Bipolar outflows out to 10 kpc for massive galaxies at redshift z ≈ 1.

Galactic outflows are believed to play a critical role in the evolution of galaxies by regulating their mass build-up and star formation1. Theoretical models assume bipolar shapes for the outflows that extend well into the circumgalactic medium (CGM), up to tens of kiloparsecs (kpc) perpendicular to the galaxies. They have been directly observed in the local Universe in several individual galaxies, for example, around the Milky Way and M82 (refs. 2,3). At higher redshifts, cosmological simulations of galaxy formation predict an increase in the frequency and efficiency of galactic outflows owing to the increasing star-formation activity4. Galactic outflows are usually of low gas density and low surface brightness and therefore difficult to observe in emission towards high redshifts. Here we present an ultra-deep Multi-Unit Spectroscopic Explorer (MUSE) image of the mean Mg II emission surrounding a sample of galaxies at z ≈ 1 that strongly suggests the presence of outflowing gas on physical scales of more than 10 kpc. We find a strong dependence of the detected signal on the inclination of the central galaxy, with edge-on galaxies clearly showing enhanced Mg II emission along the minor axis, whereas face-on galaxies show much weaker and more isotropic emission. We interpret these findings as supporting the idea that outflows typically have a bipolar cone geometry perpendicular to the galactic disk. We demonstrate that this CGM-scale outflow is prevalent among galaxies with stellar mass M* ≳ 109.5M⊙.

Large-scale foundation model on single-cell transcriptomics.

Large pretrained models have become foundation models leading to breakthroughs in natural language processing and related fields. Developing foundation models for deciphering the 'languages' of cells and facilitating biomedical research is promising yet challenging. Here we developed a large pretrained model scFoundation, also named 'xTrimoscFoundationα', with 100 million parameters covering about 20,000 genes, pretrained on over 50 million human single-cell transcriptomic profiles. scFoundation is a large-scale model in terms of the size of trainable parameters, dimensionality of genes and volume of training data. Its asymmetric transformer-like architecture and pretraining task design empower effectively capturing complex context relations among genes in a variety of cell types and states. Experiments showed its merit as a foundation model that achieved state-of-the-art performances in a diverse array of single-cell analysis tasks such as gene expression enhancement, tissue drug response prediction, single-cell drug response classification, single-cell perturbation prediction, cell type annotation and gene module inference.

Different machine learning methods based on maxillary sinus in sex estimation for northwestern Chinese Han population.

BACKGROUND & OBJECTIVE: Sex estimation is a critical aspect of forensic expertise. Some special anatomical structures, such as the maxillary sinus, can still maintain integrity in harsh environmental conditions and may be served as a basis for sex estimation. Due to the complex nature of sex estimation, several studies have been conducted using different machine learning algorithms to improve the accuracy of sex prediction from anatomical measurements. MATERIAL & METHODS: In this study, linear data of the maxillary sinus in the population of northwest China by using Cone-Beam Computed Tomography (CBCT) were collected and utilized to develop logistic, K-Nearest Neighbor (KNN), Support Vector Machine (SVM) and random forest (RF) models for sex estimation with R 4.3.1. CBCT images from 477 samples of Han population (75 males and 81 females, aged 5-17 years; 162 males and 159 females, aged 18-72) were used to establish and verify the model. Length (MSL), width (MSW), height (MSH) of both the left and right maxillary sinuses and distance of lateral wall between two maxillary sinuses (distance) were measured. 80% of the data were randomly picked as the training set and others were testing set. Besides, these samples were grouped by age bracket and fitted models as an attempt. RESULTS: Overall, the accuracy of the sex estimation for individuals over 18 years old on the testing set was 77.78%, with a slightly higher accuracy rate for males at 78.12% compared to females at 77.42%. However, accuracy of sex estimation for individuals under 18 was challenging. In comparison to logistic, KNN and SVM, RF exhibited higher accuracy rates. Moreover, incorporating age as a variable improved the accuracy of sex estimation, particularly in the 18-27 age group, where the accuracy rate increased to 88.46%. Meanwhile, all variables showed a linear correlation with age. CONCLUSION: The linear measurements of the maxillary sinus could be a valuable tool for sex estimation in individuals aged 18 and over. A robust RF model has been developed for sex estimation within the Han population residing in the northwestern region of China. The accuracy of sex estimation could be higher when age is used as a predictive variable.

