Accuracy and clinical validity of automated cephalometric analysis using convolutional neural networks.

BACKGROUND: This study aimed to assess the error range of cephalometric measurements based on the landmarks detected using cascaded CNNs and determine how horizontal and vertical positional errors of individual landmarks affect lateral cephalometric measurements. METHODS: In total, 120 lateral cephalograms were obtained consecutively from patients (mean age, 32.5 ± 11.6) who visited the Asan Medical Center, Seoul, Korea, for orthodontic treatment between 2019 and 2021. An automated lateral cephalometric analysis model previously developed from a nationwide multi-centre database was used to digitize the lateral cephalograms. The horizontal and vertical landmark position error attributable to the AI model was defined as the distance between the landmark identified by the human and that identified by the AI model on the x- and y-axes. The differences between the cephalometric measurements based on the landmarks identified by the AI model vs those identified by the human examiner were assessed. The association between the lateral cephalometric measurements and the positioning errors in the landmarks comprising the cephalometric measurement was assessed. RESULTS: The mean difference in the angular and linear measurements based on AI vs human landmark localization was .99 ± 1.05°, and .80 ± .82 mm, respectively. Significant differences between the measurements derived from AI-based and human localization were observed for all cephalometric variables except SNA, pog-Nperp, facial angle, SN-GoGn, FMA, Bjork sum, U1-SN, U1-FH, IMPA, L1-NB (angular) and interincisal angle. CONCLUSIONS: The errors in landmark positions, especially those that define reference planes, may significantly affect cephalometric measurements. The possibility of errors generated by automated lateral cephalometric analysis systems should be considered when using such systems for orthodontic diagnoses.

Epidemiology of occupational injuries in construction workers between 2009 and 2018 in South Korea.

BACKGROUND: This study aimed to investigate the characteristics of occupational injuries based on fatality, sex, and classification of occupations among construction workers using workers' compensation (WC) insurance data in South Korea. METHODS: We collected WC insurance data from the Korea Workers' Compensation & Welfare Service for all construction workers between 2009 and 2018. Data from 158,947 accepted claims for occupational injury were extracted, and the demographic features, occupational injury types, and annual trends were analyzed for fatal and nonfatal cases. The annual incidence and mortality trends of occupational injury were estimated using negative binomial regression and Poisson regression models, for injury incidence and mortality respectively. RESULTS: Among a total of 158,947 occupational injury cases, there were 155,772 (98%) nonfatal injuries and 3175 (2%) fatal injuries. For all occupational injuries, Construction Elementary Workers (6th Korean Standard Classification of Occupations (KSCO) 910; 45.7%) was the most frequent occupation, followed by Construction-Related Technical Workers (6th KSCO 772; 39.2%). The most frequent injury type was a fracture, followed by ruptures or lacerations and contusions. The incidence of all occupational injuries increased from 700.36 per 100,000 persons in 2009 to 1,195.98 per 100,000 persons in 2018. Further, deaths from injuries at work followed a significantly increasing annual trend [mortality rate ratio 1.04 (95% CI: 1.03-1.05)] from 2009 to 2018. CONCLUSION: The over two-thirds increased incidence of occupational injuries and significantly increasing mortality trends for occupational injuries during the last 10 years indicate the need for aggressive intervention in occupational safety and health management within the Korean construction industry.

Three-Dimensional Quantitative Assessment of Condylar Displacement and Adaptive Remodeling in Asymmetrical Mandibular Prognathism Patients After Sagittal Split Ramus Osteotomy.

