1
|
Moreira P, Tuncali K, Tempany C, Tokuda J. AI-Based Isotherm Prediction for Focal Cryoablation of Prostate Cancer. Acad Radiol 2023; 30 Suppl 1:S14-S20. [PMID: 37236896 PMCID: PMC10524864 DOI: 10.1016/j.acra.2023.04.016] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/03/2023] [Revised: 04/04/2023] [Accepted: 04/15/2023] [Indexed: 05/28/2023]
Abstract
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 0.4second and has proven its feasibility to be implemented in an intraprocedural planning algorithm.
Collapse
Affiliation(s)
- Pedro Moreira
- Brigham and Women's Hospital, 75 Francis St, Boston, MA 22115 (P.M., K.T., C.T., J.T.); Harvard Medical School, 25 Shattuck St, Boston, MA 02115 (P.M., K.T., C.T., J.T.).
| | - Kemal Tuncali
- Brigham and Women's Hospital, 75 Francis St, Boston, MA 22115 (P.M., K.T., C.T., J.T.); Harvard Medical School, 25 Shattuck St, Boston, MA 02115 (P.M., K.T., C.T., J.T.)
| | - Clare Tempany
- Brigham and Women's Hospital, 75 Francis St, Boston, MA 22115 (P.M., K.T., C.T., J.T.); Harvard Medical School, 25 Shattuck St, Boston, MA 02115 (P.M., K.T., C.T., J.T.)
| | - Junichi Tokuda
- Brigham and Women's Hospital, 75 Francis St, Boston, MA 22115 (P.M., K.T., C.T., J.T.); Harvard Medical School, 25 Shattuck St, Boston, MA 02115 (P.M., K.T., C.T., J.T.)
| |
Collapse
|
2
|
Rieder C, Schwenke M, Pätz T, Georgii J, Ballhausen H, Schwen LO, Haase S, Preusser T. Evaluation of a numerical simulation for cryoablation - comparison with bench data, clinical kidney and lung cases. Int J Hyperthermia 2021; 37:1268-1278. [PMID: 33198534 DOI: 10.1080/02656736.2020.1845402] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/14/2022] Open
Abstract
PURPOSE The accuracy of a numerical simulation of cryoablation ice balls was evaluated in gel phantom data as well as clinical kidney and lung cases. MATERIALS AND METHODS To evaluate the accuracy, 64 experimental single-needle cryoablations and 12 multi-needle cryoablations in gel phantoms were re-simulated with the corresponding freeze-thaw-freeze cycles. The simulated temperatures were compared over time with the measurements of thermocouples. For single needles, temperature values were compared at each thermocouple location. For multiple needles, Euclidean distances between simulated and measured isotherms (10 °C, 0 °C, -20 °C, -40 °C) were computed. Furthermore, surface and volume of simulated 0 °C isotherms were compared to cryoablation-induced ice balls in 14 kidney and 13 lung patients. For this purpose, needle positions and relevant anatomical structures defining material parameters (kidney/lung, tumor) were reconstructed from pre-ablation CT images and fused with postablation CT images (from which ice balls were extracted by manual delineation). RESULTS The single-needle gel phantom cases showed less than 5 °C prediction error on average. Over all multiple needle experiments in gel, the mean and maximum isotherm distance were less than 2.3 mm and 4.1 mm, respectively. Average Dice coefficients of 0.82/0.63 (kidney/lung) and mean surface distances of 2.59/3.12 mm quantify the prediction performance of the numerical simulation. However, maximum surface distances of 10.57/10.8 mm indicate that locally larger errors have to be expected. CONCLUSION A very good agreement of the numerical simulations for gel experiments was measured and a satisfactory agreement of the numerical simulations with measured ice balls in patient data was shown.
