Bronchoscope image feature comparison marking system and method based on deep learning

Abstract

The invention discloses a bronchoscope image feature comparison marking system based on deep learning, and the system comprises: an input layer which is used for receiving a bronchoscope image collected by a bronchoscope, carrying out the recognition of the received bronchoscope image, and transmitting a recognized in-vivo image to a judgment layer; a judgment layer which is used for recognizing the in-vivo image from the input layer, judging a part corresponding to the in-vivo image, judging whether a lesion part exists or not and judging whether the lesion part is benign or malignant or not, and then feeding back a recognition result to the output layer; and an output layer which is used for displaying the identification result from the judgment layer. The invention further discloses a bronchoscope image feature comparison marking method based on deep learning. According to the invention, the central lung tumor focus part under the bronchoscope can be identified by carrying out feature comparison on the bronchoscope image.

Description

technical field [0001] The invention relates to an image processing system, in particular to a bronchoscope image feature comparison and marking system based on deep learning. The invention also relates to a method for comparing and marking bronchoscope image features based on deep learning. Background technique [0002] Central lung cancer refers to tumors in which the lesions occur in the bronchi above the segmental mouth. Because it occurs in the larger bronchi, it can be found by general electronic bronchoscopy. Bronchoscopy can not only directly understand the location, shape and size of bronchial tumors, but also clarify the pathological tissue type of the tumor through biopsy and brush examination, providing an important basis for surgery, radiotherapy and chemotherapy. Therefore, the use of bronchoscopy to examine central lung cancer is currently the most important and reliable diagnostic method. However, bronchoscopy is highly dependent on the clinical experience...

AI Technical Summary

Problems solved by technology

Fluorescence bronchoscopy is characterized by high sensitivity and low specificity, and it is easy to find lesions, but it is difficult to distinguish benign from malignant lesions; while narrow-spectrum bronchoscopy is characterized by only observing the blood vessels in the lesions, and cannot distinguish between benign and malignant lesions.

Images