Soft tissue stereo-tracking

Abstract

The disclosed method encompasses reconstruction of a three-dimensional position of a tracking structure (which may comprise a target of radiation treatment) as reconstructed tracking structure data from pairs of two-dimensional tracking images which are input as tracking image data. Each tracking image contained in a pair of tracking images is compared to a tracking representation of the tracking structure contained in a search template image generated from the same perspective onto the tracking structure as the associated tracking image and input as search template data. The tracking image having the highest at local degree of similarity to its associated search template image is selected as a starting point (the first tracking image) for computing a corresponding image position (a complement point) in the other tracking image (the second tracking image) on the basis of applying epipolar geometry outgoing from the position in the first tracking image associated with the highest local degree of similarity. The method then continues with determining whether there is a point in the second tracking image having a higher degree of similarity than the complement point. Depending on the result of this analysis, an accumulated value of similarity is determined for each pair of tracking images depending on the sum of similarity values of the maximum similarity points in the first and second tracking images so determined. The position of the tracking structure is determined as the intersection of back-projection lines of the points being associated with the highest sum of associated similarity values. Thereby, the reliability of position determination from stereoscopic two-dimensional x-ray images can be enhanced.