A pilot study of a deep learning approach to detect marginal bone loss around implants

Liu, Min; Wang, Shimin; Hu, Changwei; Liu, Yunsong

doi:10.1186/s12903-021-02035-8

Cited by 36 publications

(14 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several deep learning studies related to dental implants have been reported. The marginal bone loss around implants has also been extensively studied [ 17 , 18 ]. Liu et al used a balanced database, but the incidence of bone resorption at implant margins was low [ 17 ].…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep learning-based prediction of osseointegration for dental implant using plain radiography

Kim

et al. 2023

BMC Oral Health

View full text Add to dashboard Cite

Background In this study, we investigated whether deep learning-based prediction of osseointegration of dental implants using plain radiography is possible. Methods Panoramic and periapical radiographs of 580 patients (1,206 dental implants) were used to train and test a deep learning model. Group 1 (338 patients, 591 dental implants) included implants that were radiographed immediately after implant placement, that is, when osseointegration had not yet occurred. Group 2 (242 patients, 615 dental implants) included implants radiographed after confirming successful osseointegration. A dataset was extracted using random sampling and was composed of training, validation, and test sets. For osseointegration prediction, we employed seven different deep learning models. Each deep-learning model was built by performing the experiment 10 times. For each experiment, the dataset was randomly separated in a 60:20:20 ratio. For model evaluation, the specificity, sensitivity, accuracy, and AUROC (Area under the receiver operating characteristic curve) of the models was calculated. Results The mean specificity, sensitivity, and accuracy of the deep learning models were 0.780–0.857, 0.811–0.833, and 0.799–0.836, respectively. Furthermore, the mean AUROC values ranged from to 0.890–0.922. The best model yields an accuracy of 0.896, and the worst model yields an accuracy of 0.702. Conclusion This study found that osseointegration of dental implants can be predicted to some extent through deep learning using plain radiography. This is expected to complement the evaluation methods of dental implant osseointegration that are currently widely used.

show abstract

Section: Discussionmentioning

confidence: 99%

“…The marginal bone loss around implants has also been extensively studied [ 17 , 18 ]. Liu et al used a balanced database, but the incidence of bone resorption at implant margins was low [ 17 ]. And there was a need to improve model performance through standardized radiographs produced via the paralleling technique.…”

Section: Discussionmentioning

confidence: 99%

Deep learning-based prediction of osseointegration for dental implant using plain radiography

Kim

et al. 2023

BMC Oral Health

View full text Add to dashboard Cite

show abstract

“…The mask R‐CNN strategy was created based on Quicker R‐CNN to distinguish targets on images and provide high‐quality division and segmentation [76]. In addition, as stated by Liu, an AI framework based on Speedier R‐CNN examination of periapical radiographs could be a promising assistant demonstrative apparatus for peri‐implant bone loss discovery [77]. The Faster R‐CNN model could be used for comparative analysis in association with the implant detection task.…”

Section: Application Of Ai In Implantologymentioning

confidence: 99%

Applying artificial intelligence to detect and analyse oral and maxillofacial bone loss—A scoping review

et al. 2023

View full text Add to dashboard Cite

Radiographic evaluation of bone changes is one of the main tools in the diagnosis of many oral and maxillofacial diseases. However, this approach to assessment has limitations in accuracy, inconsistency and comparatively low diagnostic efficiency. Recently, artificial intelligence (AI)‐based algorithms like deep learning networks have been introduced as a solution to overcome these challenges. Based on recent studies, AI can improve the detection accuracy of an expert clinician for periapical pathology, periodontal diseases and their prognostication, as well as peri‐implant bone loss. Also, AI has been successfully used to detect and diagnose oral and maxillofacial lesions with a high predictive value. This study aims to review the current evidence on artificial intelligence applications in the detection and analysis of bone loss in the oral and maxillofacial regions.

show abstract

“…In 2022, Liu et al use R-CNN to detect marginal bone loss around dental implants ( Liu et al, 2022 ). They find that their model output performs similarly to the resident dentist but is less accurate than the experienced dentist.…”

Section: Related Workmentioning

confidence: 99%

TVGG Dental Implant Identification System

et al. 2022

View full text Add to dashboard Cite

Identifying the right accessories for installing the dental implant is a vital element that impacts the sustainability and the reliability of the dental prosthesis when the medical case of a patient is not comprehensive. Dentists need to identify the implant manufacturer from the x-ray image to determine further treatment procedures. Identifying the manufacturer is a high-pressure task under the scaling volume of patients pending in the queue for treatment. To reduce the burden on the doctors, a dental implant identification system is built based on a new proposed thinner VGG model with an on-demand client-server structure. We propose a thinner version of VGG16 called TVGG by reducing the number of neurons in the dense layers to improve the system’s performance and gain advantages from the limited texture and patterns in the dental radiography images. The outcome of the proposed system is compared with the original pre-trained VGG16 to verify the usability of the proposed system.

show abstract

A pilot study of a deep learning approach to detect marginal bone loss around implants

Cited by 36 publications

References 43 publications

Deep learning-based prediction of osseointegration for dental implant using plain radiography

Deep learning-based prediction of osseointegration for dental implant using plain radiography

Applying artificial intelligence to detect and analyse oral and maxillofacial bone loss—A scoping review

TVGG Dental Implant Identification System

Contact Info

Product

Resources

About