Method and electronic device for generating medical imaging report

Through machine learning -based medical imaging reporting methods, the problem of loosening diagnosis after all knee joint replacement was solved, and the accuracy and diagnosis efficiency of early detection were achieved.

CN114694790BActive Publication Date: 2025-01-28THE CHINESE UNIVERSITY OF HONG KONG
View PDF 2 Cites 0 Cited by

Patent Information

Application Number
CN202011578412.5
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2020-12-28
Publication Date
2025-01-28
Estimated Expiration
2040-12-28

AI Technical Summary

Technical Problem

The prior art When assisting the diagnosis of looseness after total knee arthroplasty, imaging methods are expensive, insensitive and invasive, and early detection of looseness is difficult, affecting patients' timely correction and pain reduction.

Method used

Use machine -learning -based medical imaging reporting methods to generate medical imaging into a medical imaging report to generate convolutional neural networks, obtain the feature chart of the image, and generate medical image report based on feature maps to display the location distribution of predictive classification.

Benefits of technology

It improves the early detection accuracy of loosening after the full -knee joint replacement, reducing the dependence on expensive imaging methods, improving diagnostic efficiency and accuracy, and timely helping patients to correction, reducing long -term pain.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN114694790B_ABST
    Figure CN114694790B_ABST
Patent Text Reader

Abstract

The present application relates to a method, electronic device, computer-readable storage medium and computer program product for generating a medical imaging report based on machine learning, the method comprising: inputting a medical image into a medical imaging report generating convolutional neural network; obtaining a feature map of the medical image using the medical imaging report generating convolutional neural network; and generating a medical imaging report based on the feature map, wherein the position distribution of the predicted classification is shown in the medical imaging report with different display attributes, wherein the medical imaging report generating convolutional neural network comprises at least: an input layer, the input layer comprising a plurality of convolution kernels corresponding to different channels respectively; and an output layer, connected to the input layer to fuse features corresponding to different channels.
Need to check novelty before this filing date? Find Prior Art

Citation Information

Patent Citations

  • Prediction method for survival probability of infectious disease, and training method and device of prediction model

    CN111564223A

  • KR20190106609A