Spine CAMP (1.1)

Spine CAMP™ (1.1) is an automated software system designed to analyze spinal X-rays using an AI-driven image processing methodology to provide quantitative metrics on spinal morphology, alignment, and motion. It aims to support clinical decision-making by objectively characterizing spinal health, including intervertebral motion and spinopelvic parameters, with performance demonstrated through statistical equivalence to predicate and reference methods.

Spine CAMP™ (1.1) is a fully-automated image processing software designed to assist healthcare professionals in assessing spinal health. It analyzes sagittal plane X-ray images of the lumbar and/or cervical spine from skeletally mature patients (18 years and older). The software aims to provide objective metrics for characterizing spinal conditions such as stability, alignment, degeneration, fusion, motion preservation, and implant performance, thereby supporting clinical decision-making. The system employs an artificial intelligence (AI) engine for vertebral body detection, landmark specification, and registration. It calculates various measurements including distances, angles, linear and angular displacements, and presents these findings in reports, annotated images, and visualizations of intervertebral motion using an image registration method called "stabilization." Version 1.1 features an AI engine retrained with additional imaging data for enhanced performance and generalization, includes logic improvements, and introduces the capability to identify femoral heads for spinopelvic measurements. Performance testing, including comparisons against its previous version (v1.0) and a reference method (QMA) for spinopelvic parameters on a dataset of over 400 radiographs, demonstrated statistical equivalence in vertebral landmark coordinates, image calibration, and intervertebral and spinopelvic measurements.

AI Regulatory Concerns

Powered by

Jev reads the full FDA letter and returns calibrated concern probabilities per regulatory category. These are AI estimates, not regulatory advice.

• Q1. How does the "stabilization" image registration method account for patient positioning variability between flexion/extension X-rays when assessing intervertebral motion?; What specific AI models are used within the AI Engine, and what was the diversity of the "more imaging" dataset used for retraining in terms of patient demographics, pathologies, and image quality?; How does the software's performance in identifying femoral heads and generating spinopelvic measurements compare to manual measurements by expert radiologists in terms of accuracy and inter-observer variability?; What are the known failure modes of the AI Engine, even after logic improvements, and what are the recommended actions for users when the software fails to provide an accurate analysis?; Beyond statistical equivalence, what is the clinical impact of using Spine CAMP™ v1.1 on diagnostic accuracy, treatment planning efficiency, or patient outcomes compared to traditional assessment methods?