Sawsan Ali Alomari

Dr. Sawsan Ali Alomari

orcid

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
4 April 2026 in Children
Verified
Journal Article
Open access
PDF file
NHNarmin Helal
Narmin Helal
AAAbdulrahman Fuad Aljehani
Abdulrahman Fuad Aljehani
SASawsan Ali Alomari
Sawsan Ali Alomari
RMReem A. Mahmoud
Reem A. Mahmoud
HKHanadi M Khalifa
Hanadi M Khalifa
Background/Objectives: This study aimed to develop and evaluate deep learning models for the detection, localization, and classification of impacted maxillary canines, and to compare their performance with cone-beam computed tomography (CBCT) as the reference standard. Methods: This cross-sectional diagnostic accuracy study was conducted at King Abdulaziz University Dental Hospital to develop and validate artificial intelligence (AI) models for detecting and localizing maxillary canine impactions using panoramic and cone-beam computed tomography (CBCT) imaging data. A total of 641 panoramic ra and 158 CBCT scans were collected, of which 158 cases had matched panoramic–CBCT pairs for localization analysis. Images were annotated and validated by expert radiologists and orthodontists, with consensus review ensuring labeling reliability. Data augmentation expanded each panoramic and CBCT category to 500 samples for panoramic and 1000 samples for CBCT, resulting in 1935 panoramic and 5703 CBCT images after preprocessing and normalization. The datasets were divided into (training + validation) (80%) and testing (20%) subsets. MobileNetV2 architectures were used for classification, and whdiographsile, a ResNet-50–based Few-Shot Learning framework, enabled spatial localization of impacted canines. Models were trained using the Adam optimizer with a learning rate of 1 × 10−4 and evaluated using accuracy, precision, recall, F1 score, and area under the receiver operating characteristic curve (AUC). Cohen’s kappa and 95% confidence intervals were used to assess agreement between AI predictions and expert annotations. Results: Panoramic classification achieved 94% accuracy, demonstrating the highest performance in normal cases and reduced recall for bilateral impactions. The CBCT classifier achieved 98% accuracy across positional categories. Cross-modality prediction reached 93.5% accuracy, with strong agreement compared to CBCT (Cohen’s kappa = 0.91). Expert review confirmed reliable localization of impacted canines on both imaging modalities. Conclusions: Artificial intelligence applied to panoramic radiographs supports the detection, localization, and characterization of impacted maxillary canines with performance comparable to CBCT. This approach may enable lower-radiation decision support for clinical triage.

9 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
HSHanadi Sabban
Hanadi Sabban
SBSara Bagher
Sara Bagher
DADaniah Alhazmi
Daniah Alhazmi
RHRotana Hafiz
Rotana Hafiz
RBRahaf Babader
Rahaf Babader
OFOsama Felemban
Osama Felemban
Background/Objectives: Bitewing (BW) radiographs are essential for detecting proximal caries but may cause discomfort and anxiety in children. Virtual reality (VR) distraction reduces procedural pain in several dental interventions, but its use during dental radiography has not been investigated. This study evaluated the effect of VR distraction on objective and subjective discomfort and pain during BW imaging in children aged 4–12 years. Methods: In this parallel-group randomized controlled clinical trial at King Abdulaziz University Dental Hospital, Jeddah, Saudi Arabia (ClinicalTrials.gov NCT07376941), 74 cooperative children were randomized 1:1 to VR distraction (n = 37) or no distraction (n = 37). Sessions were video recorded, and two calibrated examiners scored objective pain behavior with a modified Face, Legs, Activity, Cry, and Consolability (FLACC) scale (Face item excluded because the headset obscured facial expressions), the primary outcome. Immediately afterwards, children rated pain with the Arabic Wong–Baker FACES Pain Rating Scale and satisfaction on a 10-point Likert scale (secondary outcomes). Results: Groups were comparable at baseline. A modified FLACC score of zero was more frequent in the VR group (83.8% vs. 67.6%), but the difference was not significant (p = 0.267). More children in the VR group self-reported zero pain (91.9% vs. 70.3%; p = 0.044). Maximum satisfaction did not differ significantly (89.2% vs. 83.8%; p = 0.368). No adverse events were reported. Conclusions: VR distraction did not significantly reduce examiner-rated pain behavior, the primary outcome. The significant difference in self-reported pain, a secondary outcome without adjustment for multiplicity, should be regarded as exploratory. Adequately powered multicenter trials with blinded outcome assessment are needed.