Thyroid cancer pathological image classification method based on deep learning

Abstract

The invention discloses a thyroid cancer pathological image classification method based on deep learning, and mainly solves the problem of poor thyroid cancer pathological image classification effectof an existing method. According to the implementation scheme, the method comprises the following steps: reading a thyroid pathology image database, extracting low-level convolution and pooling features by a receptive field network, and fusing the features to obtain fused low-level features; extracting high-level features, namely predicted category vectors, from the fused low-level features through a capsule network; updating the category vector through a dynamic routing algorithm to obtain a final category vector, and calculating the modulus of the category vector through a compression activation function; carrying out image reconstruction on the vector with the maximum modulus value through a decoding reconstruction network; iteratively updating weights in the receptive field network andthe capsule network to complete model training; and finally, inputting a thyroid pathological image to be classified into the trained model to obtain a final classification result. The invention improves the classification accuracy of the thyroid cancer pathological images and can be used for computer-aided diagnosis.

Description

technical field [0001] The invention belongs to the technical field of image processing, and further relates to a classification method of pathological images of thyroid cancer, which can be used for feature extraction of pathological images of thyroid cancer and classification of pathological images of thyroid cancer. Background technique [0002] In recent years, the incidence of thyroid cancer in the world has gradually increased. The incidence of thyroid cancer ranks fourth among malignant tumors among women in urban areas in my country. Since the 1990s, the incidence of thyroid cancer in my country has increased by about three Times, with an average annual increase of 5%, the harm of thyroid cancer is getting bigger and bigger. The main diagnostic methods for thyroid cancer include thyroid autoantibodies and tumor markers, computerized tomography CT, magnetic resonance imaging MRI, and pathological diagnosis of thyroid cancer cells, among which pathological diagnosis of ...

AI Technical Summary

Problems solved by technology

However, the above method loses a lot of feature information during feature extraction, and requires a lot of data when training the classification network, resulting in poor classification effect of thyroid cancer pathological images

Images