A generalized model for monitor units determination in ocular proton therapy using machine learning: A proof-of-concept study.

Objective.Determining and verifying the number of monitor units is crucial to achieving the desired dose distribution in radiotherapy and maintaining treatment efficacy. However, current commercial treatment planning system(s) dedicated to ocular passive eyelines in proton therapy do not provide the number of monitor units for patient-specific plan delivery. Performing specific pre-treatment field measurements, which is time and resource consuming, is usually gold-standard practice. This proof-of-concept study reports on the development of a multi-institutional-based generalized model for monitor units determination in proton therapy for eye melanoma treatments.Approach.To cope with the small number of patients being treated in proton centers, three European institutes participated in this study. Measurements data were collected to address output factor differences across the institutes, especially as function of field size, spread-out Bragg peak modulation width, residual range, and air gap. A generic model for monitor units prediction using a large number of 3748 patients and broad diversity in tumor patterns, was evaluated using six popular machine learning algorithms: (i) decision tree; (ii) random forest, (iii) extra trees, (iv) K-nearest neighbors, (v) gradient boosting, and (vi) the support vector regression. Features used as inputs into each machine learning pipeline were: Spread-out Bragg peak width, range, air gap, fraction and calibration doses. Performance measure was scored using the mean absolute error, which was the difference between predicted and real monitor units, as collected from institutional gold-standard methods.Main results.Predictions across algorithms were accurate within 3% uncertainty for up to 85.2% of the plans and within 10% uncertainty for up to 98.6% of the plans with the extra trees algorithm.Significance.A proof-of-concept of using machine learning-based generic monitor units determination in ocular proton therapy has been demonstrated. This could trigger the development of an independent monitor units calculation tool for clinical use.

3D Dosimetry Based on LiMgPO4 OSL Silicone Foils: Facilitating the Verification of Eye-Ball Cancer Proton Radiotherapy.

A direct verification of the three-dimensional (3D) proton clinical treatment plan prepared for tumor in the eyeball, using the Eclipse Ocular Proton Planning system (by Varian Medical Systems), has been presented. To achieve this, a prototype of the innovative two-dimensional (2D) circular silicone foils, made of a polymer with the embedded optically stimulated luminescence (OSL) material in powder form (LiMgPO4), and a self-developed optical imaging system, consisting of an illuminating light source and a high-sensitive CCD camera has been applied. A specially designed lifelike eyeball phantom has been used, constructed from 40 flat sheet LMP-based silicone foils stacked and placed together behind a spherical phantom made by polystyrene, all to reflect the curvature of the real eyeball. Two-dimensional OSL signals were captured and further analyzed from each single silicone foil after irradiation using a dedicated patient collimator and a 58.8 MeV modulated proton beam. The reconstructed 3D proton depth dose distribution matches very well with the clinical treatment plan, allowing for the consideration of the new OSL system for further 3D dosimetry applications within the proton radiotherapy area.

Experimental assessment of inter-centre variation in stopping-power and range prediction in particle therapy.

PURPOSE: Experimental assessment of inter-centre variation and absolute accuracy of stopping-power-ratio (SPR) prediction within 17 particle therapy centres of the European Particle Therapy Network. MATERIAL AND METHODS: A head and body phantom with seventeen tissue-equivalent materials were scanned consecutively at the participating centres using their individual clinical CT scan protocol and translated into SPR with their in-house CT-number-to-SPR conversion. Inter-centre variation and absolute accuracy in SPR prediction were quantified for three tissue groups: lung, soft tissues and bones. The integral effect on range prediction for typical clinical beams traversing different tissues was determined for representative beam paths for the treatment of primary brain tumours as well as lung and prostate cancer. RESULTS: An inter-centre variation in SPR prediction (2σ) of 8.7%, 6.3% and 1.5% relative to water was determined for bone, lung and soft-tissue surrogates in the head setup, respectively. Slightly smaller variations were observed in the body phantom (6.2%, 3.1%, 1.3%). This translated into inter-centre variation of integral range prediction (2σ) of 2.9%, 2.6% and 1.3% for typical beam paths of prostate-, lung- and primary brain-tumour treatments, respectively. The absolute error in range exceeded 2% in every fourth participating centre. The consideration of beam hardening and the execution of an independent HLUT validation had a positive effect, on average. CONCLUSION: The large inter-centre variations in SPR and range prediction justify the currently clinically used margins accounting for range uncertainty, which are of the same magnitude as the inter-centre variation. This study underlines the necessity of higher standardisation in CT-number-to-SPR conversion.

Characterization of the HollandPTC proton therapy beamline dedicated to uveal melanoma treatment and an interinstitutional comparison.

