[Research on intelligent tooth segmentation method combining multiple seed region growth and boundary extension].

The segmentation of dental models is a crucial step in computer-aided diagnosis and treatment systems for oral healthcare. To address the issues of poor universality and under-segmentation in tooth segmentation techniques, an intelligent tooth segmentation method combining multiple seed region growth and boundary extension is proposed. This method utilized the distribution characteristics of negative curvature meshes in teeth to obtain new seed points and effectively adapted to the structural differences between the top and sides of teeth through differential region growth. Additionally, the boundaries of the initial segmentation were extended based on geometric features, which was effectively compensated for under-segmentation issues in region growth. Ablation experiments and comparative experiments with current state-of-the-art algorithms demonstrated that the proposed method achieved better segmentation of crowded dental models and exhibited strong algorithm universality, thus possessing the capability to meet the practical segmentation needs in oral healthcare.

3D evaluation model of facial aesthetics based on multi-input 3D convolution neural networks for orthognathic surgery.

BACKGROUND: Quantitative evaluation of facial aesthetics is an important but also time-consuming procedure in orthognathic surgery, while existing 2D beauty-scoring models are mainly used for entertainment with less clinical impact. METHODS: A deep-learning-based 3D evaluation model DeepBeauty3D was designed and trained using 133 patients' CT images. The customised image preprocessing module extracted the skeleton, soft tissue, and personal physical information from raw DICOM data, and the predicting network module employed 3-input-2-output convolution neural networks (CNN) to receive the aforementioned data and output aesthetic scores automatically. RESULTS: Experiment results showed that this model predicted the skeleton and soft tissue score with 0.231 ± 0.218 (4.62%) and 0.100 ± 0.344 (2.00%) accuracy in 11.203 ± 2.824 s from raw CT images. CONCLUSION: This study provided an end-to-end solution using real clinical data based on 3D CNN to quantitatively evaluate facial aesthetics by considering three anatomical factors simultaneously, showing promising potential in reducing workload and bridging the surgeon-patient aesthetics perspective gap.

Micro-expression recognition based on multi-scale 3D residual convolutional neural network.

In demanding application scenarios such as clinical psychotherapy and criminal interrogation, the accurate recognition of micro-expressions is of utmost importance but poses significant challenges. One of the main difficulties lies in effectively capturing weak and fleeting facial features and improving recognition performance. To address this fundamental issue, this paper proposed a novel architecture based on a multi-scale 3D residual convolutional neural network. The algorithm leveraged a deep 3D-ResNet50 as the skeleton model and utilized the micro-expression optical flow feature map as the input for the network model. Drawing upon the complex spatial and temporal features inherent in micro-expressions, the network incorporated multi-scale convolutional modules of varying sizes to integrate both global and local information. Furthermore, an attention mechanism feature fusion module was introduced to enhance the model's contextual awareness. Finally, to optimize the model's prediction of the optimal solution, a discriminative network structure with multiple output channels was constructed. The algorithm's performance was evaluated using the public datasets SMIC, SAMM, and CASME Ⅱ. The experimental results demonstrated that the proposed algorithm achieves recognition accuracies of 74.6, 84.77 and 91.35% on these datasets, respectively. This substantial improvement in efficiency compared to existing mainstream methods for extracting micro-expression subtle features effectively enhanced micro-expression recognition performance and increased the accuracy of high-precision micro-expression recognition. Consequently, this paper served as an important reference for researchers working on high-precision micro-expression recognition.

Automatic three-dimensional reconstruction of the oesophagus in achalasia patients undergoing POEM: an innovative approach for evaluating treatment outcomes.

