Addressing the Global Expertise Gap in Radiation Oncology: The Radiation Planning Assistant

Abstract

PURPOSE Automation, including the use of artificial intelligence, has been identified as a possible opportunity to help reduce the gap in access and quality for radiotherapy and other aspects of cancer care. The Radiation Planning Assistant (RPA) project was conceived in 2015 (and funded in 2016) to use automated contouring and treatment planning algorithms to support the efforts of oncologists in low- and middle-income countries, allowing them to scale their efforts and treat more patients safely and efficiently (to increase access). DESIGN In this review, we discuss the development of the RPA, with a particular focus on clinical acceptability and safety/risk across jurisdictions as these are important indicators for the successful future deployment of the RPA to increase radiotherapy availability and ameliorate global disparities in access to radiation oncology. RESULTS RPA tools will be offered through a webpage, where users can upload computed tomography data sets and download automatically generated contours and treatment plans. All interfaces have been designed to maximize ease of use and minimize risk. The current version of the RPA includes automated contouring and planning for head and neck cancer, cervical cancer, breast cancer, and metastases to the brain. CONCLUSION The RPA has been designed to bring high-quality treatment planning to more patients across the world, and it may encourage greater investment in treatment devices and other aspects of cancer treatment.

Artificial Intelligence–Based Radiotherapy Contouring and Planning to Improve Global Access to Cancer Care

“…The Radiation Planning Assistant (RPA) is a fully automated RT contouring and planning system that can provide high-quality RT solutions for low-resource centers around the world. 16 , 17 The RPA is designed to be agnostic to equipment and software at each site; as a remotely accessed website, it can be used for contouring and planning regardless of the local vendor. As of May 2023, the RPA has been US Food and Drug Administration (FDA) 510(k) cleared, not yet being marketed.…”

Clinical acceptability of automatically generated lymph node levels and structures of deglutition and mastication for head and neck radiation therapy

“…This is especially true if contours are not comprehensively edited after it is generated by the atlas or sparsely trained nnUnet model (the nnUnet predictions required only minor revisions; the atlas required more extensive revisions). These models for lymph nodes and swallowing and chewing structures are being integrated into our clinical practice as well as the Radiation Planning Assistant (RPA), a web-based, FDA 510 k cleared platform that provides contouring and planning to clinics with low resources [36] , [37] .…”

Validation of an automated contouring and treatment planning tool for pediatric craniospinal radiation therapy

“…The RPA architecture has been proven to be robust to downtime, thus providing a reliable service to resource-constrained clinics ( 29 ). Finally, the RPA aims to provide autocontouring and autoplanning tools at minimal (most likely zero) cost to resource-constrained clinics in LMICs yielding potential for broad impact ( 16 ).…”

“…The Radiation Planning Assistant (RPA) planning team has developed algorithms to automate contouring, treatment planning, and quality assurance for adult disease sites, including the cervix, chest wall, spine, head and neck, and whole brain (10)(11)(12)(13)(14)(15). Court et al recently summarized how the RPA was designed alongside leaders in resource-constrained countries to address the global expertise gap in radiation oncology (16). In short, clinicians import a patient CT scan with a planning prescription into the RPA webpage.…”

“…Court et al. recently summarized how the RPA was designed alongside leaders in resource-constrained countries to address the global expertise gap in radiation oncology ( 16 ). In short, clinicians import a patient CT scan with a planning prescription into the RPA webpage.…”