Capsule endoscope image recognition method and device based on deep learning and medium

Abstract

The invention provides a capsule endoscope image recognition method and device based on deep learning and a medium. The method comprises the steps of collecting N original images through a capsule endoscope according to a time generation sequence; segmenting the N original images into M groups of original image sequences with the same size by adopting a sliding window segmentation method; analyzing the N original images or analyzing the M groups of original image sequences to form M groups of RGB image sequences, and analyzing the N original images or analyzing the M groups of RGB image sequences to form M groups of optical flow images, wherein each RGB image sequence is composed of image data in an RGB format, and each optical flow image sequence is composed of image data formed by calculating optical flow fields of adjacent RGB images; and respectively inputting the RGB image sequences and the optical flow image sequences into a 3D convolutional neural network model to output an identification result, wherein the identification result is a probability value of occurrence of a preset parameter. The image recognition precision is improved.

Description

technical field [0001] The present invention relates to the field of medical equipment imaging, in particular to a capsule endoscope image recognition method based on deep learning, electronic equipment and a readable storage medium. Background technique [0002] Capsule endoscope is a kind of medical equipment, which integrates core components such as camera and wireless transmission antenna; and collects images in the digestive tract of the body and transmits them synchronously to the outside of the body for medical examination based on the obtained image data. Capsule endoscopes will collect tens of thousands of images during the detection process, and a large amount of image data makes the work of image reading difficult and time-consuming; with the development of technology, the use of image processing and computer vision technology for lesion identification has gained wide popularity. focus on. [0003] In the prior art, the Chinese patent application with the publica...

AI Technical Summary

Problems solved by technology

[0005] The solutions mentioned in the prior art all recognize a single image, and only the information captured by a single image can be used in the identification process, and the image information captured before and after cannot be comprehensively utilized; thus, images captured at a single angle cannot be intuitively It reflects the overall situation of the lesion, especially the images of digestive tract folds and gastric wall taken at certain angles are easy to be confused with polyps, bulges and other lesions; in addition, the existing technology cannot obtain the spatial and temporal information of the shooting content at the same time, The accuracy of lesion identification is low

Images