This study was performed to evaluate the condylar displacement and associated condylar remodeling in class III patients following mandibular setback surgery via sagittal split ramus osteotomy (SSRO). The sample comprised of 26 condyles of 13 subjects (mean age of 21.2±2.6 y). We evaluated patients with mandibular prognathism and facial asymmetry who had undergone SSRO for mandibular setback at Korea University Hospital between January 2016 and December 2018. Three-dimensional segmentation of the mandibular condyles was done using the initial cone-beam computed tomography scan and scan taken 12 months postoperatively or later. Quantitative assessments of the 3-dimensional condylar displacement from T0 to T1 and bony remodeling of 8 regions of the condylar head were performed. The correlation between the condylar displacement and condylar head remodeling on the deviated (D) and nondeviated (ND) sides was analyzed. Significant correlations between condylar displacement and surface remodeling were observed in both D and ND condyles. The anteroposterior condylar displacement was significantly different between the D and ND sides (P=0.007). There was no significant difference in condylar remodeling between the 2 sides. Condylar displacement and adaptive remodeling after SSRO varied greatly among individuals. Compared with displacement in the ND condyle, displacement in the D condyle has a greater association with condylar remodeling in both D and ND condyles. There is no significant difference in condylar head remodeling between D and ND condyles.

Three-Dimensional Changes in the Mandibular Proximal Segment After Using a Surgery-First Approach in Patients With Class III Malocclusion and Facial Asymmetry.

ABSTRACT: This study was performed to evaluate condylar position and angulation after asymmetric mandibular setback between a conventional (CA) and surgery-first approach (SFA) using three-dimensional analysis. The condylar positions of 30 patients with skeletal Class III malocclusion and facial asymmetry who underwent 1-jaw (sagittal split ramus osteotomy) or 2-jaw orthognathic surgery (Le Fort I osteotomy and sagittal split ramus osteotomy) with CA (n = 18) or SFA (n = 12) from 2 university hospitals were studied. The three-dimensional assessment of condylar changes was performed using computed tomography images at the initial time point (T0) and at least 6 months after surgery (T1). Segmentation of condyles and cranial base assessment from cone-beam computed tomography images were performed using ITK-SNAP software (version 3.4.0). Condylar position and angulation changes were calculated using 3D Slicer software (version 4.10.2), and statistical analysis was performed. No significant translational or rotational condylar changes were observed between the deviated and non-deviated sides in each group or between the CA and SFA groups except yaw ( p = 0.014). Linear mixed-model analysis and multi-variate analysis showed no significant difference between the CA and SFA groups. Surgery-first approach might not be associated with more harmful effects on the condylar position and angulation changes as compared with CA.

RGB Channel Superposition Algorithm with Acetowhite Mask Images in a Cervical Cancer Classification Deep Learning Model.

Cervical cancer is one of the main causes of death from cancer in women. However, it can be treated successfully at an early stage. This study aims to propose an image processing algorithm based on acetowhite, which is an important criterion for diagnosing cervical cancer, to increase the accuracy of the deep learning classification model. Then, we mainly compared the performance of the model, the original image without image processing, a mask image made with acetowhite as the region of interest, and an image using the proposed algorithm. In conclusion, the deep learning classification model based on images with the proposed algorithm achieved an accuracy of 81.31%, which is approximately 9% higher than the model with original images and approximately 4% higher than the model with acetowhite mask images. Our study suggests that the proposed algorithm based on acetowhite could have a better performance than other image processing algorithms for classifying stages of cervical images.

Accuracy of auto-identification of the posteroanterior cephalometric landmarks using cascade convolution neural network algorithm and cephalometric images of different quality from nationwide multiple centers.

INTRODUCTION: The purpose of this study was to evaluate the accuracy of auto-identification of the posteroanterior (PA) cephalometric landmarks using the cascade convolution neural network (CNN) algorithm and PA cephalogram images of a different quality from nationwide multiple centers nationwide. METHODS: Of the 2798 PA cephalograms from 9 university hospitals, 2418 images (2075 training set and 343 validation set) were used to train the CNN algorithm for auto-identification of 16 PA cephalometric landmarks. Subsequently, 99 pretreatment images from the remaining 380 test set images were used to evaluate the accuracy of auto-identification of the CNN algorithm by comparing with the identification by a human examiner (gold standard) using V-Ceph 8.0 (Ostem, Seoul, South Korea). Pretreatment images were used to eliminate the effects of orthodontic bracket, tube and wire, surgical plate, and surgical screws. Paired t test was performed to compare the x- and y-coordinates of each landmark. The point-to-point error and the successful detection rate (range, within 2.0 mm) were calculated. RESULTS: The number of landmarks without a significant difference between the location identified by the human examiner and by auto-identification by the CNN algorithm were 8 on the x-coordinate and 5 on the y-coordinate, respectively. The mean point-to-point error was 1.52 mm. The low point-to-point error (<1.0 mm) was observed at the left and right antegonion (0.96 mm and 0.99 mm, respectively) and the high point-to-point error (>2.0 mm) was observed at the maxillary right first molar root apex (2.18 mm). The mean successful detection rate of auto-identification was 83.3%. CONCLUSIONS: Cascade CNN algorithm for auto-identification of PA cephalometric landmarks showed a possibility of an effective alternative to manual identification.

