JGJoseph George Ghafari

Joseph George Ghafari

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Joseph George Ghafari has a total of 13 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Long-Term (>10 Years) Effects of Medical and Surgical Airway Obstruction Treatment on Dentofacial Morphology

    by Anthony T. Macari, Annie Babakhanian, Ingrid Karam, Joseph G. Ghafari

    Airway obstruction may lead to dentofacial dysmorphogenesis, with severity influenced by age, duration, and extent of obstruction. Aims: to evaluate long-term craniofacial changes in children with a history of mouth breathing, comparing outcomes between those treated with lymphoid tissue removal or with medication, and considering treatment age. Materials and Methods: Fifty-seven patients with a mean age of 19.09 years (range: 15.1–25.2 years) who had been evaluated in an earlier study (T1) were recalled at an average of 13 years follow-up (T2) and classified into a surgical group (n = 34), who had an adenoidectomy, and a non-surgical group (n = 23) treated with medication. Lateral cephalograms were obtained and compared with the original pre-treatment records. Control groups were included, matching the subjects in both groups for age and sex. Statistical analyses included group comparisons and associations among variables. Results: Significant improvement in both treatment groups were observed for the gonial angle (Ar-Go-Me), facial convexity (S-N-Me) and facial height (N-Gn), but T2-T1 changes in the surgical group were statistically significantly greater than in the medical therapy group. The palatal plane inclination to the horizontal (PP/H) and the mandibular plane inclination (MP/H) and to cranial base (MP/SN) were significantly improved in both groups (0.001 < p < 0.01). Conclusions: Both surgical and medical treatment of airway obstruction resulted in the reversal of the harmful effect of the obstruction. However, adenoidectomy was associated with greater improvements, possibly because the original obstruction was more severe and longer-standing. The results underline the importance of early recognition and management of airway obstruction to mitigate developmental orofacial dysmorphology.

  • Open Access

    Three-Dimensional Semantic Segmentation of Palatal Rugae and Maxillary Teeth and Motion Evaluation of Orthodontically Treated Teeth Using Convolutional Neural Networks

    by Abdul Rehman El Bsat, Elie Shammas, Daniel Asmar, Kinan G. Zeno, Anthony T. Macari, Joseph G. Ghafari

    Background: The segmentation of individual teeth in three-dimensional (3D) dental models is a key step in orthodontic computer-aided design systems. Traditional methods lack robustness when handling challenging cases such as missing or misaligned teeth. Objectives: to semantically segment maxillary teeth and palatal rugae in 3D textured scans using Convolutional Neural Networks (CNNs) and assess tooth movement after orthodontic treatment using stable rugae references. Methods: Building on the robustness of two-dimensional image semantic segmentation, we developed a method to convert 3D textured palate scans into two-dimensional images for segmentation, then back projected them onto the original 3D meshes. A dataset of 100 textured scans from 100 patients seeking orthodontic treatment was manually segmented by orthodontic experts. The proposed 3D segmentation method was applied to these scans. Finally, each pair of segmented 3D scans from the same patient, before and after treatment, was aligned by superimposing them on the stable rugae region. Results: The 3D segmentation method achieved an accuracy of 98.69% and an average Intersection over Union (IoU) of 84.5%. The common stable coordinate frame for both scans using the rugae area as a stable reference enabled the computation of the 3D translational and rotational motions of each maxillary tooth. Neither pre- nor post-processing of the data was required to enhance segmentation. Conclusions: The proposed method enabled successful motion measurement of teeth using the rugal area as a stable reference and providing rotation and translational measurements of the maxillary teeth.


