Tumor cell image recognition device and equipment based on quantum gate circuit neural network

Abstract

The present invention provides a tumor image identification device based on quantum gate circuit neural network, which is used to identify tumor images to determine the cancerous stage of tumor images. Carry out cutting processing to form a plurality of cut images to be recognized with a pixel size of m×n; the image conversion part performs quantization conversion on the cut images to be recognized, and obtains corresponding quantized cut images to be recognized; the classification and recognition part contains trained The quantum gate circuit neural network model is used to classify and identify the quantized cutting image corresponding to the tumor image to obtain the classification corresponding to different cancer stages. In the training process of the quantum gate circuit neural network model, The update of the weights of each layer adopts the momentum update rule. The present invention also provides an image recognition device including the above-mentioned tumor image recognition device based on quantum gate circuit neural network.

Description

technical field [0001] The invention relates to an image recognition device and equipment, in particular to a tumor cell image recognition device and equipment based on quantum gate circuit neural network. Background technique [0002] Clinically, the pathological diagnosis of tumors mainly relies on medical microscopic images, that is, after sampling images of tissue slices, doctors can judge the cancerous stage (including normal, hyperplasia, and cancer) with naked eyes. Such a diagnosis method relies on manual judgment, so it has the disadvantages of low work efficiency and prone to human misjudgment. [0003] In order to overcome the above shortcomings, scholars at home and abroad have carried out a lot of related research, including the development of identification devices that can automatically judge the stage of canceration based on tissue images; at the same time, the vigorous development of artificial intelligence technology in recent years has also made the combin...

AI Technical Summary

Problems solved by technology

However, since these methods are all based on the binary development of existing computer technology, and the binary calculation requires a very large amount of calculation to represent and calculate the pixel value of the image, therefore, increasing the training set will lead to too long training time This in turn leads to inefficiency and reduced practicability. On the contrary, reducing the number of images in the training set to improve efficiency will lead to poor accuracy and also reduce practicability.

Images