The Significance Detection of Pulmonary Nodules Based on Local Entropy

Deep learning, especially convolutional neural network, has become a hot research direction in the field of image recognition. The method for detection of lung cancer significant based on local entropy is put forward in this paper. The experimental result shows that this method is better than the Itti visual attention model to highlight the significant of lung cancer region. Therefore, the detection method of pulmonary nodule significance based on local entropy can be used to preprocess the input data of deep learning, reduce the size of input image, reduce the convolution times of deep learning for pulmonary nodule detection, and accelerate the detection speed of deep learning of pulmonary nodule