The establishment of static digital humans and the integration with spinal models
🤖 AI Summary
To address the need for precise assessment of adolescent idiopathic scoliosis (AIS), this study proposes a novel modeling framework integrating patient-specific spinal geometry with a high-fidelity static digital human. Methodologically, we couple 3D Gaussian Splatting–reconstructed patient point clouds with the SMPL parametric human model and jointly register CT-derived 3D spinal reconstructions to a standard skeletal atlas via a hybrid rigid–nonrigid registration scheme. Evaluated on six AIS patient datasets, our method achieves Cobb angle prediction errors ≤1°, substantially outperforming conventional radiographic assessment. The resulting high-accuracy static digital twin provides a robust anatomical foundation for subsequent dynamic digital human modeling and enables scalable, patient-specific biomechanical analysis of AIS. This work establishes both a high-fidelity static baseline and an extensible technical framework for computational musculoskeletal research in scoliosis.
Application Category
📝 Abstract
Adolescent idiopathic scoliosis (AIS), a prevalent spinal deformity, significantly affects individuals' health and quality of life. Conventional imaging techniques, such as X - rays, computed tomography (CT), and magnetic resonance imaging (MRI), offer static views of the spine. However, they are restricted in capturing the dynamic changes of the spine and its interactions with overall body motion. Therefore, developing new techniques to address these limitations has become extremely important. Dynamic digital human modeling represents a major breakthrough in digital medicine. It enables a three - dimensional (3D) view of the spine as it changes during daily activities, assisting clinicians in detecting deformities that might be missed in static imaging. Although dynamic modeling holds great potential, constructing an accurate static digital human model is a crucial initial step for high - precision simulations. In this study, our focus is on constructing an accurate static digital human model integrating the spine, which is vital for subsequent dynamic digital human research on AIS. First, we generate human point - cloud data by combining the 3D Gaussian method with the Skinned Multi - Person Linear (SMPL) model from the patient's multi - view images. Then, we fit a standard skeletal model to the generated human model. Next, we align the real spine model reconstructed from CT images with the standard skeletal model. We validated the resulting personalized spine model using X - ray data from six AIS patients, with Cobb angles (used to measure the severity of scoliosis) as evaluation metrics. The results indicate that the model's error was within 1 degree of the actual measurements. This study presents an important method for constructing digital humans.
Problem
Research questions and friction points this paper is trying to address.
Develops static digital human model integration
Enhances 3D spine deformity detection accuracy
Validates model with AIS patient data
Innovation
Methods, ideas, or system contributions that make the work stand out.
3D Gaussian and SMPL integration
CT-based spine alignment
X-ray validated personalized model
🔎 Similar Papers
No similar papers found.