PURPOSE: Eye-dedicated proton therapy (PT) facilities are used to treat malignant intraocular lesions, especially uveal melanoma (UM). The first commercial ocular PT beamline from Varian was installed in the Netherlands. In this work, the conceptual design of the new eyeline is presented. In addition, a comprehensive comparison against five PT centers with dedicated ocular beamlines is performed, and the clinical impact of the identified differences is analyzed. MATERIAL/METHODS: The HollandPTC eyeline was characterized. Four centers in Europe and one in the United States joined the study. All centers use a cyclotron for proton beam generation and an eye-dedicated nozzle. Differences among the chosen ocular beamlines were in the design of the nozzle, nominal energy, and energy spectrum. The following parameters were collected for all centers: technical characteristics and a set of distal, proximal, and lateral region measurements. The measurements were performed with detectors available in-house at each institution. The institutions followed the International Atomic Energy Agency (IAEA) Technical Report Series (TRS)-398 Code of Practice for absolute dose measurement, and the IAEA TRS-398 Code of Practice, its modified version or International Commission on Radiation Units and Measurements Report No. 78 for spread-out Bragg peak normalization. Energy spreads of the pristine Bragg peaks were obtained with Monte Carlo simulations using Geant4. Seven tumor-specific case scenarios were simulated to evaluate the clinical impact among centers: small, medium, and large UM, located either anteriorly, at the equator, or posteriorly within the eye. Differences in the depth dose distributions were calculated. RESULTS: A pristine Bragg peak of HollandPTC eyeline corresponded to the constant energy of 75 MeV (maximal range 3.97 g/cm2 in water) with an energy spread of 1.10 MeV. The pristine Bragg peaks for the five participating centers varied from 62.50 to 104.50 MeV with an energy spread variation between 0.10 and 0.70 MeV. Differences in the average distal fall-offs and lateral penumbrae (LPs) (over the complete set of clinically available beam modulations) among all centers were up to 0.25 g/cm2 , and 0.80 mm, respectively. Average distal fall-offs of the HollandPTC eyeline were 0.20 g/cm2 , and LPs were between 1.50 and 2.15 mm from proximal to distal regions, respectively. Treatment time, around 60 s, was comparable among all centers. The virtual source-to-axis distance of 120 cm at HollandPTC was shorter than for the five participating centers (range: 165-350 cm). Simulated depth dose distributions demonstrated the impact of the different beamline characteristics among institutions. The largest difference was observed for a small UM located at the posterior pole, where a proximal dose between two extreme centers was up to 20%. CONCLUSIONS: HollandPTC eyeline specifications are in accordance with five other ocular PT beamlines. Similar clinical concepts can be applied to expect the same high local tumor control. Dosimetrical properties among the six institutions induce most likely differences in ocular radiation-related toxicities. This interinstitutional comparison could support further research on ocular post-PT complications. Finally, the findings reported in this study could be used to define dosimetrical guidelines for ocular PT to unify the concepts among institutions.

Harmonization of proton treatment planning for head and neck cancer using pencil beam scanning: first report of the IPACS collaboration group.

Background and purpose: A collaborative network between proton therapy (PT) centres in Trento in Italy, Poland, Austria, Czech Republic and Sweden (IPACS) was founded to implement trials and harmonize PT. This is the first report of IPACS with the aim to show the level of harmonization that can be achieved for proton therapy planning of head and neck (sino-nasal) cancer.Methods: CT-data sets of five patients were included. During several face-to-face and online meetings, a common treatment planning protocol was developed. Each centre used its own treatment planning system (TPS) and planning approach with some restrictions specified in the treatment planning protocol. In addition, volumetric modulated arc therapy (VMAT) photon plans were created.Results: For CTV1, the average Dmedian was 59.3 ± 2.4 Gy(RBE) for protons and 58.8 ± 2.0 Gy(RBE) for VMAT (aim was 56 Gy(RBE)). For CTV2, the average Dmedian was 71.2 ± 1.0 Gy(RBE) for protons and 70.6 ± 0.4 Gy(RBE) for VMAT (aim was 70 Gy(RBE)). The average D2% for the spinal cord was 25.1 ± 8.5 Gy(RBE) for protons and 47.6 ± 1.4 Gy(RBE) for VMAT. The average D2% for chiasm was 46.5 ± 4.4 Gy(RBE) for protons and 50.8 ± 1.4 Gy(RBE) for VMAT, respectively. Robust evaluation was performed and showed the least robust plans for plans with a low number of beams.Discussion: In conclusion, several influences on harmonization were identified: adherence/interpretation to/of the protocol, available technology, experience in treatment planning and use of different beam arrangements. In future, all OARs that should be included in the optimization need to be specified in order to further harmonize treatment planning.

Profile of European proton and carbon ion therapy centers assessed by the EORTC facility questionnaire.

BACKGROUND: We performed a survey using the modified EORTC Facility questionnaire (pFQ) to evaluate the human, technical and organizational resources of particle centers in Europe. MATERIAL AND METHODS: The modified pFQ consisted of 235 questions distributed in 11 sections accessible on line on an EORTC server. Fifteen centers from 8 countries completed the pFQ between May 2015 and December 2015. RESULTS: The average number of patients treated per year and per particle center was 221 (range, 40-557). The majority (66.7%) of centers had pencil beam or raster scanning capability. Four (27%) centers were dedicated to eye treatment only. An increase in the patients-health professional FTE ratio was observed for eye tumor only centers when compared to other centers. All centers treated routinely chordomas/chondrosarcomas, brain tumors and sarcomas but rarely breast cancer. The majority of centers treated pediatric cases with particles. Only a minority of the queried institutions treated non-static targets. CONCLUSIONS: As the number of particle centers coming online will increase, the experience with this treatment modality will rise in Europe. Children can currently be treated in these facilities in a majority of cases. The majority of these centers provide state of the art particle beam therapy.