BACKGROUND AND AIMS: Peroral endoscopic myotomy (POEM) is a standard treatment option for achalasia patients. Treatment response varies due to factors such as achalasia type, degree of dilatation, pressure and distensibility indices. We present an innovative approach for treatment response prediction based on an automatic three-dimensional (3-D) reconstruction of the tubular oesophagus (TE) and the lower oesophageal sphincter (LES) in patients undergoing POEM for achalasia. METHODS: A software was developed, integrating data from high-resolution manometry, timed barium oesophagogram and endoscopic images to automatically generate 3-D reconstructions of the TE and LES. Novel normative indices for TE (volume×pressure) and LES (volume/pressure) were automatically integrated, facilitating pre-POEM and post-POEM comparisons. Treatment response was evaluated by changes in volumetric and pressure indices for the TE and the LES before as well as 3 and 12 months after POEM. In addition, these values were compared with normal value indices of non-achalasia patients. RESULTS: 50 treatment-naive achalasia patients were enrolled prospectively. The mean TE index decreased significantly (p<0.0001) and the mean LES index increased significantly 3 months post-POEM (p<0.0001). In the 12-month follow-up, no further significant change of value indices between 3 and 12 months post-POEM was seen. 3 months post-POEM mean LES index approached the mean LES of the healthy control group (p=0.077). CONCLUSION: 3-D reconstruction provides an interactive, dynamic visualisation of the oesophagus, serving as a comprehensive tool for evaluating treatment response. It may contribute to refining our approach to achalasia treatment and optimising treatment outcomes. TRIAL REGISTRATION NUMBER: 22-0149.

descSPIM: an affordable and easy-to-build light-sheet microscope optimized for tissue clearing techniques.

Despite widespread adoption of tissue clearing techniques in recent years, poor access to suitable light-sheet fluorescence microscopes remains a major obstacle for biomedical end-users. Here, we present descSPIM (desktop-equipped SPIM for cleared specimens), a low-cost ($20,000-50,000), low-expertise (one-day installation by a non-expert), yet practical do-it-yourself light-sheet microscope as a solution for this bottleneck. Even the most fundamental configuration of descSPIM enables multi-color imaging of whole mouse brains and a cancer cell line-derived xenograft tumor mass for the visualization of neurocircuitry, assessment of drug distribution, and pathological examination by false-colored hematoxylin and eosin staining in a three-dimensional manner. Academically open-sourced ( https://github.com/dbsb-juntendo/descSPIM ), descSPIM allows routine three-dimensional imaging of cleared samples in minutes. Thus, the dissemination of descSPIM will accelerate biomedical discoveries driven by tissue clearing technologies.

CMAN: Cascaded Multi-scale Spatial Channel Attention-guided Network for large 3D deformable registration of liver CT images.

Deformable image registration is an essential component of medical image analysis and plays an irreplaceable role in clinical practice. In recent years, deep learning-based registration methods have demonstrated significant improvements in convenience, robustness and execution time compared to traditional algorithms. However, registering images with large displacements, such as those of the liver organ, remains underexplored and challenging. In this study, we present a novel convolutional neural network (CNN)-based unsupervised learning registration method, Cascaded Multi-scale Spatial-Channel Attention-guided Network (CMAN), which addresses the challenge of large deformation fields using a double coarse-to-fine registration approach. The main contributions of CMAN include: (i) local coarse-to-fine registration in the base network, which generates the displacement field for each resolution and progressively propagates these local deformations as auxiliary information for the final deformation field; (ii) global coarse-to-fine registration, which stacks multiple base networks for sequential warping, thereby incorporating richer multi-layer contextual details into the final deformation field; (iii) integration of the spatial-channel attention module in the decoder stage, which better highlights important features and improves the quality of feature maps. The proposed network was trained using two public datasets and evaluated on another public dataset as well as a private dataset across several experimental scenarios. We compared CMAN with four state-of-the-art CNN-based registration methods and two well-known traditional algorithms. The results show that the proposed double coarse-to-fine registration strategy outperforms other methods in most registration evaluation metrics. In conclusion, CMAN can effectively handle the large-deformation registration problem and show potential for application in clinical practice. The source code is made publicly available at https://github.com/LocPham263/CMAN.git.

Insights into polycrystalline microstructure of blood films with 3D Mueller matrix imaging approach.

