• Imaging Science in Dentistry
• /
• v.54 no.3
• /
• pp.232-239
• /
• 2024

Purpose: The use of artificial intelligence (AI) and deep learning algorithms in dentistry, especially for processing radiographic images, has markedly increased. However, detailed information remains limited regarding the accuracy of these algorithms in detecting mandibular fractures. Materials and Methods: This meta-analysis was conducted in accordance with the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines. Specific keywords were generated regarding the accuracy of AI algorithms in detecting mandibular fractures on radiographic images. Then, the PubMed/Medline, Scopus, Embase, and Web of Science databases were searched. The Quality Assessment of Diagnostic Accuracy Studies 2 (QUADAS-2) tool was employed to evaluate potential bias in the selected studies. A pooled analysis of the relevant parameters was conducted using STATA version 17 (StataCorp, College Station, TX, USA), utilizing the metandi command. Results: Of the 49 studies reviewed, 5 met the inclusion criteria. All of the selected studies utilized convolutional neural network algorithms, albeit with varying backbone structures, and all evaluated panoramic radiography images. The pooled analysis yielded a sensitivity of 0.971 (95% confidence interval [CI]: 0.881-0.949), a specificity of 0.813 (95% CI: 0.797-0.824), and a diagnostic odds ratio of 7.109 (95% CI: 5.27-8.913). Conclusion: This review suggests that deep learning algorithms show potential for detecting mandibular fractures on panoramic radiography images. However, their effectiveness is currently limited by the small size and narrow scope of available datasets. Further research with larger and more diverse datasets is crucial to verify the accuracy of these tools in in practical dental settings.

• Imaging Science in Dentistry
• /
• v.54 no.3
• /
• pp.240-250
• /
• 2024

Purpose: This study was performed to assess the clinical validity and accuracy of a deep learning-based automatic landmarking algorithm for cone-beam computed tomography (CBCT). Three-dimensional (3D) CBCT head measurements obtained through manual and automatic landmarking were compared. Materials and Methods: A total of 80 CBCT scans were divided into 3 groups: non-surgical (39 cases); surgical without hardware, namely surgical plates and mini-screws (9 cases); and surgical with hardware (32 cases). Each CBCT scan was analyzed to obtain 53 measurements, comprising 27 lengths, 21 angles, and 5 ratios, which were determined based on 65 landmarks identified using either a manual or a 3D automatic landmark detection method. Results: In comparing measurement values derived from manual and artificial intelligence landmarking, 6 items displayed significant differences: R U6CP-L U6CP, R L3CP-L L3CP, S-N, Or_R-R U3CP, L1L to Me-GoL, and GoR-Gn/S-N (P<0.05). Of the 3 groups, the surgical scans without hardware exhibited the lowest error, reflecting the smallest difference in measurements between human- and artificial intelligence-based landmarking. The time required to identify 65 landmarks was approximately 40-60 minutes per CBCT volume when done manually, compared to 10.9 seconds for the artificial intelligence method (PC specifications: GeForce 2080Ti, 64GB RAM, and an Intel i7 CPU at 3.6 GHz). Conclusion: Measurements obtained with a deep learning-based CBCT automatic landmarking algorithm were similar in accuracy to values derived from manually determined points. By decreasing the time required to calculate these measurements, the efficiency of diagnosis and treatment may be improved.

• The korean journal of orthodontics
• /
• v.36 no.4
• /
• pp.284-294
• /
• 2006

Objective: Activating mutations in the fibroblast growth factor receptor-2 (FGFR2) have been shown to cause syndromic craniosynostosis such as Apert and Crouzon syndromes. The purpose of this pilot study was to investigate the resultant phenotypes induced by the two distinctive bone-targeted gene constructs of FGFR2, Pro253Arg and Cys278Phe, corresponding to human Apert and Crouzon syndromes respectively. Methods: Wild type and a transgenic mouse model with normal FGFR2 were used as controls to examine the validity of the microinjection. Micro-CT and morphometric analysis on the skull revealed the following results. Results: Both Apert and Crouzon mutants of FGFR2 induced fusion of calvarial sutures and anteroposteriorly constricted facial dimension, with anterior crossbite present only in Apert mice. Apert mice differed from Crouzon mice and transgenic mice with normal FGFR2 in the anterior cranial base flexure and calvarial flexure angle which implies a possible difference in the pathogenesis of the two mutations. In contrast, the transgenic mice with normal FGFR2 displayed normal craniofacial phenotype. Conclusion: Apert and Crouzon mutations appear to lead to genotype-specific phenotypes, possibly causing the distinctive sites and sequence of synostosis in the calvaria and cranial base. The exact function of the altered FGFR2 at each suture needs further investigation.

