1
|
Koganezawa AS, Matsuura T, Kawahara D, Nakashima T, Shiba E, Murakami Y, Nagata Y. Unbiased evaluation of predicted gamma passing rate by an event-mixing technique. Med Phys 2024; 51:5-17. [PMID: 38009570 DOI: 10.1002/mp.16848] [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: 06/21/2023] [Revised: 10/31/2023] [Accepted: 10/31/2023] [Indexed: 11/29/2023] Open
Abstract
BACKGROUND Predicting models of the gamma passing rate (GPR) have been studied to substitute the measurement-based gamma analysis. Since these studies used data from different radiotherapy systems comprising TPS, linear accelerator, and detector array, it has been difficult to compare the performances of the predicting models among institutions with different radiotherapy systems. PURPOSE We aimed to develop unbiased scoring methods to evaluate the performance of the models predicting the GPR, by introducing both best and worst limits for the performance of the GPR prediction. METHODS Two hundred head-and-neck VMAT plans were used to develop a framework. The GPRs were measured using the ArcCHECK device. The predicted GPR [p] was generated using a deep learning-based model [pDL ]. The predicting model was evaluated using four metrics: standard deviation (SD) [σ], Pearson's correlation coefficient (CC) [r], mean squared error (MSE) [s], and mean absolute error (MAE) [a]. The best limit [σ m ${\sigma _m}$ ,r m ${r_m}$ ,s m ${s_m}$ , anda m ${a_m}$ ] was estimated by measuring the SD of measured GPR [m] by shifting the device along the longitudinal direction to measure different sampling points. Mimicked best and worst p's [pbest and pworst ] were generated from pDL . The worst limit was defined such that m and p have no correlation [CC ∼ 0]. The worst limit [σMix , rMix , sMix , and aMix ] was generated using the event-mixing (EM) technique originally introduced in high-energy physics experiments. The range of σ, r, s, and a was defined to be[ σ m , σ Mix ] $[ {{\sigma _m},{\sigma _{{\mathrm{Mix}}}}} ]$ ,[ 0 , r m ] $[ {0,{r_m}} ]$ ,[ s m , s Mix ] $[ {{s_m},{s_{{\mathrm{Mix}}}}} ]$ , and[ a m , a Mix ] $[ {{a_m},{a_{{\mathrm{Mix}}}}} ]$ . The achievement score (AS) independently based on σ, r, s, and a were calculated for pDL , pbest and pworst . The probability that p fails the gamma analysis (alert frequency; AF) was estimated as a function ofσ d ${\sigma _d}$ values within the [σ m ${\sigma _m}$ , σMix ] range for the 3%/2 mm data with a 95% criterion. RESULTS SDs of the best limit were well reproduced byσ m = 0.531 100 - m ${\sigma _m} = \;0.531\sqrt {100 - m} $ . The EM technique successfully generated the( m , p ) $( {m,p} )$ pairs with no correlation. The AS using four metrics showed good agreement. This agreement indicates successful definitions of both best and worst limits, consistent definitions of the AS, and successful generations of mixed events. The AF for the DL-based model with the 3%/2 mm tolerance was 31.5% and 63.0% with CL's 99% and 99.9%, respectively. CONCLUSION We developed the AS to evaluate the predicting model of the GPR in an unbiased manner by excluding the effects of the precision of the radiotherapy system and the spreading of the GPR. The best and worst limits of the GPR prediction were successfully generated using the measured precision of the GPR and the EM technique, respectively. The AS andσ p ${\sigma _p}$ are expected to enable objective evaluation of the predicting model and setting exact achievement goal of precision for the predicted GPR.
