An automatic identification system, computer equipment, and storage medium for metastatic lymph nodes in the upper abdomen based on deep learning

Abstract

The invention discloses an automatic identification system for metastatic lymph nodes in the upper abdomen based on deep learning, which belongs to the technical field of image identification. The system includes: a faster-rcnn model, the faster-rcnn model includes: a feature extraction network, a region generation network and a fast-rcnn target detector; first, the image features of the input CT image are abstracted and generated using the feature extraction network Convolutional feature map; then, use the area generation network to screen the convolutional feature map to generate a candidate region for metastatic lymph nodes; finally, in the fast-rcnn target detector, the region of interest feature pooling layer is used to The convolution feature map and the candidate area are convolved to obtain a set of low-dimensional features, and the low-dimensional features are respectively input into two sub-fully connected layers for regression and classification, and finally output the position of the metastatic lymph node area and probability.

Description

technical field [0001] The present invention relates to the technical field of image recognition, in particular to an automatic recognition system for metastatic lymph nodes in the upper abdomen based on deep learning, computer equipment, and storage media. Background technique [0002] In the traditional diagnosis, professional physicians observe the image images, compare and analyze a series of images of the case, and rely on experience to extract and mark the metastatic lymph nodes in the upper abdomen. This method requires professional doctors to perform cumbersome manual operations on a large amount of data. At the same time, the accuracy and reliability of the diagnostic results of this method are heavily dependent on the doctor's experience, knowledge and professional quality, and the accuracy of the diagnostic results is limited. [0003] In recent years, due to the rapid development of computer technology and the maturity of graphics and image processing technology,...

AI Technical Summary

Problems solved by technology

This method requires professional doctors to perform cumbersome manual operations on a large amount of data. At the same time, the accuracy and reliability of the diagnostic results of this method are heavily dependent on the doctor's experience, knowledge and professional quality, and the accuracy of the diagnostic results is limited.

Images