A national perspective about the current work situation at modern radiotherapy departments

Clinical assessment of deep learning-based uncertainty maps in lung cancer segmentation

Objective. Prior to radiation therapy planning, accurate delineation of gross tumour volume (GTVs) and organs at risk (OARs) is crucial. In the current clinical practice, tumour delineation is performed manually by radiation oncologists, which is time-consuming and prone to large inter-observer variability. With the advent of deep learning (DL) models, automated contouring has become possible, speeding up procedures and assisting clinicians. However, these tools are currently used in the clinic mostly for contouring OARs, since these systems are not reliable yet for contouring GTVs. To improve the reliability of these systems, researchers have started exploring the topic of probabilistic neural networks. However, there is still limited knowledge of the practical implementation of such networks in real clinical settings.Approach. In this work, we developed a 3D probabilistic system that generates DL-based uncertainty maps for lung cancer CT segmentations. We employed the Monte Carlo (MC) dropout technique to generate probabilistic and uncertainty maps, while the model calibration was evaluated by using reliability diagrams. A clinical validation was conducted in collaboration with a radiation oncologist to qualitatively assess the value of the uncertainty estimates. We also proposed two novel metrics, namely mean uncertainty (MU) and relative uncertainty volume (RUV), as potential indicators for clinicians to assess the need for independent visual checks of the DL-based segmentation. Main results. Our study showed that uncertainty mapping effectively identified cases of under or over-contouring. Although the overconfidence of the model, a strong correlation was observed between the clinical opinion and MU metric. Moreover, both MU and RUV revealed high AUC values in discretising between low and high uncertainty cases.Significance. Our study is one of the first attempts to clinically validate uncertainty estimates in DL-based contouring. The two proposed metrics exhibited promising potential as indicators for clinicians to independently assess the quality of tumour delineation.

Resource planning principles for the radiotherapy process using simulations applied to a longer vacation period use case

PURPOSE

Radiotherapy (RT) resources need to be used wisely to balance workload and patient throughput. There are no known strategies on how to plan resource use around longer vacation periods to avoid patient waiting times. We created a simulation model over the RT workflow to evaluate different scenarios for this purpose.

MATERIALS AND METHODS

The simulation model mimics a large modern RT department in Sweden. It was based on real data on patient referral patterns and resource use extracted from clinical systems (3666 treatment courses). Workshops with managers and staff were held to investigate nine different scenarios for the summer vacation period including one scenario to validate the model. Different capacity reductions, vacation period lengths and timing of the vacation periods between the preparatory part of the RT workflow and the treatment part were evaluated.

RESULTS

For an eight-week period, resource utilization was predicted to be high both before and after the vacation period regardless of timing. However, more patients would be waiting with completed preparations with simultaneous vacation periods than when the preparatory part started one-two weeks prior to the treatment part. With shorter vacation periods, treatment would require overtime during the vacation period with higher levels of patients waiting compared to an eight-week scenario.

CONCLUSIONS

Our proposed strategy aided managers to identify a preferred scenario for the summer vacation period with the preparatory part starting one-two weeks prior to the treatment part for an eight-week vacation period. This can help other RT departments to plan for similar situations.

Linear accelerator utilization: Concept and tool to aid the scheduling of patients for radiotherapy

Background and purpose

Resources in radiotherapy (RT) need to be used effectively to meet the current clinical demand. The aim of this data-driven study is to identify temporal trends in the scheduling of patients for RT and to develop a tool for a visual overview of future scheduling levels.

Material and methods

Scheduling data at an eight-linac modern RT department in Sweden were collected twice daily for planned and observed linac use in 2018-2020. Information was retrieved each day for the present (Day 0) and the forthcoming 100 weekdays with total linac utilization rates (LURs) calculated for two activity categories: treatment and non-treatment. An in-house tool based on the LUR concept, database queries from the oncology information system (OIS)/automatic calculations was developed and evaluated by RT managers and scheduling staff (n = 10).

Results

Overall median LURs were 87%/89% (planned/observed; p < 0.01) with more frequent and larger daily increase for non-treatment activities compared with treatment activities. LUR increased with shorter planning horizons and reached 100% for fully-operating linacs ≈3 weeks before Day 0. The tool was reported by 88% to ease the work and to contribute towards an even scheduling of patients (responses: 8/10).

Conclusion

Alterations from a planned RT schedule occurs frequently. Having a tool that helps to reduce the abundance of booking information into clinically relevant overviews promise to increase the understanding of present and future scheduling levels. Our proposed concept and tool suggest that this is a feasible approach to schedule patients for RT more evenly.