Collapse
Affiliation(s)
- Akito S Koganezawa
- Department of Radiation Oncology, Hiroshima University Hospital, Hiroshima, Japan
- Department of Information and Electronic Engineering, Faculty of Science and Engineering, Teikyo University, Tochigi, Japan
| | - Takaaki Matsuura
- Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, Japan
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Daisuke Kawahara
- Department of Radiation Oncology, Hiroshima University Hospital, Hiroshima, Japan
| | - Takeo Nakashima
- Department of Clinical Support, Radiation Therapy Section, Hiroshima University Hospital, Hiroshima, Japan
| | - Eiji Shiba
- Department of Radiation Oncology, Hospital of the University of Occupational and Environmental Health, Fukuoka, Japan
| | - Yuji Murakami
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Yasushi Nagata
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| |
Collapse
|
2
|
Ishizaka N, Kinoshita T, Sakai M, Tanabe S, Nakano H, Tanabe S, Nakamura S, Mayumi K, Akamatsu S, Nishikata T, Takizawa T, Yamada T, Sakai H, Kaidu M, Sasamoto R, Ishikawa H, Utsunomiya S. Prediction of patient-specific quality assurance for volumetric modulated arc therapy using radiomics-based machine learning with dose distribution. J Appl Clin Med Phys 2024; 25:e14215. [PMID: 37987544 PMCID: PMC10795425 DOI: 10.1002/acm2.14215] [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: 03/09/2023] [Revised: 09/29/2023] [Accepted: 10/30/2023] [Indexed: 11/22/2023] Open
Abstract
PURPOSE We sought to develop machine learning models to predict the results of patient-specific quality assurance (QA) for volumetric modulated arc therapy (VMAT), which were represented by several dose-evaluation metrics-including the gamma passing rates (GPRs)-and criteria based on the radiomic features of 3D dose distribution in a phantom. METHODS A total of 4,250 radiomic features of 3D dose distribution in a cylindrical dummy phantom for 140 arcs from 106 clinical VMAT plans were extracted. We obtained the following dose-evaluation metrics: GPRs with global and local normalization, the dose difference (DD) in 1% and 2% passing rates (DD1% and DD2%) for 10% and 50% dose threshold, and the distance-to-agreement in 1-mm and 2-mm passing rates (DTA1 mm and DTA2 mm) for 0.5%/mm and 1.0%.mm dose gradient threshold determined by measurement using a diode array in patient-specific QA. The machine learning regression models for predicting the values of the dose-evaluation metrics using the radiomic features were developed based on the elastic net (EN) and extra trees (ET) models. The feature selection and tuning of hyperparameters were performed with nested cross-validation in which four-fold cross-validation is used within the inner loop, and the performance of each model was evaluated in terms of the root mean square error (RMSE), the mean absolute error (MAE), and Spearman's rank correlation coefficient. RESULTS The RMSE and MAE for the developed machine learning models ranged from <1% to nearly <10% depending on the dose-evaluation metric, the criteria, and dose and dose gradient thresholds used for both machine learning models. It was advantageous to focus on high dose region for predicating global GPR, DDs, and DTAs. For certain metrics and criteria, it was possible to create models applicable for patients' heterogeneity by training only with dose distributions in phantom. CONCLUSIONS The developed machine learning models showed high performance for predicting dose-evaluation metrics especially for high dose region depending on the metric and criteria. Our results demonstrate that the radiomic features of dose distribution can be considered good indicators of the plan complexity and useful in predicting measured dose evaluation metrics.
Collapse
Affiliation(s)
- Natsuki Ishizaka
- Department of RadiologyNiigata Prefectural Shibata HospitalShibata CityNiigataJapan
| | - Tomotaka Kinoshita
- Department of Radiological TechnologyNiigata University Graduate School of Health SciencesNiigata CityNiigataJapan
| | - Madoka Sakai
- Department of RadiologyNagaoka Chuo General HospitalNagaokaNiigataJapan
- Department of Radiation OncologyNiigata University Medical and Dental HospitalNiigata CityNiigataJapan
| | - Shunpei Tanabe
- Department of Radiation OncologyNiigata University Medical and Dental HospitalNiigata CityNiigataJapan
| | - Hisashi Nakano
- Department of Radiation OncologyNiigata University Medical and Dental HospitalNiigata CityNiigataJapan
| | - Satoshi Tanabe
- Department of Radiation OncologyNiigata University Medical and Dental HospitalNiigata CityNiigataJapan
| | - Sae Nakamura
- Department of Radiation OncologyNiigata Neurosurgical HospitalNiigata CityNiigataJapan
| | - Kazuki Mayumi
- Department of Radiological TechnologyNiigata University Graduate School of Health SciencesNiigata CityNiigataJapan
| | - Shinya Akamatsu
- Department of Radiological TechnologyNiigata University Graduate School of Health SciencesNiigata CityNiigataJapan
- Department of RadiologyTakeda General HospitalAizuwakamatsu CityFukushimaJapan
| | - Takayuki Nishikata
- Department of Radiological TechnologyNiigata University Graduate School of Health SciencesNiigata CityNiigataJapan
- Division of RadiologyNagaoka Red Cross HospitalNagaoka‐shiNiigataJapan
| | - Takeshi Takizawa
- Department of Radiation OncologyNiigata University Medical and Dental HospitalNiigata CityNiigataJapan
- Department of Radiation OncologyNiigata Neurosurgical HospitalNiigata CityNiigataJapan
| | - Takumi Yamada
- Section of Radiology, Department of Clinical SupportNiigata University Medical and Dental HospitalNiigata CityNiigataJapan
| | - Hironori Sakai
- Section of Radiology, Department of Clinical SupportNiigata University Medical and Dental HospitalNiigata CityNiigataJapan
| | - Motoki Kaidu
- Department of Radiology and Radiation OncologyNiigata University Graduate School of Medical and Dental SciencesNiigata CityNiigataJapan
