AI Segmentation
Varian Medical Systems, Inc.AI Segmentation is a cloud-based software product that uses artificial intelligence to automatically segment anatomical structures from CT images. It is designed to assist medical professionals in radiation therapy treatment planning by providing automated contours of organs in regions such as the head and neck, thorax, pelvis, and abdomen. The segmented structures can be reviewed, edited, and approved by qualified treatment planners and physicians to streamline planning and improve accuracy.
Intended Use
AI Segmentation uses CT images to segment patient anatomy for use in radiation therapy treatment planning, utilizing a pre-defined set of organ structures in head and neck, thorax, pelvis, and abdomen regions.
Technology
The device is a cloud-based web application combining deep learning and classical algorithms to automatically segment organs at risk on CT images. It provides a user interface for review, editing, and export of segmentation results to the Eclipse Treatment Planning System. The AI models are static and non-adaptive.
Performance
Software verification and validation testing was completed following FDA guidance for software in medical devices. Non-clinical testing included performance evaluation of AI models using DICE similarity index compared against ground truth and literature values. Expert clinician review confirmed 80% of contours were acceptable with minor or no adjustments. No clinical or animal studies were conducted. The subject device showed equivalent performance to the predicate device.
Predicate Devices
No predicate devices specified
Device Timeline
- 1
Submission
6/21/2021
2 months - 2
FDA Approval
9/2/2021
Other devices from Varian Medical Systems, Inc.
- Gating Reflector Block2024 • 510K
- Vitesse (5.0)2024 • 510K
- Ethos Treatment Management (3.0); Ethos Treatment Planning (2.0)2024 • 510K
Ready to Sharpen Your Edge?
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.