Method for automatically recognizing white blood cells in leucorrhea based on convolution neural network

Abstract

The present invention discloses a method for automatically recognizing white blood cells in leucorrhea based on the convolution neural network, and belongs to the field of automatically recognizing medical microscopic images by using a machine vision scheme. The method comprises: firstly artificially identifying a plurality of white blood cell images and non-white blood cell images; establishing a 9-layer neural network, and training the 9-layer neural network according to the artificially identified images; and carrying out corresponding adjustment in real time on training parameters and a learning rate of the neural network during the training process; and after completion of training the neural network, carrying out detection on to-be-detected target images. According to the method disclosed by the present invention, effects of reducing labor intensity of image reading by doctors and improving the diagnostic accuracy are achieved.

Description

technical field [0001] The invention belongs to the automatic identification of medical microscopic images by using a machine vision scheme, and specifically refers to an automatic identification method for white blood cells in leucorrhea based on a convolutional neural network. Background technique [0002] Vaginal disease is a common disease in gynecology and has the characteristics of multiple occurrence. Moreover, in recent years, the incidence of vaginal infectious diseases in women is increasing year by year, which has a certain degree of impact on women's life and work. Therefore, as the most routine inspection item in gynecology, routine leucorrhea inspection has a wide range of applications. Vaginal diseases are caused by a variety of pathogenic bacteria. As a direct manifestation of vaginal inflammation or bacterial infection, white blood cells in leucorrhea have important clinical significance and great research value. However, due to the shortcomings of low manu...

AI Technical Summary

Problems solved by technology

First, a deep understanding of cells is required to pose difficult problems for machine vision workers who are not medical staff

Second, different features need to be designed for specific images, which limits the versatility of the design features, resulting in poor portability and poor scalability

Third, the original image cannot be used directly, resulting in the loss of a large number of image detail features, which can easily lead to false detection and missed detection

Images