 |
|
|
|
|
VolRover encapsulates functionalities, which are computer accelerated methods for contour extraction, dynamic mesh reduction for improved interactive display, real-time rendering working with compressed data stream, and using topological and volumetric quantitative signature for feature extraction, along with the filtering and feature extraction techniques, into volumetric exploratory visualization tool. |
|
|
| :Blood Vessel Boundary Extraction | | Pulmonary embolism can be detected by checking the shape of pulmonary artery in three-dimensional CTA images, since PE has darker gray colors in CTA images than normal blood vessels and it makes the irregular shape of pulmonary artery. Some locations of pulmonary artery containing PE look like squashed blood vessel. Therefore, correct boundary detection and vessel tracking are important steps to detect PE from three-dimensional CTA images. Intensity-based boundary detection and tracking may not be good idea for PE detection, because of the partial volume effect, in which several materials are mixed within a voxel. In this project, we extracted the boundary of blood vessels using 1st and 2nd derivatives as well as intensity values. The following figures show the differences of the two boundary detection algorithms. |
| | Blood Vessel Boundary Extraction | |
| | (a) Intensity, 1st, and 2nd Derivatives |
| | | Blood Vessel Boundary Extraction | |
| | (b) Intensity Value Only |
| | |
|
|
|
|
|
