Fast and automatic periacetabular osteotomy fragment pose estimation using intraoperatively implanted fiducials and single-view fluoroscopy

Providing a computationally derived, mechanically optimised target correction during preoperative planning can improve joint contact mechanics of hip dysplasia treated with periacetabular osteotomy

AIM

Preoperative identification of acetabular corrections that optimally improve joint stability and reduce elevated contact stresses could further reduce osteoarthritis progression in patients with hip dysplasia who are treated with periacetabular osteotomy (PAO). The purpose of this study was to investigate how providing patient-specific, mechanically optimal acetabular reorientations to the surgeon during preoperative planning affected the surgically achieved correction.

METHODS

Preoperative CT scans were used to create patient-specific hip models for 6 patients scheduled for PAO. A simulated acetabular fragment was extracted from the preoperative pelvis model and computationally rotated to simulate candidate acetabular reorientations. For each candidate, discrete element analysis was used to compute contact stresses during walking, which were summed over the gait cycle and scaled by patient age to obtain chronic contact stress-time exposure. The ideal patient-specific reorientation was identified using a cost function that balances minimising chronic stress exposures and achieving surgically acceptable acetabular coverage angles. The optimal reorientation angles and associated contact mechanics were provided to the surgeon preoperatively. After PAO was performed, a model of the surgically achieved correction was created from a postoperative CT scan. Radiographic coverage and contact mechanics were compared between preoperative, optimal, and surgically achieved orientations.

RESULTS

While surgically achieved reorientations were not significantly different from optimal reorientations in radiographically measured lateral (p = 0.094) or anterior (p = 0.063) coverage, surgically achieved reorientations had significantly (p = 0.031) reduced total contact area compared to optimal reorientations. The difference in lateral coverage and peak chronic exposure between surgically achieved and optimal reorientations decreased with increasing surgeon experience using the models (R² = 0.758, R2 = 0.630, respectively).

CONCLUSIONS

Providing hip surgeons with a patient-specific, computationally optimal reorientation during preoperative planning may improve contact mechanics after PAO, which may help reduce osteoarthritis progression in patients with hip dysplasia.

Technology for High-Sensitivity Analysis of Medical Diagnostic Images

Control and analysis of small, inaccessible to human vision changes in medical images make it possible to focus on diagnostically important radiological signs important for the correct diagnosis.

The aim of the study was to develop information technology facilitating the early diagnosis of diseases using medical images.

The Impact of Machine Learning on 2D/3D Registration for Image-Guided Interventions: A Systematic Review and Perspective

Image-based navigation is widely considered the next frontier of minimally invasive surgery. It is believed that image-based navigation will increase the access to reproducible, safe, and high-precision surgery as it may then be performed at acceptable costs and effort. This is because image-based techniques avoid the need of specialized equipment and seamlessly integrate with contemporary workflows. Furthermore, it is expected that image-based navigation techniques will play a major role in enabling mixed reality environments, as well as autonomous and robot-assisted workflows. A critical component of image guidance is 2D/3D registration, a technique to estimate the spatial relationships between 3D structures, e.g., preoperative volumetric imagery or models of surgical instruments, and 2D images thereof, such as intraoperative X-ray fluoroscopy or endoscopy. While image-based 2D/3D registration is a mature technique, its transition from the bench to the bedside has been restrained by well-known challenges, including brittleness with respect to optimization objective, hyperparameter selection, and initialization, difficulties in dealing with inconsistencies or multiple objects, and limited single-view performance. One reason these challenges persist today is that analytical solutions are likely inadequate considering the complexity, variability, and high-dimensionality of generic 2D/3D registration problems. The recent advent of machine learning-based approaches to imaging problems that, rather than specifying the desired functional mapping, approximate it using highly expressive parametric models holds promise for solving some of the notorious challenges in 2D/3D registration. In this manuscript, we review the impact of machine learning on 2D/3D registration to systematically summarize the recent advances made by introduction of this novel technology. Grounded in these insights, we then offer our perspective on the most pressing needs, significant open problems, and possible next steps.