A fully autonomous AI system for accurate and reproducible Cobb angle measurement in Adolescent Idiopathic Scoliosis: a multicenter study.
Authors
Affiliations (8)
Affiliations (8)
- EpiDisease SL, Parc Científic de la Universitat de València, Paterna, València, Spain.
- Plaia Technologies SL.
- Hospital Infantil Universitario Niño Jesús, Madrid, Spain.
- Hospital Universitari Vall d'Hebron, Barcelona, Spain, Vall D'Hebron Research Institute (VHIR), Barcelona, Spain.
- Hospital Sant Joan de Déu, Barcelona, Spain.
- Hospital Universitari i Politècnic La Fe, Instituto de Investigación Sanitaria IIS La Fe, València, Spain.
- Departamento de Fisiología, Facultad de Medicina y Odontología, Universitat de València, València, Spain; INCLIVA Biomedical Research Institute, Valencia, Spain; Center for Biomedical Network Research on Rare Diseases (CIBERER), Carlos III Health Institute, Valencia, Spain.
- Departamento de Fisiología, Facultad de Medicina y Odontología, Universitat de València, València, Spain; INCLIVA Biomedical Research Institute, Valencia, Spain. Electronic address: [email protected].
Abstract
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. 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. Retrospective, observational, multicenter study. We performed a multicenter study involving four 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 three 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. 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 -41.30° 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°. 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 three specialists with more than 10 years' experience. SPARC removes the intra-observer 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.