Abstrak 
Identify pulpitis at dental X-ray periapical radiography based on edge detection, texture description and artificial neural networks
Bernard Y. Tumbelaka, Fahmi Oscandar, Faisal Nur Baihaki, Suhardjo Sitam, Mandojo Rukmo
Universitas Padjadjaran, Conference Paper June 2013 DOI: 10.4103/1658-5984.138139 See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/253327800
Bahasa Inggris
Universitas Padjadjaran, Conference Paper June 2013 DOI: 10.4103/1658-5984.138139 See discussions, stats, and author profiles for this publication at: https://www.researchgate.net/publication/253327800
and mean square error (MSE)., artificial neural networks (ANNs), Dental X-ray, edge detection, image entropy, periapical radiography, Pulpitis, texture description
Objectives: Our research interest is aimed to identify pulpitis at the dental X-ray periapical radiography by applying edges as basis image features, the texture description and the artificial neural networks (ANNs). Methods: First, we need to convert the radiography data records digitally and to preprocess the input image as its original image where we use the Gaussian Filter to obtain the best intensity distribution. The second step, we use the local image differentiation technique that can produce edge detector operators, e(x,y) as the image gradient; Vf(x,y) providing useful information about the local intensity variations. The third step, we analyze these results by using the texture descriptors to obtain digitally the image entropy, H. The fourth step, we characterize all by the ANNs. Results: First we obtain that the edge detection carries important information about the object boundaries of pulpitis as disinfected and infected significantly which can be valuable for the pulpitis interpretation. Second, the image entropy obtained from texture descriptors in region segmentation and then inputting to the ANNs analysis where the curves of disinfected and infected regions are figured convergence with disinfected line from 4.9014 to 4.6843 decreases to infected line from 4.6812 to 4.5926 at the same of MSE around 0.0003. Conclusions: Refer to these results, we get that the correlation of the image entropy and the ANNs analysis can be linearly classified with the critical point of 4.6827. Finally, we conclude that the direct reading radiography is better to be digitized in order to provide us the best choice for diagnose validation.