Dataset Information

Estimation of Alveolar Bone Loss in Periodontitis Using Machine Learning.

ABSTRACT:

Aim

The objective of this research was to perform a pilot study to develop an automatic analysis of periapical radiographs from patients with and without periodontitis for the percentage alveolar bone loss (ABL) on the approximal surfaces of teeth using a supervised machine learning model, that is, convolutional neural networks (CNN).

Material and methods

A total of 1546 approximal sites from 54 participants on mandibular periapical radiographs were manually annotated (MA) for a training set (n = 1308 sites), a validation set (n = 98 sites), and a test set (n = 140 sites). The training and validation sets were used for the development of a CNN algorithm. The algorithm recognised the cemento-enamel junction, the most apical extent of the alveolar crest, the apex, and the surrounding alveolar bone.

Results

For the total of 140 images in the test set, the CNN scored a mean of 23.1 ± 11.8 %ABL, whilst the corresponding value for MA was 27.8 ± 13.8 %ABL. The intraclass correlation (ICC) was 0.601 (P < .001), indicating moderate reliability. Further subanalyses for various tooth types and various bone loss patterns showed that ICCs remained significant, although the algorithm performed with excellent reliability for %ABL on nonmolar teeth (incisors, canines, premolars; ICC = 0.763).

Conclusions

A CNN trained algorithm on radiographic images showed a diagnostic performance with moderate to good reliability to detect and quantify %ABL in periapical radiographs.

SUBMITTER: Tsoromokos N

PROVIDER: S-EPMC9485533 | biostudies-literature | 2022 Oct

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Estimation of Alveolar Bone Loss in Periodontitis Using Machine Learning.

Tsoromokos Nektarios N Parinussa Sarah S Claessen Frank F Moin David Anssari DA Loos Bruno G BG

International dental journal 20220513 5

<h4>Aim</h4>The objective of this research was to perform a pilot study to develop an automatic analysis of periapical radiographs from patients with and without periodontitis for the percentage alveolar bone loss (ABL) on the approximal surfaces of teeth using a supervised machine learning model, that is, convolutional neural networks (CNN).<h4>Material and methods</h4>A total of 1546 approximal sites from 54 participants on mandibular periapical radiographs were manually annotated (MA) for a t ...[more]

PMID: 35570013

Similar Datasets

Project description:SLIT2, a member of neuronal guidance cues, has been reported to regulate inflammation and cancer progression. Periodontitis is an oral inflammatory disease that degenerates periodontal tissue, alveolar bone and tooth. This study aims to explore the expression pattern of SLIT2 in periodontitis and its role in disease progression and bone loss. Gingival tissue of 20 periodontitis patients and 20 healthy-controls was obtained. Ligature-induced periodontitis (LIP) mice-model was developed in Slit2-Tg and wild-type mice. The effect of SLIT2 on inflammation, immune cell infiltration, M1 macrophage polarization, and alveolar bone loss in periodontitis was analyzed extensively. In periodontitis-affected gingival-tissue, SLIT2 expression was 4.4-fold higher compared to healthy-volunteers. LIP enhanced SLIT2 expression in mice periodontitis-affected periodontal tissue (PAPT) and blood circulation of wild-type mice by 4. 6-, and 5.0-fold, respectively. In Slit2-Tg-mice PAPT, SLIT2 expression was 1.8-fold higher compared to wild-type mice. Micro-CT and histomorphometric analysis revealed a 1.3-fold higher cement-enamel-junction to the alveolar-bone-crest (CEJ-ABC) distance and alveolar bone loss in LIP Slit2-Tg-mice compare to LIP wild-type mice. Results from RNA-sequencing, RT-qPCR, and ELISA showed a higher expression of Cxcr2, Il-18, TNFα, IL-6, and IL-1β in Slit2-Tg-mice PAPT compared to wild-type-mice. Slit2-Tg-mice PAPT showed a higher number of osteoclasts, M1 macrophages, and the upregulation of Robo1 expression. Slit2-Tg-mice PAPT showed upregulation of M1 macrophage marker CD16/32 and osteoclastogenic markers Acp5, Ctsk, and Nfatc1, but osteogenic markers (Alp, Bglap) remained unchanged. Immunohistochemistry unveiled the higher vasculature and infiltration of leucocytes and macrophages in Slit2-Tg-mice PAPT. RNA-sequencing, GO-pathway enrichment analysis, and western blot analysis revealed the activation of the MAPK signaling pathway in Slit2-Tg mice PAPT. In conclusion, SLIT2 overexpression in periodontitis intensifies inflammation, immune cells infiltration, M1 macrophage polarization, osteoclastogenesis, and alveolar bone loss, possibly via activation of MAPK signaling, suggesting the role of SLIT2 on exacerbation of periodontitis and alveolar bone loss.

Dataset Information

Estimation of Alveolar Bone Loss in Periodontitis Using Machine Learning.

Aim

Material and methods

Results

Conclusions

Publications

Estimation of Alveolar Bone Loss in Periodontitis Using Machine Learning.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets