Automation and artificial intelligence in radiation therapy treatment planning

Abstract

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.

Artificial intelligence to unlock real‐world evidence in clinical oncology: A primer on recent advances

“…AI applications in radiation treatment planning have also advanced notably. These models expedite the treatment planning process by automating dose distribution predictions and beam angle and intensity selections, tasks that are traditionally manual and time‐consuming 90 . However, challenges such as ensuring model generalizability across different patient demographics and smooth integration into existing clinical workflows persist.…”

Artificial Intelligence and the future of radiotherapy planning: The Australian radiation therapists prepare to be ready

“…AI will expand the ability to rapidly create a personalised treatment for each patient and at each stage of their treatment journey. As clearly explained by Jones et al., 13 in their recently published commentary, this evolution represents not only an opportunity, but also cause for some concern both for the evolution of the current processes and the future of the multidisciplinary team (MDT). In particular, in countries like Australia where the radiation therapists (RTs) are largely responsible for both treatment planning and delivery, discussions are in progress in preparation for safely transitioning to automation with AI.…”

“…In particular, in countries like Australia where the radiation therapists (RTs) are largely responsible for both treatment planning and delivery, discussions are in progress in preparation for safely transitioning to automation with AI. In Jones et al., 13 table 1 summarises some key points considered crucial for this transition that include, among others, the establishment of a multi‐professional core group, which will include RTs, medical physicists (MP), radiation oncologists (ROs) but will also rely on the expertise of other professions (such as IT specialists and radiation engineers), that can be engaged in the deployment of these tools. This is paramount to ensure that the same high‐level quality assurance and control, as currently used in human‐based processes, can be developed in AI‐driven ones keeping in mind that the ethics and standards implications, ranging from data sourcing reliability to build the algorithms to the need of AI‐dedicated regulation and governance, are still not resolved.…”

“…AI has the potential to dictate treatment choices from diagnosis to plan preparation, and all the way to treatment evaluation, by the incorporation of all of the patients' related data in an automated way. Jones et al 13 point out that this shift is bound to have a large impact also on the roles and responsibilities of the RTs, along with the whole MD team. We envision that the MDT will have to re-think or re-develop some of the current tasks, and even relationships, among the different craft groups to adapt to the changes introduced by AI tools.…”

“…Education will be essential, both in academic and clinical settings, for practitioners to ensure adequate competence with these new developments, currently perceived mostly as a 'black box'. 6 An important point discussed by Jones et al 13 is maintaining the expertise and skills that allow a critical oversight when these new automated tools are introduced to the clinic. It will be a balancing act, however, to make sure that a more traditional knowledge of planning tasks is still transmitted to new staff in the workforce while also promoting the understanding and the safe use of AI advanced tools.…”