Rationale and Objectives
Focal therapies have emerged as minimally invasive alternatives for patients with
localized low-risk prostate cancer (PCa) and those with postradiation recurrence.
Among the available focal treatment methods for PCa, cryoablation offers several technical
advantages, including the visibility of the boundaries of frozen tissue on the intraprocedural
images, access to anterior lesions, and the proven ability to treat postradiation
recurrence. However, predicting the final volume of the frozen tissue is challenging
as it depends on several patient-specific factors, such as proximity to heat sources
and thermal properties of the prostatic tissue.
Materials and Methods
This paper presents a convolutional neural network model based on 3D-Unet to predict
the frozen isotherm boundaries (iceball) resultant from a given a cryo-needle placement.
Intraprocedural magnetic resonance images acquired during 38 cases of focal cryoablation
of PCa were retrospectively used to train and validate the model. The model accuracy
was assessed and compared against a vendor-provided geometrical model, which is used
as a guideline in routine procedures.
Results
The mean Dice Similarity Coefficient using the proposed model was 0.79 ± 0.08 (mean + SD) vs 0.72 ± 0.06 using the geometrical model (P < .001).
Conclusion
The model provided an accurate iceball boundary prediction in less than 0.4 second and has proven its feasibility to be implemented in an intraprocedural planning
algorithm.
Key Words
To read this article in full you will need to make a payment
Purchase one-time access:
Academic & Personal: 24 hour online accessCorporate R&D Professionals: 24 hour online accessOne-time access price info
- For academic or personal research use, select 'Academic and Personal'
- For corporate R&D use, select 'Corporate R&D Professionals'
Subscribe:
Subscribe to Academic RadiologyAlready a print subscriber? Claim online access
Already an online subscriber? Sign in
Register: Create an account
Institutional Access: Sign in to ScienceDirect
References
- Cancer statistics, 2022.CA Cancer J Clin. 2022; 72: 7-33
- Minimally invasive magnetic resonance image-guided prostate interventions.Br J Radiol. 2022; 95: 1-10
- Intraoperative Digital Analysis of Ablation Margins (DAAM) by fluorescent confocal microscopy to improve partial prostate gland cryoablation outcomes.Cancers. 2021; 13: 4382-4390
- Focal therapy for localized prostate cancer with either high intensity focused ultrasound or cryoablation: a single institution experience.J Urol. 2020; 203: 320-330
- Salvage high-intensity focused ultrasound (HIFU) for locally recurrent prostate cancer after failed radiation therapy: multi-institutional analysis of 418 patients.BJU Int. 2017; 119: 896-904
- Focal salvage MR imaging-guided cryoablation for localized prostate cancer recurrence after radiotherapy: 12-month follow-up.J Vasc Interv Radiol. 2020; 31: 35-41
- Percutaneous MR-guided focal cryoablation for recurrent prostate cancer following radiation therapy: retrospective analysis of iceball margins and outcomes.Eur Radiol. 2017; 27: 4828-4836
- The impact of placement errors on the tumor coverage in MRI-guided focal cryoablation of prostate cancer.Acad Radiol. 2020; 28: 841-848
- Salvage focal prostate cryoablation for locally recurrent prostate cancer after radiotherapy: initial results from the cryo on-line data registry.Prostate. 2015; 75: 1-7
- Focal cryoablation: a treatment option for unilateral low-risk prostate cancer.BJU Int. 2014; 113: 56-64
- Focal therapy for prostate cancer: an “A la Carte” approach.Eur Urol. 2016; 69: 973-975
Nicholas, F., Tokuda, J., Moreira, P., et al. AI-assisted analysis of iceball coverage on patient outcomes following MR-guided focal cryoablation for prostate cancer: a retrospective study. Anual meeting ISMRM, London, UK, 2022.
- Finite-element analysis of hepatic cryoablation around a large blood vessel.IEEE Trans Biomed Eng. 2008; 55: 2087-2093
- A finite element model for ice ball evolution in a multiprobe cryosurgery.Comput Methods Biomech Biomed Eng. 2003; 6: 197-208
- Finite-element analysis of ex vivo and in vivo hepatic cryoablation.IEEE Trans Biomed Eng. 2007; 54: 1177-1185
Rabin Y, Shimada K, Joshi P, et al. A computerized tutor prototype for prostate cryotherapy: key building blocks and system evaluation. Energy-based Treatment of Tissue and Assessment IX 10066, 100660Z, 2017.
- Two-phase computerized planning of cryosurgery using bubble-packing and force-field analogy.J Biomech Eng. 2006; 128: 49-58
- Numerical modeling and optimization of the cryosurgery operations.J Comput Appl Math. 2015; 290: 259-267
- Key issues in bioheat transfer simulations for the application of cryosurgery planning.Cryobiology. 2008; 56: 248-250
- Towards intra-operative computerized planning of prostate cryosurgery.Int J Med Robot Comput Assist Surg. 2007; 3: 10-19
- GPU-based 3D iceball modeling for fast cryoablation simulation and planning.Int J Comput Assist Radiol Surg. 2019; 14: 1577-1588
- Development of a searchable database of cryoablation simulations for use in treatment planning.Cardiovasc Interv Radiol. 2017; 40: 761-768
- Automatic needle segmentation and localization in MRI with 3-D convolutional neural networks: application to MRI-targeted prostate biopsy.IEEE Trans Med Imaging. 2019; 38: 1026-1036
Çiçek, Ö., Abdulkadir, A., Lienkamp, S., et al. 3D U-Net: learning dense volumetric segmentation from sparse annotation. Medical Image Computing and Computer-Assisted Intervention - MICCAI 2016 (2016) 424–432.
- Deep learning whole-gland and zonal prostate segmentation on a public MRI dataset.J Magn Reson Imaging. 2021; 54: 452-459
Boston-Scientific Cryoablation: Treatment Planning, 2020.
- Validation of a web-based planning tool for percutaneous cryoablation of renal tumors.Cardiovasc Interv Radiol. 2020; 43: 1661-1670
Article info
Publication history
Published online: May 24, 2023
Accepted:
April 15,
2023
Received in revised form:
April 4,
2023
Received:
February 3,
2023
Publication stage
In Press Corrected ProofIdentification
Copyright
© 2023 The Association of University Radiologists. Published by Elsevier Inc. All rights reserved All rights reserved.