• The korean journal of orthodontics
• /
• v.26 no.4
• /
• pp.325-340
• /
• 1996

Along with traditional goal of 'straightening teeth', today's orthodontics put more and more emphasis on facial esthetics. Naturally, the importance of soft tissue, which dictates one's facial form, is noticed. There have been many cephalometric studies on growth of hard tissue ; however, only a few on that of soft tissue. In Korea, various methods of sampling, measuring and analysing were used to study soft tissue changes, and yet, soft tissue changes along with process of normal growth have not been studied. The author carried out this study as a part of semi-longitudinal study on craniofacial growth and development of Korean children from ages of six to seventeen. 409 boys and 436 girls who'd had no systemic disease for the last three years and shown normal developmental and occlusal status were chosen as subjects. Cephalometric X-rays were taken of each subject, and facial form, lip position & form, nose form, and lip thickness were measured. Mean values and standard deviations were calculated according to age and gender, and figures and tables were drawn accordingly. The following results were obtained: 1. In respect to facial form, boys showed growth for longer period compared to girls. Also, lower face showed higher growth rate than upper face. 2. There was not much change in thickness of upper and lower lips with age; however, they appeared more prominent compared to caucasian children. 3. Nose grew horizontally with age. 4. Horizontal thickness of lower face increased with age, and upper lip thickness at nose base[A-Sn(FH)] showed more growth than anywhere else.

• Journal of Chest Surgery
• /
• v.37 no.7
• /
• pp.591-596
• /
• 2004

Recently, thoracic sympathicotomy for craniofacial hyperhidrosis (FH) is increasingly avoided contrast to palmar hyperhidrosis. We recently demonstrated that selective T2 sympathicotomy for FH in woman might be recommended because of differences of the postoperative satisfaction between man and woman. Therefore, this study was designed to analyze the postoperative long term results, evaluate the effectiveness of T2 sympathicotomy and establish the new strategy in treatment of FH in woman. Material and Method: From May 1998 to July 2001, 27 cases of FH in woman that were performed T2 sympathicotomy and minimum 2 years have passed since then at the follow up period. Among them, 20 cases were evaluated by telephone review and medical record. Bilateral sympathetic trunks were severed on the 2nd rib with 2mm thoracoscopic instruments. 7 patients combined with gustatory sweating (GS). Ages ranged from 25 to 62 (mean age, 46.4 years). Result: All patients were relieved of symptom immediately after operation. At postoperative 1 week, all patients were satisfied: 15 patients, “very satisfaction” and 5 patients, “relatively satisfaction”. However, during long term follow up period (from 25 to 63 months postoperatively), 9 patients (45%) were relatively satisfied, 8 patients (40%) complained that there was no difference of postoperative satisfaction and 3 patients (15%) complained of non satisfactory results (regret for surgery). 16 patients (80%) had complaint of uncomfortable feeling because of postoperative GS. Some degree of compensatory sweating (CS) had occurred in all patients: severe 10 patients (50%), severe but acceptable 6 patients (30%), and just conventional 4 patients (20%). The sites of CS were trunk, back, axilla and extremities. Conclusion: Thoracoscopic T2 sympathicotomy is relatively considerable method for FH in woman and the postoperative satisfaction depends on GS and the degree of individual adaptation for CS. Therefore, it is required that the prediction of preoperative risk factors for GS and CS and then careful selection of patients to increase the postoperative satisfaction, and the development of acceptable new treatment modalities.

• The korean journal of orthodontics
• /
• v.29 no.1 s.72
• /
• pp.51-72
• /
• 1999

In orthodontic field, it is very important to understand the normal growth. Such an understanding can be derived from observation of normal growth in various samples from childhood to adulthood, and this builds a foundation from which growth abnormality or variation can be defined. Thus, a broad data collection of normal children, as well as basic study reviewing such data become necessary. The relationship between the mean values of cephalometric measurements in Growth and Development was studied among the groups(boys and girls) of Korean chidren from the ages 6-years to 16-years. 220 boys 170 girls were chosen as subjects : Cephalometric X-ray were taken for 3 years and hard tissue analysis on McNamara and Ricketts Analysis which was divided into measurements of 5 parts(Cranial base, Cranial base and Maxilla & Mandible, Maxilla and Mandible, Mandible, Dental measurements). The relationship of craniofacial growth was studied. The following conclusions were obtained: 1. There were statistically significant differences in anterior cranial base between the two sexes of 14 and 15-year grouips. 2. In comparison of growth amounts among different age groups, statistically singnificant difference in Posterior facial height exhisted among $10\~11,\;12\~13\;and\;14\~15$ year-old interval groups. This pattern increased with aging. 3. Na perpendicular to A showed earlier growth peak in females(11-12years) than males(12-13years). When horizontal measurements of point A and Pogonion are compared, mandibular growth appeared to be greater. 4. Maximum growth peak of cranial base and mandible was earlier in females (11-12years) than males(13-14 years). 5. Upper central incisor flared out with aging, and there were increases in lower incisor to A-Pg, and lower incisor inclination There was significant difference between the two sexes in 10-year-old group.

