In orthopedic surgeries, such as osteotomy and osteosynthesis, an intraoperative 3D reconstruction of the bone would enable surgeons to quickly assess the fracture reduction procedure with preoperative planning. Scanners equipped with such functionality are often more expensive than a conventional C-arm fluoroscopy device. Moreover, a C-arm fluoroscopy device is commonly available in many orthopedic facilities. Based on the widespread use of such equipment, this paper proposes a method to reconstruct the 3D structure of bone with a conventional C-arm fluoroscopy device. We focus on wrist bones as the target of reconstruction in this research as this will facilitate a flexible imaging scheme. Planar markers are attached to the target object and are tracked in the fluoroscopic image for C-arm pose estimation. The initial calibration of the device is conducted using a checkerboard pattern. In general, reconstruction algorithms are sensitive to geometric calibration errors. To assess the practicality of the method for reconstruction, a simulation study demonstrating the effect of checkerboard thickness and spherical marker size on reconstruction quality was conducted.

To compare a 3D preoperative planning image and fluoroscopic image, a 3D bone position estimation system that displays 3D images in response to changes in the position of fluoroscopic images was developed. The objective of the present study was to evaluate the accuracy of the estimated position of 3D bone images with reference to fluoroscopic images. Bone positions were estimated from reference points on a fluoroscopic image compared with those on a 3D image. The four reference markers positional relationships on the fluoroscopic image were compared with those on the 3D image to evaluate whether a 3D image may be drawn by tracking positional changes in the radius model. Intra-class correlations coefficients for reference marker distances between the fluoroscopic image and 3D image were 0.98–0.99. Average differences between measured values on the fluoroscopic image and 3D bone image for each marker corresponding to the direction of the bone model were 1.1 ± 0.7 mm, 2.4 ± 1.8 mm, 1.4 ± 0.8 mm, and 2.0 ± 1.6 mm in the anterior-posterior view, ulnar side lateral view, posterior-anterior view, and radial side lateral view, respectively. Marker positions were more accurate in the anterior-posterior and posterior-anterior views than in the radial and ulnar side lateral views. This system helps in real-time comparison of dynamic changes in preoperative 3D and intraoperative fluoroscopy images.

Ultrasound imaging of the medial elbow is crucial for early detection of Ulnar Collateral Ligament (UCL) injuries. Specifically, measuring the elbow joint space on ultrasound images enables the assessment of valgus instability. Automating this measurement requires a precisely annotated dataset to leverage recent advances in deep neural networks; however, no publicly available dataset has been proposed to date. In this work, we introduce a novel medial elbow ultrasound dataset with landmark annotations, facilitating the development of deep neural networks for joint space measurement. The dataset comprises 4,109 medial elbow ultrasound images from 22 participants, with precise landmark annotations on the humerus and ulna, performed under the supervision of three orthopedic surgeons. We evaluate several landmark detection models on our dataset and demonstrate its effectiveness in training models. Additionally, we propose Shape Subspace Refinement (SSR) to refine landmark heatmap peaks, improving the accuracy of heatmap-based landmark detection models. Furthermore, we show that the detected landmarks can be utilized for point-based segmentation of the humerus and ulna. The dataset is publicly available at [dataset link].

Intraoperative fluoroscopy is a frequently used modality in minimally invasive orthopedic surgeries. Aligning the intraoperatively acquired X-ray image with the preoperatively acquired 3D model of a computed tomography (CT) scan reduces the mental burden on surgeons induced by the overlapping anatomical structures in the acquired images. This paper proposes a fully automatic registration method that is robust to extreme viewpoints and does not require manual annotation of landmark points during training. It is based on a fully convolutional neural network (CNN) that regresses the scene coordinates for a given X-ray image. The scene coordinates are defined as the intersection of the back-projected rays from a pixel toward the 3D model. Training data for a patient-specific model were generated through a realistic simulation of a C-arm device using preoperative CT scans. In contrast, intraoperative registration was achieved by solving the perspective-n-point (PnP) problem with a random sample and consensus (RANSAC) algorithm. Experiments were conducted using a pelvic CT dataset that included several real fluoroscopic (X-ray) images with ground truth annotations. The proposed method achieved an average mean target registration error (mTRE) of 3.79 mm in the 50th percentile of the simulated test dataset and projected mTRE of 9.65 mm in the 50th percentile of real fluoroscopic images for pelvis registration.