1
|
Xue S, Gafita A, Dong C, Zhao Y, Tetteh G, Menze BH, Ziegler S, Weber W, Afshar-Oromieh A, Rominger A, Eiber M, Shi K. Application of machine learning to pretherapeutically estimate dosimetry in men with advanced prostate cancer treated with 177Lu-PSMA I&T therapy. Eur J Nucl Med Mol Imaging 2022; 49:4064-4072. [PMID: 35771265 PMCID: PMC9525373 DOI: 10.1007/s00259-022-05883-w] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/25/2022] [Accepted: 06/16/2022] [Indexed: 12/01/2022]
Abstract
Purpose Although treatment planning and individualized dose application for emerging prostate-specific membrane antigen (PSMA)-targeted radioligand therapy (RLT) are generally recommended, it is still difficult to implement in practice at the moment. In this study, we aimed to prove the concept of pretherapeutic prediction of dosimetry based on imaging and laboratory measurements before the RLT treatment. Methods Twenty-three patients with metastatic castration-resistant prostate cancer (mCRPC) treated with 177Lu-PSMA I&T RLT were included retrospectively. They had available pre-therapy 68 Ga-PSMA-HEBD-CC PET/CT and at least 3 planar and 1 SPECT/CT imaging for dosimetry. Overall, 43 cycles of 177Lu-PSMA I&T RLT were applied. Organ-based standard uptake values (SUVs) were obtained from pre-therapy PET/CT scans. Patient dosimetry was calculated for the kidney, liver, spleen, and salivary glands using Hermes Hybrid Dosimetry 4.0 from the planar and SPECT/CT images. Machine learning methods were explored for dose prediction from organ SUVs and laboratory measurements. The uncertainty of these dose predictions was compared with the population-based dosimetry estimates. Mean absolute percentage error (MAPE) was used to assess the prediction uncertainty of estimated dosimetry. Results An optimal machine learning method achieved a dosimetry prediction MAPE of 15.8 ± 13.2% for the kidney, 29.6% ± 13.7% for the liver, 23.8% ± 13.1% for the salivary glands, and 32.1 ± 31.4% for the spleen. In contrast, the prediction based on literature population mean has significantly larger MAPE (p < 0.01), 25.5 ± 17.3% for the kidney, 139.1% ± 111.5% for the liver, 67.0 ± 58.3% for the salivary glands, and 54.1 ± 215.3% for the spleen. Conclusion The preliminary results confirmed the feasibility of pretherapeutic estimation of treatment dosimetry and its added value to empirical population-based estimation. The exploration of dose prediction may support the implementation of treatment planning for RLT. Supplementary Information The online version contains supplementary material available at 10.1007/s00259-022-05883-w.
Collapse
Affiliation(s)
- Song Xue
- Dept. Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Andrei Gafita
- Dept. Nuclear Medicine, Technical University of Munich, Munich, Germany.,Dept. Molecular & Medical Pharmacology, University of California, Los Angeles, CA, USA
| | - Chao Dong
- Dept. Electrical Engineering, Technical University of Munich, Munich, Germany
| | - Yu Zhao
- Dept. Informatics, Technical University of Munich, Munich, Germany
| | - Giles Tetteh
- Dept. Informatics, Technical University of Munich, Munich, Germany
| | - Bjoern H Menze
- Dept. Informatics, Technical University of Munich, Munich, Germany
| | - Sibylle Ziegler
- Dept. Nuclear Medicine, University Hospital, LMU Munich, Munich, Germany
| | - Wolfgang Weber
- Dept. Nuclear Medicine, Technical University of Munich, Munich, Germany
| | - Ali Afshar-Oromieh
- Dept. Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Axel Rominger
- Dept. Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland
| | - Matthias Eiber
- Dept. Nuclear Medicine, Technical University of Munich, Munich, Germany
| | - Kuangyu Shi
- Dept. Nuclear Medicine, Inselspital, Bern University Hospital, University of Bern, Bern, Switzerland. .,Dept. Informatics, Technical University of Munich, Munich, Germany.
