Friday, July 12, 2019
RaySearch has received 510(k) clearance from the FDA in the USA for version 8B of the treatment planning system RayStation®. RayStation 8B was released in December 2018 and includes the first machine learning applications in a treatment planning system on the radiation oncology market today.
The machine learning applications for automated treatment planning and automated organ segmentation in RayStation help improve efficiency and consistency in the clinic. The machine learning framework allows for models to be trained on the clinic's available data, and it is also possible to use pre-trained models provided by RaySearch.
The machine learning application for organ segmentation, using deep neural networks, was developed by RaySearch's in-house machine learning department and the machine learning planning was developed in collaboration with Princess Margaret Cancer Centre in Toronto, Canada.
The FDA clearance for the deep learning segmentation allows for automated generation of organs for all body sites while the clearance for machine learning planning application was provided at the model level, where a Prostate VMAT planning model from Princess Margaret Cancer Centre was approved.
Johan Löf, founder and CEO of RaySearch, says: "This clearance is a major step towards unleashing the unlimited potential of oncology software, led by RaySearch. More sophisticated automation means increased usability, efficiency and patient safety. This allows resources and clinicians to be focused on more challenging cases, education and such. Continuous development within oncology software is a key component in tomorrow's patient specific care plans."
