Method, device and equipment for classifying capillary images in epithelial nipples and medium

Abstract

The embodiment of the invention discloses a method, a device and equipment for classifying capillary images in epithelial nipples and a medium. The method comprises the following steps: inputting an endoscopic image of a capillary in an epithelial nipple into a pre-trained neural network model to obtain an effective area of the endoscopic image; obtaining a target blood vessel region in the endoscopic image from the effective region according to a connected domain algorithm; and obtaining the characteristic diameter, the characteristic distortion quantized value, the characteristic area proportion, the centroid eccentricity and the whole image density of the target blood vessel in the target blood vessel region, and inputting the obtained values into a pre-trained classification model to obtain a classification result of the endoscopic image. According to the method, the target blood vessel in the endoscopic image is extracted based on the neural network technology, the five indexes for evaluating the target blood vessel are obtained, the esophageal cancer infiltration depth is accurately judged according to the five indexes, and the efficiency and accuracy of judging the esophageal cancer infiltration depth are improved.

Description

technical field [0001] The present invention relates to the technical field of medical assistance, in particular to a method, device, equipment and medium for classifying images of capillaries in epithelial papillae. Background technique [0002] Intraa Pillary Capillary Loops (IPCL) are microvessels formed perpendicular to branch vessels under the squamous epithelium. Among them, the degree of morphological change of capillary loops in the epithelial papilla is a key indicator for diagnosing the depth of esophageal cancer invasion under endoscopy, and the destruction of IPCL structure increases with the infiltration of tumors. plays an important role in. When squamous cell carcinoma invades the lamina propria, irregular microvessels form in the form of loops with enlarged diameters; when the tumor invades the muscularis mucosa or superficially invades the submucosa, the abnormal microvascular loops disappear and appear obvious The elongated deformation of the tumor; the t...

AI Technical Summary

Problems solved by technology

[0004] The embodiment of the present invention provides a classification method, device, equipment and medium for images of capillaries in the epithelial papilla, which solves the technical problem in the prior art that the infiltration depth of esophageal cancer cannot be accurately identified under chromoendoscopy

Images