This study introduces a novel approach in the realm of liquid biopsies, employing a 3D Mueller-matrix (MM) image reconstruction technique to analyze dehydrated blood smear polycrystalline structures. Our research centers on exploiting the unique optical anisotropy properties of blood proteins, which undergo structural alterations at the quaternary and tertiary levels in the early stages of diseases such as cancer. These alterations manifest as distinct patterns in the polycrystalline microstructure of dried blood droplets, offering a minimally invasive yet highly effective method for early disease detection. We utilized a groundbreaking 3D MM mapping technique, integrated with digital holographic reconstruction, to perform a detailed layer-by-layer analysis of partially depolarizing dry blood smears. This method allows us to extract critical optical anisotropy parameters, enabling the differentiation of blood films from healthy individuals and prostate cancer patients. Our technique uniquely combines polarization-holographic and differential MM methodologies to spatially characterize the 3D polycrystalline structures within blood films. A key advancement in our study is the quantitative evaluation of optical anisotropy maps using statistical moments (first to fourth orders) of linear and circular birefringence and dichroism distributions. This analysis provides a comprehensive characterization of the mean, variance, skewness, and kurtosis of these distributions, crucial for identifying significant differences between healthy and cancerous samples. Our findings demonstrate an exceptional accuracy rate of over 90 % for the early diagnosis and staging of cancer, surpassing existing screening methods. This high level of precision and the non-invasive nature of our technique mark a significant advancement in the field of liquid biopsies. It holds immense potential for revolutionizing cancer diagnosis, early detection, patient stratification, and monitoring, thereby greatly enhancing patient care and treatment outcomes. In conclusion, our study contributes a pioneering technique to the liquid biopsy domain, aligning with the ongoing quest for non-invasive, reliable, and efficient diagnostic methods. It opens new avenues for cancer diagnosis and monitoring, representing a substantial leap forward in personalized medicine and oncology.

Natural scenes reveal diverse representations of 2D and 3D body pose in the human brain.

Human pose, defined as the spatial relationships between body parts, carries instrumental information supporting the understanding of motion and action of a person. A substantial body of previous work has identified cortical areas responsive to images of bodies and different body parts. However, the neural basis underlying the visual perception of body part relationships has received less attention. To broaden our understanding of body perception, we analyzed high-resolution fMRI responses to a wide range of poses from over 4,000 complex natural scenes. Using ground-truth annotations and an application of three-dimensional (3D) pose reconstruction algorithms, we compared similarity patterns of cortical activity with similarity patterns built from human pose models with different levels of depth availability and viewpoint dependency. Targeting the challenge of explaining variance in complex natural image responses with interpretable models, we achieved statistically significant correlations between pose models and cortical activity patterns (though performance levels are substantially lower than the noise ceiling). We found that the 3D view-independent pose model, compared with two-dimensional models, better captures the activation from distinct cortical areas, including the right posterior superior temporal sulcus (pSTS). These areas, together with other pose-selective regions in the LOTC, form a broader, distributed cortical network with greater view-tolerance in more anterior patches. We interpret these findings in light of the computational complexity of natural body images, the wide range of visual tasks supported by pose structures, and possible shared principles for view-invariant processing between articulated objects and ordinary, rigid objects.

Quantitative analysis of commercial coating penetration into Fagus crenata wood using X-ray microtomography.

Recent advances in wood treatment include the use of eco-friendly coatings to improve the wood's dimensional stability and appearance. Assessing coating performance during its service life is critical for establishing a knowledge base for product optimization. Numerous approaches, including microimaging, are available for analyzing coating behavior. In addition to conventional microscopic techniques, high-resolution X-ray microtomography is a tool that provides nondestructive imaging of coatings and their substrates. In this study, we performed two-dimensional (2D) and three-dimensional (3D) visualization of tomographic reconstruction images of two coating types, spray and brush, to observe and assess the distribution of several commercial Japanese coating materials in Fagus crenata. X-ray images and plot profiles were used to determine the penetration depths and thicknesses of coatings. Each coated sample was scanned using X-ray microtomography, which allowed successful visualization and quantification of the coating penetration depth. Chemical content and concentration of the coating materials influenced penetration depth and amount.

Compressed sensing 3D T2WI radiomics model: improving diagnostic performance in muscle invasion of bladder cancer.