Vertical bony step between proximal and distal segments after mandibular setback is related with relapse: A cone-beam computed tomographic study.

INTRODUCTION: Vertical bony step (VBS) occurs between proximal and distal segments of the mandible during mandibular setback surgery with bilateral sagittal split ramus osteotomy. The purpose of this study was to investigate whether VBS is correlated with the relapse of mandibular setback using 3-dimensional models constructed from cone-beam computed tomography. METHODS: The subjects consisted of 30 patients who underwent bilateral sagittal split ramus osteotomy for a mandibular setback. Double jaw surgery was performed in 18 patients, and isolated mandibular setback surgery was performed in 12 patients. Cone-beam computed tomography scans were taken at pretreatment (T0), postsurgery (T1), and posttreatment (T2). Treatment changes and the correlations between measurements were evaluated. RESULTS: The mean mandibular setback was -11.9 mm, and the mean VBS was -5.6 mm. Correlations with the relapse of mandibular setback were found in the amount of mandibular setback (T1 - T0), development of VBS (T1 - T0), posterior movement of the proximal segment (T1 - T0), counterclockwise rotation of symphysis (T2 - T1), and the resolution of VBS (T2 - T1). CONCLUSIONS: The development and resolution of VBS were correlated with the relapse of mandibular setback. Minimizing VBS is recommended to reduce the relapse of mandibular setback.

Prediction of hand-wrist maturation stages based on cervical vertebrae images using artificial intelligence.

OBJECTIVE: To predict the hand-wrist maturation stages based on the cervical vertebrae (CV) images, and to analyse the accuracy of the proposed algorithms. SETTINGS AND POPULATION: A total of 499 pairs of hand-wrist radiographs and lateral cephalograms of 455 orthodontic patients aged 6-18 years were used for developing the prediction model for hand-wrist skeletal maturation stages. MATERIALS AND METHODS: The hand-wrist radiographs and the lateral cephalograms were collected from two university hospitals and a paediatric dental clinic. After identifying the 13 anatomic landmarks of the CV, the width-height ratio, width-perpendicular height ratio and concavity ratio of the CV were used as the morphometric features of the CV. Patients' chronological age and sex were also included as input data. The ground truth data were the Fishman SMI based on the hand-wrist radiographs. Three specialists determined the ground truth SMI. An ensemble machine learning methods were used to predict the Fishman SMI. Five-fold cross-validation was performed. The mean absolute error (MAE), round MAE and root mean square error (RMSE) values were used to assess the performance of the final ensemble model. RESULTS: The final ensemble model consisted of eight machine learning models. The MAE, round MAE and RMSE were 0.90, 0.87 and 1.20, respectively. CONCLUSION: Prediction of hand-wrist SMI based on CV images is possible using machine learning methods. Chronological age and sex increased the prediction accuracy. An automated diagnosis of the skeletal maturation may aid as a decision-supporting tool for evaluating the optimal treatment timing for growing patients.

Accuracy of automated identification of lateral cephalometric landmarks using cascade convolutional neural networks on lateral cephalograms from nationwide multi-centres.

