A motion vector sensor-enabled 3D spinal morphology monitoring suit for intelligent scoliosis identification

Early identification of scoliosis is important for timely clinical intervention. However, conventional static screening methods rely on subjective assessments, resulting in limited accuracy and insufficient continuity. Here, we propose a motion vector sensor-enabled 3D spinal morphology monitoring suit for intelligent scoliosis identification. We engineer a highly anisotropic mesh with orderly aligned conductive fibers, enabling the motion sensors to precisely perceive motion amplitude and direction. The suit integrates motion sensors positioned at symmetrical body locations to quantify 3D spinal motions bz capturing skin-surface deformation amplitude and direction. We achieve dynamic scoliosis identification through machine learning-powered evaluation of spinal kinematic symmetry. We test performance on a multi-center cohort comprising four hospitals and one school-based screening program, demonstrating 92.63%, 71.05%, and 82.76% accuracy for scoliosis detection, curvature degree quantification, and curvature location identification, respectively. This radiation-free alternative has the potential to support longitudinal follow-up and reduce repeat radiographs in scoliosis management. Early detection of scoliosis is critical for timely intervention, but current screening lacks accuracy. Here the authors develop a motion vector sensor-enabled 3D spinal morphology monitoring suit for accurate, intelligent scoliosis identification.