Automatic segmenting teeth in X-ray images: Trends, a novel data set, benchmarking and future perspectives

Silva, Gil; Oliveira, Luciano; Pithon, Matheus Melo

doi:10.1016/j.eswa.2018.04.001

Cited by 152 publications

(78 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Regarding tooth segmentation, the higher performance was achieved for canines, followed by incisors, premolars, and molars. To the best of our knowledge, only four previous studies have tested the use of AI tools for automatic detection and segmentation of all teeth on panoramic radiographs [21,[23][24][25]. The lower values achieved by the three aforementioned studies [10,12,13] were probably related to smaller data set sizes or different applied methodologies.…”

Section: Discussionmentioning

confidence: 96%

See 1 more Smart Citation

Artificial intelligence-driven novel tool for tooth detection and segmentation on panoramic radiographs

et al. 2020

View full text Add to dashboard Cite

Objective To evaluate the performance of a new artificial intelligence (AI)-driven tool for tooth detection and segmentation on panoramic radiographs. Materials and methods In total, 153 radiographs were collected. A dentomaxillofacial radiologist labeled and segmented each tooth, serving as the ground truth. Class-agnostic crops with one tooth resulted in 3576 training teeth. The AI-driven tool combined two deep convolutional neural networks with expert refinement. Accuracy of the system to detect and segment teeth was the primary outcome, time analysis secondary. The Kruskal-Wallis test was used to evaluate differences of performance metrics among teeth groups and different devices and chi-square test to verify associations among the amount of corrections, presence of false positive and false negative, and crown and root parts of teeth with potential AI misinterpretations. Results The system achieved a sensitivity of 98.9% and a precision of 99.6% for tooth detection. For segmenting teeth, lower canines presented best results with the following values for intersection over union, precision, recall, F1-score, and Hausdorff distances: 95.3%, 96.9%, 98.3%, 97.5%, and 7.9, respectively. Although still above 90%, segmentation results for both upper and lower molars were somewhat lower. The method showed a clinically significant reduction of 67% of the time consumed for the manual. Conclusions The AI tool yielded a highly accurate and fast performance for detecting and segmenting teeth, faster than the ground truth alone. Clinical significance An innovative clinical AI-driven tool showed a faster and more accurate performance to detect and segment teeth on panoramic radiographs compared with manual segmentation.

show abstract

Section: Discussionmentioning

confidence: 96%

“…Artificial intelligence (AI)-driven methods have also been investigated to detect [22] and segment teeth on panoramic radiographs [21,[23][24][25]. Regarding segmentation studies, previous AI tools allowed to achieve results with accuracy metrics below 90%.…”

Section: Introductionmentioning

confidence: 99%

Artificial intelligence-driven novel tool for tooth detection and segmentation on panoramic radiographs

et al. 2020

View full text Add to dashboard Cite

show abstract

“…From data analysis aspect, these methods offer only a limited amount of information. X-ray-based techniques produce intensity graphs of transmitted radiation, i.e., grayscale images, and allow for analysis of spatial structures and their brightness only [1][2][3][4]. X-ray techniques do not acquire any color information or provide comparable multichannel images.…”

Section: Introductionmentioning

confidence: 99%

Oral and Dental Spectral Image Database—ODSI-DB

et al. 2020

View full text Add to dashboard Cite

The most common imaging methods used in dentistry are X-ray imaging and RGB color photography. However, both imaging methods provide only a limited amount of information on the wavelength-dependent optical properties of the hard and soft tissues in the mouth. Spectral imaging, on the other hand, provides significantly more information on the medically relevant dental and oral features (e.g. caries, calculus, and gingivitis). Due to this, we constructed a spectral imaging setup and acquired 316 oral and dental reflectance spectral images, 215 of which are annotated by medical experts, of 30 human test subjects. Spectral images of the subjects’ faces and other areas of interest were captured, along with other medically relevant information (e.g., pulse and blood pressure). We collected these oral, dental, and face spectral images, their annotations and metadata into a publicly available database that we describe in this paper. This oral and dental spectral image database (ODSI-DB) provides a vast amount of data that can be used for developing, e.g., pattern recognition and machine vision applications for dentistry.

show abstract

“…Dental records have been extensively used in disaster victim identification, such as 9/11 bombing and Asian tsunami [11], [12]. Many authors [13]- [17] successfully demonstrated the uses of dental radiographs for human identification. There are still a number of challenges to overcome like poor image quality, changes in the dentition over time, such as tooth eruption and loss, the emergence, abrasion, falling and replacement of dental restorations [13]- [17].…”

Section: Introductionmentioning

confidence: 99%

“…Many authors [13]- [17] successfully demonstrated the uses of dental radiographs for human identification. There are still a number of challenges to overcome like poor image quality, changes in the dentition over time, such as tooth eruption and loss, the emergence, abrasion, falling and replacement of dental restorations [13]- [17]. In such cases, hand radiographs can be considered for authentication purposes as bones cannot be easily damaged due to burning, rashes, and wounding.…”

Section: Introductionmentioning

confidence: 99%

Deep Learning Based Person Authentication Using Hand Radiographs: A Forensic Approach

Joshi¹,

Kanphade²

2020

IEEE Access

View full text Add to dashboard Cite

Biometric radiographs have gained importance in recent times owing to the rise in crime and disaster incidents. In recent times, authentication and identification of a person has become an essential part of most of the computer vision automation systems. Conventional fingerprint, iris, face, palm prints fail to recognize the human when the external biometric parts have been damaged due to rashes, wounds, and severe burning. Security, robustness, privacy, and non-forgery are the critical aspects of any person authentication system. In such situations, identification based on radiographs of the skull, hand, and teeth are effective replacement methods. In this paper, a novel forensic hand radiograph based human authentication is proposed using a deep neural network. Three-layered convolutional deep neural network architecture is used for the feature extraction of hand radiographs and for recognition; KNN and SVM classifiers are used. As a part of the experimentation, a total of 750 hand radiographs acquired from 150 subjects of different age groups, professions, and gender are considered. The performance of the algorithm is evaluated based on crossvalidation accuracy by varying striding pixels, polling window size, kernel size, and the number of filters. Our experiment reveals that hand radiographs contain biometric information that can be used to identify humans in disaster victim identification. The experimental study also indicates that the proposed approach is significantly effective than conventional methods for the person authentication using hand radiographs. INDEX TERMS Biometrics, identification of persons, image forensics, neural networks, pattern recognition, radiography.

show abstract

Automatic segmenting teeth in X-ray images: Trends, a novel data set, benchmarking and future perspectives

Cited by 152 publications

References 47 publications

Artificial intelligence-driven novel tool for tooth detection and segmentation on panoramic radiographs

Artificial intelligence-driven novel tool for tooth detection and segmentation on panoramic radiographs

Oral and Dental Spectral Image Database—ODSI-DB

Deep Learning Based Person Authentication Using Hand Radiographs: A Forensic Approach

Contact Info

Product

Resources

About