Prostate multimode MR image classification method and system based on fovea central residual network

Abstract

The invention discloses a prostate multimode MR image classification method and system based on a fovea centralis residual network, and the method comprises the steps: replacing a convolution kernel of a residual network with a fuzzy kernel in a fovea centralis operator, and constructing the fovea centralis residual network; training a fovea centralis residual network by using the prostate multimode MR image with the category label to obtain a trained fovea centralis residual network; and classifying the to-be-classified prostate multimode MR image by using the concave central residual network to obtain a classification result. According to the method, the fovea centralis operator is designed, the fuzzy kernel of the operator is extracted and used for replacing the convolution kernel in the residual network on the basis of the human visual characteristics, so that the fovea centralis deep learning network is constructed, the characteristics conforming to the human visual characteristics can be extracted, and the classification precision of the prostate multi-modal MR image is improved.

Description

technical field [0001] The invention belongs to the field of image classification, and more particularly relates to a method and system for classification of prostate multimode MR images based on a fovea residual network. Background technique [0002] Prostate cancer is the most common malignant tumor in the male reproductive system. According to the report of the American Cancer Society in 2018, prostate cancer ranks first among new male cases and ranks second in death cases. In recent years, with the significant improvement of people's living standards and the change of population age structure in our country, the incidence and mortality of prostate cancer in my country have shown an obvious upward trend. [0003] MRI can reflect changes in tissue and internal organ functions and biochemical metabolic reactions. It has the advantages of high-resolution imaging of soft tissues, and has important application value in the early diagnosis of prostate cancer. In recent years, ...

AI Technical Summary

Problems solved by technology

[0007] Aiming at the above defects or improvement needs of the prior art, the present invention provides a method and system for the classification of prostate multimodal MR images based on the fovea residual network, thereby solving the problems in the prior art that it is difficult to extract features that conform to the visual characteristics of the human eye , the technical problem of low accuracy of prostate image classification based on deep learning

Images