Medical technology company RaySearch Laboratories reported on Wednesday the receipt of 510(k) clearance from the US FDA for the 8B version of the treatment planning system RayStation.

According to the company, RayStation 8B includes the first machine learning applications in a treatment planning system on the radiation oncology market. The machine learning applications for automated treatment planning and automated organ segmentation in RayStation are designed to 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.

The machine's learning application for organ segmentation, using deep neural networks, was developed by the company's in-house machine learning department and the machine learning planning was developed in collaboration with Princess Margaret Cancer Centre in Toronto, Canada.

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. The company markets the RayStation treatment planning system and RayCare, the next-generation oncology information system, worldwide.