AUTOMATED PROCESSING AND INTERPRETATION OF MASTOGRAPHIC IMAGES FOR LEVEL ASSIGNMENT IN THE BI-RADS SCALE.

摘要

The present disclosure is related to the image interpretation through a computer. More specifically, related to a mastographic image interpretation technique using image segmentation methods and an artificial neural network for classification. The advantage of the present invention over those of the state of the art is that the present invention manages to detect, in the regions of interest, a 100% of the important areas for the assignment of the BI-RADS level. In addition, the efficiency achieved in determining the BI-RADS level was calculated equal to 98.61. The method comprises the following steps: A) Eliminating unwanted regions and identifying regions of interest; B) Determining the characteristics of each region of interest; and C) Classifying each region of interest by an artificial neural network.