An integrated approach for surface finding in medical images

The wide availability of three-dimensional medical images has made their direct analysis a necessity. Accurately segmenting and quantifying structures is a key issue for such images. Conventional gradient-based surface finding however often suffers from a variety of limitations. This paper proposes a surface finding approach that uses in addition to gradient information, region information. This makes the resulting procedure more robust to noise and improper initialization. It uses Gauss's Divergence theorem to find the surface of of a homogeneous region-classified area in the image and integrates this with a gray level gradient-based surface finder. Experimental results show that indeed, as expected, a significant improvement is achieved as a consequence of the use of this extra information. Further these improvements are achieved with little increase in computational overhead, an advantage derived from the application of Gauss's Divergence theorem.