Boundary extraction method for three dimensional ultrasonic echo imaging using fuzzy reasoning and relaxation techniques

Extraction of organ boundaries from ultrasonic echo images is essential to generate a high quality three dimensional (3D) image in 3D display techniques. Automatic detection of the boundaries is difficult due to poor intensity contrast, echo drop-outs and speckle noisy nature of the images. Here, the authors present a new approach that employs fuzzy reasoning and relaxation techniques to automatically extract the boundaries from ultrasonic echo images. In the proposed method, each voxel is classified as having one of the three attributes, Liquid (e.g., amniotic fluid, blood, etc.), Boundary and Soft Tissue. Two feature parameters are used as the input to a fuzzier unit. The defuzzification process differs from other conventional fuzzy logic controllers, in which it employs relaxation techniques. The experimental results of the authors' approach for the clinical data indicate that organ boundaries are pertinently extracted. The proposed approach may be expected as an effective boundary extraction method for the future for generating a high quality 3D image of each part of an organism from the volume data of ultrasonic echo images.<>