Refine
Has Fulltext
- yes (24)
Is part of the Bibliography
- yes (24)
Document Type
- Journal article (23)
- Doctoral Thesis (1)
Keywords
- HNSCC (5)
- artificial intelligence (5)
- head and neck cancer (5)
- caloric restriction (3)
- deep learning (3)
- machine learning (3)
- prediction (3)
- ARONJ (2)
- HGF (2)
- Met (2)
- amino acid restriction (2)
- cancer metabolism (2)
- classification (2)
- mass spectrometry (2)
- methionine (2)
- osteonecrosis of the jaw (2)
- osteoradionecrosis (2)
- 2-DG (1)
- 2-deoxy-D-glucose (1)
- AMPK (1)
- Adult (1)
- CBCT (1)
- CD44 (1)
- COPD (1)
- Cephalometry (1)
- Compound 3k (1)
- DASA-58 (1)
- Dysgnathie (1)
- FasL (1)
- Fernröntgenseitenbild (1)
- Head (1)
- Kephalometrie (1)
- Kraniometrie (1)
- L929 (1)
- LC/MS (1)
- MRONJ (1)
- NFκB (1)
- OHIP-49 (1)
- ONJ (1)
- PD-L1 (1)
- PET (1)
- PKM2 (1)
- Rhabdomyosarcoma (1)
- SCCHN (1)
- SLC-family (1)
- SWLS (1)
- Spindle cell (1)
- Surgery (1)
- TNFα (1)
- TPCA1 (1)
- TXNIP (1)
- Volumentomographie (1)
- Warburg effect (1)
- X-ray (1)
- agar diffusion test (1)
- alveolar bone loss (1)
- amino acid (1)
- amino acid transporter (1)
- ampicillin (1)
- antibiotic bone concentration (1)
- antiresorptive drug-related osteonecrosis of the jaw (1)
- apoptosis (1)
- beta-lactam (1)
- bone loss (1)
- cancer (1)
- case report (1)
- cell vitality (1)
- cisplatin (1)
- complications (1)
- computer-aided (1)
- contact inhibition (1)
- craniofacial orthodontics (1)
- design (1)
- donor-site morbidity (1)
- energy restriction (1)
- fibroblast activation protein (1)
- fibula (1)
- frailty (1)
- free skin grafts (1)
- geriatric cancer patient (1)
- gingivitis (1)
- glucose restriction (1)
- glycolysis (1)
- graft (1)
- immune therapy (1)
- inflammation (1)
- inhibitor (1)
- intraosseous (1)
- ischemia (1)
- jaw bone (1)
- lateral radiograph (1)
- length of stay (1)
- liquid chromatography/mass spectrometry (1)
- low carb (1)
- low energy metabolism (1)
- lymph node (1)
- malocclusion (1)
- mandible (1)
- mandibular (1)
- manufacturing (CAD/CAM) (1)
- maxillofacial surgery (1)
- medication-related osteonecrosis of the jaw (1)
- metabolomics (1)
- methionine restriction (1)
- model (1)
- molecular imaging (1)
- multicentric (1)
- object detection (1)
- operative planning (1)
- oral functional capacity (1)
- oral health (1)
- oral health-related quality of life (1)
- oral microbiome (1)
- oral squamous cell carcinoma (1)
- oral-health-related quality of life (1)
- oro-antral communication (1)
- oro-antral fistula (1)
- oroantral fistula (1)
- oropharyngeal carcinoma (1)
- osteocutaneous (1)
- pN1 (1)
- perfusion culture (1)
- periodontitis (1)
- physical examination (1)
- planning (1)
- platelet-rich fibrin (1)
- preoperative (1)
- progression-free survival (1)
- proliferation (1)
- prospective (1)
- prosthetic rehabilitation (1)
- pseudocarcinomatous hyperplasia (1)
- quality of life (1)
- radial forearm flap (1)
- radiographic bone loss (1)
- radiotherapy (1)
- reconstruction (1)
- recurrent/metastatic head and neck squamous cell carcinoma (1)
- resection (1)
- satisfaction with life (1)
- surgery (1)
- survival (1)
- teeth extraction (1)
- three-dimensional imaging (1)
- tooth extraction (1)
- treatment benefit (1)
Institute
- Klinik und Poliklinik für Mund-, Kiefer- und Plastische Gesichtschirurgie (24)
- Comprehensive Cancer Center Mainfranken (4)
- Pathologisches Institut (3)
- Poliklinik für Zahnärztliche Prothetik (3)
- Theodor-Boveri-Institut für Biowissenschaften (3)
- Institut für Hygiene und Mikrobiologie (2)
- Institut für Pharmazie und Lebensmittelchemie (2)
- Medizinische Klinik und Poliklinik II (2)
- Institut für diagnostische und interventionelle Radiologie (Institut für Röntgendiagnostik) (1)
- Klinik und Poliklinik für Hals-, Nasen- und Ohrenkrankheiten, plastische und ästhetische Operationen (1)
Sonstige beteiligte Institutionen
Periodontitis is one of the most prevalent diseases worldwide. The degree of radiographic bone loss can be used to assess the course of therapy or the severity of the disease. Since automated bone loss detection has many benefits, our goal was to develop a multi-object detection algorithm based on artificial intelligence that would be able to detect and quantify radiographic bone loss using standard two-dimensional radiographic images in the maxillary posterior region. This study was conducted by combining three recent online databases and validating the results using an external validation dataset from our organization. There were 1414 images for training and testing and 341 for external validation in the final dataset. We applied a Keypoint RCNN with a ResNet-50-FPN backbone network for both boundary box and keypoint detection. The intersection over union (IoU) and the object keypoint similarity (OKS) were used for model evaluation. The evaluation of the boundary box metrics showed a moderate overlapping with the ground truth, revealing an average precision of up to 0.758. The average precision and recall over all five folds were 0.694 and 0.611, respectively. Mean average precision and recall for the keypoint detection were 0.632 and 0.579, respectively. Despite only using a small and heterogeneous set of images for training, our results indicate that the algorithm is able to learn the objects of interest, although without sufficient accuracy due to the limited number of images and a large amount of information available in panoramic radiographs. Considering the widespread availability of panoramic radiographs as well as the increasing use of online databases, the presented model can be further improved in the future to facilitate its implementation in clinics.