Sex estimation using maxillary sinus volume for Chinese subjects based on cone-beam computed tomography.

BACKGROUND: Sex estimate is a key stage in forensic science for identifying individuals. Some anatomical structures may be useful for sex estimation since they retain their integrity even after highly severe events. However, few studies are focusing on the Chinese population. Some researchers used teeth for sex estimation, but comparison with maxillary sinus were lack. As a result, the objective of this research is to develop a sex estimation formula for the northwestern Chinese population by the volume of the maxillary sinus and compare with the accuracy of sex estimation based on teeth through cone-beam computed tomography (CBCT). METHODS: CBCT images from 349 samples were used to establish and verify the formula. The volume of both the left and right maxillary sinuses was measured and examined for appropriate formula coefficients. To create the formula, we randomly picked 80% of the data as the training set and 20% of the samples as the testing set. Another set of samples, including 20 males and 20 females, were used to compare the accuracy of maxillary sinuses and teeth. RESULTS: Overall, sex estimation accuracy by volume of the left maxillary sinus can reach 78.57%, while by the volume of the right maxillary sinus can reach 74.29%. The accuracy for females, which can reach 91.43% using the left maxillary sinus, was significantly higher than that for males, which was 65.71%. The result also shows that maxillary sinus volume was higher in males. The comparison with the available results using measurements of teeth for sex estimation performed by our group showed that the accuracy of sex estimation using canines volume was higher than the one using maxillary sinus volume, the accuracies based on mesiodistal diameter of canine and first molar were the same or lower than the volume of maxillary sinus. CONCLUSIONS: The study demonstrates that measurement of maxillary sinus volume based on CBCT scans was an available and alternative method for sex estimation. And we established a method to accurately assess the sex of the northwest Chinese population. The comparison with the results of teeth measurements made the conclusion more reliable.

Age-related patterns in mandibular third molar eruption: presenting new forensic age assessment reference data from a Chinese population.

Valid reference data are essential for reliable forensic age assessment procedures in the living, a fact that extends to the trait of mandibular third molar eruption in dental panoramic radiographs (PAN). The objective of this study was to acquire valid reference data for a northern Chinese population. The study was guided by the criteria for reference studies in age assessment.To this end, a study population from China comprising 917 panoramic radiographs obtained from 430 females and 487 males aged between 15.00 and 25.99 years was analysed. Of the 917 PANs, a total of 1230 mandibular third molars were evaluated.The PANs, retrospectively evaluated, were performed for medical indication during the period from 2016 to 2021. The assessment of mandibular third molars was conducted using the staging scale presented by Olze et al. in 2012. Two independent examiners, trained in assessing PANs for forensic age estimation, evaluated the images. In instances where the two examiners diverged in their assessments these were subsequently deliberated, and a consensus stage was assigned.The mean age increased with higher stages for both teeth and both sexes. The minimum age recorded for stage D, indicating complete tooth eruption, was 15.6 years in females and 16.1 years in males. Consequently, the completion of mandibular third molar eruption was observed in both sexes well before reaching the age of 18. In light of our results, it is evident that relying solely on the assessment of mandibular third molar eruption may not be sufficient for accurately determining the age of majority. Contrary to previous literature, this finding of a completed eruption of the mandibular third molars in northern Chinese individuals is only suitable for detecting the completion of the 16th year of life in males according to our results. However, as the results are inconsistent compared to other studies in the literature, the trait should not be used as the only decisive marker to prove this age threshold in males from northern China.

Dental Age Estimation in Northern Chinese Han Children and Adolescents Using Demirjian's Method Combined with Machine Learning Algorithms.

