Tooth detection for each tooth type by application of faster R-CNNs to divided analysis areas of dental panoramic X-ray images
Tóm tắt
This study aimed to propose a computerized method for detecting the tooth region for each tooth type as the initial stage in the development of a computer-aided diagnosis (CAD) scheme for dental panoramic X-ray images. Our database consists of 160 panoramic dental X-ray images obtained from 160 adult patients. To reduce false positives (FPs), the proposed method first extracts a rectangular area including all teeth from a dental panoramic X-ray image with a faster region using a convolutional neural network (Faster R-CNN). From the rectangular area including all teeth, six divided areas are then extracted with Faster R-CNN: top left, top center, top right, bottom left, bottom center, and bottom right. Faster R-CNNs for detecting tooth regions for each tooth type were trained individually for each of the divided areas that narrowed down the target tooth types. By applying these Faster R-CNNs to each divided area, the bounding boxes of each tooth were detected and classified into 32 tooth types. A k-fold cross-validation method with k = 4 was used for training and testing the proposed method. The detection rate for each tooth, number of FPs per image, mean intersection over union for each tooth, and classification accuracy for the 32 tooth types were 98.9%, 0.415, 0.748, and 91.7%, respectively, showing an improvement compared to the application of the Faster R-CNN once to the entire image (98.0%, 1.194, 0.736, and 88.8%).
Tài liệu tham khảo
Katsumata A. Progress of diagnostic imaging in dentistry. Med Imaging Inf Sci. 2014;31(4):65–9. https://doi.org/10.11318/mii.31.65.
Muramatsu C, Matsumoto T, Hayashi T, Hara T, Katsumata A, Zhou X, Lida Y, Matsuoka M, Wakisaka T, Fujita H. Automatic method for measuring mandibular cortical thickness by using active contour model on dental panoramic radiographs. Inst Electron Inf Commun Eng. 2011;111(127):1–5. https://doi.org/10.1007/s11548-012-0800-8.
Rushton VE, Horner K, Worthington HV. The quality of panoramic radiographs in a sample of general dental practices. Br Dent J. 1999;186(12):630–3. https://doi.org/10.1038/sj.bdj.4800182.
Dhillon M, Raju SM, Verma S, Tomar D, Mohan RS, Lakhanpal M, Krishnamoorthy B. Positioning errors and quality assessment in panoramic radiography. Imaging Sci Dentistry. 2012;42(4):207–12. https://doi.org/10.5624/isd.2012.42.4.207.
Doi K. Computer-aided diagnosis in medical imaging: historical review current status and future potential. Comput Med Imaging Graph. 2007;31(4–5):198–211. https://doi.org/10.1016/j.compmedimag.2007.02.002.
Katsumata A. Vision for the renaissance of panoramic radiography. J Gifu Dental Soc. 2012;38:117–28.
Miyazaki T, Hotta Y, Kunii J, Kuriyama S, Tamaki Y. A review of dental CAD/CAM: current status and future perspectives from 20 years of experience. Dent Mater J. 2009;28(1):44–56. https://doi.org/10.4012/dmj.28.44.
Lin PL, Lai YH, Huang PW. An effective classification and numbering system for dental bitewing radiographs using teeth region and contour information. Pattern Recogn. 2010;43(4):1380–92. https://doi.org/10.1016/j.patcog.2009.10.005.
Lira PH, Giraldi GA, Neves LA. Panoramic dental X-Ray image segmentation and feature extraction. In Proceedings of V workshop of computing vision. Brazil. 2009. https://doi.org/10.4018/jncr.2010100101.
Nishitani Y, Nakayama R, Hayashi D, Hiziukuri H, Murata K. Segmentation of teeth in panoramic dental X-ray images using U-Net with a loss function weighted on the tooth edge. Radiol Phys Technol. 2021;14(1):64–9. https://doi.org/10.1007/s12194-020-00603-1.
Tuzoff DV, Tuzova LN, Bornstein MM, Krasnov AS, Kharchenko MA, Nikolenko SI, Sveshnikov MM, Bednenko GB. Tooth detection and numbering in panoramic radiographs using convolutional neural networks. Dentomaxillofacial Radiol. 2019;48(4):20180051. https://doi.org/10.1259/dmfr.20180051.
Muramatsu C, Morishita T, Takahashi R, Hayashi T, Nishiyama W, Ariji Y, Zhou X, Hara T, Katsumata A, Ariji E, Fujita H. Tooth detection and classification on panoramic radiographs for automatic dental chart filing: improved classification by multi-sized input data. Oral Radiol. 2021;37(1):13–9. https://doi.org/10.1007/s11282-019-00418-w.
Bilgir E, Bayrakdar IS, Celik O, Orhan K, Akkoca F, Saglam H, Odabas A, Aslan AF, Ozecetin C, Killi M, Rozylo-Kalinowska I. An artifıcial ıntelligence approach to automatic tooth detection and numbering in panoramic radiographs. BMC Med Imaging. 2021;21(1):1–9. https://doi.org/10.1186/s12880-021-00656-7.
Yuksel AE, Gultekin S, Simsar E, Ozdemir SD, Gundogar M, Tokgoz SB, Hamamci IE. Dental enumeration and multiple treatment detection on panoramic X-rays using deep learning. Sci Rep. 2021;11(1):1–10. https://doi.org/10.1038/s41598-021-90386-1.
Ren S, He K, Girshick R, Sun J. Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell. 2016;39(6):1137–49. https://doi.org/10.1109/TPAMI.2016.2577031.
Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Ravinovich A. Going deeper with convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2015: pp. 1–9. https://doi.org/10.1109/CVPR.2015.7298594.
Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Adv Neural Inf Process Syst. 2012;25:1097–105. https://doi.org/10.1145/3065386.
Kingma DP, Ba J. Adam: A method for stochastic optimization. 2014. arXiv preprint arXiv:1412.6980.