ABSTRACT
Objective: To develop a multi-classification orthodontic image recognition system using the SqueezeNet deep learning model for automatic classification of orthodontic image data. Methods: A total of 35 000 clinical orthodontic images were collected in the Department of Orthodontics, Capital Medical University School of Stomatology, from October to November 2020 and June to July 2021. The images were from 490 orthodontic patients with a male-to-female ratio of 49∶51 and the age range of 4 to 45 years. After data cleaning based on inclusion and exclusion criteria, the final image dataset included 17 453 face images (frontal, smiling, 90° right, 90° left, 45° right, and 45° left), 8 026 intraoral images [frontal occlusion, right occlusion, left occlusion, upper occlusal view (original and flipped), lower occlusal view (original and flipped) and coverage of occlusal relationship], 4 115 X-ray images [lateral skull X-ray from the left side, lateral skull X-ray from the right side, frontal skull X-ray, cone-beam CT (CBCT), and wrist bone X-ray] and 684 other non-orthodontic images. A labeling team composed of orthodontic doctoral students, associate professors, and professors used image labeling tools to classify the orthodontic images into 20 categories, including 6 face image categories, 8 intraoral image categories, 5 X-ray image categories, and other images. The data for each label were randomly divided into training, validation, and testing sets in an 8∶1∶1 ratio using the random function in the Python programming language. The improved SqueezeNet deep learning model was used for training, and 13 000 natural images from the ImageNet open-source dataset were used as additional non-orthodontic images for algorithm optimization of anomaly data processing. A multi-classification orthodontic image recognition system based on deep learning models was constructed. The accuracy of the orthodontic image classification was evaluated using precision, recall, F1 score, and confusion matrix based on the prediction results of the test set. The reliability of the model's image classification judgment logic was verified using the gradient-weighted class activation mapping (Grad-CAM) method to generate heat maps. Results: After data cleaning and labeling, a total of 30 278 orthodontic images were included in the dataset. The test set classification results showed that the precision, recall, and F1 scores of most classification labels were 100%, with only 5 misclassified images out of 3 047, resulting in a system accuracy of 99.84%(3 042/3 047). The precision of anomaly data processing was 100% (10 500/10 500). The heat map showed that the judgment basis of the SqueezeNet deep learning model in the image classification process was basically consistent with that of humans. Conclusions: This study developed a multi-classification orthodontic image recognition system for automatic classification of 20 types of orthodontic images based on the improved SqueezeNet deep learning model. The system exhibitted good accuracy in orthodontic image classification.
Subject(s)
Humans , Male , Female , Child, Preschool , Child , Adolescent , Young Adult , Adult , Middle Aged , Deep Learning , Reproducibility of Results , Radiography , Algorithms , Cone-Beam Computed TomographyABSTRACT
Objective: To establish a comprehensive diagnostic classification model of lateral cephalograms based on artificial intelligence (AI) to provide reference for orthodontic diagnosis. Methods: A total of 2 894 lateral cephalograms were collected in Department of Orthodontics, Capital Medical University School of Stomatology from January 2015 to December 2021 to construct a data set, including 1 351 males and 1 543 females with a mean age of (26.4± 7.4) years. Firstly, 2 orthodontists (with 5 and 8 years of orthodontic experience, respectively) performed manual annotation and calculated measurement for primary classification, and then 2 senior orthodontists (with more than 20 years of orthodontic experience) verified the 8 diagnostic classifications including skeletal and dental indices. The data were randomly divided into training, validation, and test sets in the ratio of 7∶2∶1. The open source DenseNet121 was used to construct the model. The performance of the model was evaluated by classification accuracy, precision rate, sensitivity, specificity and area under the curve (AUC). Visualization of model regions of interest through class activation heatmaps. Results: The automatic classification model of lateral cephalograms was successfully established. It took 0.012 s on average to make 8 diagnoses on a lateral cephalogram. The accuracy of 5 classifications was 80%-90%, including sagittal and vertical skeletal facial pattern, mandibular growth, inclination of upper incisors, and protrusion of lower incisors. The acuracy rate of 3 classifications was 70%-80%, including maxillary growth, inclination of lower incisors and protrusion of upper incisors. The average AUC of each classification was ≥0.90. The class activation heat map of successfully classified lateral cephalograms showed that the AI model activation regions were distributed in the relevant structural regions. Conclusions: In this study, an automatic classification model for lateral cephalograms was established based on the DenseNet121 to achieve rapid classification of eight commonly used clinical diagnostic items.
Subject(s)
Male , Female , Humans , Young Adult , Adult , Artificial Intelligence , Deep Learning , Cephalometry , Maxilla , Mandible/diagnostic imagingABSTRACT
The treatment of skeletal Class III malocclusion in adolescents is challenging.Maxillary protraction, particularly that using bone anchorage, has been proven to be an effective method for the stimulation of maxillary growth. However, the conventional procedure, which involves the surgical implantation of mini-plates, is traumatic and associated with a high risk. Three-dimensional (3D) digital technology offers the possibility of individualized treatment. Customized miniplates can be designed according to the shape of the maxillary surface and the positions of the roots on cone-beam computed tomography scans; this reduces both the surgical risk and patient trauma. Here we report a case involving a 12-year-old adolescent girl with skeletal Class III malocclusion and midface deficiency that was treated in two phases. In phase 1, rapid maxillary expansion and protraction were performed using 3D-printed mini-plates for anchorage.The mini-plates exhibited better adaptation to the bone contour, and titanium screw implantation was safer because of the customized design. The orthopedic force applied to each mini-plate was approximately 400–500 g, and the plates remained stable during the maxillary protraction process, which exhibited efficacious orthopedic effects and significantly improved the facial profile and esthetics. In phase 2, fixed appliances were used for alignment and leveling of the maxillary and mandibular dentitions. The complete two-phase treatment lasted for 24 months. After 48 months of retention, the treatment outcomes remained stable.
ABSTRACT
The miniplate was designed and three-dimensional (3D) printed according to the positions of roots and tooth germs and then it was used as skeletal anchorage to protract the maxilla. The maxilla moved forward obviously after treatment. Custom designed and 3D printed miniplate could be used for maxillary protraction.
ABSTRACT
Vaccinia virus ( VACV) has been widely used in humans for the eradication of small-pox. Since its natural ability of selective infection and replication in tumor cells without harming the normal tissue, VACV becomes a promising candidate in cancer therapy. In recent years, a variety of strategies have been successfully applied to further enhance the tumor selectivity and anti-tumor efficacy of VACV. These engineered VACVs, such as JX-594, have shown promising results in cancer treatment and have made re-markable progress in clinical trials. This review first briefly introduces the oncolytic VACV, and then focuses on the strategies applied in VACV engineering. We also discuss the main challenges and the future directions in the development of oncolytic VACV.