Growing region technique in the detection of autonomous structures within X-ray radiographs

Nodule identification is a major issue in chest radiography and cancer prevention and detection. The recognition of cancer nodule characteristics in chest radiographs is a key point to the detection procedure. The method described here is based on the extraction of the major geometrical as well as luminance characteristics that make nodule recognizable and easy to detect. The purpose of the proposed method is to detect within a given block of chest X-ray image any homogeneous and autonomous mass that might means the existence of a nodule or some structure within it. The idea of pixels of interest is introduced which makes the growing a finite steps procedure. The growing of the region around a given point is realized gradually in a finite number of iterations at each one of which a set of criteria is evaluated. These criteria are established in a prior training procedure.