BACKGROUND: Preoperative discrimination between non-muscle-invasive bladder cancer (NMIBC) and the muscle invasive bladder cancer (MIBC) is a determinant of management. The purpose of this research is to employ radiomics to evaluate the diagnostic value in determining muscle invasiveness of compressed sensing (CS) accelerated 3D T2-weighted-SPACE sequence with high resolution and short acquisition time. METHODS: This prospective study involved 108 participants who underwent preoperative 3D-CS-T2-weighted-SPACE, 3D-T2-weighted-SPACE and T2-weighted sequences. The cohort was divided into training and validation cohorts in a 7:3 ratio. In the training cohort, a Rad-score was constructed based on radiomic features selected by intraclass correlation coefficients, pearson correlation coefficient and least absolute shrinkage and selection operator . Multivariate logistic regression was used to develop a nomogram combined radiomics and clinical indices. In the validation cohort, the performances of the models were evaluated by ROC, calibration, and decision curves. RESULTS: In the validation cohort, the area under ROC curve of 3D-CS-T2-weighted-SPACE, 3D-T2-weighted-SPACE and T2-weighted models were 0.87(95% confidence interval (CI):0.73-1.00), 0.79(95%CI:0.63-0.96) and 0.77(95%CI:0.60-0.93), respectively. The differences in signal-to-noise ratio and contrast-to-noise ratio between 3D-CS-T2-weighted-SPACE and 3D-T2-weighted-SPACE sequences were not statistically significant(p > 0.05). While the clinical model composed of three clinical indices was 0.74(95%CI:0.55-0.94) and the radiomics-clinical nomogram model was 0.88(95%CI:0.75-1.00). The calibration curves confirmed high goodness of fit, and the decision curve also showed that the radiomics model and combined nomogram model yielded higher net benefits than the clinical model. CONCLUSION: The radiomics model based on compressed sensing 3D T2WI sequence, which was acquired within a shorter acquisition time, showed superior diagnostic efficacy in muscle invasion of bladder cancer. Additionally, the nomogram model could enhance the diagnostic performance.

[Evaluation of augmented reality technology in the recognizing of oral and maxillofacial anatomy].

OBJECTIVE: To evaluate the outcome of Augmented reality technology in the recognizing of oral and maxillofacial anatomy. METHODS: This study was conducted on the undergraduate students in Peking University School of Stomatology who were learning oral and maxillofacial anatomy. The image data were selected according to the experiment content, and the important blood vessels and bone tissue structures, such as upper and lower jaws, neck arteries and veins were reconstructed in 3D(3-dimensional) by digital software to generate experiment models, and the reconstructed models were encrypted and stored in the cloud. The QR (quick response) code corresponding to the 3D model was scanned by a networked mobile device to obtain augmented reality images to assist experimenters in teaching and subjects in recognizing. Augmented reality technology was applied in both the theoretical explanation and cadaveric dissection respectively. Subjects' feedback was collected in the form of a post-class questionnaire to evaluate the effectiveness of augmented reality technology-assisted recognizing. RESULTS: In the study, 83 undergraduate students were included as subjects in this study. Augmented reality technology could be successfully applied in the recognizing of oral and maxillofacial anatomy. All the subjects could scan the QR code through a connected mobile device to get the 3D anatomy model from the cloud, and zoom in/out/rotate the model on the mobile. Augmented reality technology could provide personalized 3D model, based on learners' needs and abilities. The results of likert scale showed that augmented reality technology was highly recognized by the students (9.19 points), and got high scores in terms of forming a three-dimensional sense and stimulating the enthusiasm for learning (9.01 and 8.85 points respectively). CONCLUSION: Augmented reality technology can realize the three-dimensional visualization of important structures of oral and maxillofacial anatomy and stimulate students' enthusiasm for learning. Besides, it can assist students in building three-dimensional space imagination of the anatomy of oral and maxillofacial area. The application of augmented reality technology achieves favorable effect in the recognizing of oral and maxillofacial anatomy.

Deep learning-based approach for 3D bone segmentation and prediction of missing tooth region for dental implant planning.

Recent studies have shown that dental implants have high long-term survival rates, indicating their effectiveness compared to other treatments. However, there is still a concern regarding treatment failure. Deep learning methods, specifically U-Net models, have been effectively applied to analyze medical and dental images. This study aims to utilize U-Net models to segment bone in regions where teeth are missing in cone-beam computerized tomography (CBCT) scans and predict the positions of implants. The proposed models were applied to a CBCT dataset of Taibah University Dental Hospital (TUDH) patients between 2018 and 2023. They were evaluated using different performance metrics and validated by a domain expert. The experimental results demonstrated outstanding performance in terms of dice, precision, and recall for bone segmentation (0.93, 0.94, and 0.93, respectively) with a low volume error (0.01). The proposed models offer promising automated dental implant planning for dental implantologists.

[Clinic-X-ray characteristics of periodontal disease in elderly patients.]

