University Clinic of Dentistry
Position: Lecturer
ORCID: 0000-0003-4386-6237
balazs.feher@muv.ac.at
Keywords
Artificial Intelligence; Biostatistics; Bone Regeneration; Guided Tissue Regeneration; Oral Medicine; Oral Surgical Procedures
Research group(s)
- Competence Center of Oral Biology
Head: Reinhard Gruber
Research Area: The Competence Center Oral Biology is involved in dental research and training. The work is done in an interdisciplinary team with national and international cooperation, integrating academia and industry.
Members:
Research interests
Balazs Feher conducts research at the Medical University of Vienna as well as the Harvard School of Dental Medicine. He is also an invited contributor to the ITU/WHO/WIPO Global Initiative on Artificial Intelligence for Health as well as a member of the European Association for Osseointegration's Junior Committee. In 2018, he was awarded the European Prize for Research in Implant Dentistry.
His clinical research focuses on applied data science and artificial intellgence in oral surgery. In extensive collaborative efforts with multiple universities around the world, Prof. Kuchler and Dr. Feher apply novel research methods to the field of dental surgery, ranging from advanced statistical modeling for surgical risk and outcome prediction to artificial intelligence and convolutional neural networks for automated diagnosis.
Dr. Feher further conducts preclinical research focusing on osteocytic signaling in bone regeneration. Osteocytes play a crucial role in bone resorption and regeneration. However, several aspects of their elaborate signaling remain elusive. Prof. Gruber and Dr. Feher investigate osteocytic signaling using Cre/loxP knockout models in cooperation with the Center for Biomedical Research.
Techniques, methods & infrastructure
In their clinical projects, Prof. Kuchler and Dr. Feher use large datasets and advanced analytics to estimate biological processes like postoperative cyst regeneration and predict surgical risk after procedures like wisdom tooth removal or dental implant placement. Moreover, deep learning, specifically convolutional neural networks are used in cooperation with various research institutions, including the Charité in Berlin as well as the Harvard School of Dental Medicine in Boston.
In their preclinical projects, Prof. Gruber and Dr. Feher use Cre/lox knockout models to selectively disable parts of the osteocytic signaling pathway. For analysis, ex vivo micro-computed tomography, histology, and histomorphometry are used in cooperation with the Core Facility Hard Tissue and Biomaterial Research.
Grants
- Osteocytic RANKL expression in bone graft consolidation (2020)
Source of Funding: Osteology Foundation, Young Researcher Grant
Principal Investigator - Disabling osteocyte apoptosis in mice: Impact on calvarial bone regeneration (2019)
Source of Funding: International Team for Implantology Foundation, Small Research Grant
Principal Investigator - Molecular aspects of periodontal health and disease (0)
Source of Funding: Osteology Foundation, Research Scholarship
Principal Investigator
Selected publications
- Feher, B. et al. (2023) ‘The effect of osteocyte‐derived RANKL on bone graft remodeling: An in vivo experimental study’, Clinical Oral Implants Research, 34(12), pp. 1417–1427. Available at: https://doi.org/10.1111/clr.14187.
- Feher, B. et al. (2022) ‘Emulating Clinical Diagnostic Reasoning for Jaw Cysts with Machine Learning’, Diagnostics, 12(8), p. 1968. Available at: https://doi.org/10.3390/diagnostics12081968.
- Feher, B. et al. (2021) ‘Prediction of post-traumatic neuropathy following impacted mandibular third molar removal’, Journal of Dentistry, 115, p. 103838. Available at: https://doi.org/10.1016/j.jdent.2021.103838.
- Feher, B. et al. (2021) ‘A volumetric prediction model for postoperative cyst shrinkage’, Clinical Oral Investigations, 25(11), pp. 6093–6099. Available at: https://doi.org/10.1007/s00784-021-03907-7.
- Feher, B. et al. (2020) ‘An advanced prediction model for postoperative complications and early implant failure’, Clinical Oral Implants Research, 31(10), pp. 928–935. Available at: https://doi.org/10.1111/clr.13636.