Spine Journal - 2026-07-01 - Journal Article; Multicenter Study; Observational Study
A fully autonomous AI system for accurate and reproducible Cobb angle measurement in adolescent idiopathic scoliosis: a multicenter study.
Casabó-Vallés G, Aldecoa R, Pérez-Machado G, Egea-Gámez RM, Sánchez-Raya J, Vilalta-Vidal I, Rubio-Belmar PA, Galán-Olleros M, Salat-Batlle J, Fabrés Martín C, Bas P, Martínez-González C, Bagó J, Gómez-Chiari M, Bovea-Marco M, González-Díaz R, García-García R, Garcia-Guallarte J, García-López E, García-Giménez JL, Bas T, Mena-Mollá S
Topics
Key Takeaway
The SPARC AI system detected 94.0% of consensus scoliosis curves with a mean absolute error of 3.01°±2.71°, outperforming initial specialist evaluation (86.4% detection, MAE 2.41°±3.24°) while achieving a tighter error range (±20.3° vs ±41.3°).
Summary Depth
Choose how much analysis to show on this article page.
Summary
This multicenter retrospective study evaluated whether a fully autonomous deep learning pipeline (SPARC) could accurately measure Cobb angles on full-spine AP/PA radiographs in AIS patients without human intervention. Three independent clinicians per center established consensus measurements on 1,054 curves from 484 images; SPARC was benchmarked against this consensus and against initial pre-consensus specialist readings. SPARC detected 94.0% of consensus curves with MAE 3.01°±2.71° and error range -14.6° to 20.3°, remaining within the accepted clinical threshold of ≤6° MAE, while initial specialist readings detected only 86.4% with a wider error range extending to ±40.7°.
Key Limitation
The consensus ground truth was derived from the same clinicians whose initial readings were used as the comparator, creating circular validation that does not fully isolate AI performance from the biases embedded in the training and reference standard.
Original Abstract
BACKGROUND CONTEXT
The gold standard diagnostic test for Adolescent idiopathic scoliosis (AIS) involves manually measuring the spinal column deformity by determining the Cobb angle on a full-spine X-ray image. This measurement involves a subjective interpretation of vertebrae position and angle calculation, and inter-observer variability is widely accepted as one of the main causes of diagnosis uncertainty.
PURPOSE
Our objective was to develop an automated and reproducible system based on artificial intelligence (AI) to assist in Cobb angle estimation on full-spine radiographs without human intervention.
STUDY DESIGN
Retrospective, observational, multicenter study.
METHODS
We performed a multicenter study involving 4 tertiary hospitals in which we collected full-spine anteroposterior/posteroanterior (AP/PA) X-ray images from AIS patients with Cobb angles ranging from mild to severe. Images were analyzed by 3 independent clinicians in each center (first dataset). Any discrepancies in clinician-reported measurements prompted reevaluation of images and data curation. We developed a deep learning pipeline featuring two specialized AI models designed to detect the spine's curvature from X-ray images, identify the individual vertebrae, and accurately estimate the Cobb angles of all curves detected in the spine.
RESULTS
From a total of 484 X-ray images collected, spine surgeons reached consensus on 1,054 curves. Initial analysis identified 86.4% of these curves, with a mean absolute error (MAE) of 2.41°±3.24° relative to the consensus measurement after reevaluation and with error values ranging from -1.30° to 40.7°. In comparison, our SPinal Autonomous Radiological Cobb-assessment (SPARC) AI system detected 94.0% of the consensus curves, with a MAE of 3.01°±2.71°, which is within the clinical acceptance threshold (≤6°), and with a more constrained range of error showing values from -14.6° to 20.3°.
CONCLUSION
SPARC is an AI-based system developed for automatic, reproducible, and accurate calculation of Cobb angles in full AP/PA spine radiographs without human intervention. SPARC demonstrates superior performance by detecting a higher proportion of spinal curves (94.0% vs 86.4%) and achieving a lower error range in Cobb angle estimation (±20.3° vs ±41.3°) compared to the initial evaluation by 3 specialists with more than 10 years' experience.
CLINICAL SIGNIFICANCE
SPARC removes the intraobserver error and inter-observer variability inherent to manual measurements, and significantly decreases radiograph measurement and interpretation times, thus supporting clinicians in patient management and providing a reliable tool for less experienced practitioners involved in the care of patients at all stages of the AIS journey.