Faezeh Dehghan Ghanatkaman

Dr. Faezeh Dehghan Ghanatkaman

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
17 June 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
JRJohan Andreas Balle Rubak
Johan Andreas Balle Rubak
SHSara Haghighat
Sara Haghighat
SJSanyam Jain
Sanyam Jain
Mostafa AldesokiMostafa Aldesoki
Mostafa Aldesoki
Akhilanand ChaurasiaAkhilanand Chaurasia
Akhilanand Chaurasia
Ruben PauwelsRuben Pauwels
Ruben Pauwels
Impaction of the mandibular third molar in proximity to the mandibular canal increases the risk of inferior alveolar nerve injury. Panoramic radiography is routinely used to assess this relationship. Automated classification of molar–canal overlap could support clinical triage and reduce unnecessary CBCT referrals, while Federated Learning (FL) enables multi-center collaboration without sharing patient data. We compared Local Learning (LL), FL, and Centralized Learning (CL) for binary overlap/no-overlap classification on cropped panoramic radiographs partitioned across eight independent labelers in a simulated heterogeneous multi-center setting. A pretrained ResNet-34 was trained under each paradigm and evaluated using per-client metrics with locally optimized thresholds and pooled test performance with a global threshold. Performance was assessed using area under the receiver operating characteristic curve (AUC) and threshold-based metrics, alongside training dynamics, Grad-CAM visualizations, and server-side aggregate monitoring signals. On the test set, CL achieved the highest performance (AUC 0.831; accuracy ≈ 0.782), FL showed intermediate performance (AUC 0.757; accuracy ≈ 0.703), and LL generalized poorly across clients (AUC range ≈ 0.619–0.734; mean ≈ 0.672). Training curves suggested overfitting, particularly in LL models, and Grad-CAM indicated more anatomically focused attention in CL and FL. Overall, centralized training provided the strongest performance, while FL offers a privacy-preserving alternative that outperforms LL.

1 January 2026 in BioMed Research International
Verified
Journal Article
Open access
PDF file
RSReyhaneh Shoorgashti
Reyhaneh Shoorgashti
Faezeh Dehghan GhanatkamanFaezeh Dehghan Ghanatkaman
Faezeh Dehghan Ghanatkaman
SBSana Baghizadeh
Sana Baghizadeh
SESarah Sadat Ehsani
Sarah Sadat Ehsani
SLSimin Lesan
Simin Lesan
HEHooman Ebrahimi
Hooman Ebrahimi
Background: Methicillin‐resistant Staphylococcus aureus poses a serious threat to global health due to its resistance to conventional antibiotics and its ability to form resilient biofilms. Cold atmospheric plasma has emerged as a promising alternative for microbial biofilm inactivation. Objective: To systematically evaluate the in vitro efficacy of cold atmospheric plasma in disrupting or eradicating methicillin‐resistant Staphylococcus aureus biofilms and to identify factors influencing treatment outcomes Methods: A comprehensive search was conducted in five databases (PubMed/MEDLINE, Embase, Scopus, Web of Science, and Google Scholar) for in vitro studies published up to July 2025. Eligible studies assessed cold atmospheric plasma effects on methicillin‐resistant Staphylococcus aureus biofilms. Data were extracted on study characteristics, cold atmospheric plasma device parameters, exposure conditions, and microbial outcomes. Risk of bias was assessed using a modified version of the ToxRTool. Results: Seventeen in vitro studies were included. Most studies originated from European countries ( n = 10), with a peak in publications observed in 2021. Dielectric barrier discharge and plasma jets were the most common devices. Air‐based plasmas were the most commonly used in 12 studies, followed by helium. All studies reported cold atmospheric plasma‐mediated reductions in methicillin‐resistant Staphylococcus aureus biofilm load, with log 10 colony‐forming unit reductions ranging from 1 to > 6, depending on exposure time, surface material, and device configuration. Several studies demonstrated near‐complete biofilm eradication within minutes. Synergistic effects were observed when cold atmospheric plasma was combined with antibiotics. Conclusions: These findings suggest that cold atmospheric plasma may have potential as an adjunctive strategy for biofilm‐related infection control, although further standardized and clinically relevant studies are needed.

5 November 2026 in Journal of Biomedical Materials Research Part B: Applied Biomaterials
Verified
Journal Article
Closed access
PDF file
PAPouya Azarandaz
Pouya Azarandaz
Faezeh Dehghan GhanatkamanFaezeh Dehghan Ghanatkaman
Faezeh Dehghan Ghanatkaman
RSReyhaneh Shoorgashti
Reyhaneh Shoorgashti
FAFarzaneh Azargoshasbi
Farzaneh Azargoshasbi
MMMehran Mirbagheri
Mehran Mirbagheri
MRMaziar Ramezani
Maziar Ramezani

20 May 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
SJSanyam Jain
Sanyam Jain
SHSara Haghighat
Sara Haghighat
Mostafa AldesokiMostafa Aldesoki
Mostafa Aldesoki
Akhilanand ChaurasiaAkhilanand Chaurasia
Akhilanand Chaurasia
SESarah Sadat Ehsani
Sarah Sadat Ehsani
Ruben PauwelsRuben Pauwels
Ruben Pauwels
In oral surgery, the classification of the proximity of the mandibular third molar to the mandibular canal, typically performed on panoramic radiographs, is essential for surgical planning. While artificial intelligence (AI) tools have been explored for this task, their performance is limited due to data scarcity and class imbalance. In this work, we study the potential of synthetic data generation for this task using Denoising Diffusion Probabilistic Models (DDPMs) and Generative Adversarial Networks (GANs), both unconditional and conditioned to the tooth-canal relationship. We used public datasets to create and label a training dataset of 5416 images. The results show the lowest Fréchet inception distance (FID) / second-highest Inception Score (IS) for the unconditional GAN (32.48 / 2.14). The unconditional DDPM showed an FID of 34.28 and IS of 1.95. Conditional models showed similar IS but a worse overall FID of 68.19 and 219.11 for DDPM and GAN, respectively. In a paired observer study between the two unconditional models, clinical observers found the DDPM image to be more realistic in 69.6% of cases. Future work should investigate downstream effects of GANs and DDPMs used in data augmentation for the training of an AI classifier.