| | - Ryuta Sasamoto
- Department of Radiological TechnologyNiigata University Graduate School of Health SciencesNiigata CityNiigataJapan
| | - Hiroyuki Ishikawa
- Department of Radiology and Radiation OncologyNiigata University Graduate School of Medical and Dental SciencesNiigata CityNiigataJapan
| | - Satoru Utsunomiya
- Department of Radiological TechnologyNiigata University Graduate School of Health SciencesNiigata CityNiigataJapan
| |
Collapse
|
3
|
Huang Y, Qin T, Yang M, Liu Z. Impact of ovary-sparing treatment planning on plan quality, treatment time and gamma passing rates in intensity-modulated radiotherapy for stage I/II cervical cancer. Medicine (Baltimore) 2023; 102:e36373. [PMID: 38115303 PMCID: PMC10727547 DOI: 10.1097/md.0000000000036373] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/04/2023] [Revised: 11/07/2023] [Accepted: 11/08/2023] [Indexed: 12/21/2023] Open
Abstract
BACKGROUND This study aimed to investigate the impact of ovary-sparing intensity-modulated radiotherapy (IMRT) on plan quality, treatment time, and gamma passing rates for stage I/II cervical cancer patients. METHODS Fifteen stage I/II cervical cancer patients were retrospectively enrolled, and a pair of clinically suitable IMRT plans were designed for each patient, with (Group A) and without (Group B) ovary-sparing. Plan factors affecting plan quality, treatment time, and gamma passing rates, including the number of segments, monitor units, percentage of small-area segments (field area < 20 cm2), and percentage of small-MU segments (MU < 10), were compared and statistically analyzed. Key plan quality indicators, including ovarian dose, target dose coverage (D98%, D95%, D50%, D2%), conformity index, and homogeneity index, were evaluated and statistically assessed. Treatment time and gamma passing rates collected by IBA MatriXX were also compared. RESULTS The median ovarian dose in Group A and Group B was 7.61 Gy (range 6.71-8.51 Gy) and 38.52 Gy (range 29.84-43.82 Gy), respectively. Except for monitor units, all other plan factors were significantly lower in Group A than in Group B (all P < .05). Correlation coefficients between plan factors, treatment time, and gamma passing rates that were statistically different were all negative. Both Groups of plans met the prescription requirement (D95% ≥ 45.00 Gy) for clinical treatment. D98% was smaller for Group A than for Group B (P < .05); D50% and D2% were larger for Group A than for Group B (P < .05, P < .05). Group A plans had worse conformity index and homogeneity index than Group B plans (P < .05, P < .05). Treatment time did not differ significantly (P > .05). Gamma passing rates in Group A were higher than in Group B with the criteria of 2%/3 mm (P < .05) and 3%/2 mm (P < .05). CONCLUSION Despite the slightly decreased quality of the treatment plans, the ovary-sparing IMRT plans exhibited several advantages including lower ovarian dose and plan complexity, improved gamma passing rates, and a negligible impact on treatment time.
Collapse
Affiliation(s)
- Yangyang Huang
- Department of Radiotherapy, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China
| | - Tingting Qin
- Department of Radiotherapy, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China
| | - Menglin Yang
- Department of Radiotherapy, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China
| | - Zongwen Liu
- Department of Radiotherapy, The Second Affiliated Hospital of Zhengzhou University, Zhengzhou, Henan Province, China
| |
Collapse
|
4
|
Matsuura T, Kawahara D, Saito A, Yamada K, Ozawa S, Nagata Y. A synthesized gamma distribution-based patient-specific VMAT QA using a generative adversarial network. Med Phys 2023; 50:2488-2498. [PMID: 36609669 DOI: 10.1002/mp.16210] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/03/2022] [Revised: 12/23/2022] [Accepted: 12/25/2022] [Indexed: 01/08/2023] Open
Abstract
BACKGROUND Artificial intelligence (AI)-based gamma passing rate (GPR) prediction has been proposed as a time-efficient virtual patient-specific QA method for the delivery of volumetric modulation arc therapy (VMAT). However, there is a limitation that the GPR value loses the locational information of dose accuracy. PURPOSE The objective was to predict the failing points in the gamma distribution and the GPR using a synthesized gamma distribution of VMAT QA with a deep convolutional generative adversarial network (GAN). METHODS The fluence maps of 270 VMAT beams for prostate cancer were measured using an electronic portal imaging device and analyzed using gamma evaluation with 3%/2-mm, 2%/1-mm, 1%/1-mm, and 1%/0.5-mm tolerances. The 270 gamma distributions were divided into two datasets: 240 training datasets for creating a model and 30 test datasets for evaluation. The image prediction network for the fluence maps calculated by the treatment planning system (TPS) to the gamma distributions was created using a GAN. The sensitivity, specificity, and accuracy of detecting failing points were evaluated using measured and synthesized gamma distributions. In addition, the difference between measured GPR (mGPR) and predicted GPR (pGPR) values calculated from the synthesized gamma distributions was evaluated. RESULTS The root mean squared errors between mGPR and pGPR were 1.0%, 2.1%, 3.5%, and 3.6% for the 3%/2-mm, 2%/1-mm, 1%/1-mm, and 1%/0.5-mm tolerances, respectively. The accuracies for detecting failing points were 98.9%, 96.9%, 94.7%, and 93.7% for 3%/2-mm, 2%/1-mm, 1%/1-mm, and 1%/0.5-mm tolerances, respectively. The sensitivity and specificity were the highest for 1%/0.5-mm and 3%/2-mm tolerances, which were 82.7% and 99.6%, respectively. CONCLUSIONS We developed a novel system using a GAN to generate a synthesized gamma distribution-based patient-specific VMAT QA. The system is promising from the point of view of quality assurance in radiotherapy because it shows high performance and can detect failing points.
