Automation and artificial intelligence (AI) is already possible for many radiation therapy planning and treatment processes with the aim of improving workflows and increasing efficiency in radiation oncology departments. Currently, AI technology is advancing at an exponential rate, as are its applications in radiation oncology. This commentary highlights the way AI has begun to impact radiation therapy treatment planning and looks ahead to potential future developments in this space. Historically, radiation therapist's (RT's) role has evolved alongside the adoption of new technology. In Australia, RTs have key clinical roles in both planning and treatment delivery and have been integral in the implementation of automated solutions for both areas. They will need to continue to be informed, to adapt and to transform with AI technologies implemented into clinical practice in radiation oncology departments. RTs will play an important role in how AI‐based automation is implemented into practice in Australia, ensuring its application can truly enable personalised and higher‐quality treatment for patients. To inform and optimise utilisation of AI, research should not only focus on clinical outcomes but also AI's impact on professional roles, responsibilities and service delivery. Increased efficiencies in the radiation therapy workflow and workforce need to maintain safe improvements in practice and should not come at the cost of creativity, innovation, oversight and safety.

Within the professions of radiation therapy and medical imaging, clinician led research activity is becoming more prevalent. However, more is needed. A key component of continuing to develop professional groups who are both research active and producing high quality clinical research, is research mentoring. The authors of this paper share a common interest in enhancing research capacity through research mentoring within the health workforce, and came together to run a workshop on this issue at the 11th Annual Scientific Meeting of Medical Imaging and Radiation Therapy (ASMMIRT 2016) conference in Brisbane. Theory, clinical insights and issues regarding research mentoring were raised in the workshop as were the benefits of having dedicated research positions embedded within the health workforce to help provide support and build capacity. Key elements from this workshop are shared within this article, with the objective to encourage clinicians and clinical researchers to invest the time and effort into seeking and providing good quality research mentoring. A single service example is used to demonstrate how this can lead to enhanced research engagement and productivity.

Introduction Three‐dimensional printing technology has the potential to streamline custom bolus production in radiotherapy. This study evaluates the volumetric, dosimetric and cost differences between traditional wax and 3D printed versions of nose bolus. Method Nose plaster impressions from 24 volunteers were CT scanned and planned. Planned virtual bolus was manufactured in wax and created in 3D print (100% and 18% shell infill density) for comparison. To compare volume variations and dosimetry, each constructed bolus was CT scanned and a plan replicating the reference plan fields generated. Bolus manufacture time and material costs were analysed. Results Mean volume differences between the virtual bolus (VB) and wax, and the VB and 18% and 100% 3D shells were −3.05 ± 11.06 cm³, −1.03 ± 8.09 cm³ and 1.31 ± 2.63 cm³, respectively. While there was no significant difference for the point and mean doses between the 100% 3D shell filled with water and the VB plans (P> 0.05), the intraclass coefficients for these dose metrics for the 100% 3D shell filled with wax compared to VB doses (0.69–0.96) were higher than those for the 18% and 100% 3D shell filled with water and the wax (0.48–0.88). Average costs for staff time and materials were higher for the wax ($138.54 and $20.49, respectively) compared with the 3D shell prints ($10.58 and $13.87, respectively). Conclusion Three‐dimensional printed bolus replicated the VB geometry with less cost for manufacture than wax bolus. When shells are printed with 100% infill density, 3D bolus dosimetrically replicates the reference plan.

