---

The Departments of Medical Physics and Oncology at the University of the Free State (UFS), together with Universitas Academic Hospital, was the first clinical site worldwide to integrate artificial intelligence (AI) into cancer treatment planning. In adopting the Radiation Planning Assistant (RPA), a web-based AI platform developed at MD Anderson Cancer Center in Houston, Texas, they are leading this groundbreaking initiative to assist in the creation of radiotherapy treatment plans.

Under the leadership of Dr William Shaw, Senior Lecturer and Deputy Manager in the Department of Medical Physics, the department has built a long-standing academic partnership with Prof Laurence Court and his team at the MD Anderson Cancer Center (MDACC) — a collaboration that is now yielding transformative results.

“The introduction and clinical integration of the RPA at the UFS and Universitas Hospital represents a major advancement for oncology services — both regionally and nationally. It signifies the transition from research collaboration to real-world application, where artificial intelligence is being used to improve access to safe, high-quality cancer care. The early clinical implementation of the technology — including the treatment of nearly 50 patients to date — has positioned the Bloemfontein teams as global leaders in the responsible clinical use of AI in radiotherapy,” says Dr Shaw.

According to him, this is a significant advancement for cancer care in South Africa. It reflects the UFS and Universitas Hospital’s commitment to safe innovation, rigorous clinical standards, and patient-centred care. Through their leadership, this technology is not only improving efficiency and access — it is raising the standard of care for cancer patients across the province and beyond.

The success of the RPA in Bloemfontein serves as a model for broader health system innovation. The experience gained through this implementation provides a foundation for the safe, phased rollout of similar systems in other provinces.

Prof Vasu Reddy, Deputy Vice-Chancellor for Research and Internationalisation at the UFS, says: “We extend our congratulations to our colleagues for their exemplary collaborative achievements. Your pioneering work represents the transformative power of multidisciplinary research in advancing medical science and improving patient outcomes.”

While the RPA was initially implemented at Universitas Hospital for the treatment of cervix cancer — which represents the largest proportion of patients receiving radiotherapy at the institution. It has since been applied and tested for other cancers including across a broader range of clinical indications. These include breast cancer, head and neck cancers, and primary brain tumours. With ongoing institutional input, including from the teams at Universitas Hospital and the UFS, the system holds significant promise for broader application across nearly all major tumour types treated with external beam radiotherapy.

Streamlining treatment planning

“Designed to support clinical teams in both high- and low-resource settings, the RPA helps streamline one of the most time-consuming steps in cancer care: the formulation of patient-specific radiation treatment plans. The RPA is a cloud-based software platform designed to support radiotherapy services by automating key components of the treatment planning process,” explains Dr Shaw.

“It enables the consistent production of high-quality radiotherapy plans while reducing the demand on highly specialised clinical staff. The process begins with the acquisition of a planning CT scan, which serves as the sole imaging input to the RPA.”

Once the CT dataset has been captured, he continues, it is uploaded to the RPA platform via a secure web interface. The user then completes a short digital form, providing basic administrative details and selecting the treatment site. No additional imaging modalities are required, but important information on treatment plan specifications detailing the individual patients’ characteristics are specified by specialised clinical staff. After this process, the RPA uses advanced machine learning algorithms to automatically identify and delineate both tumour volumes and critical normal tissues (organs-at-risk). Following the completion of the contouring process, the system proceeds to automatically generate a full radiotherapy treatment plan.

Contributes to better patient care

As cancer incidence rises across low- and middle-income countries, the innovation and leadership shown by those involved, offer a compelling model for how academic medical centres can respond with agility, scientific rigour, and global solidarity. It demonstrates how international partnerships can bring cutting-edge technologies to the frontlines of healthcare — and make them work, in real clinics, for real patients

“Our aim is to use artificial intelligence not as a shortcut, but as a tool to standardise, scale, and improve cancer care in places where the need is greatest,” says Dr Shaw. “The RPA enhances the quality, consistency, and timeliness of cancer treatment in radiotherapy settings — particularly in environments where clinical capacity is limited — by automating the most labour-intensive components of the treatment planning process.

“These benefits translate into improved tumor control, fewer complications, and a more efficient and responsive treatment experience for patients across a wide range of clinical settings,” says Dr Shaw.

This work was supported by the Nuclear Technologies in Medicine and the Biosciences Initiative (NTeMBI). NTeMBI is a national technology platform developed and managed by the South African Nuclear Energy Corporation (Necsa) and funded by the Technology Innovation Agency (TIA).

The impact is immediate and meaningful for cancer patients as the technology enables faster access to well-constructed, evidence-based treatment plans that are reviewed and refined by experts. This translates to more timely care, fewer unplanned treatment interruptions, and improved protection of normal tissues — resulting in fewer side effects and better overall outcomes.

Encouraged by these successes, the Department of Oncology, led by Prof Alicia Sherriff, has joined the initiative as an active clinical partner. This multi-disciplinary collaboration has laid the foundation for further research and innovation at the interface of medical physics, oncology, and data science.

Beyond improving clinical workflows and expanding access to radiotherapy in resource-constrained settings, the RPA has wider significance. By providing standardised treatment plans, the platform has the potential to reduce inter-institutional variability, helping to establish consistent radiotherapy protocols across clinical trials. This consistency is critical for reliable multi-centre research and paves the way for improved global benchmarking in cancer care.

Developing safe, reliable clinical processes to integrate AI tools

Prof Court has extended access to the RPA to other radiotherapy centres in South Africa, with expansion to other countries planned for the near future — a decision informed in part by the positive outcomes and implementation expertise demonstrated by the Bloemfontein teams.

In addition to their work in external beam radiotherapy, the UFS and Universitas teams are also advancing the use of interstitial brachytherapy for cervix cancer. While not the first globally to implement this specialised technique, the Bloemfontein team is among the earliest adopters on the African continent, helping to expand access to this advanced modality in settings where it is most needed. The team is now focused on optimising the integration of external beam radiotherapy and brachytherapy — a well-established combination in the treatment of cervix cancer — to enhance treatment outcomes and adapt protocols to meet local clinical realities more effectively.

Crucially, Dr Shaw’s team has played a central role in developing safe, reliable clinical processes to integrate AI tools like the RPA into daily practice — ensuring that automation enhances, rather than replaces, professional expertise.

“The future we are heading towards is one where human innovation and digital technologies work together to elevate the standard of care, rather than replace humanity in medicine,” says Prof Reddy.

He added: “It is encouraging to see how our colleagues are internationalising our footprint, together with machine precision to enhance detection, personalise treatment and perhaps importantly, empowering clinicians with data-driven insights for patient care. These innovations give meaning to the vision and aspirations of Vision 130, predicated on research excellence, innovation and social impact.”