Collapse
Affiliation(s)
- Takaaki Matsuura
- Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, Japan.,Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Daisuke Kawahara
- Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Akito Saito
- Department of Radiation Oncology, Hiroshima University Hospital, Hiroshima, Japan
| | - Kiyoshi Yamada
- Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, Japan
| | - Shuichi Ozawa
- Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, Japan.,Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| | - Yasushi Nagata
- Hiroshima High-Precision Radiotherapy Cancer Center, Hiroshima, Japan.,Department of Radiation Oncology, Graduate School of Biomedical and Health Sciences, Hiroshima University, Hiroshima, Japan
| |
Collapse
|
5
|
Predictive gamma passing rate of 3D detector array-based volumetric modulated arc therapy quality assurance for prostate cancer via deep learning. Phys Eng Sci Med 2022; 45:1073-1081. [PMID: 36202950 DOI: 10.1007/s13246-022-01172-w] [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: 03/14/2022] [Accepted: 08/04/2022] [Indexed: 11/07/2022]
Abstract
To predict the gamma passing rate (GPR) of the three-dimensional (3D) detector array-based volumetric modulated arc therapy (VMAT) quality assurance (QA) for prostate cancer using a convolutional neural network (CNN) with the 3D dose distribution. One hundred thirty-five VMAT plans for prostate cancer were selected: 110 plans were used for training and validation, and 25 plans were used for testing. Verification plans were measured using a helical 3D diode array (ArcCHECK). The dose distribution on the detector element plane of these verification plans was used as input data for the CNN model. The measured GPR (mGPR) values were used as the training data. The CNN model comprises eighteen layers and predicted GPR (pGPR) values. The mGPR and pGPR values were compared, and a cumulative frequency histogram of the prediction error was created to clarify the prediction error tendency. The correlation coefficients of pGPR and mGPR were 0.67, 0.69, 0.66, and 0.73 for 3%/3-mm, 3%/2-mm, 2%/3-mm, and 2%/2-mm gamma criteria, respectively. The respective mean±standard deviations of pGPR-mGPR were -0.87±2.18%, -0.65±2.93%, -0.44±2.53%, and -0.71±3.33%. The probabilities of false positive error cases (pGPR < mGPR) were 72%, 60%, 68%, and 56% for each gamma criterion. We developed a deep learning-based prediction model of the 3D detector array-based VMAT QA for prostate cancer, and evaluated the accuracy and tendency of prediction GPR. This model can provide a proactive estimation for the results of the patient-specific QA before the verification measurement.
