Establishment method of lung nodule segmentation device based on mask-rcnn neural network

Abstract

The invention discloses a method for establishing a pulmonary nodule segmentation device based on Mask-RCNN neural network, which includes: establishing training samples: sequentially performing cropping, data enhancement, and indistinguishable negative sample mining processing on collected three-dimensional lung CT images, Obtain a training sample set; establish a pulmonary nodule segmentation network: the network includes sequentially connected input layers, the first maximum pooling layer, 64*64*64 convolutional layers, the second maximum pooling layer, and 32*32*32 dense blocks Layer, the third maximum pooling layer, 16*16*16 dense block layer, the feature map output by the 16*16*16 dense block layer is upsampled and fused with the feature map output by the 32*32*32 dense block layer, The feature map after feature fusion is input to the RPN network after the POL pooling layer; training the lung nodule segmentation network: using the training samples to train the lung nodule segmentation network to obtain a lung nodule segmentation device.

Description

technical field [0001] The invention belongs to the field of image processing, and in particular relates to a method for establishing a lung nodule segmentation device based on a Mask-RCNN neural network. Background technique [0002] There are many existing methods for detecting pulmonary nodules in lung CT images using deep learning algorithms, but the detection accuracy is not high. The main reasons for the low accuracy are: [0003] (1) The recall rate in the detection stage is lower than that of some special types of pulmonary nodules, resulting in missed detection and low detection accuracy. [0004] (2) The size of pulmonary nodules is uneven, and smaller pulmonary nodules are easily overlooked. [0005] Based on the above two reasons, the typicality and representativeness of pulmonary nodules detected and segmented by deep learning algorithms are insufficient. [0006] Therefore, improving the accuracy of pulmonary nodule detection and training the network to segm...

AI Technical Summary

Problems solved by technology

[0003] (1) The recall rate in the detection stage is lower than that of some special types of pulmonary nodules, resulting in missed detection and low detection accuracy

[0004] (2) The size of pulmonary nodules is uneven, and smaller pulmonary nodules are easily overlooked

[0005] Based on the above two reasons, the typicality and representativeness of pulmonary nodules detected and segmented by deep learning algorithms are insufficient.

Images