J022023 空洞強調フィルタと領域拡張法によるCT像からの気管支領域抽出手法([J02202]診療技術と臨床バイオメカニクス(2))

概要

論文の詳細を見る
In this paper, a novel method for extracting airway trees from three-dimensional CT images based on the cavity enhancement filter (CEF) and the region-growing method are proposed. Airway trees are useful for structural analyses of the lungs, virtualized bronchoscopy, and numerical simulations of respiratory functions. For these purposes, precise airway trees are required. Since airway trees have tubular structure and the CEF enhances voxels in cavities selectively, voxels belonging to airway trees are enhanced. By using the proposed method, first, voxles which are enhanced by the CEF are tracked to extract airway trees. Then eigen values of Hessian matrix are used as a condition for tracking to extract thinner airway trees. On the basis of the results of applying the proposed method to six cases of CT images, it was determined that the number and total length of the extracted bronchial branches increased while very few false positive regions were extracted.
一般社団法人日本機械学会の論文
2011-09-11