OBJECTIVES: To investigate the application value of combining the Demirjian's method with machine learning algorithms for dental age estimation in northern Chinese Han children and adolescents. METHODS: Oral panoramic images of 10 256 Han individuals aged 5 to 24 years in northern China were collected. The development of eight permanent teeth in the left mandibular was classified into different stages using the Demirjian's method. Various machine learning algorithms, including support vector regression (SVR), gradient boosting regression (GBR), linear regression (LR), random forest regression (RFR), and decision tree regression (DTR) were employed. Age estimation models were constructed based on total, female, and male samples respectively using these algorithms. The fitting performance of different machine learning algorithms in these three groups was evaluated. RESULTS: SVR demonstrated superior estimation efficiency among all machine learning models in both total and female samples, while GBR showed the best performance in male samples. The mean absolute error (MAE) of the optimal age estimation model was 1.246 3, 1.281 8 and 1.153 8 years in the total, female and male samples, respectively. The optimal age estimation model exhibited varying levels of accuracy across different age ranges, which provided relatively accurate age estimations in individuals under 18 years old. CONCLUSIONS: The machine learning model developed in this study exhibits good age estimation efficiency in northern Chinese Han children and adolescents. However, its performance is not ideal when applied to adult population. To improve the accuracy in age estimation, the other variables can be considered.

Electromyographic activities of the jaw and facial muscles in subjects with different vertical skeletal patterns and breathing modes.

BACKGROUND: Mouth breathing (MB) can affect morphological changes in the craniofacial structures, electromyography is widely used for quantitative analysis of muscle function. OBJECTIVE: The aim was to evaluate the electromyographic (EMG) activities of the anterior temporalis (TA), masseter muscle (MM), orbicularis oris superior (OOS) and mentalis muscle (MT) in children with different vertical skeletal patterns and breathing modes during rest and various functional mandibular movements. METHODS: BioEMG III was used to measure the variations in EMG activities of TA, MM, OOS, and MT in 185 subjects aged 6-12 years during continuous clenching, rest, maximal intercuspation, lips closed lightly and swallowing. RESULTS: The results of logistic regression analysis showed that the model with vertical skeletal patterns as the dependent variable was ineffective (p = .106), while the model with breathing modes as the dependent variable was effective (p = .000). When considering both vertical skeletal patterns and breathing modes, the following significant differences were found. (1) In the normal-angle group, the EMG ratio in OOS with lips closed lightly of MB was significantly higher than NB (p = .005). (2) In the low-angle group, EMG ratios in TA and MM during the swallowing of MB were significantly lower than NB (p = .020, p = .040, respectively). (3) In the high-angle group, EMG ratios of MB were significantly higher in MT during continuous clenching, rest, lips closed lightly and swallowing (p = .038, p = .036, p = .005, p = .028, respectively), and OOS with lips closed lightly compared to NB (p = .005). CONCLUSION: Breathing modes and vertical skeletal patterns interacted to alter maxillofacial EMG activities, with breathing modes having a greater effect.

Artificial intelligence for histological subtype classification of breast cancer: combining multi-scale feature maps and the recurrent attention model.

AIMS: The aim of this study was to apply a two-stage deep model combining multi-scale feature maps and the recurrent attention model (RAM) to assist with the pathological diagnosis of breast cancer histological subtypes by the use of whole slide images (WSIs). METHODS AND RESULTS: In this article, we propose an integrated framework combining multi-scale feature maps from Inception V3 and the recurrent attention model to classify the six histological subtypes of breast cancer. This model was trained with 194 WSIs, and on 63 validation WSIs the model achieved accuracies of 0.9030 for patch-level classification and 0.8889 for WSI-level classification. In the testing stage, a total of 65 WSIs were used to achieve an accuracy of 0.8462 without any form of data curation. The t-distributed stochastic neighbour embedding showed that features extracted by the feature network of the RAM from WSIs of the same category can cluster together after training, and the visualization of decision steps showed that the decision-making glimpses are focused on the middle tumour area of an example from test WSIs. Finally, the false classification patches indicated that the morphological similarities between tumour tissues of different subtypes or non-tumour tissues and tumour tissues in patches might contribute to misclassification. CONCLUSIONS: This model can imitate the diagnostic process of pathologists, pay attention to a series of local features on the pathology image, and summarize related information, in order to accurately classify breast cancer into its histological subtypes, which is important for treatment and prognosis.

Forensic bone age estimation of adolescent pelvis X-rays based on two-stage convolutional neural network.