Collapse
Affiliation(s)
- Christian Rieder
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| | - Michael Schwenke
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| | - Torben Pätz
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| | - Joachim Georgii
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| | - Hanne Ballhausen
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| | - Lars Ole Schwen
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| | - Sabrina Haase
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| | - Tobias Preusser
- Fraunhofer Institute for Digital Medicine MEVIS, Bremen, Germany
| |
Collapse
|
3
|
Baust JM, Rabin Y, Polascik TJ, Santucci KL, Snyder KK, Van Buskirk RG, Baust JG. Defeating Cancers' Adaptive Defensive Strategies Using Thermal Therapies: Examining Cancer's Therapeutic Resistance, Ablative, and Computational Modeling Strategies as a means for Improving Therapeutic Outcome. Technol Cancer Res Treat 2018; 17:1533033818762207. [PMID: 29566612 PMCID: PMC5871056 DOI: 10.1177/1533033818762207] [Citation(s) in RCA: 11] [Impact Index Per Article: 1.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022] Open
Abstract
BACKGROUND Diverse thermal ablative therapies are currently in use for the treatment of cancer. Commonly applied with the intent to cure, these ablative therapies are providing promising success rates similar to and often exceeding "gold standard" approaches. Cancer-curing prospects may be enhanced by deeper understanding of thermal effects on cancer cells and the hosting tissue, including the molecular mechanisms of cancer cell mutations, which enable resistance to therapy. Furthermore, thermal ablative therapies may benefit from recent developments in computer hardware and computation tools for planning, monitoring, visualization, and education. METHODS Recent discoveries in cancer cell resistance to destruction by apoptosis, autophagy, and necrosis are now providing an understanding of the strategies used by cancer cells to avoid destruction by immunologic surveillance. Further, these discoveries are now providing insight into the success of the diverse types of ablative therapies utilized in the clinical arena today and into how they directly and indirectly overcome many of the cancers' defensive strategies. Additionally, the manner in which minimally invasive thermal therapy is enabled by imaging, which facilitates anatomical features reconstruction, insertion guidance of thermal probes, and strategic placement of thermal sensors, plays a critical role in the delivery of effective ablative treatment. RESULTS The thermal techniques discussed include radiofrequency, microwave, high-intensity focused ultrasound, laser, and cryosurgery. Also discussed is the development of thermal adjunctive therapies-the combination of drug and thermal treatments-which provide new and more effective combinatorial physical and molecular-based approaches for treating various cancers. Finally, advanced computational and planning tools are also discussed. CONCLUSION This review lays out the various molecular adaptive mechanisms-the hallmarks of cancer-responsible for therapeutic resistance, on one hand, and how various ablative therapies, including both heating- and freezing-based strategies, overcome many of cancer's defenses, on the other hand, thereby enhancing the potential for curative approaches for various cancers.
Collapse
Affiliation(s)
- John M Baust
- 1 CPSI Biotech, Owego, NY, USA.,2 Institute of Biomedical Technology, State University of New York at Binghamton, Binghamton, NY, USA
| | - Yoed Rabin
- 3 Department of Mechanical Engineering, Carnegie Mellon University, Pittsburgh, PA, USA
| | - Thomas J Polascik
- 4 Division of Urology, Department of Surgery, Duke University Medical Center, Durham, NC, USA
| | - Kimberly L Santucci
- 1 CPSI Biotech, Owego, NY, USA.,2 Institute of Biomedical Technology, State University of New York at Binghamton, Binghamton, NY, USA
| | - Kristi K Snyder
- 1 CPSI Biotech, Owego, NY, USA.,2 Institute of Biomedical Technology, State University of New York at Binghamton, Binghamton, NY, USA
| | - Robert G Van Buskirk
- 1 CPSI Biotech, Owego, NY, USA.,2 Institute of Biomedical Technology, State University of New York at Binghamton, Binghamton, NY, USA.,5 Department of Biological Sciences, Binghamton University, Binghamton, NY, USA
| | - John G Baust
- 2 Institute of Biomedical Technology, State University of New York at Binghamton, Binghamton, NY, USA.,5 Department of Biological Sciences, Binghamton University, Binghamton, NY, USA
| |
Collapse
|
4
|
Joshi P, Sehrawat A, Rabin Y. The role of exposure time in computerized training of prostate cryosurgery: performance comparison of surgical residents with engineering students. Int J Comput Assist Radiol Surg 2018; 13:541-549. [PMID: 29396685 DOI: 10.1007/s11548-017-1700-8] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/09/2017] [Accepted: 12/22/2017] [Indexed: 10/18/2022]
Abstract
PURPOSE This study aims at the evaluation of a prototype of a computerized trainer for cryosurgery-the controlled destruction of cancer tumors by freezing. The hypothesis in this study is that computer-based cryosurgery training for an optimal cryoprobe layout is essentially a matter of exposure time, rather than trainee background or the specific computer-generated planning target. Key geometric features under considerations are associated with spatial limitations on cryoprobes placement and the match between the resulted thermal field and the unique anatomy of the prostate. METHODS All experiments in this study were performed on the cryosurgery trainer-a prototype platform for computerized cryosurgery training, which has been presented previously. Among its key features, the cryosurgery trainer displays the prostate shape and its contours and provides a distance measurement tool on demand, in order to address spatial constraints during ultrasound imaging guidance. Another unique feature of the cryosurgery trainer is an output movie, displaying the simulated thermal field at the end of the cryoprocedure. RESULTS The current study was performed on graduate engineering students having no formal background in medicine, and the results were benchmarked against data obtained on surgical residents having no experience with cryosurgery. Despite fundamental differences in background and experience, neither group displayed superior performance when it comes to cryoprobe layout planning. CONCLUSIONS This study demonstrates that computer-based training of an optimal cryoprobe layout is feasible. This study demonstrates that the training quality is essentially related to the training exposure time, rather than to a specific planning strategy from those investigated.
Collapse
Affiliation(s)
- Purva Joshi
- Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA
| | - Anjali Sehrawat
- Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA
| | - Yoed Rabin
- Department of Mechanical Engineering, Carnegie Mellon University, 5000 Forbes Avenue, Pittsburgh, PA, 15213, USA.
| |
Collapse
|