The significant prevalence of periodontal diseases in elderly patients makes the research relevant. By now, the issues of complex clinical and radiological semiotics of generalized periodontitis using high-tech research methods is not sufficiently studied. The research addressed the clinical picture and three-dimensional computed tomographic semiotics of severe chronic generalized periodontitis focusing 25 elderly patients with severe chronic generalized periodontitis. It verified the necessity to use an organ-oriented program of multiplanar (volumetric) cone-beam computed tomography coupled with the analysis of the research results, as well as a mandatory analysis of densitometry indicators of the jaw bone tissue in diagnostically significant periodontal zones.

Paired conditional generative adversarial network for highly accelerated liver 4D MRI.

Purpose.4D MRI with high spatiotemporal resolution is desired for image-guided liver radiotherapy. Acquiring densely sampling k-space data is time-consuming. Accelerated acquisition with sparse samples is desirable but often causes degraded image quality or long reconstruction time. We propose the Reconstruct Paired Conditional Generative Adversarial Network (Re-Con-GAN) to shorten the 4D MRI reconstruction time while maintaining the reconstruction quality.Methods.Patients who underwent free-breathing liver 4D MRI were included in the study. Fully- and retrospectively under-sampled data at 3, 6 and 10 times (3×, 6× and 10×) were first reconstructed using the nuFFT algorithm. Re-Con-GAN then trained input and output in pairs. Three types of networks, ResNet9, UNet and reconstruction swin transformer (RST), were explored as generators. PatchGAN was selected as the discriminator. Re-Con-GAN processed the data (3D +t) as temporal slices (2D +t). A total of 48 patients with 12 332 temporal slices were split into training (37 patients with 10 721 slices) and test (11 patients with 1611 slices). Compressed sensing (CS) reconstruction with spatiotemporal sparsity constraint was used as a benchmark. Reconstructed image quality was further evaluated with a liver gross tumor volume (GTV) localization task using Mask-RCNN trained from a separate 3D static liver MRI dataset (70 patients; 103 GTV contours).Results.Re-Con-GAN consistently achieved comparable/better PSNR, SSIM, and RMSE scores compared to CS/UNet models. The inference time of Re-Con-GAN, UNet and CS are 0.15, 0.16, and 120 s. The GTV detection task showed that Re-Con-GAN and CS, compared to UNet, better improved the dice score (3× Re-Con-GAN 80.98%; 3× CS 80.74%; 3× UNet 79.88%) of unprocessed under-sampled images (3× 69.61%).Conclusion.A generative network with adversarial training is proposed with promising and efficient reconstruction results demonstrated on an in-house dataset. The rapid and qualitative reconstruction of 4D liver MR has the potential to facilitate online adaptive MR-guided radiotherapy for liver cancer.

Single-Center Experience in Microsurgical Resection of Acoustic Neurinomas and the Benefit of Microscope-Based Augmented Reality.

Background and Objectives: Microsurgical resection with intraoperative neuromonitoring is the gold standard for acoustic neurinomas (ANs) which are classified as T3 or T4 tumors according to the Hannover Classification. Microscope-based augmented reality (AR) can be beneficial in cerebellopontine angle and lateral skull base surgery, since these are small areas packed with anatomical structures and the use of this technology enables automatic 3D building of a model without the need for a surgeon to mentally perform this task of transferring 2D images seen on the microscope into imaginary 3D images, which then reduces the possibility of error and provides better orientation in the operative field. Materials and Methods: All patients who underwent surgery for resection of ANs in our department were included in this study. Clinical outcomes in terms of postoperative neurological deficits and complications were evaluated, as well as neuroradiological outcomes for tumor remnants and recurrence. Results: A total of 43 consecutive patients (25 female, median age 60.5 ± 16 years) who underwent resection of ANs via retrosigmoid osteoclastic craniotomy with the use of intraoperative neuromonitoring (22 right-sided, 14 giant tumors, 10 cystic, 7 with hydrocephalus) by a single surgeon were included in this study, with a median follow up of 41.2 ± 32.2 months. A total of 18 patients underwent subtotal resection, 1 patient partial resection and 24 patients gross total resection. A total of 27 patients underwent resection in sitting position and the rest in semi-sitting position. Out of 37 patients who had no facial nerve deficit prior to surgery, 19 patients were intact following surgery, 7 patients had House Brackmann (HB) Grade II paresis, 3 patients HB III, 7 patients HB IV and 1 patient HB V. Wound healing deficit with cerebrospinal fluid (CSF) leak occurred in 8 patients (18.6%). Operative time was 317.3 ± 99 min. One patient which had recurrence and one further patient with partial resection underwent radiotherapy following surgery. A total of 16 patients (37.2%) underwent resection using fiducial-based navigation and microscope-based AR, all in sitting position. Segmented objects of interest in AR were the sigmoid and transverse sinus, tumor outline, cranial nerves (CN) VII, VIII and V, petrous vein, cochlea and semicircular canals and brain stem. Operative time and clinical outcome did not differ between the AR and the non-AR group. However, use of AR improved orientation in the operative field for craniotomy planning and microsurgical resection by identification of important neurovascular structures. Conclusions: The single-center experience of resection of ANs showed a high rate of gross total (GTR) and subtotal resection (STR) with low recurrence. Use of AR improves intraoperative orientation and facilitates craniotomy planning and AN resection through early improved identification of important anatomical relations to structures of the inner auditory canal, venous sinuses, petrous vein, brain stem and the course of cranial nerves.