In the forensic estimation of bone age, the pelvis is important for identifying the bone age of teenagers. However, studies on this topic remain insufficient as a result of lower accuracy due to the overlapping of pelvic organs in X-ray images. Segmentation networks have been used to automate the location of key pelvic areas and minimize restrictions like doubling images of pelvic organs to increase the accuracy of estimation. This study conducted a retrospective analysis of 2164 pelvis X-ray images of Chinese Han teenagers ranging from 11 to 21 years old. Key areas of the pelvis were detected with a U-Net segmentation network, and the findings were combined with the original X-ray image for regional augmentation. Bone age estimation was conducted with the enhanced and not enhanced pelvis X-ray images by separately using three convolutional neural networks (CNNs). The root mean square errors (RMSE) of the Inception-V3, Inception-ResNet-V2, and VGG19 convolutional neural networks were 0.93 years, 1.12 years, and 1.14 years, respectively, and the mean absolute errors (MAE) of these networks were 0.67 years, 0.77 years, and 0.88 years, respectively. For comparison, a network without segmentation was employed to conduct the estimation, and it was found that the RMSE of the three CNNs above became 1.22 years, 1.25 years, and 1.63 years, respectively, and the MAE became 0.93 years, 0.96 years, and 1.23 years. Bland-Altman plots and attention maps were also generated to provide a visual comparison. The proposed segmentation network can be used to reduce the influence of restrictions like image overlapping of organs and can thus increase the accuracy of pelvic bone age estimation.

With or without human interference for precise age estimation based on machine learning?

Age estimation can aid in forensic medicine applications, diagnosis, and treatment planning for orthodontics and pediatrics. Existing dental age estimation methods rely heavily on specialized knowledge and are highly subjective, wasting time, and energy, which can be perfectly solved by machine learning techniques. As the key factor affecting the performance of machine learning models, there are usually two methods for feature extraction: human interference and autonomous extraction without human interference. However, previous studies have rarely applied these two methods for feature extraction in the same image analysis task. Herein, we present two types of convolutional neural networks (CNNs) for dental age estimation. One is an automated dental stage evaluation model (ADSE model) based on specified manually defined features, and the other is an automated end-to-end dental age estimation model (ADAE model), which autonomously extracts potential features for dental age estimation. Although the mean absolute error (MAE) of the ADSE model for stage classification is 0.17 stages, its accuracy in dental age estimation is unsatisfactory, with the MAE (1.63 years) being only 0.04 years lower than the manual dental age estimation method (MDAE model). However, the MAE of the ADAE model is 0.83 years, being reduced by half that of the MDAE model. The results show that fully automated feature extraction in a deep learning model without human interference performs better in dental age estimation, prominently increasing the accuracy and objectivity. This indicates that without human interference, machine learning may perform better in the application of medical imaging.

Efficiency evaluation of maxillary molar distalization using Invisalign based on palatal rugae registration.

INTRODUCTION: This study aimed to compare the predicted maxillary molar distalization with the achieved clinical outcome using the palatal rugae area for registration and superimposition of digital models. Understanding Invisalign efficiency may assist clinicians in predicting changes, thus applying specific measures to minimize the chance of midcourse correction later. METHODS: The study sample included 38 patients with a mean age of 25.4 years, eligible for Invisalign treatment and requiring distalization of maxillary molars. Two digital models were acquired using iTero intraoral scanner (Align Technology, Santa Clara, Calif) before treatment and after maxillary first and second molar distalization. The 2 digital models were superimposed using the palatal rugae area for registration. The predicted tooth movement compared to the achieved values. One hundred forty-two maxillary molars (71 first molar and 71 second molar) were measured for distal movement, and 228 maxillary anterior teeth were evaluated for anterior anchorage loss. RESULTS: The predicted distal movement of the maxillary first molar (P <0.0001) and maxillary second molar (P <0.0001) differed significantly from the actual values. There was a statistically significant correlation between the amount of distal molar movement and the amount of anchorage loss (r = 0.3900, P <0.008) for the central incisor, and (r = 0.3595, P <0.013) for the lateral incisor. CONCLUSIONS: Invisalign can be used successfully for adult patients requiring maxillary molar distalization when a mean distalization movement of 2.6 mm was prescribed. Clinicians should be aware of the countereffect if maxillary molars are planned to move distally, especially if the patient presented initially with a large overjet, so the need to prescribe overcorrection or the use of auxiliaries can be addressed earlier.

Three-dimensional evaluation of hyoid bone position in nasal and mouth breathing subjects with skeletal Class I, and Class II.