OBJECTIVE: To investigate the accuracy of automated identification of cephalometric landmarks using the cascade convolutional neural networks (CNN) on lateral cephalograms acquired from nationwide multi-centres. SETTINGS AND SAMPLE POPULATION: A total of 3150 lateral cephalograms were acquired from 10 university hospitals in South Korea for training. MATERIALS AND METHODS: We evaluated the accuracy of the developed model with independent 100 lateral cephalograms as an external validation. Two orthodontists independently identified the anatomic landmarks of the test data set using the V-ceph software (version 8.0, Osstem, Seoul, Korea). The mean positions of the landmarks identified by two orthodontists were regarded as the gold standard. The performance of the CNN model was evaluated by calculating the mean absolute distance between the gold standard and the automatically detected positions. Factors associated with the detection accuracy for landmarks were analysed using the linear regression models. RESULTS: The mean inter-examiner difference was 1.31 ± 1.13 mm. The overall automated detection error was 1.36 ± 0.98 mm. The mean detection error for each landmark ranged between 0.46 ± 0.37 mm (maxillary incisor crown tip) and 2.09 ± 1.91 mm (distal root tip of the mandibular first molar). A significant difference in the detection accuracy among cephalograms was noted according to hospital (P = .011), sensor type (P < .01), and cephalography machine model (P < .01). CONCLUSION: The automated cephalometric landmark detection model may aid in preliminary screening for patient diagnosis and mid-treatment assessment, independent of the type of the radiography machines tested.

Intergenic recombination in feline calicivirus associated with a hemorrhagic-like disease in the Republic of Korea.

Feline calicivirus (FCV) is a common cause of upper respiratory tract disease in cats. In this study, the complete genome sequence of FCV 14Q315, which was detected from a dead domestic cat with a hemorrhagic-like disease, was analyzed to identify the genetic characteristics. The FCV 14Q315 genome was 7,684 bp. Phylogenetic analyses based on the ORF1, ORF2, and ORF3 sequences indicated that FCV 14Q315 is more closely related to FCV 15D022 than to other FCV strains. ORF1 of FCV 14Q315 shared high sequence similarity with ORF1 of FCVs 15D022 and UTCVM-H1. We further evaluated genetic recombination in ORF1 of FCV 14Q315 and detected intergenic recombination between p30 and the ORF1/ORF2 junction with high significance. Particularly, the non-recombination region in ORF1 of FCV 14Q315 showed high sequence similarity with FCVs GX2019, CH-JL2, and 15D022. The recombination region in ORF1 of FCV 14Q315 showed the highest similarity with FCV UTCVM-H1, which is associated with a hemorrhagic-like disease. The results suggest that the UTCVM-H1-like FCV was introduced into the Republic of Korea and presumably recombined with Korean FCVs by occasional mixed infections. In addition, the Korean FCV strains were located in several phylogenetic clusters with marked genetic diversity in the ORF2 region. These results imply that Korean FCVs possess high genetic diversity owing to mutations and recombination. Furthermore, it is possible that certain FCVs caused cyclical infections in the Korean cat population based on a phylogenetic analysis of FCVs isolated at different time points. Keywords: calicivirus; virulent systemic feline calicivirus; recombination; hemorrhagic-like disease.

Factors associated with spontaneous angular changes of impacted mandibular third molars as a result of second molar protraction.

INTRODUCTION: This study aimed to identify significant factors affecting the spontaneous angular changes of impacted mandibular third molars as a result of second molar protraction. Temporary skeletal anchorage devices in the missing mandibular first molar (ML-6) or missing deciduous mandibular second molar (ML-E) with missing succedaneous premolar spaces provided traction. METHODS: Forty-one mandibular third molars of 34 patients (10 male and 24 female; mean age 18.3 ± 3.7 years) that erupted after second molar protraction were included in this study. They were classified into upright (U) and tilted (T) groups. Linear and angular measurements were performed at the time of treatment initiation (T1) and of ML-6 or ML-E space closure (T2). Regression analyses were used to identify significant factors related to third molar uprighting. RESULTS: Nolla stage (odds ratio [OR] 4.1), sex (OR 0.003 for male), third molar angulation at T1 (OR 1.1), missing tooth space (OR 0.006), rate of third molar eruption (OR 23.3), and rate of second molar protraction (OR 0.2) significantly affected third molar uprighting. Age, third molar angulation at T1, rate of third molar eruption, and rate of second molar protraction were significant factors for predicting third molar angulation at T2. CONCLUSIONS: Available space for third molar eruption before and after second molar protraction is not associated with uprighting of erupting third molars. Older patients whose third molars are in greater Nolla stage, are in a more upright position at T1, and have a greater eruption rate have a greater chance for third molar uprighting. Alternatively, an increase in second molar protraction rate results in mesial tipping of the third molars.

