1
|
Chen M, Pang B, Zeng Y, Xu C, Chen J, Yang K, Chang Y, Yang Z. Evaluation of an automated clinical decision system with deep learning dose prediction and NTCP model for prostate cancer proton therapy. Phys Med Biol 2024; 69:115056. [PMID: 38718814 DOI: 10.1088/1361-6560/ad48f6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/08/2023] [Accepted: 05/08/2024] [Indexed: 05/31/2024]
Abstract
Objective.To evaluate the feasibility of using a deep learning dose prediction approach to identify patients who could benefit most from proton therapy based on the normal tissue complication probability (NTCP) model.Approach.Two 3D UNets were established to predict photon and proton doses. A dataset of 95 patients with localized prostate cancer was randomly partitioned into 55, 10, and 30 for training, validation, and testing, respectively. We selected NTCP models for late rectum bleeding and acute urinary urgency of grade 2 or higher to quantify the benefit of proton therapy. Propagated uncertainties of predicted ΔNTCPs resulting from the dose prediction errors were calculated. Patient selection accuracies for a single endpoint and a composite evaluation were assessed under different ΔNTCP thresholds.Main results.Our deep learning-based dose prediction technique can reduce the time spent on plan comparison from approximately 2 days to as little as 5 seconds. The expanded uncertainty of predicted ΔNTCPs for rectum and bladder endpoints propagated from the dose prediction error were 0.0042 and 0.0016, respectively, which is less than one-third of the acceptable tolerance. The averaged selection accuracies for rectum bleeding, urinary urgency, and composite evaluation were 90%, 93.5%, and 93.5%, respectively.Significance.Our study demonstrates that deep learning dose prediction and NTCP evaluation scheme could distinguish the NTCP differences between photon and proton treatment modalities. In addition, the dose prediction uncertainty does not significantly influence the decision accuracy of NTCP-based patient selection for proton therapy. Therefore, automated deep learning dose prediction and NTCP evaluation schemes can potentially be used to screen large patient populations and to avoid unnecessary delays in the start of prostate cancer radiotherapy in the future.
Collapse
Affiliation(s)
- Mei Chen
- Department of Radiation Oncology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 20025, People's Republic of China
| | - Bo Pang
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, People's Republic of China
| | - Yiling Zeng
- Department of Medical Physics, School of Physics and Technology, Wuhan University, Wuhan 430072, People's Republic of China
| | - Cheng Xu
- Department of Radiation Oncology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 20025, People's Republic of China
| | - Jiayi Chen
- Department of Radiation Oncology, Ruijin Hospital, Shanghai Jiao Tong University School of Medicine, Shanghai 20025, People's Republic of China
| | - Kunyu Yang
- Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, People's Republic of China
- Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, People's Republic of China
| | - Yu Chang
- Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, People's Republic of China
- Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, People's Republic of China
| | - Zhiyong Yang
- Cancer Center, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, People's Republic of China
- Institute of Radiation Oncology, Union Hospital, Tongji Medical College, Huazhong University of Science and Technology, Wuhan 430022, People's Republic of China
| |
Collapse
|
2
|
Huet-Dastarac M, Michiels S, Rivas ST, Ozan H, Sterpin E, Lee JA, Barragan-Montero A. Patient selection for proton therapy using Normal Tissue Complication Probability with deep learning dose prediction for oropharyngeal cancer. Med Phys 2023; 50:6201-6214. [PMID: 37140481 DOI: 10.1002/mp.16431] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/22/2022] [Revised: 03/07/2023] [Accepted: 04/01/2023] [Indexed: 05/05/2023] Open
Abstract
BACKGROUND In cancer care, determining the most beneficial treatment technique is a key decision affecting the patient's survival and quality of life. Patient selection for proton therapy (PT) over conventional radiotherapy (XT) currently entails comparing manually generated treatment plans, which requires time and expertise. PURPOSE We developed an automatic and fast tool, AI-PROTIPP (Artificial Intelligence Predictive Radiation Oncology Treatment Indication to Photons/Protons), that assesses quantitatively the benefits of each therapeutic option. Our method uses deep learning (DL) models to directly predict the dose distributions for a given patient for both XT and PT. By using models that estimate the Normal Tissue Complication Probability (NTCP), namely the likelihood of side effects to occur for a specific patient, AI-PROTIPP can propose a treatment selection quickly and automatically. METHODS A database of 60 patients presenting oropharyngeal cancer, obtained from the Cliniques Universitaires Saint Luc in Belgium, was used in this study. For every