BACKGROUND: This retrospective study investigated the effect of breathing pattern, skeletal class (Class I, Class II), and age on the hyoid bone position (HBP) in normodivergent subjects. METHODS: A total of 126 subjects (61 males, 65 females) aged 7-9 years and 10-12 years were scanned using cone-beam computed tomography (CBCT). All participants were classified according to the anteroposterior skeletal pattern into (Class I, Class II). Each skeletal group was further divided according to the breathing mode into mouth breathers (MB) and nasal breathers (NB). The HBP was measured accordingly. Independent sample t-test and Mann Whitney U test were used to detect significant differences between the groups, and binary logistic regression was used to identify MB predictive indicators. RESULTS: The breathing mode and skeletal class affected the vertical HBP in subjects with 7-9 years, while they affected the anteroposterior HBP in subjects with 10-12 years. Regarding the age effect, hyoid bone was located more anteriorly in the older NB subjects, and hyoid bone was more inferiorly in the older age group. A regression equation of the significant variables was formulated, C3-Me (P: 001, OR: 2.27), and H-EB (P: 0.046, OR: 1.16) were positively correlated with occurrence of MB. CONCLUSION: There were significantly different HBPs among subjects with different anteroposterior skeletal classes, breathing modes, and age cohorts. Moreover, C3-Me, and H-EB were significant predictors and correlated with increased likelihood of being MB subject.

Three-dimensional evaluation of pharyngeal airway and maxillary arch in mouth and nasal breathing children with skeletal Class I and II.

OBJECTIVE: This study aimed to investigate whether the subjects with mouth breathing (MB) or nasal breathing (NB) with different sagittal skeletal patterns showed different maxillary arch and pharyngeal airway characteristics. METHODS: Cone-beam computed tomography scans from 70 children aged 10 to 12 years with sagittal skeletal Classes I and II were used to measure the pharyngeal airway, maxillary width, palatal area, and height. The independent t-test and the Mann-Whitney U test were used for the intragroup analysis of pharyngeal airway and maxillary arch parameters. RESULTS: In the Skeletal Class I group, nasopharyngeal airway volume (P < 0.01), oropharyngeal airway volume (OPV), and total pharyngeal airway volume (TPV) (all P < 0.001) were significantly greater in subjects with NB than in those with MB. Furthermore, intermolar width, maxillary width at the molars, intercanine width, maxillary width at the canines, and palatal area were significantly larger in subjects with NB than in those with MB (all P < 0.001). In the Skeletal Class II group, OPV, TPV (both P < 0.05) were significantly greater in subjects with NB than in those with MB. No significant differences in pharyngeal airway parameters in the MB group between subjects with Skeletal Class I and those with Skeletal Class II. CONCLUSION: Regardless of sagittal Skeletal Class I or II, the pharyngeal airway and maxillary arch in children with MB differ from those with NB. However, the pharyngeal airway was not significantly different between Skeletal Class I and II in children with MB.

Accurate age classification using manual method and deep convolutional neural network based on orthopantomogram images.

Age estimation is an important challenge in many fields, including immigrant identification, legal requirements, and clinical treatments. Deep learning techniques have been applied for age estimation recently but lacking performance comparison between manual and machine learning methods based on a large sample of dental orthopantomograms (OPGs). In total, we collected 10,257 orthopantomograms for the study. We derived logistic regression linear models for each legal age threshold (14, 16, and 18 years old) for manual method and developed the end-to-end convolutional neural network (CNN) which classified the dental age directly to compare with the manual method. Both methods are based on left mandibular eight permanent teeth or the third molar separately. Our results show that compared with the manual methods (92.5%, 91.3%, and 91.8% for age thresholds of 14, 16, and 18, respectively), the end-to-end CNN models perform better (95.9%, 95.4%, and 92.3% for age thresholds of 14, 16, and 18, respectively). This work proves that CNN models can surpass humans in age classification, and the features extracted by machines may be different from that defined by human.

A potential method for sex estimation of human skeletons using deep learning and three-dimensional surface scanning.