• The korean journal of orthodontics
• /
• v.28 no.2 s.67
• /
• pp.219-229
• /
• 1998

The purpose of this study is to define the characteristics of the skeleton and soft tissues of severe adult class III malocclusion. The materials selected for this study were lateral cephalograms of 112 adult class III malocclusion patients with ANB difference below -2 degrees. and the mean age was 22.9 years old. The normal control sampler consisted of lateral cephalograms of 50 adults in normal occlusion and the mean age was 22.1 years old. The Horizontal reference line was FH line and the vertical reference line was nasion perpendicular to FH line. The skeletal and soft tissue characteristics of Class III malocclusion are as follows : 1. In the skeletal profile evaluated by vertical reference line (Nasion perpendicular to FH), the forehead and maxilla was similar to normal, but the mandible was protruded significantly. 2. The soft tissue profile is concave. The thickness of soft tissue covering forehead area and nose is within normal range. but the upper lip is thicker and the nasolabial angle is smaller than normal. The lower lip and inferior labial sulcus is thinner than normal. The degree of eversion of lower lip is lesser than normal. 3. The cranial base of class III malocclusion is shorter and saddle angle is smaller than normal. 4. The location of midface evaluated in relations to cranial base is within normal range but, the length of midface is shorter than normal when compared from the deep portion of the facial skeleton. 5. The location of maxilla in reference to cranial base is within normal range but the length of maxilla was shorter in class III malocclusion. 6. The mandible was protruded, ramus height and body length, gonial angle were greater than normal, and the chin angle was smaller. 7. Upper incisor was proclined, lower incisor was retroclined.

• The korean journal of orthodontics
• /
• v.25 no.3 s.50
• /
• pp.273-286
• /
• 1995

The purpose of this study was to compare the difference of the growth aspects in three facial growth patterns. The biennial serial cephalometric radiographs of 33 samples(19males, 14females) with normal occlusion from 8.5 years to 18.5 yews of age were used in this study. The facial growth patterrn was categorized in 3 types(Drop type, Neutral type, Forward type) by the total amounts of the Y-axis which changed from 8.5 years to 18.5 years of age. The growth change of the craniofacial area during 10 years in each growth type was analyzed and was compared among the 3 growth types. The results of this study might be summarized as follows. 1. The samples that were classified by total change of the Y-axis during this study period were distributed to 52% of the neutral type, 27% of the forward type, 21% of the drop type. 2. The anterior growth of the maxilla to the cranial base(N per A) showed larger in the forward type than in other 2 types(p<0.05). 3. The palatal plane to the FH plane showed more anterior-superior inclination in the forward type with age during this study period. 4. The anterior growth of the mandible to the cranial base(N per Pog) appeared large in rank order, of largest the forward type, second the neutral type, and third the drop type(p<0.05). 5. During this study period the mandibular plane(SN/MN,FMA) showed more counterclockwise rotation in the forward type than in the drop type(p<0.05), and this tendency was stronger in males than in females(p<0.05). 6. The growth of the mandibular corpus length(Go-Me) showed smaller in the drop type than in the other 2 types(p<0.05). 7. In the forward type and the neutral type, the anterior growth of the mandible was larger than that of the maxilla(p<0.05). 8. In the craniofacial growth distances and angulations turned out to be somewhat variable, but the vertical proportion had a strong tendency whose original relation was maintained consistently during this study period. 9. Through these analyzed data, the profilograms on each growth type were constructed to evaluate individual growth pattern in the orthodontic diagnosis.

