Ying-Chun Pan1,2, Hsun-Liang Chan3, Xiangbo Kong3, Lubomir M Hadjiiski2, Oliver D Kripfgans1,2. 1. Department of Biomedical Engineering, College of Engineering, University of Michigan, Ann Arbor, Michigan, United States of America. 2. Department of Radiology, School of Medicine, University of Michigan, Ann Arbor, Michigan, United States of America. 3. Department of Periodontics and Oral Medicine, School of Dentistry, University of Michigan, Ann Arbor, Michigan, United States of America.
Abstract
OBJECTIVES: Ultrasound emerges as a complement to cone-beam computed tomography in dentistry, but struggles with artifacts like reverberation and shadowing. This study seeks to help novice users recognize soft tissue, bone, and crown of a dental sonogram, and automate soft tissue height (STH) measurement using deep learning. METHODS: In this retrospective study, 627 frames from 111 independent cine loops of mandibular and maxillary premolar and incisors collected from our porcine model (N = 8) were labeled by a reader. 274 premolar sonograms, including data augmentation, were used to train a multi class segmentation model. The model was evaluated against several test sets, including premolar of the same breed (n = 74, Yucatan) and premolar of a different breed (n = 120, Sinclair). We further proposed a rule-based algorithm to automate STH measurements using predicted segmentation masks. RESULTS: The model reached a Dice similarity coefficient of 90.7±4.39%, 89.4±4.63%, and 83.7±10.5% for soft tissue, bone, and crown segmentation, respectively on the first test set (n = 74), and 90.0±7.16%, 78.6±13.2%, and 62.6±17.7% on the second test set (n = 120). The automated STH measurements have a mean difference (95% confidence interval) of -0.22 mm (-1.4, 0.95), a limit of agreement of 1.2 mm, and a minimum ICC of 0.915 (0.857, 0.948) when compared to expert annotation. CONCLUSION: This work demonstrates the potential use of deep learning in identifying periodontal structures on sonograms and obtaining diagnostic periodontal dimensions.
OBJECTIVES: Ultrasound emerges as a complement to cone-beam computed tomography in dentistry, but struggles with artifacts like reverberation and shadowing. This study seeks to help novice users recognize soft tissue, bone, and crown of a dental sonogram, and automate soft tissue height (STH) measurement using deep learning. METHODS: In this retrospective study, 627 frames from 111 independent cine loops of mandibular and maxillary premolar and incisors collected from our porcine model (N = 8) were labeled by a reader. 274 premolar sonograms, including data augmentation, were used to train a multi class segmentation model. The model was evaluated against several test sets, including premolar of the same breed (n = 74, Yucatan) and premolar of a different breed (n = 120, Sinclair). We further proposed a rule-based algorithm to automate STH measurements using predicted segmentation masks. RESULTS: The model reached a Dice similarity coefficient of 90.7±4.39%, 89.4±4.63%, and 83.7±10.5% for soft tissue, bone, and crown segmentation, respectively on the first test set (n = 74), and 90.0±7.16%, 78.6±13.2%, and 62.6±17.7% on the second test set (n = 120). The automated STH measurements have a mean difference (95% confidence interval) of -0.22 mm (-1.4, 0.95), a limit of agreement of 1.2 mm, and a minimum ICC of 0.915 (0.857, 0.948) when compared to expert annotation. CONCLUSION: This work demonstrates the potential use of deep learning in identifying periodontal structures on sonograms and obtaining diagnostic periodontal dimensions.
Authors: Tony Vanderstuyft; Mihai Tarce; Bahoz Sanaan; Reinhilde Jacobs; Karla de Faria Vasconcelos; Marc Quirynen Journal: J Clin Periodontol Date: 2019-09-09 Impact factor: 8.728
Authors: Hsun-Liang Chan; Hom-Lay Wang; Jeffery Brian Fowlkes; William V Giannobile; Oliver D Kripfgans Journal: Clin Oral Implants Res Date: 2016-03-19 Impact factor: 5.977