METHOD FOR BRIGHTNESS LEVEL CALCULATION IN THE AREA OF INTEREST OF A DIGITAL X-RAY IMAGE FOR MEDICAL APPLICATIONS

摘要

The invention relates to methods for calculating the brightness level in the area of interest of a digital medical X-ray image on the basis of a histogram of said image using an artificial neural network. The calculation is carried out as follows: an image is obtained, a histogram of the image is calculated, the values of the histogram are converted into input arguments for a neural network, and the output value of the neural network is calculated. Histogram values calculated with a given class interval and normalized to 1 are used as the input arguments for the neural network. The brightness level is calculated as a linear function from the output value of the neural network. The neural network is learned using a learning set calculated on the basis of a given bank of images, and brightness levels calculated for each image pertaining to the area of interest and scaled to the range of the activation function of a neuron of the output layer of the neural network are used as the set of target values.