The Emergence of Artificial Intelligence within Radiation Oncology Treatment Planning

Abstract

<b><i>Background:</i></b> The future of artificial intelligence (AI) heralds unprecedented change for the field of radiation oncology. Commercial vendors and academic institutions have created AI tools for radiation oncology, but such tools have not yet been widely adopted into clinical practice. In addition, numerous discussions have prompted careful thoughts about AI’s impact upon the future landscape of radiation oncology: How can we preserve innovation, creativity, and patient safety? When will AI-based tools be widely adopted into the clinic? Will the need for clinical staff be reduced? How will these devices and tools be developed and regulated? <b><i>Summary:</i></b> In this work, we examine how deep learning, a rapidly emerging subset of AI, fits into the broader historical context of advancements made in radiation oncology and medical physics. In addition, we examine a representative set of deep learning-based tools that are being made available for use in external beam radiotherapy treatment planning and how these deep learning-based tools and other AI-based tools will impact members of the radiation treatment planning team. <b><i>Key Messages:</i></b> Compared to past transformative innovations explored in this article, such as the Monte Carlo method or intensity-modulated radiotherapy, the development and adoption of deep learning-based tools is occurring at faster rates and promises to transform practices of the radiation treatment planning team. However, accessibility to these tools will be determined by each clinic’s access to the internet, web-based solutions, or high-performance computing hardware. As seen by the trends exhibited by many technologies, high dependence on new technology can result in harm should the product fail in an unexpected manner, be misused by the operator, or if the mitigation to an expected failure is not adequate. Thus, the need for developers and researchers to rigorously validate deep learning-based tools, for users to understand how to operate tools appropriately, and for professional bodies to develop guidelines for their use and maintenance is essential. Given that members of the radiation treatment planning team perform many tasks that are automatable, the use of deep learning-based tools, in combination with other automated treatment planning tools, may refocus tasks performed by the treatment planning team and may potentially reduce resource-related burdens for clinics with limited resources.

Varian ethos online adaptive radiotherapy for prostate cancer: Early results of contouring accuracy, treatment plan quality, and treatment time

“…11,12 Until recently, the technical and logistical challenges of OART made it practically infeasible for most radiotherapy centers. The introduction of artificial intelligence (AI) 13,14 and graphics processing unit (GPU) based calculation engines [15][16][17] have allowed for the many steps in an online adaptive workflow to be performed in the timeframe required for OART. The Varian Ethos system (Varian Medical Systems, Palo Alto, CA) was recently developed as a completely self -contained online adaptive solution, and has been reported to be capable of performing adaptive treatments within 15-20 min.…”

Quantum deep reinforcement learning for clinical decision support in oncology: application to adaptive radiotherapy

“…Similarly, an extensive sensitivity analysis of the features will be necessary for better representation of the response prediction, range of variability, and the uncertainty estimates of our framework. In terms of application, our framework should be used in a complementary fashion and consistent with other clinical tools such as the RT treatment planner, plan optimizer, and image guidance system 29 for clinical implementation.…”

“…For comparison, we trained and validated three frameworks: DRL, qDRL trained on a Qiskit quantum computing simulator 27 , and qDRL trained on an IBM quantum (IBMQ) 16 Melbourne 15-qubit processor 28 . We trained our framework on 67 stage III NSCLC patient datasets from a single institution 13 and validated our framework on an independent multi-institutional cohort of 174 NSCLC patients treated under the Radiation Therapy Oncology Group- (RTOG-) 0617 protocol 29 .…”

Clinical implementation of automated treatment planning for whole‐brain radiotherapy

“…While their WBRT planning does not allow a patient‐specific plan customization, the presented study allows for a physician to select either traditional WBRT or scalp sparing WBRT with treatment extent to C1 or C2 vertebrae. Many studies have previously focused on automating individual tasks in the treatment planning process, 1 , 2 , 5 , 15 , 16 , 17 , 18 yet very few offer end‐to‐end solutions which include automation of target definition, normal tissue contouring, beam selection, and dose optimization and calculation. Trained with clinical WBRT cases, the deep learning network could generate treatment fields comparable to clinical fields.…”