patient, a PT plan and an XT plan were generated. The dose distributions were used to train the two dose DL prediction models (one for each modality). The model is based on U-Net architecture, a type of convolutional neural network currently considered as the state of the art for dose prediction models. A NTCP protocol used in the Dutch model-based approach, including grades II and III xerostomia and grades II and III dysphagia, was later applied in order to perform automatic treatment selection for each patient. The networks were trained using a nested cross-validation approach with 11-folds. We set aside three patients in an outer set and each fold consists of 47 patients in training, five in validation and five for testing. This method allowed us to assess our method on 55 patients (five patients per test times the number of folds). RESULTS The treatment selection based on the DL-predicted doses reached an accuracy of 87.4% for the threshold parameters set by the Health Council of the Netherlands. The selected treatment is directly linked with these threshold parameters as they express the minimal gain brought by the PT treatment for a patient to be indicated to PT. To validate the performance of AI-PROTIPP in other conditions, we modulated these thresholds, and the accuracy was above 81% for all the considered cases. The difference in average cumulative NTCP per patient of predicted and clinical dose distributions is very similar (less than 1% difference). CONCLUSIONS AI-PROTIPP shows that using DL dose prediction in combination with NTCP models to select PT for patients is feasible and can help to save time by avoiding the generation of treatment plans only used for the comparison. Moreover, DL models are transferable, allowing, in the future, experience to be shared with centers that would not have PT planning expertise.
Collapse
Affiliation(s)
| | - Steven Michiels
- Molecular Imaging, Radiotherapy and Oncology (MIRO), IREC, UCLouvain, Brussels, Belgium
| | - Sara Teruel Rivas
- Molecular Imaging, Radiotherapy and Oncology (MIRO), IREC, UCLouvain, Brussels, Belgium
| | - Hamdiye Ozan
- Molecular Imaging, Radiotherapy and Oncology (MIRO), IREC, UCLouvain, Brussels, Belgium
| | - Edmond Sterpin
- Molecular Imaging, Radiotherapy and Oncology (MIRO), IREC, UCLouvain, Brussels, Belgium
- Department of Oncology, Laboratory of Experimental Radiotherapy, KU Leuven, Leuven, Belgium
| | - John A Lee
- Molecular Imaging, Radiotherapy and Oncology (MIRO), IREC, UCLouvain, Brussels, Belgium
| | - Ana Barragan-Montero
- Molecular Imaging, Radiotherapy and Oncology (MIRO), IREC, UCLouvain, Brussels, Belgium
| |
Collapse
|
3
|
Gu X, Strijbis VIJ, Slotman BJ, Dahele MR, Verbakel WFAR. Dose distribution prediction for head-and-neck cancer radiotherapy using a generative adversarial network: influence of input data. Front Oncol 2023; 13:1251132. [PMID: 37829347 PMCID: PMC10565853 DOI: 10.3389/fonc.2023.1251132] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/30/2023] [Accepted: 08/25/2023] [Indexed: 10/14/2023] Open
Abstract
Purpose A three-dimensional deep generative adversarial network (GAN) was used to predict dose distributions for locally advanced head and neck cancer radiotherapy. Given the labor- and time-intensive nature of manual planning target volume (PTV) and organ-at-risk (OAR) segmentation, we investigated whether dose distributions could be predicted without the need for fully segmented datasets. Materials and methods GANs were trained/validated/tested using 320/30/35 previously segmented CT datasets and treatment plans. The following input combinations were used to train and test the models: CT-scan only (C); CT+PTVboost/elective (CP); CT+PTVs+OARs+body structure (CPOB); PTVs+OARs+body structure (POB); PTVs+body structure (PB). Mean absolute errors (MAEs) for the predicted dose distribution and mean doses to individual OARs (individual salivary glands, individual swallowing structures) were analyzed. Results For the five models listed, MAEs were 7.3 Gy, 3.5 Gy, 3.4 Gy, 3.4 Gy, and 3.5 Gy, respectively, without significant differences among CP-CPOB, CP-POB, CP-PB, among CPOB-POB. Dose volume histograms showed that all four models that included PTV contours predicted dose distributions that had a high level of agreement with clinical treatment plans. The best model CPOB and the worst model PB (except model C) predicted mean dose to within ±3 Gy of the clinical dose, for 82.6%/88.6%/82.9% and 71.4%/67.1%/72.2% of all OARs, parotid glands (PG), and submandibular glands (SMG), respectively. The R2 values (0.17/0.96/0.97/0.95/0.95) of OAR mean doses for each model also indicated that except for model C, the predictions correlated highly with the clinical dose distributions. Interestingly model C could reasonably predict the dose in eight patients, but on average, it performed inadequately. Conclusion We demonstrated the influence of the CT scan, and PTV and OAR contours on dose prediction. Model CP was not statistically different from model CPOB and represents the minimum data statistically required to adequately predict the clinical dose distribution in a group of patients.
