Computational connected cellular network - a novel learning system to study bone formation

It is believed that bone cells can sense and transmit signals produced by external mechanical loading. The signals are processed and integrated through cell-to-cell communications in a connected cellular network (CCN) before reaching bone forming cells on bone surface. However, the mechanism of cell-to-cell communication is still unknown. Our previous study (2000) has shown that a backpropagation neural network model can be used to capture the functional relation between the mechanical loading and the amount of bone formation. To better understand the cell-to-cell communication in bone matrix, a new computational CCN learning system has been developed with a structure that mimics the actual biological CCN in the bone. We show that a network with binary weights and a simple error feedback rule provides encouraging results