Oncospace is a software tool designed to help radiation oncologists and dosimetrists plan cancer treatments more efficiently. It uses machine learning to predict dose objectives for organs at risk based on patient anatomy, assists in setting up treatment protocols, and integrates with treatment planning systems to optimize and review radiotherapy plans. This helps clinicians design safer and more effective radiation schedules for patients with cancers in various body regions.
Oncospace is used to configure and review radiotherapy treatment plans for a patient with malignant or benign disease in the head and neck, thoracic, abdominal, and pelvic regions. It allows for set up of radiotherapy treatment protocols, association of a potential treatment plan with the protocol(s), submission of a dose prescription and achievable dosimetric goals to a treatment planning system, and review of the treatment plan. It is intended for use by qualified, trained radiation therapy professionals (such as medical physicists, oncologists, and dosimetrists). This device is for prescription use by order of a physician.
Oncospace is a software-only medical device that functions alongside treatment planning systems, incorporating locked machine learning algorithms to predict organ-at-risk dosimetric goals based on patient-specific anatomical geometry. It automates initiation of plan optimization by supplying dose prescriptions, delivery methods, and protocol-based target objectives, and enables review of treatment plans. The software includes NLP models to standardize organ at risk naming to AAPM TG-263 standards and uses client-server architecture with cloud-based Windows servers.
Verification tests confirmed compliance with system requirements including clinical, UI, and cybersecurity standards. Validation used retrospective clinical datasets for multiple anatomical sites to demonstrate that plans created with Oncospace-generated objectives are non-inferior in organ-at-risk sparing compared to traditional plans. External validation showed mean absolute dose error within clinically acceptable margins. NLP model for OAR naming demonstrated high accuracy (>90%). Clinical performance testing confirmed safety and effectiveness across diverse datasets.
No predicate devices specified
Join hundreds of your peers who rely on RadAI Slice. Get the essential weekly briefing that empowers you to navigate the future of radiology.
We respect your privacy. Unsubscribe at any time.