Deep learning based on radiological methods has attracted considerable attention in forensic anthropology because of its superior classification capacities over human experts. However, radiological instruments are limited in their nature of high cost and immobility. Here, we integrated a deep learning algorithm and three-dimensional (3D) surface scanning technique into a portable system for pelvic sex estimation. Briefly, the images of the ventral pubis (VP), dorsal pubis (DP), and greater sciatic notch (GSN) were cropped from virtual pelvic samples reconstructed from CT scans of 1000 individuals; 80% of them were used to train and internally evaluate convolutional neural networks (CNNs) that were then evaluated externally with the remaining samples. An additional 105 real pelvises were documented virtually with a handheld 3D surface scanner, and the corresponding snapshots of the VP, DP, and GSN were predicted by the trained CNN models. The CNN models achieved excellent performance in the external testing using CT-based images, with accuracies of 98.0%, 98.5%, and 94.0% for VP, DP, and GSN, respectively. When the CT-based models were applied to 3D scanning images, they obtained satisfactory accuracies above 95% on the VP and DP images compared to the GSN with 73.3%. In a single-blind trial, a multiple design that combined the three CNN models yielded a superior accuracy of 97.1% with 3D surface scanning images over two anthropologists. Our study demonstrates the great potential of deep learning and 3D surface scanning for rapid and accurate sex estimation of skeletal remains.

Lip morphology estimation models based on three-dimensional images in a modern adult population from China.

Lips are the main part of the lower facial soft tissue and are vital to forensic facial approximation (FFA). Facial soft tissue thickness (FSTT) and linear measurements in three dimensions are used in the quantitative analysis of lip morphology. With most FSTT analysis methods, the surface of soft tissue is unexplicit. Our study aimed to determine FSTT and explore the relationship between the hard and soft tissues of lips in different skeletal occlusions based on cone-beam CT (CBCT) and 3dMD images in a Chinese population. The FSTT of 11 landmarks in CBCT and 29 lip measurements in CBCT and 3dMD of 180 healthy Chinese individuals (90 males, 90 females) between 18 and 30 years were analyzed. The subjects were randomly divided into two groups with different skeletal occlusions distributed equally: 156 subjects in the experimental group to establish the prediction regression formulae of lip morphology and 24 subjects in the test group to assess the accuracy of the formulae. The results indicated that FSTT in the lower lip region varied among different skeletal occlusions. Furthermore, sex discrepancy was noted in the FSTT in midline landmarks and linear measurements. Measurements showing the highest correlation between soft and hard tissues were between total upper lip height and Ns-Pr (0.563 in males, 0.651 in females). The stepwise multiple regression equations were verified to be reliable with an average error of 1.246 mm. The method of combining CBCT with 3dMD provides a new perspective in predicting lip morphology and expands the database for FFA.

Dental age estimation based on the radiographic visibility of the periodontal ligament in the lower third molars: application of a new stage classification.

The purpose of the present study was to test whether a new stage classification based on radiographic visibility of the periodontal ligament in lower third molars in a Chinese population can be used for the 18- and 21-year thresholds. A total of 1300 orthopantomograms, including equal numbers of northern Chinese males and females evenly distributed between the ages of 15 and 40 years, were analyzed. The stages were defined according to the visibility of periodontal ligament for the outer parts of lower third molar roots because the visibility status of the periodontal ligament between the roots of lower third molars is none valuable in many Chinese individuals. Stage 0 was first achieved at the age of 17.05 years in males and 17.46 years in females. The earliest appearance of stage 1 was 17.47 years in males and 17.86 years in females. Stage 2 was first observed in males at the age of 21.43 years and in females at the age of 21.96 years. The onset of stage 3 was first observed at the age of 25.83 years in males and 23.14 years in females. Compared with the stage classification of Olze et al., which also considers the mesial parts of the roots, the number of assessable cases could be significantly increased. Therefore, our novel approach is effective for age estimation in the Chinese population.

Three-dimensional prediction of nose morphology in Chinese young adults: a pilot study combining cone-beam computed tomography and 3dMD photogrammetry system.

