A New Algorithm for Local Surface Smoothing with Application to Chest Wall Nodule Segmentation in Lung CT Data

摘要

We present an algorithm for local surface smoothing in a defined Volume of Interest (VOI) cropped from 3D volume data, such as lung CT data. There is generally a smooth and piecewise linear surface in the VOI, with one or more bumps on the surface. In lung CT data, such bumps can be nodules that are grown from the chest wall, which represent a possibility of lung cancer. Through surface smoothing, the nodules are segmented from the chest wall and its size can be measured as diagnostic evidence. The algorithm has the advantage of high consistency and robustness, and is useful in a segmentation module of a Compute Aided Diagnosis (CAD) system.