Abstract
Tissue segmentation based on 2D and 3D feature map derived from high resolution MR images was performed in phantoms, normal humans and particularly those with brain tumors (four benign and two malignant). Three inputs: proton density, T2 - and, as a third, T1-weighted MRI, were utilized. Statistical and anisotropic diffusion filters were applied to the data and k-Nearest Neighborhood segmentation algorithm was utilized. The inclusion of T1 based images into segmentation produced dramatic improvement in tissue identification. Our technique utilizing all three inputs provided better segmentation (p < 0.001) than that based on any combination of two inputs. In benign brain tumors, we identified tumor volume prior to the injection of gadolinium-DTPA. In malignant tumors, up to four abnormal tissues were identified: 1) solid tumor core, 2) cyst, 3) edema in white matter and 4) edema in grey matter. Subsequent neurosurgery confirmed our model. These results encourage further investigation.
Original language | English (US) |
---|---|
Pages (from-to) | 481-482 |
Number of pages | 2 |
Journal | Annual International Conference of the IEEE Engineering in Medicine and Biology - Proceedings |
Volume | 17 |
Issue number | 1 |
State | Published - 1995 |
Externally published | Yes |
Event | Proceedings of the 1995 IEEE Engineering in Medicine and Biology 17th Annual Conference and 21st Canadian Medical and Biological Engineering Conference. Part 2 (of 2) - Montreal, Can Duration: Sep 20 1995 → Sep 23 1995 |
ASJC Scopus subject areas
- Signal Processing
- Biomedical Engineering
- Computer Vision and Pattern Recognition
- Health Informatics