Deformation Method for Three-Dimension Object Detection of Lung Nodule Images
| Autor: | Chun Long Chang, 張竣隆 |
|---|---|
| Rok vydání: | 1999 |
| Druh dokumentu: | 學位論文 ; thesis |
| Popis: | 87 The computer tomography (CT) is a promising tool for the early diagnosis of lung nodules. The three-dimensional information makes it possible to detect a subtle change in any field of the lung. However, the diagnosis procedure is time-consuming, since a considerable number of images have to be reviewed in one examination. In order to lessen the physician reviewing burden and to improve the accuracy of diagnosis, this thesis presents a three-dimensional deformable model to perform cross-sectional medical image contours in three-dimensional form. We control the parameters of the deformable model and use cross-correlation of the tissue in lung to search nodules. We use CT medical images of the eight patients to prove the practicability of the method we publish. According to the experiment results, the method can be used to detect the lung nodule, successfully. And we use the other way to compare the result of the method. The other way is to control the parameters of Superquadrics method to construct the different deformable models. Then, the deformable model can be used to fit the sphere object in the lung CT images. And we also can apply the deformable model to reconstruct the three-dimensional visualization image that based on the model with global deformation manner. |
| Databáze: | Networked Digital Library of Theses & Dissertations |
| Externí odkaz: |
|