Recently, a new type of radiochromic film, the EBT-XD film, has been introduced for high dose radiotherapy. The EBT-XD film contains the same structure as the EBT3 film but has a slightly different composition and a thinner active layer. This study benchmarks the EBT-XD against EBT3 film for 6 MV and 10 MV photon beams, as well as for 97.4 MeV and 148.2 MeV proton beams and 15–100 kV x-rays. Dosimetric and film reading characteristics, such as post irradiation darkening, film orientation effect, lateral response artifact (LRA), film sensitivity, energy and beam quality dependency were investigated. Furthermore, quenching effects in the Bragg peak were investigated for a single proton beam energy for both film types, in addition measurements were performed in a spread-out Bragg peak. EBT-XD films showed the same characteristic on film darkening as EBT3. The effects between portrait and landscape orientation were reduced by 3.1% (in pixel value) for EBT-XD compared to EBT3 at a dose of 2000 cGy. The LRA is reduced for EBT-XD films for all investigated dose ranges. The sensitivity of EBT-XD films is superior to EBT3 for doses higher than 500 cGy. In addition, EBT-XD showed a similar dosimetric response for photon and proton irradiation with low energy and beam quality dependency. A quenching effect of 10% was found for both film types. The slight decrease in the thickness of the active layer and different composition configuration of EBT-XD resulted in a reduced film orientation effect and LRA, as well as a sensitivity increase in high-dose regions for both photon and proton beams. Overall, the EBT-XD film improved regarding film reading characteristics and showed advantages in the high-dose region for photon and proton beams.

Purpose: To present the technical details of the runner‐up model in the open knowledge‐based planning (OpenKBP) challenge for the dose–volume histogram (DVH) stream. The model was designed to ensure simple and reproducible training, without the necessity of costly advanced generative adversarial network (GAN) techniques.Methods: The model was developed based on the OpenKBP challenge dataset, consisting of 200 and 40 head‐and‐neck patients for training and validation, respectively. The final model is a U‐Net with additional ResNet blocks between up‐ and down convolutions. The results were obtained by training the model with AdamW with the One Cycle scheduler. The loss function is a combination of the L1 loss with a feature loss, which uses a pretrained video classifier as a feature extractor. The performance was evaluated on another 100 patients in the OpenKBP test dataset. The DVH metrics of the test data were evaluated, where , and were calculated for the organs at risk (OARs) and , , and were computed for the target structures. DVH metric differences between predicted and true dose are reported in percentage.Results: The model achieved 2nd and 4th place in the DVH and dose stream of the OpenKBP challenge, respectively. The dose and DVH score were 2.62 ± 1.10 and 1.52 ± 1.06, respectively. Mean dose differences for the different structures and DVH parameters were within ±1%.Conclusion: This straightforward approach produced excellent results. It incorporated One Cycle Learning, ResNet, and feature‐based losses, which are common computer vision techniques.

Tools for auto-segmentation in radiotherapy are widely available, but guidelines for clinical implementation are missing. The goal was to develop a workflow for performance evaluation of three commercial auto-segmentation tools to select one candidate for clinical implementation. One hundred patients with six treatment sites (brain, head-and-neck, thorax, abdomen, and pelvis) were included. Three sets of AI-based contours for organs-at-risk (OAR) generated by three software tools and manually drawn expert contours were blindly rated for contouring accuracy. The dice similarity coefficient (DSC), the Hausdorff distance, and a dose/volume evaluation based on the recalculation of the original treatment plan were assessed. Statistically significant differences were tested using the Kruskal-Wallis test and the post-hoc Dunn Test with Bonferroni correction. The mean DSC scores compared to expert contours for all OARs combined were 0.80 ± 0.10, 0.75 ± 0.10, and 0.74 ± 0.11 for the three software tools. Physicians' rating identified equivalent or superior performance of some AI-based contours in head (eye, lens, optic nerve, brain, chiasm), thorax (e.g., heart and lungs), and pelvis and abdomen (e.g., kidney, femoral head) compared to manual contours. For some OARs, the AI models provided results requiring only minor corrections. Bowel-bag and stomach were not fit for direct use. During the interdisciplinary discussion, the physicians' rating was considered the most relevant. A comprehensive method for evaluation and clinical implementation of commercially available auto-segmentation software was developed. The in-depth analysis yielded clear instructions for clinical use within the radiotherapy department.