Collapse
Affiliation(s)
- Xiaojin Gu
- Department of Radiation Oncology, Amsterdam UMC Location Vrije Universiteit Amsterdam, Amsterdam, Netherlands
- Cancer Center Amsterdam, Cancer Treatment and Quality of Life, Amsterdam, Netherlands
| | - Victor I. J. Strijbis
- Department of Radiation Oncology, Amsterdam UMC Location Vrije Universiteit Amsterdam, Amsterdam, Netherlands
- Cancer Center Amsterdam, Cancer Treatment and Quality of Life, Amsterdam, Netherlands
| | - Ben J. Slotman
- Department of Radiation Oncology, Amsterdam UMC Location Vrije Universiteit Amsterdam, Amsterdam, Netherlands
- Cancer Center Amsterdam, Cancer Treatment and Quality of Life, Amsterdam, Netherlands
| | - Max R. Dahele
- Department of Radiation Oncology, Amsterdam UMC Location Vrije Universiteit Amsterdam, Amsterdam, Netherlands
- Cancer Center Amsterdam, Cancer Treatment and Quality of Life, Amsterdam, Netherlands
| | - Wilko F. A. R. Verbakel
- Department of Radiation Oncology, Amsterdam UMC Location Vrije Universiteit Amsterdam, Amsterdam, Netherlands
- Cancer Center Amsterdam, Cancer Treatment and Quality of Life, Amsterdam, Netherlands
| |
Collapse
|
4
|
Jayarathna S, Shen X, Chen RC, Li HH, Guida K. The effect of integrating knowledge-based planning with multicriteria optimization in treatment planning for prostate SBRT. J Appl Clin Med Phys 2023:e13940. [PMID: 36827178 DOI: 10.1002/acm2.13940] [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: 10/10/2022] [Revised: 12/21/2022] [Accepted: 02/06/2023] [Indexed: 02/25/2023] Open
Abstract
Knowledge-based planning (KBP) and multicriteria optimization (MCO) are two powerful tools to assist treatment planners in achieving optimal target coverage and organ-at-risk (OAR) sparing. The purpose of this work is to investigate if integrating MCO with conventional KBP can further improve treatment plan quality for prostate cancer stereotactic body radiation therapy (SBRT). A two-phase study was designed to investigate the impact of MCO and KBP in prostate SBRT treatment planning. The first phase involved the creation of a KBP model based on thirty clinical SBRT plans, generated by manual optimization (KBP_M). A ten-patient validation cohort was used to compare manual, MCO, and KBP_M optimization techniques. The next phase involved replanning the original model cohort with additional tradeoff optimization via MCO to create a second model, KBP_MCO. Plans were then generated using linear integration (KBP_M+MCO), non-linear integration (KBP_MCO), and a combination of integration methods (KBP_MCO+MCO). All plans were analyzed for planning target volume (PTV) coverage, OAR constraints, and plan quality metrics. Comparisons were generated to evaluate plan and model quality. Phase 1 highlighted the necessity of KBP and MCO in treatment planning, as both optimization methods improved plan quality metrics (Conformity and Heterogeneity Indices) and reduced mean rectal dose by 2 Gy, as compared to manual planning. Integrating MCO with KBP did not further improve plan quality, as little significance was seen over KBP or MCO alone. Principal component score (PCS) fitting showed KBP_MCO improved bladder and rectum estimated and modeled dose correlation by 5% and 22%, respectively; however, model improvements did not significantly impact plan quality. KBP and MCO have shown to reduce OAR dose while maintaining desired PTV coverage in this study. Further integration of KBP and MCO did not show marked improvements in treatment plan quality while requiring increased time in model generation and optimization time.
