Lung tumor recognition system and method based on convolutional neural network

A convolutional network, lung technology, applied in the field of lung tumor recognition system based on convolutional neural network, can solve the problem of low recognition accuracy, and achieve the effect of improving the recognition rate, improving the recognition accuracy, and reducing the amount of calculation.
CN106203327AActive Publication Date: 2016-12-07TSINGHUA UNIV
5 Cites 40 Cited by

Patent Information

Authority / Receiving Office
CN · China
Current Assignee / Owner
TSINGHUA UNIV
Publication Date
2016-12-07

Smart Images

  • Figure 1
    Figure 1
  • Figure 2
    Figure 2
  • Figure 3
    Figure 3
Patent Text Reader

Abstract

The invention provides a lung tumor recognition system and method based on a convolutional neural network. The lung tumor recognition method based on the convolutional neural network includes the steps that multiple cascading images collected along a preset dimensionality are received; the cascading images are blocked according to the rule that moving is the same in the same window, the image blocks in the cascading images corresponding to the same window position are combined and convolved to obtain feature image blocks, and down-sampling is conducted on each feature image block; the feature image blocks subjected to down-sampling are subjected to up-sampling; a heat degree prediction map is drawn on the basis of probability that each pixel in the heat degree prediction map corresponds to at least one feature image block subjected to up-sampling may be true or false. The system and method effectively increase the recognition rate of local areas of the cascading images with spatial association.
Need to check novelty before this filing date? Find Prior Art

Description

technical field

[0001] The present invention relates to an image processing technology, in particular to a lung tumor recognition system and method based on a convolutional neural network. Background technique

[0002] In recent years, convolutional neural networks have demonstrated their advantages in image feature recognition tasks. For example, during the construction of a 2D image to a 3D image, a convolutional neural network is used to perform bad block screening on 2D image blocks. Most of the current convolutional neural networks use deep learning methods to classify images as true or false. As a model with a slightly special structure, the fully convolutional neural network has made great progress in local recognition tasks, including object bounding box detection, prediction of key parts and key points of objects, etc. These prediction methods still use the method of learning the classifier to improve the recognition and classification of image blocks. The disadv...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More