Pathological image classification device and method and use method of device

Abstract

The invention discloses a pathological image classification device, and the device comprises an image data set generation unit which is used for carrying out the sampling of morphological digital slices, and generating a first small image data set; the sampling module is also used for sampling the morphological digital slices and generating a small block image data set II in combination with a set data set rule; the region classification unit is used for calculating prediction region classification labels of the small-block image data in the small-block image data set I; combining a predetermined region classification rule, and synthesizing the small images into regions on the morphological digital slices; the pathology classification unit is used for calculating a predicted pathology classification label of small block abnormal image data in the small block image data set II; and calculating predicted pathological classification labels of the small abnormal image data blocks in the same abnormal area to obtain pathological classification labels of the abnormal areas. The invention further discloses a pathological image classification method. The invention discloses a use method of a pathological image classification device. According to the invention, rapid and accurate pathological image classification can be realized.

Description

technical field [0001] The present invention relates to the field of image recognition and deep learning, and more particularly, to a pathological image classification technology. Background technique [0002] Pathological images are the gold standard for the final diagnosis of cancer. However, the current classification of pathological images based on doctors' manual work is not only time-consuming and labor-intensive, but also the diagnosis results are easily affected by subjective human factors such as doctor's experience and level. The introduction of computer-aided diagnosis systems can not only improve the diagnosis efficiency, but also assist Provide more objective and accurate diagnostic results. In recent years, some convolutional neural network models have been used in computer-aided diagnosis systems to automatically classify pathological images, among which the ResNet convolutional neural network is the most widely used. However, since the ResNet convolutional ...

AI Technical Summary

Problems solved by technology

However, because the ResNet convolutional neural network is designed for natural images, in order to obtain more accurate image recognition results, the number of layers required is generally deep, and the calculation is time-consuming; on the other hand, there are many model parameters, and a large amount of training data is required to train the parameters. , in order to obtain higher accuracy

However, due to the small size of the pathological image data set, the above model is directly used in the computer-aided diagnosis system to automatically classify pathological images, which is prone to overfitting and reduces the accuracy and reliability of classification.

Images