首页>
外国专利>
Method and system for reading capsule endoscopy image based on artificial intelligence
Method and system for reading capsule endoscopy image based on artificial intelligence
展开▼
机译:基于人工智能的胶囊内窥镜图像读取方法及系统
展开▼
页面导航
摘要
著录项
相似文献
摘要
The present invention relates to an artificial intelligence-based capsule endoscope image reading method and system, wherein the artificial intelligence-based capsule endoscope image reading system comprises a pre-processing unit for pre-processing an image (capsule endoscope image) taken by a capsule endoscope; And a convolutional neural network (CNN) that classifies a pre-processed capsule endoscope image as an image with a lesion and an image without a lesion, and the composite product neural network (CNN) receives the pre-processed capsule endoscope image as an input. layer; A composite product layer for extracting features for the pre-processed capsule endoscope image input through the input unit; A maximum pooling layer that sub-samples the characteristics of the extracted small intestinal endoscopy image to increase stability and efficiency of the system; A global average pooling layer that replaces the fully connected layer and obtains a class activation map (CAM); And an output layer for outputting a probability that a lesion exists and a probability value without a lesion for each capsule endoscope image. According to the present invention, it is possible to reduce the reading time of a doctor who reads a large amount of endoscope images photographed by a capsule endoscope and increase the accuracy of reading, thereby enabling quality medical treatment.
展开▼