magnetic resonance images acquired during Thirty-eight cases of focal cryoablation of PCa were retrospectively used to train and validate the model.
Reference
- Moreira P, Tuncali K, Tempany C, Tokuda J. AI-Based Isotherm Prediction for Focal Cryoablation of Prostate Cancer. Acad Radiol. 2023;30 Suppl 1(Suppl 1):S14–S20. doi:10.1016/j.acra.2023.04.016 PMID: 37236896. PMCID: PMC10524864.
Grant Support
This study is supported in part by the National Institutes of health (R01CA235134, R01EB020667, P41EB028741).