| |
Collapse
|
2
|
Seo Y, Huh Y, Huang SY, Hernandez-Pampaloni JM, Hawkins RA, Gustafson WC, Vo KT, Matthay KK. Technical Note: Simplified and practical pretherapy tumor dosimetry - A feasibility study for 131 I-MIBG therapy of neuroblastoma using 124 I-MIBG PET/CT. Med Phys 2019; 46:2477-2486. [PMID: 30761545 DOI: 10.1002/mp.13446] [Citation(s) in RCA: 10] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/02/2018] [Revised: 02/07/2019] [Accepted: 02/07/2019] [Indexed: 12/13/2022] Open
Abstract
PURPOSE Radiation dose calculated on tumors for radiopharmaceutical therapy varies significantly from tumor to tumor and from patient to patient. Accurate estimation of radiation dose requires multiple time point measurements using radionuclide imaging modalities such as SPECT or PET. In this report, we show our technical development of reducing the number of scans needed for reasonable estimation of tumor and normal organ dose in our pretherapy imaging and dosimetry platform of 124 I-metaiodobenzylguanidine (MIBG) positron emission tomography/computed tomography (PET/CT) for 131 I-MIBG therapy of neuroblastoma. METHODS We analyzed the simplest kinetic data, areas of two-time point data for five patients with neuroblastoma who underwent 3 or 4 times of 124 I-MIBG PET/CT scan prior to 131 I-MIBG therapy. The data for which we derived areas were percent of injected activity (%IA) and standardized uptake value of tumors. These areas were correlated with time-integrated activity coefficients (TIACs) from full data (3 or 4 time points). TIACs are direct correlates with radiation dose as long as the volume and the radionuclide are known. RESULTS The areas of %IAs between data obtained from all the two-time points with time points 1 and 2 (day 0 and day 1), time points 2 and 3 (day 1 and day 2), and time points 1 and 3 (day 0 and day 2) showed reasonable correlation (Pearson's correlation coefficient |r| > 0.5) with not only tumor and organ TIACs but also tumor and organ absorbed doses. The tumor and organ doses calculated using %IA areas of time point 1 and time point 2 were our best fits at about 20% individual percent difference compared to doses calculated using 3 or 4 time points. CONCLUSIONS We could achieve reasonable accuracy of estimating tumor doses for subsequent radiopharmaceutical therapy using only the two-time point imaging sessions. Images obtained from these time points (within the 48-h after administration of radiopharmaceutical) were also viewed as useful for diagnostic reading. Although our analysis was specific to 124 I-MIBG PET/CT pretherapy imaging data for 131 I-MIBG therapy of neuroblastoma and the number of imaging datasets was not large, this feasible methodology would generally be applicable to other imaging and therapeutic radionuclides with an appropriate data analysis similar to our analysis to other imaging and therapeutic radiopharmaceuticals.
Collapse
Affiliation(s)
- Youngho Seo
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA.,Department of Radiation Oncology, University of California, San Francisco, San Francisco, CA, USA.,Joint Graduate Group in Bioengineering, University of California, San Francisco, Berkeley, CA, USA.,Bakar Computational Health Sciences Institute, University of California, San Francisco, San Francisco, CA, USA
| | - Yoonsuk Huh
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA
| | - Shih-Ying Huang
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA
| | | | - Randall A Hawkins
- Department of Radiology and Biomedical Imaging, University of California, San Francisco, San Francisco, CA, USA
| | - W Clay Gustafson
- Department of Pediatrics, University of California, San Francisco, San Francisco, CA, USA
| | - Kieuhoa T Vo
- Department of Pediatrics, University of California, San Francisco, San Francisco, CA, USA
| | - Katherine K Matthay
- Department of Pediatrics, University of California, San Francisco, San Francisco, CA, USA
| |
Collapse
|
3
|
Madsen MT, Menda Y, O'Dorisio TM, O'Dorisio MS. Technical Note: Single time point dose estimate for exponential clearance. Med Phys 2018; 45:2318-2324. [PMID: 29577338 DOI: 10.1002/mp.12886] [Citation(s) in RCA: 48] [Impact Index Per Article: 8.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/15/2017] [Revised: 01/16/2018] [Accepted: 01/23/2018] [Indexed: 01/02/2023] Open
Abstract
OBJECTIVE Although personalized dosimetry may be desirable for radionuclide therapy treatments, the multiple time samples required to determine the total integrated activity puts a burden on patients and clinic resources. The aim of this paper is to demonstrate that when some prior knowledge is known about the tracer kinetic parameters, the total integrated activity (and thus radiation dose) can be estimated from a single time sample. METHODS Mathematical derivations have been performed to generate equations for the total integrated activity in terms of a single time sample of activity for monoexponential and biexponential clearance. Simulations were performed using both exponential models where the rate constants and associated parameters were randomly sampled from distributions with a known mean. The actual total integrated activity for each random sample was compared with the estimated total integrated activity using the mean value of the parameters. Retrospective analysis of 90 Y DOTATOC data from a clinical trial provided a comparison of actual kidney dose with the estimated kidney dose using the single time point approach. RESULTS The optimal sampling time for the single point approach was found to be equal to the mean time of the rate constant. The simulation results for the monoexponential and biexpoential models were similar. Regressions comparing the actual and estimated total integrated activity had very high correlations (r2 > 0.95) along with acceptable standard errors of estimate, especially at the optimal sampling point. The retrospective analysis of the 90 Y DOTATOC data also yielded similar results with an r2 = 0.95 and a standard error of estimate of 61 cGy. CONCLUSIONS In situations where there is prior knowledge about the population averages of kinetic parameters, these results suggest that the single time point approach can be used to estimate the total integrated activity and dose with sufficient accuracy to manage radionuclide therapy. This will make personalized dosimetry much easier to perform and more available to the community.
Collapse
Affiliation(s)
- Mark T Madsen
- Department of Radiology, University of Iowa, Iowa City, IA, 52242, USA
| | - Yusuf Menda
- Department of Radiology, University of Iowa, Iowa City, IA, 52242, USA
| | - Thomas M O'Dorisio
- Department of Endocrinology, University of Iowa, Iowa City, IA, 52242, USA
| | - M Sue O'Dorisio
- Department of Pediatrics, University of Iowa, Iowa City, IA, 52242, USA
| |
Collapse
|