PALO ALTO, Calif., Oct. 22, 2015 /PRNewswire/ -- Studies presented earlier this week at the 2015 annual meeting of the American Society for Radiation Oncology (ASTRO) confirmed that knowledge-based treatment planning software can dramatically improve the speed and quality of cancer care. One award-winning study by a team using RapidPlan™ software from Varian Medical Systems (NYSE: VAR) showed that radiotherapy treatment planning for cervical cancer can be done in minutes rather than hours, with superior quality.

In a presentation that was named among the "Best of ASTRO" and won the Basic/ Translational Science Abstract Award in the physics category, Nan Li, PhD, postdoctoral fellow at the University of California, San Diego (UCSD), and her team1 reported on their use of a RapidPlan model that was based on a refined sample of 86 previously-treated cervical cancer cases. They found that treatment planning time for intensity-modulated radiation therapy took an average of 6.85 minutes.[1] According to Kevin Moore, PhD, senior author on the study, UCSD dosimetrists estimate that manual GYN planning would require anywhere from 2-6 hours of optimization. "The use of knowledge-based planning represents a considerable time savings and reduced personnel costs," he said.

RapidPlan also improved plan quality compared to conventionally generated plans by minimizing the impact on normal surrounding tissues. "With both dramatic efficiency gains and improved normal tissue sparing, the final automated planning module was validated as both a clinical trial quality control system and a valuable tool for high-quality clinical planning in cervical cancer," observed Li.

Moore and his physician colleagues from UCSD also described work where stereotactic radiosurgery (SRS) treatment plans created using automated knowledge-based planning algorithms that they developed were set against manually-created clinical plans in a blinded comparison study.[2]

"In a clear majority of the cases, automated SRS planning demonstrated superior or equivalent plan quality to existing manual planning processes," Moore said. "Further refinement of algorithms to balance the complex clinical tradeoffs for high-priority organs-at-risk . . . will likely improve this technique further."

Researchers from Duke University evaluated a "rapid learning approach" in which clinicians "train" the RapidPlan tool by establishing a base knowledge model and continuously evaluate and update this knowledge model using subsequent cases. In their research on pelvic cancer cases, Jackie Wu, PhD, professor of radiation oncology, and her colleagues compared the RapidPlan rapid learning approach to the batch training method: knowledge modeling based on a static set of training cases.[3]

More HCB News