Estimation of Arterial Blood Pressure Based on Artificial Intelligence Using Single Earlobe Photoplethysmography during Cardiopulmonary Resuscitation.

This study investigates the feasibility of estimation of blood pressure (BP) using a single earlobe photoplethysmography (Ear PPG) during cardiopulmonary resuscitation (CPR). We have designed a system that carries out Ear PPG for estimation of BP. In particular, the BP signals are estimated according to a long short-term memory (LSTM) model using an Ear PPG. To investigate the proposed method, two statistical analyses were conducted for comparison between BP measured by the micromanometer-based gold standard method (BPMEAS) and the Ear PPG-based proposed method (BPEST) for swine cardiac model. First, Pearson's correlation analysis showed high positive correlations (r = 0.92, p < 0.01) between BPMEAS and BPEST. Second, the paired-samples t-test on the BP parameters (systolic and diastolic blood pressure) of the two methods indicated no significant differences (p > 0.05). Therefore, the proposed method has the potential for estimation of BP for CPR biofeedback based on LSTM using a single Ear PPG.

Change in alveolar bone level of mandibular second and third molars after second molar protraction into missing first molar or second premolar space.

OBJECTIVE: To investigate the factors associated with the change in alveolar bone level of mandibular second and third molars after second molar protraction into the space of the missing first molar (L6) or second premolar (LE). METHODS: Fifty-one patients in whom space of the missing L6 or LE was treated with second molar protraction (13 males, 38 females, mean age 19.6 ± 4.7 years) from 2003 to 2015 were included. The alveolar bone level and position and angulation of the mandibular second and third molars were measured in panoramic radiographs at pre-treatment (T1), and after the alignment of the third molars following second molar protraction (T2). Factors associated with alveolar bone loss on the distal aspect of the mandibular second molars were assessed using linear regression analysis. RESULTS: Age at T1 (P < 0.001) and third molar angulation at T1 (P = 0.002) were significant factors for the prediction of alveolar bone level distal to the second molars. LIMITATION: This study used two-dimensional panoramic radiographs, and we could observe only the interproximal bone level. CONCLUSIONS: After second molar protraction into the missing first molar or second premolar space, mandibular second molars may exhibit alveolar bone resorption in the distal root in older patients and in those with mesially tilted third molars before treatment.

Bond Strengths of Orthodontic Metal Brackets to Tribochemically Silica-coated Zirconia Surfaces Using Different 10-Methacryloyloxydecyl Dihydrogen Phosphate-containing Primers.

PURPOSE: To evaluate the effects of tribochemical silica coating and different 10-methacryloyloxydecyl dihydrogen phosphate (MDP)-containing primers on the shear bond strength (SBS) of orthodontic metal brackets to yttrium-stabilized tetragonal zirconia polycrystal (Y-TZP) surfaces. MATERIALS AND METHODS: One hundred ninety polished Y-TZP specimens were randomly assigned to 19 groups (n = 10): 30 specimens were used for surface analyses after polishing with 600-grit silicon carbide paper, airborneparticle abrasion with 50-µm alumina (A), or tribochemical silica coating (CoJet [C]); 160 specimens were used in SBS testing of orthodontic metal brackets to Y-TZP after alumina airborne-particle abrasion or tribochemical silica coating and application of either ESPE-Sil (S) (ASn, ASa, CSn, CSa), Alloy Primer (AP) (AAPn, AAPa, CAPn, CAPa), Clearfil Ceramic Primer (CP) (ACPn, ACPa, CCPn, CCPa), or Scotchbond Universal (U) (AUn, AUa, CUn, CUa) and either stored in water for 24 h (non-aged, n) or thermocycled 5000 times (aged, a). The surface analyses and SBSs were statistically analyzed with ANOVA and Tukey's tests. RESULTS: Both mechanically treated surfaces had significantly greater surface roughness and surface free energy than did the polished surfaces. The type of primer and aging significantly affected the bond strength. Among the thermocycled specimens, the AAPa, AUa, and CCPa groups showed the greatest SBS. CONCLUSION: After alumina airborne-particle abrasion, the application of Alloy Primer, Clearfil Ceramic Primer, or Scotchbond Universal provided stable bonding to Y-TZP ceramics. After tribochemical silica coating, however, only Clearfil Ceramic Primer produced a durable bond to Y-TZP ceramics.