Collapse
Affiliation(s)
- Sandun Jayarathna
- Department of Radiation Oncology, University of Kansas Cancer Center, Kansas City, KS, USA.,Department of Radiation Physics, The University of Texas MD Anderson Cancer Center, Houston, TX, USA
| | - Xinglei Shen
- Department of Radiation Oncology, University of Kansas Cancer Center, Kansas City, KS, USA
| | - Ronald C Chen
- Department of Radiation Oncology, University of Kansas Cancer Center, Kansas City, KS, USA
| | - H Harold Li
- Department of Radiation Oncology, University of Kansas Cancer Center, Kansas City, KS, USA
| | - Kenny Guida
- Department of Radiation Oncology, University of Kansas Cancer Center, Kansas City, KS, USA
| |
Collapse
|
5
|
Implementation of Machine Learning Models to Ensure Radiotherapy Quality for Multicenter Clinical Trials: Report from a Phase III Lung Cancer Study. Cancers (Basel) 2023; 15:cancers15041014. [PMID: 36831358 PMCID: PMC9953775 DOI: 10.3390/cancers15041014] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/23/2022] [Revised: 01/30/2023] [Accepted: 01/30/2023] [Indexed: 02/09/2023] Open
Abstract
The outcome of the patient and the success of clinical trials involving RT is dependent on the quality assurance of the RT plans. Knowledge-based Planning (KBP) models using data from a library of high-quality plans have been utilized in radiotherapy to guide treatment. In this study, we report on the use of these machine learning tools to guide the quality assurance of multicenter clinical trial plans. The data from 130 patients submitted to RTOG1308 were included in this study. Fifty patient cases were used to train separate photon and proton models on a commercially available platform based on principal component analysis. Models evaluated 80 patient cases. Statistical comparisons were made between the KBP plans and the original plans submitted for quality evaluation. Both photon and proton KBP plans demonstrate a statistically significant improvement of quality in terms of organ-at-risk (OAR) sparing. Proton KBP plans, a relatively emerging technique, show more improvements compared with photon plans. The KBP proton model is a useful tool for creating proton plans that adhere to protocol requirements. The KBP tool was also shown to be a useful tool for evaluating the quality of RT plans in the multicenter clinical trial setting.
Collapse
|
6
|
Pirlepesov F, Wilson L, Moskvin VP, Breuer A, Parkins F, Lucas JT, Merchant TE, Faught AM. Three-dimensional dose and LET D prediction in proton therapy using artificial neural networks. Med Phys 2022; 49:7417-7427. [PMID: 36227617 PMCID: PMC9872814 DOI: 10.1002/mp.16043] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/26/2022] [Revised: 08/30/2022] [Accepted: 09/21/2022] [Indexed: 01/26/2023] Open
Abstract
PURPOSE Challenges in proton therapy include identifying patients most likely to benefit; ensuring consistent, high-quality plans as its adoption becomes more widespread; and recognizing biological uncertainties that may be related to increased relative biologic effectiveness driven by linear energy transfer (LET). Knowledge-based planning (KBP) is a domain that may help to address all three. METHODS Artificial neural networks were trained using 117 unique treatment plans and associated dose and dose-weighted LET (LETD ) distributions. The data set was split into training (n = 82), validation (n = 17), and test (n = 18) sets. Model performance was evaluated on the test set using dose- and LETD -volume metrics in the clinical target volume (CTV) and nearby organs at risk and Dice similarity coefficients (DSC) comparing predicted and planned isodose lines at 50%, 75%, and 95% of the prescription dose. RESULTS Dose-volume metrics significantly differed (α = 0.05) between predicted and planned dose distributions in only one dose-volume metric, D2% to the CTV. The maximum observed root mean square (RMS) difference between corresponding metrics was 4.3 GyRBE (8% of prescription) for D1cc to optic chiasm. DSC were 0.90, 0.93, and 0.88 for the 50%, 75%, and 95% isodose lines, respectively. LETD -volume metrics significantly differed in all but one metric, L0.1cc of the brainstem. The maximum observed difference in RMS differences for LETD metrics was 1.0 keV/μm for L0.1cc to brainstem. CONCLUSIONS We have devised the first three-dimensional dose and LETD -prediction model for cranial proton radiation therapy has been developed. Dose accuracy compared favorably with that of previously published models in other treatment sites. The agreement in LETD supports future investigations with biological doses in mind to enable the full potential of KBP in proton therapy.
