Name
Abstract | ||
|---|---|---|
The morphometric analysis of myelinated fibers is known to produce relevant information for the evaluation of several phenomena, which range from nerve demyelization/remyelization to the aging process. This analysis can be achieved manually or using computer-based image analysis systems which vary to a certain degree of automation. However, systems which are manual or semi-automated are extremely laborious, highly tedious and time-consuming. Therefore, the aim of this paper is the proposal, implementation and evaluation of a computational tool capable of automatically performing the morphometry of myelinated fibers. We have implemented and tested various methods for the segmentation of images from different types of nerve, which present differences in form, color and size. Then, we implemented an algorithm capable of extracting the required morphometric features. The developed tool has shown maximum area overlap accuracy of 83.1% and sensitivity of 90.7% for our database. The tool has widespread potential in experimental and clinical applications eliminating many of the tedious and time-consuming tasks associated with nerve morphometry. |
Year | DOI | Venue |
|---|---|---|
2013 | 10.1109/CBMS.2013.6627782 | CBMS |
Keywords | Field | DocType |
pipelines,image segmentation,neurophysiology,feature extraction | Computer vision,Pattern recognition,Neurophysiology,Segmentation,Computer science,Automation,Feature extraction,Image segmentation,Artificial intelligence | Conference |
Citations | PageRank | References |
1 | 0.38 | 3 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Romulo Bourget Novas | 1 | 1 | 0.72 |
| Valeria Paula Sassoni Fazan | 2 | 1 | 0.38 |
| Joaquim Cezar Felipe | 3 | 54 | 7.17 |