Collapse
|
6
|
Kusunoki T, Hatanaka S, Hariu M, Kusano Y, Yoshida D, Katoh H, Shimbo M, Takahashi T. Evaluation of prediction and classification performances in different machine learning models for patient-specific quality assurance of head-and-neck VMAT plans. Med Phys 2021; 49:727-741. [PMID: 34859445 DOI: 10.1002/mp.15393] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/24/2021] [Revised: 10/29/2021] [Accepted: 11/19/2021] [Indexed: 01/02/2023] Open
Abstract
PURPOSE The purpose of this study is to evaluate the prediction and classification performances of the gamma passing rate (GPR) for different machine learning models and to select the best model for achieving machine learning-based patient-specific quality assurance (PSQA). METHODS The measurement verification of 356 head-and-neck volumetric modulated arc therapy plans was performed using a diode array phantom (Delta4 Phantom), and GPR values at 2%/2 mm with global normalization and 3%/2 mm with local normalization were calculated. Machine learning models, including ridge regression (RIDGE), random forest (RF), support vector regression (SVR), and stacked generalization (STACKING), were used to predict the GPR. Each machine learning model was trained using 260 plans, and the prediction accuracy was evaluated using the remaining 96 plans. The prediction error between the measured and predicted GPR was evaluated. For the classification evaluation, the lower control limit for the measured GPR and lower control limit for predicted GPR (LCLp ) was defined to identify whether the GPR values represent a "pass" or a "fail." LCLp values with 99% and 99.9% confidence levels were calculated as the upper prediction limits for the GPR estimated from the linear regression between the measured and predicted GPR. RESULTS There was an overestimation trend of the low measured GPR. The maximum prediction errors for RIDGE, RF, SVR, and STACKING were 3.2%, 2.9%, 2.3%, and 2.2% at the global 2%/2 mm and 6.3%, 6.6%, 6.1%, and 5.5% at the local 3%/2 mm, respectively. In the global 2%/2 mm, the sensitivity was 100% for all the machine learning models except RIDGE when using 99% LCLp . The specificity was 76.1% for RIDGE, RF, and SVR and 66.3% for STACKING; however, the specificity decreased dramatically when 99.9% LCLp was used. In the local 3%/2 mm, however, only STACKING showed 100% sensitivity when using 99% LCLp . The decrease in the specificity using 99.9% LCLp was smaller than that in the global 2%/2 mm, and the specificity for RIDGE, RF, SVR, and STACKING was 61.3%, 61.3%, 72.0%, and 66.8%, respectively. CONCLUSIONS STACKING had better prediction accuracy for low GPR values than other machine learning models. Applying LCLp to a regression model enabled the consistent evaluation of quantitative and qualitative GPR predictions. Adjusting the confidence level of the LCLp helped improve the balance between the sensitivity and specificity. We suggest that STACKING can assist the safe and efficient operation of PSQA.
Collapse
Affiliation(s)
- Terufumi Kusunoki
- Section of Medical Physics and Engineering, Kanagawa Cancer Center, Yokohama, Japan.,Department of Radiation Oncology, Saitama Medical Center, Saitama Medical University, Kawagoe, Japan
| | - Shogo Hatanaka
- Department of Radiation Oncology, Saitama Medical Center, Saitama Medical University, Kawagoe, Japan
| | - Masatsugu Hariu
- Department of Radiation Oncology, Saitama Medical Center, Saitama Medical University, Kawagoe, Japan
| | - Yohsuke Kusano
- Section of Medical Physics and Engineering, Kanagawa Cancer Center, Yokohama, Japan
| | - Daisaku Yoshida
- Section of Medical Physics and Engineering, Kanagawa Cancer Center, Yokohama, Japan.,Department of Radiation Oncology, Kanagawa Cancer Center, Yokohama, Japan
| | - Hiroyuki Katoh
- Department of Radiation Oncology, Kanagawa Cancer Center, Yokohama, Japan
| | - Munefumi Shimbo
- Department of Radiation Oncology, Saitama Medical Center, Saitama Medical University, Kawagoe, Japan
| | - Takeo Takahashi
- Department of Radiation Oncology, Saitama Medical Center, Saitama Medical University, Kawagoe, Japan
| |
Collapse
|
7
|
Maes D, Bowen SR, Regmi R, Bloch C, Wong T, Rosenfeld A, Saini J. A machine learning-based framework for delivery error prediction in proton pencil beam scanning using irradiation log-files. Phys Med 2020; 78:179-186. [PMID: 33038643 DOI: 10.1016/j.ejmp.2020.09.008] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/14/2020] [Revised: 09/01/2020] [Accepted: 09/07/2020] [Indexed: 10/23/2022] Open
Abstract
PURPOSE This study aims to investigate the use of machine learning models for delivery error prediction in proton pencil beam scanning (PBS) delivery. METHODS A dataset of planned and delivered PBS spot parameters was generated from a set of 20 prostate patient treatments. Planned spot parameters (spot position, MU and energy) were extracted from the treatment planning system (TPS) for each beam. Delivered spot parameters were extracted from irradiation log-files for each beam delivery following treatment. The dataset was used as a training dataset for three machine learning models which were trained to predict delivered spot parameters based on planned parameters. K-fold cross validation was employed for hyper-parameter tuning and model selection where the mean absolute error (MAE) was used as the model evaluation metric. The model with lowest MAE was then selected to generate a predicted dose distribution for a test prostate patient within a commercial TPS. RESULTS Analysis of the spot position delivery error between planned and delivered values resulted in standard deviations of 0.39 mm and 0.44 mm for x and y spot positions respectively. Prediction error standard deviation values of spot positions using the selected model were 0.22 mm and 0.11 mm for x and y spot positions respectively. Finally, a three-way comparison of dose distributions and DVH values for select OARs indicates that the random-forest-predicted dose distribution within the test prostate patient was in closer agreement to the delivered dose distribution than the planned distribution. CONCLUSIONS PBS delivery error can be accurately predicted using machine learning techniques.