Objective. To establish an open framework for developing plan optimization models for knowledge-based planning (KBP). Approach. Our framework includes radiotherapy treatment data (i.e. reference plans) for 100 patients with head-and-neck cancer who were treated with intensity-modulated radiotherapy. That data also includes high-quality dose predictions from 19 KBP models that were developed by different research groups using out-of-sample data during the OpenKBP Grand Challenge. The dose predictions were input to four fluence-based dose mimicking models to form 76 unique KBP pipelines that generated 7600 plans (76 pipelines × 100 patients). The predictions and KBP-generated plans were compared to the reference plans via: the dose score, which is the average mean absolute voxel-by-voxel difference in dose; the deviation in dose-volume histogram (DVH) points; and the frequency of clinical planning criteria satisfaction. We also performed a theoretical investigation to justify our dose mimicking models. Main results. The range in rank order correlation of the dose score between predictions and their KBP pipelines was 0.50–0.62, which indicates that the quality of the predictions was generally positively correlated with the quality of the plans. Additionally, compared to the input predictions, the KBP-generated plans performed significantly better ( P < 0.05; one-sided Wilcoxon test) on 18 of 23 DVH points. Similarly, each optimization model generated plans that satisfied a higher percentage of criteria than the reference plans, which satisfied 3.5% more criteria than the set of all dose predictions. Lastly, our theoretical investigation demonstrated that the dose mimicking models generated plans that are also optimal for an inverse planning model. Significance. This was the largest international effort to date for evaluating the combination of KBP prediction and optimization models. We found that the best performing models significantly outperformed the reference dose and dose predictions. In the interest of reproducibility, our data and code is freely available.

Background: Deep learning‐based auto‐planning is an active research field; however, for some tasks a treatment planning system (TPS) is still required.Purpose: To introduce a deep learning‐based model generating deliverable DICOM RT treatment plans that can be directly irradiated by a linear accelerator (LINAC). The model was based on an encoder‐decoder network and can predict multileaf collimator (MLC) motion sequences for prostate VMAT radiotherapy.Methods: A total of 619 treatment plans from 460 patients treated for prostate cancer with single‐arc VMAT were included in this study. An encoder‐decoder network was trained using 465 clinical treatment plans and validated on 77 plans. The performance was analyzed on a separate test set of 77 treatment plans. Separate L1 losses were computed for the leaf and jaw positions as well as the monitor units, with the leaf loss being weighted by a factor of 100 before being added to the other losses. The generated treatment plans were recalculated in a treatment planning system and the dose‐volume metrics and gamma passing rates were compared to the original dose.Results: All generated treatment plans showed good agreement with the original data, with an average gamma passing rate (3%/3 mm) of 91.9 ± 7.1%. However, the coverage of the PTVs. was slightly lower for the generated plans (D_98% = 92.9 ± 2.6%) in comparison to the original plans (D_98% = 95.7 ± 2.2%). There was no significant difference in mean dose to the bladder between the predicted and original plan (D_mean of 28.0 ± 13.5 vs. 28.1 ± 13.3% of prescribed dose) or rectum (D_mean of 42.3 ± 7.4 vs. 42.6 ± 7.5%). The maximum dose to bladder was only slightly higher in the predicted plans (D2% of 100.7 ± 5.3 vs. 99.8 ± 4.0%) and for the rectum it was even lower (D2% of 100.5 ± 3.7 vs. 100.1 ± 4.3).Conclusions: The deep learning‐based model could predict MLC motion sequences in prostate VMAT plans, eliminating the need for sequencing inside a TPS, thus revolutionizing autonomous treatment planning workflows. This research completes the loop in deep learning‐based treatment planning processes, enabling more efficient workflows for real‐time or online adaptive radiotherapy.