Multi-Condition Latent Diffusion Network for Scene-Aware Neural Human Motion Prediction.

Inferring 3D human motion is fundamental in many applications, including understanding human activity and analyzing one's intention. While many fruitful efforts have been made to human motion prediction, most approaches focus on pose-driven prediction and inferring human motion in isolation from the contextual environment, thus leaving the body location movement in the scene behind. However, real-world human movements are goal-directed and highly influenced by the spatial layout of their surrounding scenes. In this paper, instead of planning future human motion in a "dark" room, we propose a Multi-Condition Latent Diffusion network (MCLD) that reformulates the human motion prediction task as a multi-condition joint inference problem based on the given historical 3D body motion and the current 3D scene contexts. Specifically, instead of directly modeling joint distribution over the raw motion sequences, MCLD performs a conditional diffusion process within the latent embedding space, characterizing the cross-modal mapping from the past body movement and current scene context condition embeddings to the future human motion embedding. Extensive experiments on large-scale human motion prediction datasets demonstrate that our MCLD achieves significant improvements over the state-of-the-art methods on both realistic and diverse predictions.

3D residual attention hierarchical fusion for real-time detection of the prostate capsule.

BACKGROUND: For prostate electrosurgery, where real-time surveillance screens are relied upon for operations, manual identification of the prostate capsule remains the primary method. With the need for rapid and accurate detection becoming increasingly urgent, we set out to develop a deep learning approach for detecting the prostate capsule using endoscopic optical images. METHODS: Our method involves utilizing the Simple, Parameter-Free Attention Module(SimAM) residual attention fusion module to enhance the extraction of texture and detail information, enabling better feature extraction capabilities. This enhanced detail information is then hierarchically transferred from lower to higher levels to aid in the extraction of semantic information. By employing a forward feature-by-feature hierarchical fusion network based on the 3D residual attention mechanism, we have proposed an improved single-shot multibox detector model. RESULTS: Our proposed model achieves a detection precision of 83.12% and a speed of 0.014 ms on NVIDIA RTX 2060, demonstrating its effectiveness in rapid detection. Furthermore, when compared to various existing methods including Faster Region-based Convolutional Neural Network (Faster R-CNN), Single Shot Multibox Detector (SSD), EfficientDet and others, our method Attention based Feature Fusion Single Shot Multibox Detector (AFFSSD) stands out with the highest mean Average Precision (mAP) and faster speed, ranking only below You Only Look Once version 7 (YOLOv7). CONCLUSIONS: This network excels in extracting regional features from images while retaining the spatial structure, facilitating the rapid detection of medical images.

Deep learning for 3D cephalometric landmarking with heterogeneous multi-center CBCT dataset.