The nose is the most prominent part of the face and is a crucial factor for facial esthetics as well as facial reconstruction. Although some studies have explored the features of external nose and predicted the relationships between skeletal structures and soft tissues in the nasal region, the reliability and applicability of methods used in previous studies have not been reproduced. In addition, the majority of previous studies have focused on the sagittal direction, whereas the thickness of the soft tissues was rarely analyzed in three dimensions. A few studies have explained the specific characteristics of the nose of Chinese individuals. The aim of this study was to investigate the relationship between the hard nasal structures and soft external nose in three dimensions and to predict the morphology of the nose based on hard-tissue measurements. To eliminate the influence of low resolution of CBCT and increase the accuracy of measurement, three-dimensional (3D) images captured by cone-beam computed tomography (CBCT) and 3dMD photogrammetry system were used in this study. Twenty-six measurements (15 measurements for hard tissue and 11 measurements for soft tissue) based on 5 craniometric and 5 capulometric landmarks of the nose of 120 males and 120 females were obtained. All of the subjects were randomly divided into an experimental group (180 subjects consisting of 90 males and 90 females) and a test group (60 subjects consisting of 30 males and 30 females). Correlation coefficients between hard- and soft-tissue measurements were analyzed, and regression equations were obtained based on the experimental group and served as predictors to estimate nasal morphology in the test group. Most hard- and soft-tissue measurements appeared significantly different between genders. The strongest correlation was found between basis nasi protrusion and nasospinale protrusion (0.499) in males, and nasal height and nTr-nsTr (0.593) in females. For the regression equations, the highest value of R2 was observed in the nasal bridge length in males (0.257) and nasal tip protrusion in females (0.389). The proportion of subjects with predicted errors < 10% was over 86.7% in males and 70.0% in females. Our study proved that a combined CBCT and 3dMD photogrammetry system is a reliable method for nasal morphology estimation. Further research should investigate other influencing factors such as age, skeletal types, facial proportions, or population variance in nasal morphology estimation.

Deep Convolutional Neural Networks for Automatic Detection of Orbital Blowout Fractures.

Orbital blow out fracture is a common disease in emergency department and a delay or failure in diagnosis can lead to permanent visual changes. This study aims to evaluate the ability of an automatic orbital blowout fractures detection system based on computed tomography (CT) data.Orbital CT scans of adult orbital blowout fractures patients and normal cases were obtained from Shanghai Ninth People's Hospital between January and March 2017. The region of fractures was annotated using 3D Slicer. The Inception V3 convolutional neural networks were constructed utilizing the Python programming language with PyTorch as the framework to extract high dimension features from each slice in a CT scan. These extracted features are processed through a XGBoost model to make the final differentiation of fracture cases and nonfracture ones. Accuracy, receiver operating characteristics, and area under the curve were evaluated.This study used 94 CT scans diagnosed with orbital blowout fractures and 94 healthy control cases. The automatic detection system showed accuracy of 92% in single-image classification and 87% in patient level detection. The area under the receiver operating characteristic curve was 0.9574.Using a deep learning-based automatic detection system of orbital blowout fracture can accurately detect and classify orbital blowout fractures from CT scans. The convolutional neural networks model combined with an accurate annotation system could achieve good performance in a small dataset. Further studies with large and multicenter data are required to refine this technology for possible clinical applications.

Age assessment in the living using modified Gustafson's criteria in a northern Chinese population.

Regressive dental changes appear to be suitable for age assessment in living adults. In 2012, Olze et al. showed that several criteria presented by Gustafson for extracted teeth can also be applied to orthopantomograms. The objective of this study was to test the applicability and reliability of this method in a Chinese population. For this purpose, 1300 orthopantomograms of 650 female and 650 male Chinese aged between 15 and 40 years were evaluated. The characteristics of secondary dentin formation, periodontal recession, attrition, and cementum apposition were reviewed in all the mandibular premolars. The sample was split into a training and test dataset. Based on the training set, the correlation of the individual characteristics with chronological age was studied with a stepwise multiple regression analysis, in which individual characteristics formed the independent variable. According to the results, the R values amounted to 0.80 to 0.83; the standard error of estimate was 4.29 to 4.75 years. By analyzing the test dataset, the accuracy of the present study, Olze's and Timme's formulas were determined by the difference between the estimated dental age (DA) and chronological age (CA). Taking both mean differences and mean absolute differences into account, the Chinese age estimation formula did not always perform better compared with Olze's and Timme's formulas for both males and females. It was concluded that this method can be used in Chinese individuals for age assessment. However, the applicability of the method is limited by the quality of the X-ray images, and the method should only be applied by experienced forensic odontologists.