Localization of cementoenamel junction in intraoral ultrasonographs with machine learning

• Published in: Journal of dentistry Vol. 112; p. 103752
• Main Authors: Nguyen, Kim-Cuong T., Le, Binh M., Li, Mengxun, Almeida, Fabiana T., Major, Paul W., Kaipatur, Neelambar R., Lou, Edmond H.M., Punithakumar, Kumaradevan, Le, Lawrence H.
• Format: Journal Article
• Language: English
• Published: Oxford Elsevier Ltd 01.09.2021; Elsevier Limited
• Subjects: Algorithms; Alveolar bone; Artificial intelligence; Artificial neural networks; Cementoenamel junction (CEJ); Computation; Conditional probability; Convolutional neural networks (CNNs); Deep learning; Dentistry; Disease; Labels; Learning algorithms; Localization; Machine learning; Medical equipment; Medical imaging; Neural networks; Older people; Periodontium; Radiation; Scanners; Ultrasonic imaging; Ultrasound; Ultrasound imaging; Deep learning; Medical imaging; Ultrasound imaging; Cementoenamel junction (CEJ); Machine learning; Alveolar bone; Convolutional neural networks (CNNs)
• DOI: 10.1016/j.jdent.2021.103752
• ISSN: 0300-5712

Our goal was to automatically identify the cementoenamel junction (CEJ) location in ultrasound images using deep convolution neural networks (CNNs). Three CNNs were evaluated using 1400 images and data augmentation. The training and validation were performed by an experienced nonclinical rater with 1000 and 200 images, respectively. Four clinical raters with different levels of experience with ultrasound tested the networks using the other 200 images. In addition to the comparison of the best approach with each rater, we also employed the simultaneous truth and performance level estimation (STAPLE) algorithm to estimate a ground truth based on all labelings by four clinical raters. The final CEJ location estimate was obtained by taking the first moment of the posterior probability computed using the STAPLE algorithm. The study also computed the machine learning-measured CEJ–alveolar bone crest distance. Quantitative evaluations of the 200 images showed that the comparison of the best approach with the STAPLE-estimate yielded a mean difference (MD) of 0.26 mm, which is close to the comparison with the most experienced nonclinical rater (MD=0.25 mm) but far better than the comparison with clinical raters (MD=0.27–0.33 mm). The machine learning-measured CEJ–alveolar bone crest distances correlated strongly (R = 0.933, p < 0.001) with the manual clinical labeling and the measurements were in good agreement with the 95% Bland–Altman's lines of agreement between −0.68 and 0.57 mm. The study demonstrated the feasible use of machine learning methodology to localize CEJ in ultrasound images with clinically acceptable accuracy and reliability. Likelihood-weighted ground truth by combining multiple labels by the clinical experts compared favorably with the predictions by the best deep CNN approach. Identification of CEJ and its distance from the alveolar bone crest play an important role in the evaluation of periodontal status. Machine learning algorithms can learn from complex features in ultrasound images and have potential to provide a reliable and accurate identification in subsecond. This will greatly assist dental practitioners to provide better point-of-care to patients and enhance the throughput of dental care.