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.
Male ; Female ; Humans ; Young Adult ; Adult ; Artificial Intelligence ; Deep Learning ; Cephalometry ; Maxilla ; Mandible/diagnostic imaging*

OBJECTIVE: To provide clinical basis for the diagnosis and treatment of chronic neutrophilic leukemia (CNL) and to provide possible molecular targets for the treatment. METHODS: By summarizing the clinical data of 14 patients with CNL, the clinical characteristics, gene mutation types and possible prognostic factors were analyzed. RESULTS: Among the 14 patients with CNL, males (9 cases) were more than females (5 cases), with a median age of 57 years old. The detection rate of CSF3R mutation was 92.86% (13/14), including 12 cases (85.71%) with T318I mutation and 1 case of Y799X mutation, and only 1 case was not detected for mutation of CSF3R. The ASXL1 mutation was detected in 42.86% (6/14) of the patients, all of which were nonsense mutations, including 4 cases with R693X and 2 cases with E705X, and 14.29% (2/14) of the patients was detected for SETBP1 mutation, all of which were with D868N mutation. No patients with simultaneous ASXL1 and SETBP1 mutations were found, and JAK2 and CALR mutations were not detected. All of the patients had normal karyotypes. These patients' median survival time was 30 months (95%CI 13.19-46.80), and the influence of age over 60 years old was statistically significant (21.83 months vs 35.35 months) (P＜0.05). CONCLUSION It is difficult to diagnose CNL. CSF3R T618I mutation is its specific mutation, and ASXL1 mutation and SETBP1 mutation have auxiliary diagnostic significance for CNL. The age＞60 years old at diagnosis is a factor of unfavourable prognosis.