Novel Approach Using Echo State Networks for Microscopic Cellular Image Segmentation

This paper concentrates on the use of Echo State Networks (ESNs), an effective form of reservoir computing, to improve microscopic cellular image segmentation. An ESN is a sparsely connected recurrent neural network in which most of the weights are fixed a priori to randomly chosen values. The only trainable weights are those of links connected to the outputs. The process of segmentation is conducted via two approaches: the basic form, which uses one reservoir, and our approach, which corresponds to using multiple reservoirs. Experimental results confirm the benefits of the second approach, which outperforms all state-of-the-art methods considered in this paper for the problem of microscopic image segmentation.