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.

Model based patient pre-selection for intensity-modulated proton therapy (IMPT) using automated treatment planning and machine learning.

BACKGROUND AND PURPOSE: Patient selection for intensity modulated proton therapy (IMPT), using comparative photon therapy planning, is workload-intensive and time-consuming. Pre-selection aims at avoidance of manual IMPT planning for patients that are in the end ineligible. We investigated the use of machine learning together with automated IMPT treatment planning for pre-selection of head and neck cancer patients, and validated the methodology for the Dutch model based selection (MBS) approach. MATERIALS & METHODS: For forty-five head and neck patients with a previous MBS, an IMPT plan was generated with non-clinical, fully-automated planning. Dosimetric differences of these plans with the corresponding previously generated photon plans, and the outcomes of the former MBS, were used to train a Gaussian naïve Bayes classifier for MBS outcome prediction. During training, strong emphasis was placed on avoiding misclassification of IMPT eligible patients (i.e. false negatives). RESULTS: Pre-selection with the classifier resulted in 0 false negatives, 12 (27%) true negatives, 27 (60%) true positives, and only 6 (13%) false positive predictions. Using this pre-selection, the number of formal selection procedures with involved manual IMPT planning that resulted in a negative outcome could be reduced by 67%. CONCLUSION: With pre-selection, using machine learning and automated treatment planning, the percentage of patients with unnecessary manual IMPT planning for MBS could be drastically reduced, thereby saving costs, labor and time. With the developed approach, larger patient populations can be screened, and likely bias in pre-selection of patients can be mitigated by assisting the physician during patient pre-selection.

Large Field Alpha Irradiation Setup for Radiobiological Experiments.

The use of alpha particles irradiation in clinical practice has gained interest in the past years, for example with the advance of radionuclide therapy. The lack of affordable and easily accessible irradiation systems to study the cell biological impact of alpha particles hampers broad investigation. Here we present a novel alpha particle irradiation set-up for uniform irradiation of cell cultures. By combining a small alpha emitting source and a computer-directed movement stage, we established a new alpha particle irradiation method allowing more advanced biological assays, including large-field local alpha particle irradiation and cell survival assays. In addition, this protocol uses cell culture on glass cover-slips which allows more advanced microscopy, such as super-resolution imaging, for in-depth analysis of the DNA damage caused by alpha particles. This novel irradiation set-up provides the possibility to perform reproducible, uniform and directed alpha particle irradiation to investigate the impact of alpha radiation on the cellular level.

A 3D feature point tracking method for ion radiation.

A robust and computationally efficient algorithm for automated tracking of high densities of particles travelling in (semi-) straight lines is presented. It extends the implementation of (Sbalzarini and Koumoutsakos 2005) and is intended for use in the analysis of single ion track detectors. By including information of existing tracks in the exclusion criteria and a recursive cost minimization function, the algorithm is robust to variations on the measured particle tracks. A trajectory relinking algorithm was included to resolve the crossing of tracks in high particle density images. Validation of the algorithm was performed using fluorescent nuclear track detectors (FNTD) irradiated with high- and low (heavy) ion fluences and showed less than 1% faulty trajectories in the latter.