* Zobrazit nápovědu

OBJECTIVES: Annotating carious lesions on images is challenging. For artificial intelligence (AI) applications, the aggregation of heterogeneous multi-examiner annotations into one single annotation (e.g. via majority voting, MV) is usually needed. We assessed different aggregation strategies for multi-examiner annotations of primary proximal carious lesions on orthoradial radiographs and Near-Infrared Light Transillumination (NILT) images. METHODS: A total of 1007 proximal surfaces from 522 extracted posterior teeth were assessed by five dentists. Histological analysis provided the gold standard. Surfaces were classified as (1) sound, (2) enamel lesion or (3) dentin lesion. Four label aggregation strategies - MV, Weighted Majority Voting (WMV), Dawid-Skene (DS), and multi-annotator competence estimation (MACE) - were applied to unimodal (radiographs, NILT) and multimodal (combined) datasets. The area under the receiver operating characteristic curve (AUROC) was the primary outcome metric. RESULTS: According to the gold standard, 637 (63 %) surfaces were sound, 280 (28 %) showed carious lesions limited to the enamel, and 90 (9 %) showed lesions extending into the dentin. For radiographs, aggregation using MACE outperformed MV, WMV and DS significantly across all lesion depths (p < 0.002). For NILT, MACE significantly outperformed MV across all lesion depths (p < 0.001) and DS for enamel and dentin lesions (p ≤ 0.002). In the multimodal dataset, DS outperformed the other label aggregation strategies across all lesion depths significantly (p < 0.05). CONCLUSIONS: The commonly applied MV may be suboptimal. There is a need for informed application of specific aggregation strategies, depending on the dataset characteristics. CLINICAL SIGNIFICANCE: Most AI applications for dental image analysis are trained on a single annotation, usually resulting from aggregated multi-examiner annotations of each image. However, since these annotations are usually aggregated in an in vivo setting where no definitive ground truth is available, the choice of aggregation strategy plays a crucial role.

MeSH
dentin patologie diagnostické zobrazování MeSH
lidé MeSH
počítačové zpracování obrazu * metody MeSH
rentgendiagnostika zubní MeSH
ROC křivka MeSH
transiluminace MeSH
umělá inteligence MeSH
zubní kaz * diagnostické zobrazování patologie MeSH
zubní sklovina diagnostické zobrazování patologie MeSH
Check Tag
lidé MeSH
Publikační typ
časopisecké články MeSH

Článek online

Slinné biomarkery zubního kazu
[Salivary biomarkers of dental caries]

Merglová, Vlasta, 1953-
Autor Autorita Stomatologická klinika Fakultní nemocnice a Lékařské fakulty v Plzni, Univerzita Karlova v Praze

Pediatrie pro praxi. 2024 ; 25 (6) : 378-383. [pub] 20241231

ISSN 1213-0494
Medvik
Zdroj

Zubní kaz (ZK) je jedno z nejčastějších chronických infekčních onemocnění dětského věku. Kromě nadměrného příjmu sacharidů a přítomnosti zubního mikrobiálního plaku se za další významné rizikové faktory vzniku ZK pokládá složení tvrdých zubních tkání a sliny. Slina odráží fyziologický a patologický stav dutiny ústní a hraje významnou roli při vzniku a prevenci zubního kazu. Možnými biomarkery zubního kazu je řada měřitelných vlastností sliny - množství sliny, pH sliny, pufrovací kapacita, přítomnost a množství kariogenních mikroorganismů. Hlavními složkami sliny jsou voda a různé anorganické a organické substance. Za významné organické látky se považují antimikrobiální peptidy, slinné glykoproteiny a proteiny s enzymatickou aktivitou. Tyto látky mohou sloužit jako zdroj biomarkerů pro stanovení rizika vzniku zubního kazu. Slinné biomarkery mohou být využity nejen pro predikci, diagnostiku, prognózu a ošetřování zubního kazu, ale i pro hodnocení výsledků léčení. Cílem dalších výzkumů bude charakterizovat vztahy mezi jednotlivými proteiny, jejich interakce a určit, jakým způsobem ovlivňují vznik a progresi zubního kazu.

Dental caries is one of the most common chronic infectious diseases of childhood. In addition to excessive sugar intake and presence of dental microbial plaque, other risk factors related to dental caries are the composition of hard dental tissues and saliva. Saliva can reflect the physiological and pathological state of the oral cavity and plays a crucial role in the initiation of dental caries and protection against dental caries. Many measurable characteristics of saliva are potential biomarkers for dental caries - salivary flow rate, salivary pH, buffering capacity, evaluation of the presence and amount of cariogenic bacteria. The major salivary components are water and various, inorganic and organic substances. The most important organic components of saliva comprise antibacterial peptides, salivary glycoproteins, salivary proteins and proteins with enzymatic activity. These substances can serve as a source of biomarkers for caries risk assessment. Salivary biomarkers may be exploited for the prediction, diagnosis, prognosis and management of dental caries, as well as for evaluating the outcome of therapeutic regimens. Future research is essential to characterize the interaction of salivary proteins, and determine how these affect the initiation and development of dental caries.

Článek online

Update on Focal Infection Management: A Czech Interdisciplinary Consensus

International dental journal. 2024 ; 74 (3) : 510-518. [pub] 20231203

Int Dent J
ISSN 1875-595X
Medvik
Zdroj

BACKGROUND: The focal infection theory has been used to explain several chronic systemic diseases in the past. Systemic diseases were thought to be caused by focal infections, such as caries and periodontal diseases, and dentists were held responsible for these diseases due to the spread of oral infections. As knowledge of the interrelationship between oral microorganisms and the host immune response has evolved over the last few decades, the focal infection theory has been modified in various ways. The relationship between oral and systemic health appears to be more complex than that suggested by the classical theory of focal infections. Indeed, the contribution of the oral microbiota to some systemic diseases is gaining acceptance, as there are strong associations between periodontal disease and atherosclerotic vascular disease, diabetes, and hospital-associated pneumonia, amongst others. As many jurisdictions have various protocols for managing this oral-systemic axis of disease, we sought to provide a consensus on this notion with the help of a multidisciplinary team from the Czech Republic. METHODS: A multidisciplinary team comprising physicians/surgeons in the specialities of dentistry, ear-nose and throat (ENT), cardiology, orthopaedics, oncology, and diabetology were quetioned with regard to their conceptual understanding of the focal infection theory particularly in relation to the oral-systemic axis. The team also established a protocol to determine the strength of these associations and to plan the therapeutic steps needed to treat focal odontogenic infections whenever possible. RESULTS: Scoring algorithms were devised for odontogenic inflammatory diseases and systemic risks, and standardised procedures were developed for general use. CONCLUSIONS: The designed algorithm of the oral-systemic axis will be helpful for all health care workers in guiding their patient management protocol.