A Fast Automatic Path Planning using the Energy Map and Path Tree Propagation for Virtual Colonoscopy

概要

論文の詳細を見る
Virtual colonoscopy is a non-invasive method for diagnosing colon diseases such as polyps, diverticulosis, and cancer by producing two or three dimensional images of the colon in digitized tomographic images. In virtual colonoscopy, it is crucial to generate the camera path rapidly and accurately for an efficient clinical examination. Most of conventional path planning methods are computationally expensive or converge on local minima in complex regions. In this paper, we propose a fast automatic path planning method using the energy map and path tree propagation. Robust centerline generation can be achieved by calculating the shortest path with the weights, which are determined by the distance from the source point, and the colon boundary. The propagation of the path tree generated by the fast queue sorting increases the computational efficiency. Experiments were performed to illustrate the effectiveness of the proposed scheme. The result shows a faster path planning and easier navigation. The proposed method can be successfully applied to help diagnosing the colon cancer in virtual colonoscopy.
2007-01-19