Collapse
Affiliation(s)
- Fakhriddin Pirlepesov
- Department of Radiation Oncology, St. Jude
Children’s Research Hospital, 262 Danny Thomas Place, Memphis, TN,
38105-3678
| | - Lydia Wilson
- Department of Radiation Oncology, St. Jude
Children’s Research Hospital, 262 Danny Thomas Place, Memphis, TN,
38105-3678
| | - Vadim P. Moskvin
- Department of Radiation Oncology, St. Jude
Children’s Research Hospital, 262 Danny Thomas Place, Memphis, TN,
38105-3678
| | - Alex Breuer
- Department of Pathology, St. Jude Children’s
Research Hospital, 262 Danny Thomas Place, Memphis, TN, 38105-3678
| | - Franz Parkins
- Department of Information Services, St. Jude
Children’s Research Hospital, 262 Danny Thomas Place, Memphis, TN,
38105-3678
| | - John T. Lucas
- Department of Radiation Oncology, St. Jude
Children’s Research Hospital, 262 Danny Thomas Place, Memphis, TN,
38105-3678
| | - Thomas E. Merchant
- Department of Radiation Oncology, St. Jude
Children’s Research Hospital, 262 Danny Thomas Place, Memphis, TN,
38105-3678
| | - Austin M. Faught
- Department of Radiation Oncology, St. Jude
Children’s Research Hospital, 262 Danny Thomas Place, Memphis, TN,
38105-3678
| |
Collapse
|
7
|
Hytönen R, Vanderstraeten R, Dahele M, Verbakel WFAR. Influence of Beam Angle on Normal Tissue Complication Probability of Knowledge-Based Head and Neck Cancer Proton Planning. Cancers (Basel) 2022; 14:cancers14122849. [PMID: 35740515 PMCID: PMC9221467 DOI: 10.3390/cancers14122849] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 05/06/2022] [Revised: 06/02/2022] [Accepted: 06/07/2022] [Indexed: 12/04/2022] Open
Abstract
Knowledge-based planning solutions have brought significant improvements in treatment planning. However, the performance of a proton-specific knowledge-based planning model in creating knowledge-based plans (KBPs) with beam angles differing from those used to train the model remains unexplored. We used a previously validated RapidPlanPT model and scripting to create nine KBPs, one with default and eight with altered beam angles, for 10 recent oropharynx cancer patients. The altered-angle plans were compared against the default-angle ones in terms of grade 2 dysphagia and xerostomia normal tissue complication probability (NTCP), mean doses of several organs at risk, and dose homogeneity index (HI). As KBP could be suboptimal, a proof of principle automatic iterative optimizer (AIO) was added with the aim of reducing the plan NTCP. There were no statistically significant differences in NTCP or HI between default- and altered-angle KBPs, and the altered-angle plans showed a <1% reduction in NTCP. AIO was able to reduce the sum of grade 2 NTCPs in 66/90 cases with mean a reduction of 3.5 ± 1.8%. While the altered-angle plans saw greater benefit from AIO, both default- and altered-angle plans could be improved, indicating that the KBP model alone was not completely optimal to achieve the lowest NTCP. Overall, the data showed that the model was robust to the various beam arrangements within the range described in this analysis.
Collapse
Affiliation(s)
- Roni Hytönen
- Varian Medical Systems Finland, 00270 Helsinki, Finland
- Correspondence:
| | | | - Max Dahele
- Department of Radiation Oncology, Amsterdam UMC Location Vrije Universiteit Amsterdam, 1081 HV Amsterdam, The Netherlands; (M.D.); (W.F.A.R.V.)
- Cancer Center Amsterdam, 1081 HV Amsterdam, The Netherlands
| | - Wilko F. A. R. Verbakel
- Department of Radiation Oncology, Amsterdam UMC Location Vrije Universiteit Amsterdam, 1081 HV Amsterdam, The Netherlands; (M.D.); (W.F.A.R.V.)
- Cancer Center Amsterdam, 1081 HV Amsterdam, The Netherlands
| |
Collapse
|