Seasonal variation in hemoglobin a1c in korean patients with type 2 diabetes mellitus.

A seasonal variation of glucose homeostasis in humans has been reported in various geographic regions. In this study, we examined seasonal variations in hemoglobin A1c (HbA1c) in patients with type 2 diabetes living in Korea. We analyzed 57,970 HbA1c values from 4,191 patients and the association of these values with ambient temperature for 3.5 yr. Overall, HbA1c exhibited its highest values from February to March and its lowest values from September to October (coefficient for cos t = -0.0743, P = 0.058) and the difference between the peak and nadir in a year was 0.16%-0.25%. A statistically significant seasonal variation was observed in the patients who were taking oral anti-diabetic drugs (OADs) without insulin treatment (coefficient for cos t = -0.0949, P < 0.05). The Spearman correlation coefficient between daily HbA1c values and the corresponding 3-month moving average ambient temperature was -0.2154 (95% confidence interval [CI]: -0.2711, -0.1580; P < 0.05). In conclusion, HbA1c values exhibited a seasonal variation in Korean patients with type 2 diabetes, with the highest values during the cold season, particularly in those who were treated with OADs, which should be taken into account in clinical practice for stable glucose control during the cold season.

Use of the pectoralis major, serratus anterior, and external oblique fascial flap for immediate one-stage breast reconstruction with implant.

BACKGROUND: Skin- or nipple-sparing mastectomy facilitates immediate one-stage reconstruction with an implant. Traditionally, an acellular dermal matrix or a muscle flap has been used because the inferolateral portion of the implant cannot be covered by the pectoralis major muscle. However, this method has drawbacks, including infection, cost, and donor-site morbidity. Therefore, we used an autologous conjoined fascial flap composed of the pectoralis major, serratus anterior, and external oblique fascia in patients with small-to-medium breasts. METHODS: A series of 11 immediate breast reconstructions in 11 patients was carried out from March 2010 to June 2011. The conjoined fascial flap and smooth round implants were used in all patients. Postoperative photographs were evaluated by a blinded panel and scored on a four-point scale. Patient satisfaction was evaluated by a postoperative questionnaire that had five items designed to evaluate quality of life with the reconstruction. RESULTS: The mean body mass index was 23.2 kg/m(2), follow-up period was 30.9 months, and implant volume was 286.3 cc. Regarding complications, we observed one case of partial skin flap necrosis and one case of seroma accumulation in the axilla, both of which healed with conservative care. The mean overall breast satisfaction score was 3.18 ± 0.5. CONCLUSIONS: The conjoined fascial flap is a viable alternative for immediate one-stage breast reconstruction with an implant. We recommend appropriate patient selection with a body mass index greater than 20 kg/m(2) and small-to-medium sized nonptotic breasts. LEVEL OF EVIDENCE IV: This journal requires that authors assign a level of evidence to each article. For a full description of these Evidence-Based Medicine ratings, please refer to the Table of Contents or the online Instructions to Authors http://www.springer.com/00266 .

Treatment outcome and long-term stability of orthognathic surgery for facial asymmetry: A systematic review and meta-analysis.

