ARTIFICIAL CONVOLUTION NEURAL-NETWORK TECHNIQUES AND APPLICATIONS FORLUNG NODULE DETECTION

We have developed a double-matching method and an artificial visual ne ural network technique for lung nodule detection. This neural network technique is generally applicable to the recognition of medical image pattern in gray scale imaging. The structure of the artificial neural net is a simplified network structure of human vision. The fundamental operation of the artificial neural network is local two-dimensional c onvolution rather than full connection with weighted multiplication. W eighting coefficients of the convolution kernels are formed by the neu ral network through backpropagated training. In addition, we modeled r adiologists' reading procedures in order to instruct the artificial ne ural network to recognize the image patterns predefined and those of i nterest to experts in radiology. We have tested this method for lung n odule detection. The performance studies have shown the potential use of this technique in a clinical setting. This program first performed an initial nodule search with high sensitivity in detecting round obje cts using a sphere template double-matching technique. The artificial convolution neural network acted as a final classifier to determine wh ether the suspected image block contains a lung nodule. The total proc essing time for the automatic detection of lung nodules using both pre scan and convolution neural network evaluation was about 15 seconds in a DEC Alpha workstation.