Collapse
Affiliation(s)
- Dominic Maes
- Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA; Centre for Medical Radiation Physics, University of Wollongong, Wollongong, NSW 2500, Australia.
| | - Stephen R Bowen
- Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA; Department of Radiation Oncology, University of Washington School of Medicine, 1959 NE Pacific St., Seattle, WA 98195, USA; Department of Radiology, University of Washington School of Medicine, 1959 NE Pacific St., Seattle, WA 98195, USA
| | - Rajesh Regmi
- Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA
| | - Charles Bloch
- Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA; Department of Radiation Oncology, University of Washington School of Medicine, 1959 NE Pacific St., Seattle, WA 98195, USA
| | - Tony Wong
- Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA; Department of Radiation Oncology, University of Washington School of Medicine, 1959 NE Pacific St., Seattle, WA 98195, USA
| | - Anatoly Rosenfeld
- Centre for Medical Radiation Physics, University of Wollongong, Wollongong, NSW 2500, Australia
| | - Jatinder Saini
- Seattle Cancer Care Alliance Proton Therapy Center, 1570 N 115th St., Seattle, WA 98133, USA; Department of Radiation Oncology, University of Washington School of Medicine, 1959 NE Pacific St., Seattle, WA 98195, USA
| |
Collapse
|
8
|
Krishnan MPA, Bhagyalakshmi AT, Holla R, Puzakkal N, Ranjith CP, Vysakh R, Irfad MP, Ramasubramanian V, Hu J, Momeen MU. A technique for quantifying the sensitivity of dosimetric tool gamma with 2D detector array in pretreatment IMRT plans by segment deletion method. Radiol Med 2020; 126:453-459. [PMID: 32803540 DOI: 10.1007/s11547-020-01259-y] [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] [Received: 04/10/2020] [Accepted: 08/10/2020] [Indexed: 11/28/2022]
Abstract
OBJECTIVES Motivation of this study is to check the sensitivity of dosimetric tool gamma with 2D detector array combination when unexpected errors occur while transferring intensity-modulated radiation therapy treatment plans from planning system to treatment unit. METHODS This study consists of 17 head and neck cancer patient's treatment plans. Nine types of verification plans are created for all 17 clinically approved treatment plans by consecutively deleting different segments (up to eight) one by one from each field of the plan. Decrement factor (χ) is introduced in our study which illustrated the degree of decay of gamma passing rate when intentional errors are introduced. We analyzed the data by two different methods-one without selecting the region of interest (ROI) in dose distributions and the other by selecting the region of interest. RESULTS By linear regression, the absolute value of slopes is 0.025, 0.024 and 0.015 without ROI and 0.030, 0.027 and 0.015 with ROI for 2%/2 mm, 3%/3 mm and 5%/5 mm criteria, respectively. The higher absolute value of the fitted slope indicates the higher sensitivity of this method to identify erroneous plan in treatment unit. The threshold value for 2%/2 mm equivalent to 95% passing criteria in 3%/3 mm used in clinical practice is obtained as 83.44%. CONCLUSIONS The 2D detector array with dosimetric tool gamma is less sensitive in detecting errors when unprecedented errors of segment deletion occur within the treatment plans.
Collapse
Affiliation(s)
- M P Arun Krishnan
- School of Advanced Sciences, Vellore Institute of Technology, Vellore, 632014, India.,MVR Cancer Centre and Research Institute, Kozhikode, 673601, India
| | - A T Bhagyalakshmi
- School of Advanced Sciences, Vellore Institute of Technology, Vellore, 632014, India
| | - Raghavendra Holla
- Amrita Institute of Medical Sciences and Research Centre, Kochi, 682041, India
| | - Niyas Puzakkal
- MVR Cancer Centre and Research Institute, Kozhikode, 673601, India
| | - C P Ranjith
- MVR Cancer Centre and Research Institute, Kozhikode, 673601, India
| | - R Vysakh
- MVR Cancer Centre and Research Institute, Kozhikode, 673601, India
| | - M P Irfad
- MVR Cancer Centre and Research Institute, Kozhikode, 673601, India
| | - V Ramasubramanian
- School of Advanced Sciences, Vellore Institute of Technology, Vellore, 632014, India
| | - Jianping Hu
- School of Advanced Sciences, Vellore Institute of Technology, Vellore, 632014, India.
