Accuracy of Orbital Shape Reconstruction-Comparative Analysis of Errors in Implant Shape Versus Implant Positioning: A Cadaveric Study.

INTRODUCTION: Orbital blowout fractures are commonly reconstructed with implants shaped to repair orbital cavity defects, restore ocular position and projection, and correct diplopia. Orbital implant shaping has traditionally been performed manually by surgeons, with more recent use of computer-assisted design (CAD). Accuracy of implant placement is also key to reconstruction. This study compares the placement accuracy of orbital implants, testing the hypothesis that CAD-shaped implants indexed to patient anatomy will better restore orbit geometry compared with manually shaped implants and manually placed implants. METHODS: The placement accuracy of orbital implants was assessed within a cadaveric blowout fracture model (3 skulls, 6 orbits) via 3-dimensional CT analysis. Defects were repaired with 4 different techniques: manually placed-manually shaped composite (titanium-reinforced porous polyethylene), manually placed CAD composite, indexed placed CAD composite, and indexed placed CAD titanium mesh. RESULTS: Implant placement accuracy differed significantly with the implant preparation method ( P =0.01). Indexing significantly improved the placement accuracy ( P =0.002). Indexed placed titanium mesh CAD implants (1.42±0.33 mm) were positioned significantly closer to the intact surface versus manually placed-manually shaped composite implants (2.12±0.39 mm). DISCUSSION: Computer-assisted design implants indexed to patient geometry yielded average errors below the acceptable threshold (2 mm) for enophthalmos and diplopia. This study highlights the importance of adequately indexing CAD-designed implants to patient geometry to ensure accurate orbital reconstructions.

Dual-domain accelerated MRI reconstruction using transformers with learning-based undersampling.

Acceleration in MRI has garnered much attention from the deep-learning community in recent years, particularly for imaging large anatomical volumes such as the abdomen or moving targets such as the heart. A variety of deep learning approaches have been investigated, with most existing works using convolutional neural network (CNN)-based architectures as the reconstruction backbone, paired with fixed, rather than learned, k-space undersampling patterns. In both image domain and k-space, CNN-based architectures may not be optimal for reconstruction due to its limited ability to capture long-range dependencies. Furthermore, fixed undersampling patterns, despite ease of implementation, may not lead to optimal reconstruction. Lastly, few deep learning models to date have leveraged temporal correlation across dynamic MRI data to improve reconstruction. To address these gaps, we present a dual-domain (image and k-space), transformer-based reconstruction network, paired with learning-based undersampling that accepts temporally correlated sequences of MRI images for dynamic reconstruction. We call our model DuDReTLU-net. We train the network end-to-end against fully sampled ground truth dataset. Human cardiac CINE images undersampled at different factors (5-100) were tested. Reconstructed images were assessed both visually and quantitatively via the structural similarity index, mean squared error, and peak signal-to-noise. Experimental results show superior performance of DuDReTLU-net over state-of-the-art methods (LOUPE, k-t SLR, BM3D-MRI) in accelerated MRI reconstruction; ablation studies show that transformer-based reconstruction outperformed CNN-based reconstruction in both image domain and k-space; dual-domain reconstruction architectures outperformed single-domain reconstruction architectures regardless of reconstruction backbone (CNN or transformer); and dynamic sequence input leads to more accurate reconstructions than single frame input. We expect our results to encourage further research in the use of dual-domain architectures, transformer-based architectures, and learning-based undersampling, in the setting of accelerated MRI reconstruction. The code for this project is made freely available at https://github.com/william2343/dual-domain-mri-recon-nets (Hong et al., 2022).