Objective: : This systematic review aimed to provide a comparative analysis of the treatment outcomes, including hard and soft tissues, postoperative stability, temporomandibular disorders (TMD), and quality of life (QoL), in patients with facial asymmetry who underwent orthognathic surgery. Methods: : The primary objective was to address the question, "How do different factors related to surgery affect the outcomes and stability of orthognathic surgery in the correction of facial asymmetry?" A meta-analysis was conducted on the outcome parameters, such as skeletal, dental, and soft tissue symmetry, TMD, QoL, and relapse, using the Hartung-Knapp-Sidik-Jonkman method for random-effects models. Subgroup analyses were conducted considering surgery-related factors such as surgical techniques (one-jaw vs. two-jaw), use of the surgery-first approach, utilization of computer simulation, and analytical methods employed to evaluate asymmetry (2D vs. 3D). Results: : Forty-nine articles met the inclusion criteria. The meta-analysis demonstrated a significant improvement in the symmetry of hard and soft tissues. The subgroup analysis indicated that the treatment outcomes showed significant improvement, regardless of the factors related to surgery. Changes in TMD signs and symptoms varied according to the surgical technique used. Quality of life improved in the facial, oral, and social domains. Skeletal relapse was observed during the follow-up. Conclusions: : Our findings support the positive outcomes of orthognathic surgery in the treatment of facial asymmetry in terms of skeletal and soft tissue improvements, stability, relief of TMD symptoms, and enhancement of QoL. However, most of the included studies showed a low certainty of evidence and high heterogeneity.

Development of the Korean construction job exposure matrix (KoConJEM) based on experts' judgment using the 60 consolidated occupations for construction workers.

BACKGROUND: This study was conducted as an effort to develop a Korean construction job exposure matrix (KoConJEM) based on 60 occupations recently consolidated by the construction workers mutual aid association for use by the construction industry. METHODS: The probability, intensity, and prevalence of exposure to 26 hazardous agents for 60 consolidated occupations were evaluated as binary (Yes/No) or four categories (1 to 4) by 30 industrial hygiene experts. The score for risk was calculated by multiplying the exposure intensity by the prevalence of exposure. Fleiss' kappa for each hazardous agent and occupation was used to determine agreement among the 30 experts. The JEM was expressed on a heatmap and a web-based dashboard to facilitate comparison of factors affecting exposure according to each occupation and hazardous agent. RESULTS: Awkward posture, heat/cold, heavy lifting, and noise were hazardous agents regarded as exposure is probable by at least one or more experts in all occupations, while exposure to asphalt fumes was considered hazardous in the smallest number of occupations (n = 5). Based on the degree of agreement among experts, more than half of the harmful factors and most occupations showed fair to good results. The highest risk value was 16 for awkward posture for most occupations other than safety officer. CONCLUSIONS: The KoConJEM provides information on the probability, intensity, and prevalence of exposure to harmful factors, including most occupations employing construction workers; therefore, it may be useful in the conduct of epidemiological studies on assessment of health risk for construction workers.

Accuracy of posteroanterior cephalogram landmarks and measurements identification using a cascaded convolutional neural network algorithm: A multicenter study.

Objective: : To quantify the effects of midline-related landmark identification on midline deviation measurements in posteroanterior (PA) cephalograms using a cascaded convolutional neural network (CNN). Methods: : A total of 2,903 PA cephalogram images obtained from 9 university hospitals were divided into training, internal validation, and test sets (n = 2,150, 376, and 377). As the gold standard, 2 orthodontic professors marked the bilateral landmarks, including the frontozygomatic suture point and latero-orbitale (LO), and the midline landmarks, including the crista galli, anterior nasal spine (ANS), upper dental midpoint (UDM), lower dental midpoint (LDM), and menton (Me). For the test, Examiner-1 and Examiner-2 (3-year and 1-year orthodontic residents) and the Cascaded-CNN models marked the landmarks. After point-to-point errors of landmark identification, the successful detection rate (SDR) and distance and direction of the midline landmark deviation from the midsagittal line (ANS-mid, UDM-mid, LDM-mid, and Me-mid) were measured, and statistical analysis was performed. Results: : The cascaded-CNN algorithm showed a clinically acceptable level of point-to-point error (1.26 mm vs. 1.57 mm in Examiner-1 and 1.75 mm in Examiner-2). The average SDR within the 2 mm range was 83.2%, with high accuracy at the LO (right, 96.9%; left, 97.1%), and UDM (96.9%). The absolute measurement errors were less than 1 mm for ANS-mid, UDM-mid, and LDM-mid compared with the gold standard. Conclusions: : The cascaded-CNN model may be considered an effective tool for the auto-identification of midline landmarks and quantification of midline deviation in PA cephalograms of adult patients, regardless of variations in the image acquisition method.