An optimized video system for augmented reality in endodontics: a feasibility study
- 369 Downloads
We propose an augmented reality system for the reliable detection of root canals in video sequences based on a k-nearest neighbor color classification and introduce a simple geometric criterion for teeth.
Material and methods
The new software was implemented using C++, Qt, and the image processing library OpenCV. Teeth are detected in video images to restrict the segmentation of the root canal orifices by using a k-nearest neighbor algorithm. The location of the root canal orifices were determined using Euclidean distance-based image segmentation. A set of 126 human teeth with known and verified locations of the root canal orifices was used for evaluation.
The software detects root canals orifices for automatic classification of the teeth in video images and stores location and size of the found structures. Overall 287 of 305 root canals were correctly detected. The overall sensitivity was about 94 %. Classification accuracy for molars ranged from 65.0 to 81.2 % and from 85.7 to 96.7 % for premolars.
The realized software shows that observations made in anatomical studies can be exploited to automate real-time detection of root canal orifices and tooth classification with a software system.
Automatic storage of location, size, and orientation of the found structures with this software can be used for future anatomical studies. Thus, statistical tables with canal locations will be derived, which can improve anatomical knowledge of the teeth to alleviate root canal detection in the future. For this purpose the software is freely available at: http://www.dental-imaging.zahnmedizin.uni-mainz.de/.
KeywordsAugmented reality Automatic feature detection Root canal orifices
This article contains parts of the bachelor thesis of Henning Tjaden. Further, the authors declare that there are no conflicts of interest, nor financial relations to any commercial corporation or products.
(MPG 95854 kb)
- 2.Tse B, Harwin W, Barrow A, Quinn B, San Diego J, Cox M (2010) Design and development of a haptic dental training system – Haptel. In: Kappers A, van Erp J, Bergmann-Tiest W, van der Helm F (eds) Haptics: generating and perceiving tangible sensations, 1st edn. Springer, Heidelberg, pp 101–108CrossRefGoogle Scholar
- 8.J. Eberhart, M. Frentzen, and M. Thoms (2007) New method to detect caries via fluorescence. In: Schweitzer D, Fitzmaurice M (eds) Diagnostic Optical Spectroscopy in Biomedicine IV, Vol. 6628 of Proceedings of SPIE-OSA Biomedical Optics, Optical Society of America, Washington, paper 6628_21Google Scholar
- 12.Selvarasu N, Nachiappan A, Nandhitha N (2010) Abnormality detection from medical thermographs in human using euclidean distance based color image segmentation. IEEE Computer Society (ed) International Conference on Signal Acquisition and Processing, 2010. ICSAP '10, IEEE Computer Society, Los Alamitos, pp 73–75Google Scholar
- 14.Sun B, Du J, Gao T (2009) Study on the improvement of k-nearest neighbor algorithm. In: IEEE Computer Society (ed) International Conference on Artificial Intelligence and Computational Intelligence, 2009. AICI '09, IEEE Computer Society, Los Alamitos, pp 390–393Google Scholar
- 15.Knuth D (1998) The art of computer programming, 2nd edn., Addison Wesley, BonnGoogle Scholar
- 16.Shim J, Dorai C (1999) A generalized region labeling algorithm for image coding, restoration and segmentation. In IEEE Computer Society (ed) International Conference on Image Processing, 1999. ICIP 99. Proceedings. IEEE Computer Society, Los Alamitos, pp 46–50Google Scholar
- 17.Jaehne B (2010) Digital image processing, 7st edn. Springer BerlinGoogle Scholar
- 21.Wengert C, Cattin P, Du J, Baur C, Szekely G (2006) Markerless endoscopic registration and referencing. Med Image Comput Computer-Assist Interv 9:816–823Google Scholar