Search

Abstract Background Obstructive sleep apnea (OSA) is a pervasive, chronic sleep-related respiratory condition that causes brain structural alterations and cognitive impairments. However, the causal association of OSA with brain morphology and cognitive performance has not been determined. Methods We conducted a two-sample bidirectional Mendelian randomization (MR) analysis to investigate the causal relationship between OSA and a range of neurocognitive characteristics, including brain cortical structure, brain subcortical structure, brain structural change across the lifespan, and cognitive performance. Summary-level GWAS data for OSA from the FinnGen consortium was used to identify genetically predicted OSA. Data regarding neurocognitive characteristics were obtained from published meta-analysis studies. Linkage disequilibrium score regression analysis was employed to reveal genetic correlations between OSA and related traits. Results Our MR study provided evidence that OSA was found to significantly increase the volume of the hippocampus (IVW β (95% CI) = 158.997 (76.768 to 241.227), P = 1.51e-04), with no heterogeneity and pleiotropy detected. Nominally causal effects of OSA on brain structures, such as the thickness of the temporal pole with or without global weighted, amygdala structure change, and cerebellum white matter change covering lifespan, were observed. Bidirectional causal links were also detected between brain cortical structure, brain subcortical, cognitive performance, and OSA risk. LDSC regression analysis showed no significant correlation between OSA and hippocampus volume. Conclusions Overall, we observed a positive association between genetically predicted OSA and hippocampus volume. These findings may provide new insights into the bidirectional links between OSA and neurocognitive features, including brain morphology and cognitive performance.

Background: Three-dimensional cephalometric analysis is crucial in craniomaxillofacial assessment, with landmarks detection in craniomaxillofacial (CMF) CT scans being a key component. However, creating robust deep learning models for this task typically requires extensive CMF CT datasets annotated by experienced medical professionals, a process that is time-consuming and labor-intensive. Conversely, acquiring large volume of unlabeled CMF CT data is relatively straightforward. Thus, semi-supervised learning (SSL), leveraging limited labeled data supplemented by sufficient unlabeled dataset, could be a viable solution to this challenge. Method: We developed an SSL model, named CephaloMatch, based on a strong-weak perturbation consistency framework. The proposed SSL model incorporates a head position rectification technique through coarse detection to enhance consistency between labeled and unlabeled datasets and a multilayers perturbation method which is employed to expand the perturbation space. The proposed SSL model was assessed using 362 CMF CT scans, divided into a training set (60 scans), a validation set (14 scans), and an unlabeled set (288 scans). Result: The proposed SSL model attained a detection error of 1.60 ± 0.87 mm, significantly surpassing the performance of conventional fully supervised learning model (1.94 ± 1.12 mm). Notably, the proposed SSL model achieved equivalent detection accuracy (1.91 ± 1.00 mm) with only half the labeled dataset, compared to the fully supervised learning model. Conclusions: The proposed SSL model demonstrated exceptional performance in landmarks detection using a limited labeled CMF CT dataset, significantly reducing the workload of medical professionals and enhances the accuracy of 3D cephalometric analysis.

Abstract Background Accurate cephalometric analysis plays a vital role in the diagnosis and subsequent surgical planning in orthognathic and orthodontics treatment. However, manual digitization of anatomical landmarks in computed tomography (CT) is subject to limitations such as low accuracy, poor repeatability and excessive time consumption. Furthermore, the detection of landmarks has more difficulties on individuals with dentomaxillofacial deformities than normal individuals. Therefore, this study aims to develop a deep learning model to automatically detect landmarks in CT images of patients with dentomaxillofacial deformities. Methods Craniomaxillofacial (CMF) CT data of 80 patients with dentomaxillofacial deformities were collected for model development. 77 anatomical landmarks digitized by experienced CMF surgeons in each CT image were set as the ground truth. 3D UX-Net, the cutting-edge medical image segmentation network, was adopted as the backbone of model architecture. Moreover, a new region division pattern for CMF structures was designed as a training strategy to optimize the utilization of computational resources and image resolution. To evaluate the performance of this model, several experiments were conducted to make comparison between the model and manual digitization approach. Results The training set and the validation set included 58 and 22 samples respectively. The developed model can accurately detect 77 landmarks on bone, soft tissue and teeth with a mean error of 1.81 ± 0.89 mm. Removal of region division before training significantly increased the error of prediction (2.34 ± 1.01 mm). In terms of manual digitization, the inter-observer and intra-observer variations were 1.27 ± 0.70 mm and 1.01 ± 0.74 mm respectively. In all divided regions except Teeth Region (TR), our model demonstrated equivalent performance to experienced CMF surgeons in landmarks detection (p > 0.05). Conclusions The developed model demonstrated excellent performance in detecting craniomaxillofacial landmarks when considering manual digitization work of expertise as benchmark. It is also verified that the region division pattern designed in this study remarkably improved the detection accuracy.