| | - M Ummal Momeen
- School of Advanced Sciences, Vellore Institute of Technology, Vellore, 632014, India.
| |
Collapse
|
9
|
Bai H, Zhu S, Wu X, Liu X, Chen F, Yan J. Study on the ability of 3D gamma analysis and bio-mathematical model in detecting dose changes caused by dose-calculation-grid-size (DCGS). Radiat Oncol 2020; 15:161. [PMID: 32631380 PMCID: PMC7336463 DOI: 10.1186/s13014-020-01603-6] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/13/2020] [Accepted: 06/23/2020] [Indexed: 02/06/2023] Open
Abstract
Objective To explore the efficacy and sensitivity of 3D gamma analysis and bio-mathematical model for cervical cancer in detecting dose changes caused by dose-calculation-grid-size (DCGS). Methods 17 patients’ plans for cervical cancer were enrolled (Pinnacle TPS, VMAT), and the DCGS was changed from 2.0 mm to 5.0 mm to calculate the planned dose respectively. The dose distribution calculated by DCGS = 2.0 mm as the “reference” data set (RDS), the dose distribution calculated by the rest DCGS as the“measurement”data set (MDS), the 3D gamma passing rates and the (N) TCPs of the all structures under different DCGS were obtained, and then analyze the ability of 3D gamma analysis and (N) TCP model in detecting dose changes and what factors affect this ability. Results The effect of DCGS on planned dose was obvious. When the gamma standard was 1.0 mm, 1.0 and 10.0%, the difference of the results of the DCGS on dose-effect could be detected by 3D gamma analysis (all p value < 0.05). With the decline of the standard, 3D gamma analysis’ ability to detect this difference shows weaker. When the standard was 1.0 mm, 3.0 and 10.0%, the p value of > 0.05 accounted for the majority. With DCGS = 2.0 mm being RDS, ∆gamma-passing-rate presented the same trend with ∆(N) TCPs of all structures except for the femurs only when the 1.0 mm, 1.0 and 10.0% standards were adopted for the 3D gamma analysis. Conclusions The 3D gamma analysis and bio-mathematical model can be used to analyze the effect of DCGS on the planned dose. For comparison, the former’s detection ability has a lot to do with the designed standard, and the latter’s capability is related to the parameters and calculated accuracy instrinsically.
Collapse
Affiliation(s)
- Han Bai
- Department of Radiation Oncology, Yunnan Tumor Hospital, The Third Affiliated Hospital of Kunming Medical University, No.519 Kunzhou, Road, Xishan District, Kunming, Yunnan, China
| | - Sijin Zhu
- Department of Radiation Oncology, Yunnan Tumor Hospital, The Third Affiliated Hospital of Kunming Medical University, No.519 Kunzhou, Road, Xishan District, Kunming, Yunnan, China
| | - Xingrao Wu
- Department of Radiation Oncology, Yunnan Tumor Hospital, The Third Affiliated Hospital of Kunming Medical University, No.519 Kunzhou, Road, Xishan District, Kunming, Yunnan, China.
| | - Xuhong Liu
- Department of Radiation Oncology, Yunnan Tumor Hospital, The Third Affiliated Hospital of Kunming Medical University, No.519 Kunzhou, Road, Xishan District, Kunming, Yunnan, China
| | - Feihu Chen
- Department of Radiation Oncology, Yunnan Tumor Hospital, The Third Affiliated Hospital of Kunming Medical University, No.519 Kunzhou, Road, Xishan District, Kunming, Yunnan, China
| | - Jiawen Yan
- Department of Radiation Oncology, Yunnan Tumor Hospital, The Third Affiliated Hospital of Kunming Medical University, No.519 Kunzhou, Road, Xishan District, Kunming, Yunnan, China
| |
Collapse
|
10
|
Shiba E, Saito A, Furumi M, Kawahara D, Miki K, Murakami Y, Ohguri T, Ozawa S, Tsuneda M, Yahara K, Nishio T, Korogi Y, Nagata Y. Predictive gamma passing rate for three‐dimensional dose verification with finite detector elements via improved dose uncertainty potential accumulation model. Med Phys 2020; 47:1349-1356. [DOI: 10.1002/mp.13985] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/31/2019] [Revised: 12/03/2019] [Accepted: 12/14/2019] [Indexed: 11/08/2022] Open
Affiliation(s)
- Eiji Shiba
- Department of Radiation Oncology Hospital of the University of Occupational and Environmental Health Fukuoka 807‐8556Japan
- Department of Radiation Oncology Graduate School of Biomedical and Health Sciences Hiroshima University Hiroshima 734‐8551Japan
| | - Akito Saito
- Department of Radiation Oncology Hiroshima University Hospital Hiroshima 734‐8551Japan
| | - Makoto Furumi
