brAIn™ Shoulder Positioning

brAIn™ Shoulder Positioning is a cloud-based software tool designed to assist shoulder surgeons with preoperative planning for primary total shoulder replacement surgery. The software receives patient CT scans, automatically segments shoulder anatomy using machine learning, and allows surgeons to manually position glenoid and humerus implants in a 3D interactive viewer, then generates a planning report with pre- and post-implantation measurements and visualizations.

The subject device uses automatic machine learning-based segmentation of bone anatomy, whereas the predicate device (FX SPS, K213922) performed manual segmentation. The subject device includes soft tissue visualization in the 3D viewer, pre-positioning/semi-automatic landmark detection, and displays both axial and coronal DICOM views. Both devices are Class II web-based software for pre-operative planning using CT imaging and anatomical/reverse shoulder implants.

ANSI AAMI IEC 62304:2006/A1:2016 (Medical device software life cycle processes); FDA Guidance for Content of Premarket Submissions for Software Contained in Medical Devices; FDA Content of Premarket Submission for Management of Cybersecurity in Medical Devices.

The subject device has the same intended use and similar technological characteristics as the predicate device—both assist surgeons with preoperative shoulder replacement planning using CT imaging. Minor differences (automatic vs. manual segmentation, soft tissue visualization, semi-automatic landmarks) do not raise new safety or effectiveness concerns. Performance testing demonstrated segmentation accuracy (Dice Similarity Coefficient ≥0.95), measurement accuracy (±1° angles, ±1 mm distances), and landmark positioning equivalent to manual methods, confirming the device is substantially equivalent to the predicate.