To date, 3D spine reconstruction from biplanar radiographs involves intensive user supervision and semiautomated methods that are time-consuming and not effective in clinical routine. This paper proposes a new, fast and automated 3D spine reconstruction method through which a realistic statistical shape model of the spine is fitted to images using convolutional neural networks (CNN). The CNNs automatically detect the anatomical landmarks controlling the spine model deformation through a hierarchical and gradual iterative process. The performance assessment used a set of 68 biplanar radiographs, composed of both asymptomatic subjects and adolescent idiopathic scoliosis patients, in order to compare automated reconstructions with ground truths build using multiple expertssupervised reconstructions. The mean (SD) errors of landmark locations (3D Euclidean distances) were 1.6 (1.3) mm, 1.8 (1.3) mm and 2.3 (1.4) mm for the vertebral body center, endplate centers and pedicle centers respectively. The clinical parameters extracted from the automated 3D reconstruction (reconstruction time is less than one minute) presented an absolute mean error between 2.8° and 4.7° for the main spinal parameters and between 1° and 2.1° for pelvic parameters. Automated and expert’s agreement analysis reported that, in average, 89% of automated measurements were inside the expert’s confidence intervals. The proposed automated 3D spine reconstruction method provides an important step that should help the dissemination and adoption of 3D measurements in clinical routine
8 May 2014 in Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization
Rib cage 3D reconstruction is an important prerequisite for thoracic spine modelling, particularly for studies of the deformed thorax in adolescent idiopathic scoliosis. This study proposes a new method for rib cage 3D reconstruction from biplanar radiographs, using a statistical parametric model approach. Simplified parametric models were defined at the hierarchical levels of rib cage surface, rib midline and rib surface, and applied on a database of 86 trunks. The resulting parameter database served to train statistical models which were used to quickly provide a first estimate of the reconstruction from identifications on both radiographs. This solution was then refined by manual adjustments in order to improve the matching between model and image. Accuracy was assessed by comparison with 29 rib cages from CT scans in terms of geometrical parameter differences and in terms of line-to-line error distance between the rib midlines. Intra and inter-observer reproducibility was determined for 20 scoliotic patients. The first estimate (mean reconstruction time of 2 min 30 s) was sufficient to extract the main rib cage global parameters with a 95% confidence interval lower than 7%, 8%, 2% and 4° for rib cage volume, antero-posterior and lateral maximal diameters and maximal rib hump, respectively. The mean error distance was 5.4 mm (max 35 mm) down to 3.6 mm (max 24 mm) after the manual adjustment step (3 min 30 s). The proposed method will improve developments of rib cage finite element modelling and evaluation of clinical outcomes.
1 November 2022 in IEEE Transactions on Medical Imaging
The robustness and accuracy of the intensity-based 3D/2D registration of a 3D model on planar X-ray image(s) is related to the quality of the image correspondences between the digitally reconstructed radiographs (DRR) generated from the 3D models (varying image) and the X-ray images (fixed target). While much effort may be devoted to generating realistic DRR that are similar to real X-rays (using complex X-ray simulation, adding densities information in 3D models, etc.), significant differences still remain between DRR and real X-ray images. Differences such as the presence of adjacent or superimposed soft tissue and bony or foreign structures lead to image matching difficulties and decrease the 3D/2D registration performance. In the proposed method, the X-ray images were converted into DRR images using a GAN-based cross-modality image-to-images translation. With this added prior step of XRAY-to-DRR translation, standard similarity measures become efficient even when using simple and fast DRR projection. For both images to match, they must belong to the same image domain and essentially contain the same kind of information. The XRAY-to-DRR translation also addresses the well-known issue of registering an object in a scene composed of multiple objects by separating the superimposed or/and adjacent objects to avoid mismatching across similar structures. We applied the proposed method to the 3D/2D fine registration of vertebra deformable models to biplanar radiographs of the spine. We showed that the XRAY-to-DRR translation enhances the registration results, by increasing the capture range and decreasing dependence on the similarity measure choice since the multi-modal registration becomes mono-modal.
The aim of this paper is to describe a protocol that simulates the spinal surgery undergone by adolescents with idiopathic scoliosis (AIS) by using a 3D-printed spine model. Patients with AIS underwent pre- and postoperative bi-planar low-dose X-rays from which a numerical 3D model of their spine was generated. The preoperative numerical spine model was subsequently 3D printed to virtually reproduce the spine surgery. Special consideration was given to the printing materials for the 3D-printed elements in order to reflect the radiopaque and mechanical properties of typical bones most accurately. Two patients with AIS were recruited and operated. During the virtual surgery, both pre- and postoperative images of the 3D-printed spine model were acquired. The proposed 3D-printing workflow used to create a realistic 3D-printed spine suitable for virtual surgery appears to be feasible and reliable. This method could be used for virtual-reality scoliosis surgery training incorporating 3D-printed models, and to test surgical instruments and implants.
Rigid 2D-3D image registration plays a critical role in modern image-guided interventions by enabling the alignment of intraoperative X-ray images with preoperative volumetric data such as computed tomography (CT). Accurate 2D-3D registration allows clinicians to localize anatomical structures in three-dimensional space while relying on fast and low-dose intraoperative imaging, which is essential for applications including orthopedic surgery, spine navigation, radiation therapy, and interventional radiology. Despite significant progress over the past two decades, achieving robust and accurate registration remains challenging due to factors such as limited imaging viewpoints, occlusions, imaging noise, and the large search space of rigid transformations. This paper provides a comprehensive survey of rigid 2D-3D registration methods with a particular focus on X-ray-to-CT alignment. We first introduce the mathematical formulation of the registration problem and present a taxonomy of existing approaches. We then review the key technical components underlying modern registration systems. In addition, we summarize commonly used datasets and evaluation protocols, discussing widely adopted metrics such as target registration error (TRE), pose error, and reprojection error. The survey also highlights representative clinical applications and analyzes the practical challenges that remain in real-world deployment, including robustness to imaging artifacts, variations in imaging dose, and real-time computational constraints. Finally, we discuss emerging research directions, such as differentiable rendering, deep learning based pose estimation, and multi-view registration frameworks, which are expected to further improve the accuracy, robustness, and clinical applicability of 2D-3D registration methods.