- Department of Radiation Oncology Hospital of the University of Occupational and Environmental Health Fukuoka 807‐8556Japan
| | - Daisuke Kawahara
- Department of Radiation Oncology Graduate School of Biomedical and Health Sciences Hiroshima University Hiroshima 734‐8551Japan
| | - Kentaro Miki
- Department of Radiation Oncology Hiroshima University Hospital Hiroshima 734‐8551Japan
| | - Yuji Murakami
- Department of Radiation Oncology Graduate School of Biomedical and Health Sciences Hiroshima University Hiroshima 734‐8551Japan
| | - Takayuki Ohguri
- Department of Radiation Oncology Hospital of the University of Occupational and Environmental Health Fukuoka 807‐8556Japan
| | - Shuichi Ozawa
- Department of Radiation Oncology Graduate School of Biomedical and Health Sciences Hiroshima University Hiroshima 734‐8551Japan
- Hiroshima High‐Precision Radiotherapy Cancer Center Hiroshima 732‐0057Japan
| | - Masato Tsuneda
- Department of Radiation Oncology Tokyo Women's Medical University Shinjuku Tokyo 162‐8666Japan
| | - Katsuya Yahara
- Department of Radiation Oncology Hospital of the University of Occupational and Environmental Health Fukuoka 807‐8556Japan
| | - Teiji Nishio
- Department of Medical Physics Graduate School of Medical Science Tokyo Women's Medical University Tokyo 162‐8666Japan
| | - Yukunori Korogi
- Department of Radiation Oncology Hospital of the University of Occupational and Environmental Health Fukuoka 807‐8556Japan
| | - Yasushi Nagata
- Department of Radiation Oncology Graduate School of Biomedical and Health Sciences Hiroshima University Hiroshima 734‐8551Japan
| |
Collapse
|
11
|
Ono T, Hirashima H, Iramina H, Mukumoto N, Miyabe Y, Nakamura M, Mizowaki T. Prediction of dosimetric accuracy for VMAT plans using plan complexity parameters via machine learning. Med Phys 2019; 46:3823-3832. [PMID: 31222758 DOI: 10.1002/mp.13669] [Citation(s) in RCA: 42] [Impact Index Per Article: 8.4] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/13/2019] [Revised: 06/13/2019] [Accepted: 06/13/2019] [Indexed: 12/13/2022] Open
Abstract
PURPOSE The dosimetric accuracies of volumetric modulated arc therapy (VMAT) plans were predicted using plan complexity parameters via machine learning. METHODS The dataset consisted of 600 cases of clinical VMAT plans from a single institution. The predictor variables (n = 28) for each plan included complexity parameters, machine type, and photon beam energy. Dosimetric measurements were performed using a helical diode array (ArcCHECK), and the dosimetric accuracy of the passing rates for a 5% dose difference (DD5%) and gamma index of 3%/3 mm (γ3%/3 mm) were predicted using three machine learning models: regression tree analysis (RTA), multiple regression analysis (MRA), and neural networks (NNs). First, the prediction models were applied to 500 cases of the VMAT plans. Then, the dosimetric accuracy was predicted using each model for the remaining 100 cases (evaluation dataset). The error between the predicted and measured passing rates was evaluated. RESULTS For the 600 cases, the mean ± standard deviation of the measured passing rates was 92.3% ± 9.1% and 96.8% ± 3.1% for DD5% and γ3%/3 mm, respectively. For the evaluation dataset, the mean ± standard deviation of the prediction errors for DD5% and γ3%/3 mm was 0.5% ± 3.0% and 0.6% ± 2.4% for RTA, 0.0% ± 2.9% and 0.5% ± 2.4% for MRA, and -0.2% ± 2.7% and -0.2% ± 2.1% for NN, respectively. CONCLUSIONS NNs performed slightly better than RTA and MRA in terms of prediction error. These findings may contribute to increasing the efficiency of patient-specific quality-assurance procedures.
Collapse
Affiliation(s)
- Tomohiro Ono
- Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan
| | - Hideaki Hirashima
- Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan
| | - Hiraku Iramina
- Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan
| | - Nobutaka Mukumoto
- Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan
| | - Yuki Miyabe
- Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan
| | - Mitsuhiro Nakamura
- Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan.,Division of Medical Physics, Department of Information Technology and Medical Engineering, Human Health Sciences, Graduate School Medicine, Kyoto University, Kyoto, Japan
| | - Takashi Mizowaki
- Department of Radiation Oncology and Image-applied Therapy, Graduate School of Medicine, Kyoto University, Kyoto, 606-8507, Japan
| |
Collapse
|