Title :
Bone fracture healing assessment using a neural network
Author :
Kaufman, J.J. ; Chiabrera, A. ; Hakim, N. ; Hatem, M. ; Figueiredo, M. ; Nasser, P. ; Lattuga, S. ; Trent, P. ; Pilla, A.A. ; Siffert, R.S.
Abstract :
A method is proposed to estimate the strength of a healing fractured bone. A four-port electrical network model of the low-frequency (50 Hz-1 kHz) transverse vibration response of a healing fractured bone is derived using Timoshenko beam theory. A back-propagation neural net with one hidden layer processes computer simulated bone fracture model data, and classifies it with respect to the fracture gap stiffness, relative to intact bone. The effect on classification accuracy of the number of hidden units and preprocessing of the data is evaluated. Vibration measurements from a rabbit fracture model and clinical patient data are also presented
Keywords :
biology computing; biomechanics; bone; classification; fracture; medical computing; neural nets; vibrations; 50 to 1000 Hz; Timoshenko beam theory; back-propagation neural net; bone fracture healing assessment; bone strength estimation; classification accuracy; clinical patient data; computer simulation; four-port electrical network model; fracture gap stiffness; hidden layer; preprocessing; rabbit; transverse vibration response;
Conference_Titel :
Neural Networks, 1990., 1990 IJCNN International Joint Conference on
Conference_Location :
San Diego, CA, USA
DOI :
10.1109/IJCNN.1990.137694
