St. Luke's Radiation Oncology Network: MVision AI Contour+ Cuts Planning Time 70%, Readies Plans 9.7 Hours Sooner

Title

St. Luke's Radiation Oncology Network: MVision AI Contour+ Cuts Planning Time 70%, Readies Plans 9.7 Hours Sooner

Content

St. Luke's Radiation Oncology Network (SLRON), Ireland's largest radiotherapy provider, deployed MVision AI's Contour+ auto-contouring tool across its three Dublin sites, where it has cut contouring time by up to 70% for complex head, neck, abdomen, and thoracic cases, and now makes treatment plans ready 9.7 working hours sooner on average — 10% faster than the network's targeted workflow KPIs. "In real-world practice, we saw up to 70% time savings for head and neck, abdomen, and thoracic cases. The real-world results matched or even exceeded what manual timing studies have previously reported," said Ciaran Malone, Senior Medical Physicist and Research Fellow at SLRON. "We were delighted, especially considering the added complexities of the real clinical environment with frequent interruptions and constant multi-tasking." The deployment addressed a workload crisis. SLRON treats more than 5,500 patients each year and had watched contouring times rise over four years (n=16,352 cases) as patient complexity grew — head and neck and thoracic in particular — while fixed CT-to-treatment schedules tied to KPIs left little slack. The network also runs across three Dublin sites with different treatment technologies (Varian TrueBeams, Elekta Trilogies, Varian Clinacs) and multiple planning systems (Eclipse, Monaco, OMP), making consistency hard to maintain. Funding from the Friends of St. Luke's enabled SLRON to acquire the full MVision GBS™ suite — Contour+ for auto-contouring, Verify for contour QA, and Guide for registrar training — and roll it out as a single coordinated launch across all patient cohorts at all three sites. SLRON then compared four years of pre-AI data (n=16,352) against the first year of post-AI performance (n=5,867). Technically, the deployment centers on MVision AI's GBS™ (Guideline-Based Segmentation) platform, with advanced contour-editing operations that let clinicians align AI-generated structures — for example, lymph nodes — to local clinical preferences across the three sites. At operational scale, alongside the 70% time savings on complex cases, the network now sees 8% more treatment plans ready at least two working days earlier than before Contour+, with a larger share ready up to five days ahead of schedule — translating to roughly 200 patients per year who could begin treatment earlier and helping close the experience gap between junior and senior staff across the multi-site network. Looking ahead, SLRON is integrating Guide into registrar training to move from episodic to continuous skill development, and sees the deployment as groundwork for adaptive planning and radiotherapy research. Professor Pierre Thirion, Radiation Oncologist at SLRON, framed the broader shift: "AI in RT brings changes to our practice and a complete rethinking of the way we work. It has a learning curve and pushes us out of our comfort zone. Overall, it means more than speeding up the process. It is a new approach."