  • Open Access

    Long term self-resolution of a mandibular traumatic bone cyst: A patient report

    by Kinan G Zeno, Wedad Z Saab, Lea Al Matny, Rachid Haidar, Joseph G Ghafari

    Long term self-resolution of a mandibular traumatic bone cyst: A patient report - JOOO- Print ISSN No: - 2395-6186 Online ISSN No:- 2395-6194 Article DOI No:- 10.18231/j.jooo.2024.025, Journal of Oral Medicine, Oral Surgery, Oral Pathology and Oral Radiology-J Oral Med Oral Surg Oral Pathol Oral Radiol

  • Open Access

    Semantic Segmentation of Maxillary Teeth and Palatal Rugae in Two-Dimensional Images

    by Abdul Rehman El Bsat, Elie Shammas, Daniel Asmar, George E. Sakr, Kinan G. Zeno, Anthony T. Macari, Joseph G. Ghafari

    The superimposition of sequential radiographs of the head is commonly used to determine the amount and direction of orthodontic tooth movement. A harmless method includes the timely unlimited superimposition on the relatively stable palatal rugae, but the method is performed manually and, if automated, relies on the best fit of surfaces, not only rugal structures. In the first step, motion estimation requires segmenting and detecting the location of teeth and rugae at any time during the orthodontic intervention. Aim: to develop a process of tooth segmentation that eliminates all manual steps to achieve an autonomous system of assessment of the dentition. Methods: A dataset of 797 occlusal views from photographs of teeth was created. The photographs were manually semantically segmented and labeled. Machine learning methods were applied to identify a robust deep network architecture able to semantically segment teeth in unseen photographs. Using well-defined metrics such as accuracy, precision, and the average mean intersection over union (mIoU), four network architectures were tested: MobileUnet, AdapNet, DenseNet, and SegNet. The robustness of the trained network was additionally tested on a set of 47 image pairs of patients before and after orthodontic treatment. Results: SegNet was the most accurate network, producing 95.19% accuracy and an average mIoU value of 86.66% for the main sample and 86.2% for pre- and post-treatment images. Conclusions: Four architectural tests were developed for automated individual teeth segmentation and detection in two-dimensional photos that required no post-processing. Accuracy and robustness were best achieved with SegNet. Further research should focus on clinical applications and 3D system development.


  • New insights on age‐related association between nasopharyngeal airway clearance and facial morphology

    by A. T. Macari, M. A. Bitar, J. G. Ghafari

    Macari A. T., Bitar M.A., Ghafari J.G. New insights on age‐related association between nasopharyngeal airway clearance and facial morphology Orthod Craniofac Res 2012;15:188–197. © 2012 John Wiley & Sons A/SStructured Objectives –  To evaluate the relation between adenoid hypertrophy and facial morphology across age in a pediatric population.Setting and Sample Population –  The American University of Beirut Department of Otolaryngology. Two‐hundred consecutive children (age 6.00 ± 2.62 years) referred from the Pediatric Otolaryngology unit to the Orthodontic division and requiring a lateral cephalogram for adenoid hypertrophy assessment.Methods –  Cephalometric measurements included relations among cranial base, maxilla and mandible, and airway clearance measured from adenoid to soft palate (AD). The children were classified into two age groups, Group 1: ≤ 6 years (n = 124) and Group 2: ≥ 6.01 years (n = 76), and also stratified in four subgroups (A, B, C, D) based on maxillo‐mandibular divergence (palatal to mandibular plane angle, PP‐MP): A‐ PP‐MP ≤ 27.5°, n = 34; B‐ 27.5° < PP‐MP ≤ 32°, n = 68; C‐ 32°Results –  Differences between groups 1 and 2 were statistically significant (p < 0.05) for AD (Group 1: 3.19 ± 2.32 mm, Group 2: 4.78 ± 2.80 mm), ANB (5.38 ± 2.24°, 4.38 ± 2.54°), LFH (56.61 ± 1.95%, 55.38 ± 1.84%), PP‐H (−8.41 ± 3.28°, −6.49 ± 3.46°), and overbite (0.55 ± 2.00 mm, 1.16 ± 2.36 mm). Among subgroups, statistically significant differences (p < 0.05) occurred mainly between the most hyperdivergent group (D) and the hypodivergent (A) and normodivergent (B) groups.Conclusions –  Airway measurements were smallest in children ≤ 6 years and those presenting severe hyperdivergent pattern, which denoted the most severe airway obstruction. The findings suggest airway clearance before age 6 in the most severely affected children, but follow‐up research on actual adenoidectomies in younger children is needed to determine guidelines.