My SciELO
Services on Demand
Article
Indicators
- Cited by SciELO
Related links
- Similars in SciELO
Share
Revista Cubana de Informática Médica
On-line version ISSN 1684-1859
Abstract
MONNE CLEMENTE, Yamileidy and MONNE ROQUE, Diana. Segmentation of Magnetic Resonance images of the brain based on Generalized Regression Neural Networks. RCIM [online]. 2013, vol.5, n.1, pp. 82-90. ISSN 1684-1859.
The analysis of structural changes in the brain through Magnetic Resonance Images may provide useful information for the diagnosis and clinical management of patients with dementia. While the degree of sophistication achieved by the MRI equipment is high, the quantification of structures and tissues has not been completely solved. The segmentations that these equipment provide nowadays, fail on those structures where the edges are not clearly defined. This paper presents a method for automatic segmentation of magnetic resonance images of the brain, based on the use of generalized regression neural networks using genetic algorithms for adjusting parameters. The network is trained from a single image and classifies rest of them whenever magnetic resonance images were acquired with the same protocol. A method of measuring the progressive atrophy and possible changes compared to a therapeutic effect should be essentially automatic and therefore independent of the radiologist.
Keywords : images; magnetic resonance; segmentation; neural networks; genetic algorithm.