A Novel Deep Learning-Based Approach for Segmentation of Different Type Caries Lesions on Panoramic Radiographs

Dayi, Burak; Üzen, Hüseyin; ÇİÇEK, İpek BALIKÇI; Duman, Şuayip Burak

doi:10.3390/diagnostics13020202

Cited by 33 publications

(14 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For the diagnosis of cavities and other dental diseases, we find Logicon, (49) RDFNet, (42) y DCDNet (20) who specialize in detecting cavities in dental imaging, while Mask-RCNN (40) focuses on the detection and classification of periapical lesions. In addition, there are Denti.Ai (25) y Diagnocat (21, 50) that use AI to identify a variety of dental pathologies, with Denti.Ai (25) also focusing on implants and crowns.…”

Section: Discussionmentioning

confidence: 99%

Informatic tools for diagnosis in dentistry. A compilation review

Chaple Gil,

Damas Heredia,

Afrashtehfar

2024

Preprint

View full text Add to dashboard Cite

The objective of this article was to compile the computer tools available in the scientific literature aimed at diagnosis in dentistry. An scoping review research was conducted in Pubmed, Scopus and Web of Science. Were include, original researches type articles, Articles that reported the usefulness of a computer/technological tool that helps diagnosis in dental practice, Articles published in the last 20 years (period 2004- 2024) and written in English and Spanish. Online tool Rayyan was used to establish homogeneity in the review of the authors on a single online platform where they had access and could centralize the results. Variables were extracted from each article included in the study. A total of 12648 records were recuperated from data bases. After decantation process were included 39 reports that described 36 computer tools for diagnosis in dentistry. More informatic tools related to "Restorative Dentistry" have been developed than the rest of the specialties 14 (40%), Python was the predominant programming language, 83.3% of the tools were validated and 27.8% were free. Informatics tools in dentistry enhance diagnosis and treatment planning. However, a robust regulatory framework is needed for their validation before clinical implementation. Continuous training of dental professionals in these technologies is crucial to maximize their benefits and ensure optimal patient care. The need for more research to explore the potential of informatics applications in dentistry, their integration into existing health systems, and their accessibility in resource-limited areas is emphasized.

show abstract

Section: Discussionmentioning

confidence: 99%

Informatic tools for diagnosis in dentistry. A compilation review

Chaple Gil,

Damas Heredia,

Afrashtehfar

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…The research paper introduced by Dayi et al in 2023 [3] presents a new architecture, Dental Caries Detection Network (DCDNet), for detecting and segmenting carious lesions. The dataset used is private and it is composed of 504 panoramic radiographs of unknown dimensions.…”

Section: Related Workmentioning

confidence: 99%

“…In the literature, the problem of caries identification has been investigated by different deep-learning models like U-net [3] , [4] or DeepLab [5] , but the performance of these simple models can be improved still. Furthermore, the previous approaches did not consider an ensemble model that can achieve higher accuracy than individual models by combining their predictions and reducing their errors.…”

Section: Introductionmentioning

confidence: 99%

Teeth segmentation and carious lesions segmentation in panoramic X-ray images using CariSeg, a networks' ensemble

Mărginean,

Mureşanu,

Hedeşiu

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…Dayi et al [36] evaluated the diagnostic performance of deep learning models for the segmentation of occlusal, proximal, and cervical caries lesions on panoramic radiographs. Their data consisted of 504 anonymous panoramic radiographs.…”

Section: Other Approachesmentioning

confidence: 99%

Automatic Teeth Segmentation Using Attention U-Net

Mahran¹,

Hussein²,

Saber³

2023

Preprint

View full text Add to dashboard Cite

Teeth segmentation plays a pivotal role in dental diagnosis, treatment, planning, and the development of computer-aided dental systems. It enables precise identification and analysis of dental structures, aiding in detecting dental abnormalities, measuring tooth dimensions, and assessing oral health conditions. Accurate teeth segmentation also facilitates the automation of dental workflows, leading to improved efficiency and reduced human error. Artificial Intelligence (AI) has witnessed rapid advancements, with various approaches developed or enhanced. While Convolutional Neural Networks (CNNs) have been widely used in medical image segmentation, the U-Net architecture has emerged as a standout performer due to its exceptional segmentation capabilities. This paper presents a proof of concept for the Attention U-Net architecture, as previously used in [1], applied to teeth segmentation. The study demonstrates the superior performance of this network in accurately segmenting teeth using a newly available benchmark dataset called Tufts Dental X-Ray Dataset. When trained and tested on 10-fold cross-validation, the model achieved an average dice coefficient of 95.01%, intersection over union of 90.6%, and pixel accuracy of 98.82%. These scores surpass those of all other networks implemented on the same dataset. By leveraging the Attention U-Net architecture, our research showcases the potential of advanced AI techniques in dental radiography. The findings contribute to the ongoing efforts to develop automated systems to assist dental professionals in their clinical practice.

show abstract

A Novel Deep Learning-Based Approach for Segmentation of Different Type Caries Lesions on Panoramic Radiographs

Cited by 33 publications

References 40 publications

Informatic tools for diagnosis in dentistry. A compilation review

Informatic tools for diagnosis in dentistry. A compilation review

Teeth segmentation and carious lesions segmentation in panoramic X-ray images using CariSeg, a networks' ensemble

Automatic Teeth Segmentation Using Attention U-Net

Contact Info

Product

Resources

About