Radiographs analyzed with special software may help detect caries in the early stages of development, according to a study published in the latest issue of the International Journal of Biomedical Engineering and Technology.
Researchers at RMK Engineering College, Tamil Nadu, India, developed a radiograph analysis technique that reveals pixel intensities at different x-ray wavelengths, similar to a histogram analysis of images from a high-specification digital camera.
Researchers analyzed radiographic images of normal and decayed teeth by using a signal-processing tool. They calculated the histogram and power spectrum for each image. They found that, in a histogram, the pixel intensities were concentrated in different ranges for normal teeth and decayed teeth. They also found that there were distinct differences in the spectral components between normal and decayed teeth. The spectrum of a decayed tooth has higher-frequency components than does the spectrum of a normal tooth.
Study author R. Siva Kumar, Department of Electronics and Communication Engineering, RMK Engineering College, says that the technique could be useful for dental clinicians and could be extended by using neural networks to identify the different stages of dental caries automatically.
