A comparison between two robust techniques for segmentation of blood vessels
Computers in Biology and Medicine
| Hi-index | 0.00 |
In this paper we utilize the Kohonen's self-organizing feature map to segment blood vessels from biopsies in tumor tissue. The ability of this kind of neural network to recognize very complex patterns makes it an effective computational tool for the segmentation. We propose a strategy of blood vessels segmentation using a neural network, taking into account the quality of our images and its features: complexity in shape and variability in size. Segmentation results are contingently manually corrected. The proposed segmentation strategy is tested on manual segmentation, where segmentation errors of less than 3.5% are observed. This work is a part of a global image analysis process and these images will be subject to a further morphometrical analysis in order to diagnose and prognosticate automatically malignant tumours.