Cephalometric analysis is critically important and common procedure prior to orthodontic treatment and orthognathic surgery. Recently, deep learning approaches have been proposed for automatic 3D cephalometric analysis based on landmarking from CBCT scans. However, these approaches have relied on uniform datasets from a single center or imaging device but without considering patient ethnicity. In addition, previous works have considered a limited number of clinically relevant cephalometric landmarks and the approaches were computationally infeasible, both impairing integration into clinical workflow. Here our aim is to analyze the clinical applicability of a light-weight deep learning neural network for fast localization of 46 clinically significant cephalometric landmarks with multi-center, multi-ethnic, and multi-device data consisting of 309 CBCT scans from Finnish and Thai patients. The localization performance of our approach resulted in the mean distance of 1.99 ± 1.55 mm for the Finnish cohort and 1.96 ± 1.25 mm for the Thai cohort. This performance turned out to be clinically significant i.e., ≤ 2 mm with 61.7% and 64.3% of the landmarks with Finnish and Thai cohorts, respectively. Furthermore, the estimated landmarks were used to measure cephalometric characteristics successfully i.e., with ≤ 2 mm or ≤ 2° error, on 85.9% of the Finnish and 74.4% of the Thai cases. Between the two patient cohorts, 33 of the landmarks and all cephalometric characteristics had no statistically significant difference (p < 0.05) measured by the Mann-Whitney U test with Benjamini-Hochberg correction. Moreover, our method is found to be computationally light, i.e., providing the predictions with the mean duration of 0.77 s and 2.27 s with single machine GPU and CPU computing, respectively. Our findings advocate for the inclusion of this method into clinical settings based on its technical feasibility and robustness across varied clinical datasets.

Three-Dimensional Bowing Measurement of Distal Femur at Actual Size and Clinical Implications of Total Knee Arthroplasty.

Background and Objectives: To assess femoral shaft bowing (FSB) in coronal and sagittal planes and introduce the clinical implications of total knee arthroplasty (TKA) by analyzing a three-dimensional (3D) model with virtual implantation of the femoral component. Materials and Methods: Sixty-eight patients (average age: 69.1 years) underwent 3D model reconstruction of medullary canals using computed tomography (CT) data imported into Mimics® software (version 21.0). A mechanical axis (MA) line was drawn from the midportion of the femoral head to the center of the intercondylar notch. Proximal/distal straight centerlines (length, 60 mm; diameter, 1 mm) were placed in the medullary canal's center. Acute angles between these centerlines were measured to assess lateral and anterior bowing. The acute angle between the distal centerline and MA line was measured for distal coronal and sagittal alignment in both anteroposterior (AP) and lateral views. The diameter of curve (DOC) along the posterior border of the medulla was measured. Results: The mean lateral bowing in the AP view was 3.71°, and the mean anterior bowing in the lateral view was 11.82°. The average DOC of the medullary canal was 1501.68 mm. The average distal coronal alignment of all femurs was 6.40°, while the distal sagittal alignment was 2.66°. Overall, 22 femurs had coronal bowing, 42 had sagittal bowing, and 15 had both. Conclusions: In Asian populations, FSB can occur in coronal, sagittal, or both planes. Increased anterolateral FSB may lead to cortical abutment in the sagittal plane, despite limited space in the coronal plane. During TKA, distal coronal alignment guides the distal femoral valgus cut angle, whereas distal sagittal alignment aids in predicting femoral component positioning to avoid anterior notching. However, osteotomies along the anterior cortical bone intended to prevent notching may result in outliers due to differences between the distal sagittal alignment and the distal anterior cortical axis.

Human Joint Angle Estimation Using Deep Learning-Based Three-Dimensional Human Pose Estimation for Application in a Real Environment.

Human pose estimation (HPE) is a technique used in computer vision and artificial intelligence to detect and track human body parts and poses using images or videos. Widely used in augmented reality, animation, fitness applications, and surveillance, HPE methods that employ monocular cameras are highly versatile and applicable to standard videos and CCTV footage. These methods have evolved from two-dimensional (2D) to three-dimensional (3D) pose estimation. However, in real-world environments, current 3D HPE methods trained on laboratory-based motion capture data encounter challenges, such as limited training data, depth ambiguity, left/right switching, and issues with occlusions. In this study, four 3D HPE methods were compared based on their strengths and weaknesses using real-world videos. Joint position correction techniques were proposed to eliminate and correct anomalies such as left/right inversion and false detections of joint positions in daily life motions. Joint angle trajectories were obtained for intuitive and informative human activity recognition using an optimization method based on a 3D humanoid simulator, with the joint position corrected by the proposed technique as the input. The efficacy of the proposed method was verified by applying it to three types of freehand gymnastic exercises and comparing the joint angle trajectories during motion.