US 12,254,684 B2
Smart diagnosis assistance method to solve results of inaccurate classification of image, and terminal based on medical images
Shuqiang Wang, Guangdong (CN); Wen Yu, Guangdong (CN); Yanyan Shen, Guangdong (CN); and Zhuo Chen, Guangdong (CN)
Assigned to SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY CHINESE ACADEMY OF SCIENCES, Guangdong (CN)
Appl. No. 17/763,513
Filed by SHENZHEN INSTITUTES OF ADVANCED TECHNOLOGY CHINESE ACADEMY OF SCIENCES, Guangdong (CN)
PCT Filed Nov. 19, 2019, PCT No. PCT/CN2019/119491
§ 371(c)(1), (2) Date Mar. 24, 2022,
PCT Pub. No. WO2021/097675, PCT Pub. Date May 27, 2021.
Prior Publication US 2022/0343638 A1, Oct. 27, 2022
Int. Cl. G06V 10/80 (2022.01); G06T 7/00 (2017.01); G06V 10/40 (2022.01); G06V 10/764 (2022.01); G06V 10/82 (2022.01); G16H 30/40 (2018.01)
CPC G06V 10/82 (2022.01) [G06T 7/0012 (2013.01); G06V 10/40 (2022.01); G06V 10/764 (2022.01); G06V 10/806 (2022.01); G16H 30/40 (2018.01)] 14 Claims
OG exemplary drawing
 
1. A smart diagnosis assistance method based on medical images, comprising:
acquiring a medical image to be classified;
preprocessing the medical image to be classified to obtain a preprocessed image;
inputting the preprocessed image into a trained classification model for classification processing to obtain a classification category corresponding to the preprocessed image; wherein the classification model comprises a tensorized network layer and a second-order pooling module, the classification model is a ternary generative adversarial network obtained by training sample images and classification categories corresponding to the sample images based on a preset generator model, a preset discriminator model and a preset classifier model;
wherein, the trained classification model comprises a trained classifier model, and the inputting the preprocessed image into the trained classification model for classification processing to obtain the classification category corresponding to the preprocessed image comprises:
normalizing the preprocessed image by using the classifier model to obtain a target image;
extracting key features in the target image by using the classifier model to obtain a global high-order feature map;
acquiring the classification category corresponding to the global high-order feature map by using the classifier model;
wherein, the extracting the key features in the target image by using the classifier model to obtain the global high-order feature map comprises:
extracting features in the target image through the tensorized network layer in the classifier model to obtain a first feature map;
performing channel dimension reduction on the first feature map through the second-order pooling module in the classifier model to obtain a dimension-reduced second feature map;
calculating a weight vector corresponding to the second feature map;
weighting the first feature map based on the weight vector to obtain the global high-order feature map.