Introduction: A challenge in implementing deformable image registration (DIR) in radiation therapy planning is effectively communicating registration accuracy to the radiation oncologist. This study aimed to evaluate the MIM® quality assurance (QA) tool for rating DIR accuracy.Methods: Retrospective DIR was performed on CT images for 35 head and neck cancer patients. The QA tool was used to rate DIR accuracy as good, fair or bad. Thirty registered patient images were assessed independently by three RTs and a further five patients assessed by five RTs. Ratings were evaluated by comparison of Hausdorff Distance (HD), Mean Distance to Agreement (MDA), Dice Similarity Coefficients (DSC) and Jacobian determinants for parotid and mandible subregions on the two CTs post‐DIR. Inter‐operator reliability was assessed using Krippendorff's alpha coefficient (KALPA). Rating time and volume measures for each rating were also calculated.Results: Quantitative metrics calculated for most anatomical subregions reflected the expected trend by registration accuracy, with good obtaining the most ideal values on average (HD = 7.50 ± 3.18, MDA = 0.64 ± 0.47, DSC = 0.90 ± 0.07, Jacobian = 0.95 ± 0.06). Highest inter‐operator reliability was observed for good ratings and within the parotids (KALPA 0.66–0.93), whilst ratings varied the most in regions of dental artefact. Overall, average rating time was 33 minutes and the least commonly applied rating by volume was fair.Conclusion: Results from qualitative and quantitative data, operator rating differences and rating time suggest highlighting only bad regions of DIR accuracy and implementing clinical guidelines and RT training for consistent and efficient use of the QA tool.

Introduction: To implement the modulated arc total body irradiation (MATBI) technique within the existing infrastructure of a radiation oncology department. The technique needed to treat paediatric patients of all ages, some of whom would require general anaesthesia (GA).Methods: The MATBI technique required minor modifications to be incorporated within existing departmental infrastructure. Ancillary equipment essential to the technique were identified and in some cases custom designed to meet health and safety criteria. GA equipment was also considered. To evaluate the effectiveness of the implemented technique, an audit of the cases clinically treated was conducted.Results: A motorised treatment couch was designed to allow the patient to be positioned in stabilisation equipment at a height, then lowered to the floor to accommodate source‐to‐skin‐distances from 180 cm to 198 cm to treat the fixed 40 cm × 40 cm field size. Treatment couch design also facilitated positioning of the bespoke two‐part spoiler. While organ at risk dose is limited using a beam weight optimisation technique, the dose is further reduced using compensators placed close to the patient's skin on a 3D printed custom‐made support bridge. A digital radiography system is used to verify compensator position. Fifteen patients have been treated to date for various diseases using a variety of dose fractionations ranging from 2 Gy in a single fraction to 12 Gy in 6 fractions. Five patients have required GA due to age or behavioural issues.Conclusion: The modified MATBI technique and the equipment required for treatment delivery has been found to be well tolerated by all patients.

Introduction Various techniques for whole breast radiation therapy (WBRT) have been reported to increase dose to contralateral tissues. Heart dose is of critical importance as there is no apparent dose threshold below which there is no risk. The aim of this study was to compare planning techniques for WBRT that achieves the best target dosimetry and lowest organ at risk (OAR) dose. Methods Thirty early-stage whole breast patient datasets, 15 each left- and right-sided cases, were retrospectively selected. Five techniques were generated for each data set: three-dimensional conformal radiation therapy (3DCRT), hybrid intensity modulated radiation therapy (HYI), hybrid volumetric modulated arc therapy (VMAT) - (HYV), reduced arc VMAT - bowtie (BT), and BT flattening filter free (FFF) - (BTFFF). Plan goals and OARs were evaluated and compared between techniques. Results BT had the highest median conformity index (CI) values (0.82, IQR: 0.80-0.85 left and 0.83, IQR 0.80-0.86 right). BT recorded lower mean heart doses (median value 1.19Gy, IQR: 0.90-1.55), and BTFFF recorded lower heart V2.5 (Gy), V5 (Gy); median 3.96% (IQR: 2.90-6.80) and 0.90% (IQR: 0.50-1.50) respectively for left-sided patients. There was a statistically significant difference in all ipsilateral lung measures, (p < 0.001) with BTFFF producing significantly lower doses across all measures: mean, V5 (Gy), V10 (Gy) and V20 (Gy). Conclusion Overall BT and BTFFF techniques produced lower OAR doses and equivalent PTV coverage for WBRT. BT and BTFFF techniques increased contralateral lung and breast doses; however, these were within prescribed tolerances and comparable to results published in the literature.