The Radiotherapy (RT) process, from planning to treatment delivery, is becoming increasingly complex. It involves extensive interaction between different professionals and machines. It also requires high precision among all steps of the path, which are usually labor-intensive and time-consuming.
Several new approaches have been developed to deal with the challenges of treatment planning, just as numerous quality assurance tasks are now performed to ensure quality and to detect and prevent possible errors in the care process.
For example, recent developments in artificial intelligence (AI) provide potential tools to the radiation oncology community to improve the efficiency and performance within the quality assurance process. Tools using AI have the power to improve the efficiency, accuracy, and quality assurance of radiotherapy. Such tools can be applied at all stages of a patient’s treatment, from diagnosis to treatment and follow-up, bringing unprecedented improvements in automation.
The RT treatment process can be categorized into imaging, target and organs-at-risk (OARs) segmentation, treatment plan generation, onboard imaging, treatment delivery, and quality assurance (QA) checks. Automation will typically follow the same workflow, with each task automated separately.
The main uncertainty in radiotherapy treatment planning for most tumor locations has been shown to be in the target volume contour, which can lead to systematic errors in dose administration and affect local disease control. And bearing in mind that manual segmentation (or contouring) of the target and OARs is a time-consuming and highly subjective task that lies at the core of RT planning. By using the automatic contouring tool, it is possible to drastically reduce the time required to create OAR contours for a patient while also improving contour consistency across clinicians.
The aim of automation of treatment planning in Radiotherapy is standardization and efficiency. To reduce undesired inter-patient and inter-institution variations and while increasing the efficiency and thus decreasing time to treatment.
At the same time, it is now well recognized that large numbers of patients and often limited resources in clinics to treatment planning can conflict with the pursuit of high-quality and individualized treatments. The potential to increase productivity, without losing quality becomes a central pillar when using automation. Currently, several fully automated workflows for generating plans have been developed, including automatic segmentation of organs at risk, automatic configuration of beams with gantry optimization and collimator angles and automatic creation objective functions.
Knowledge-based planning (KBP), which uses data from previous good cases to inform current patient planning parameters, has emerged as a powerful tool to accelerate the process of RT planning. And it´s use has become even more important when we need to plan high-precision treatment procedures such as Stereotaxic Body RT (SBRT) which often takes hours or even days of human effort to plan.
This process improvements and implementation of task-specific tools improved the timeliness of patient treatments, reducing the overall planning time from image acquisition to treatment.
In conclusion, integrating AI in RT processes may allow radiation oncologists to spend more time on patient consultation, while optimizing and improving the efficiency of the Radiotherapy process. It will also give dosimetrists, physicists and RTTs the possibility of spending more time learning new techniques and continuing their training and upskilling process.
Ana Raquel Coutinho
ePlanning Service Delivery Manager