Cargando…
Automatic Graph Cut Segmentation of Lesions in CT Using Mean Shift Superpixels
This paper presents a new, automatic method of accurately extracting lesions from CT data. It first determines, at each voxel, a five-dimensional (5D) feature vector that contains intensity, shape index, and 3D spatial location. Then, nonparametric mean shift clustering forms superpixels from these...
| Autores principales: | , , |
|---|---|
| Formato: | Texto |
| Lenguaje: | English |
| Publicado: |
Hindawi Publishing Corporation
2010
|
| Materias: | |
| Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC2967838/ https://www.ncbi.nlm.nih.gov/pubmed/21052498 http://dx.doi.org/10.1155/2010/983963 |