Abstract Background Preoperative planning of orthognathic surgery is indispensable for achieving ideal surgical outcome regarding the occlusion and jaws' position. However, orthognathic surgery planning is sophisticated and highly experience-dependent, which requires comprehensive consideration of facial morphology and occlusal function. This study aimed to investigate a robust and automatic method based on deep learning to predict reposition vectors of jawbones in orthognathic surgery plan. Methods A regression neural network named VSP transformer was developed based on Transformer architecture. Firstly, 3D cephalometric analysis was employed to quantify skeletal-facial morphology as input features. Next, input features were weighted using pretrained results to minimize bias resulted from multicollinearity. Through encoder-decoder blocks, ten landmark-based reposition vectors of jawbones were predicted. Permutation importance (PI) method was used to calculate contributions of each feature to final prediction to reveal interpretability of the proposed model. Results VSP transformer model was developed with 383 samples and clinically tested with 49 prospectively collected samples. Our proposed model outperformed other four classic regression models in prediction accuracy. Mean absolute errors (MAE) of prediction were 1.41 mm in validation set and 1.34 mm in clinical test set. The interpretability results of the model were highly consistent with clinical knowledge and experience. Conclusions The developed model can predict reposition vectors of orthognathic surgery plan with high accuracy and good clinically practical-effectiveness. Moreover, the model was proved reliable because of its good interpretability.

Vascular diseases are the most prevalent cause of ischemic necrosis of tissue and organ, which even result in dysfunction and death. Vascular regeneration or artificial vascular graft, as the conventional treatment modality, has received keen attentions. However, small-diameter (diameter

Periosteum is indispensable in bone repair and is an important source of skeletal stem cells (SSCs) for endogenous bone regeneration. However, there are only a few studies about SSCs in periosteum. The craniomaxillofacial bone regeneration is done under the hypoxia microenvironment, in which HIF-1α plays an important role. The effect of HIF-1α on periosteum-derived stem cells (PDSCs) and the mechanisms of PDSCs activation under hypoxia conditions are unknown. In this study, the calvarial bone defect was established, with the periosteum removed or retained. Results show that the bone regeneration was severely impaired in the periosteum removed group. Moreover, pluripotent PDSCs isolated from the periosteum were positive for mesenchymal stem cell (MSC) markers. To determine the role of HIF-1α, the expression of HIF-1α was knocked down in vivo and in vitro, impairing the bone regeneration or osteogenesis of PDSCs. Furthermore, the knockdown of HIF-1α expression also reduced periostin (POSTN) expression, and recombinant POSTN addition partly rescued the osteogenic inhibition. Finally, to explore the mechanism under POSTN activation, the phosphorylation level of the PI3K/AKT pathway was assessed in transfected PDSCs. The phosphorylation level of PI3K and AKT was enhanced with HIF-1α overexpression and inhibited with HIF-1α knockdown, and the addition of PI3K activator or AKT activator could partly rescue POSTN expression. In conclusion, as a potential target to promote bone repair under the hypoxia microenvironment, HIF-1α can regulate the osteogenic differentiation of PDSCs via the PI3K/AKT/POSTN pathway, which lay a solid foundation for periosteum-based craniomaxillofacial bone regeneration.