• The korean journal of orthodontics
• /
• v.22 no.1
• /
• pp.253-271
• /
• 1992

The purpose of this study was to investigate the difference of EMG activity of the Orbicularis oris and Mentalis muscle between normal occlusion and class III malocclusion group during various lip position and to find out whether any correlations exist between the muscular activity and craniofacial morphology. In this study, 50 subjects with a mean age of 22.9 Years (range 20.0-26.0) were investigated (25 subjects were normal occlusion, and 25 subjects were class III malocclusion). EMG data were recorded from the Orbicularis oris and Mentalis muscle during rest lip posture, lip position at maximum biting, lip position at maximum sealing effort, lip position at chewing, swallowing and phonation with the Medelec MS-25 electromyographic machine. Lateral cephalometric radiographs was taken with the mandible in intercuspal position on all subjects. All data were recorded and statistically processed. The findings of this study can be summerized as follows: 1. In normal occlusion, the maximal mean amplitude of upper lip during the lip position at chewing was lower than that of lower lip and mentalis muscle. But the maximal mean amplitude of orbicularis oris and mentalis muscle during the other lip position was not statistically different. 2. In Class III malocclusion, the maximal mean amplitude of upper lip during the lip position at chewing, swallowing and phonation was lower than that of lower lip and mentalis muscle. But the maximal mean amplitude of orbicularis oris and mentalis muscle during the other lip position was not statistically different. 3. Compare to normal occlusion, the Class III malocclusion was showed low maximal mean amplitude of upper lip during rest lip posture and the lip position at swallowing of saliva, and showed great maximal mean amplitude of lower lip and meantalis muscle during the lip position at chewing and phonation. 4. In normal occlusion, the maximal mean amplitude of upper lip during various lip position was not correlated with the length and thickness of upper lip, but the maximal mean amplitude of lower lip during the lip position at chewing and swallowing was positively correlated with the thickness of lower lip. 5. In Class III malocclusion, the maximal mean amplitude of upper lip during rest lip posture was negatively correlated with the thickness of upper lip, and the maximal mean amplitude of lower lip and mentalis muscle during the lip position at chewing and swallowing was positively correlated with the thickness of lower lip and mentalis muscle. But the maximal mean amplitude of orbicularis oris and mentalis muscle during the other lip position was not correlated with the cephalometric measurements of soft tissue. 6. The correlation between the maximal mean amplitude of orbicularis oris and mentalis muscle and cephalometric measurements of incisors was not nearly present. 7. In normal occlusion, the maximal mean amplitude of lower lip and mentalis muscle during the lip position at maximum biting was negatively correlated with the angle between palatal plane and mandibular plane. In Class III malocclusion, the maximal mean amplitude of upper lip, lower lip and mentalis muscle during function was negatively correlated with the length of maxilla, the maximal mean amplitude of upper lip and lower lip during function was negatively correlated with the SNA and SNPo, and the maximal mean amplitude of lower lip during the lip position at chewing was negatively correlated with the ANB.

• The korean journal of orthodontics
• /
• v.27 no.4 s.63
• /
• pp.643-659
• /
• 1997

For the total treatment of skeletal malocclusions, 3-dimensional evaluation and diagnosis are essential. Although anteroposterior discrepancies can be evaluated through various methods, the satisfactory methods for evaluations of facial asymmetry and transverse discrepancies are yet to be found. The adequate diagnosis and treatment of transverse discrepancies may be more important in the maintenance of functional occlusion as well as for the stability of results obtained from orthognathic surgery than the anteroposterior or vertical discrepancies. Since the soft tissue effects from the transverse discrepancies may not be pronounced, especially when combined with anteroposterior or vertical discrepancies which have prominent characteristics, the differentiation of their effects may be difficult from visual inspection alone. Therefore it is essential that the normal facial proportions would be established from the posteroanterior cephalometry as a reference for the accurate diagnosis and treatment. The present study evaluates 76 subjects from Yonsei University freshmen with normal facial symmetry and occlusion. Posteroanterior cephalograms were taken from the subjects and the normal values and facial proportions are obtained. The results are as follows. 1. The transverse and vortical values from posteroanterior cephalometry and their ratio, with means and standard deviations are calculated. 2. The ratio of vertical values to transverse values is 0.837 (male 0.836, female 0.841). 3. The Proportion of maxillary and mandibular widths is 0.747 (male 0.745, female 0.752), with statistically significant correlation. 4. Various degree of significant correlations are observed in the following craniofacial widths; (Cranial width, Bizygomaticofrontal suture width, Facial width, Maxillary width, Upper & Lower Intermolar width, Mandibular width). 5. Although the facial height as well as other line measurements increase as the facial widths increase, angle measurement ($Bj\ddot{o}rk$ Sum, Mandibular Plane Angle, Gonial Angle), decreases and posterior to anterior facial height ratio increases, therefore indicating the tendency for a brachycephalic facial type. These results may be used as references for the treatment planning in orthognathic and orthodontic treatments for the dentofacial deformity patients.