Cancer cell image recognition device and equipment based on quantum gate circuit neural networks

Abstract

The invention provides a cancer cell image recognition device based on quantum gate circuit neural networks. The cancer cell image recognition device based on the quantum gate circuit neural networksis used for recognizing cancer cell images to judge cancerization stages of the cancer cell images. The cancer cell image recognition device based on the quantum gate circuit neural networks is characterized by comprising a pretreatment part, an image conversion part and a classification and recognition part, wherein cutting treatment is carried out on the cancer cell images need to be recognizedby the pretreatment part to form a plurality of cutting images to be recognized with a pixel size of m x n; quantization conversion is carried out on the cutting images to be recognized by the image conversion part to obtain corresponding quantization cutting images to be recognized; and the classification and recognition part contains trained quantum gate circuit neural network models, and the classification and recognition part is used for performing classification and recognition on the quantization cutting images to be recognized corresponding to the cancer cell images to obtain classifications corresponding to the different cancerization stages, wherein in the training process of the quantum gate circuit neural network models, a momentum update rule is adopted in the update of each weight. The invention further provides image recognition equipment including the cancer cell image recognition device based on the quantum gate circuit neural networks.

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