Information labeling method, device and system for medical image data

Abstract

The invention discloses an information labeling method, device and system for medical image data. The method comprises the following steps: acquiring to-be-labeled medical image data; inputting medical image data to be labeled into an image pre-labeling model, obtaining pre-labeling information, and using the image pre-labeling model for conducting feature extraction on the medical image data to obtain a neural network model of the pre-labeling information; in response to displaying the medical image data containing the pre-annotation information on the target platform, obtaining adjustment information of the target platform for the pre-annotation information; and processing the adjustment information and the pre-annotation information to obtain target annotation information of the to-be-annotated medical image data. According to the method, the medical image data is labeled through the model, and the labeled information can be adjusted in combination with a man-machine interaction mode, so that the information labeling efficiency and quality of the medical image are improved.

Description

technical field [0001] The present invention relates to the technical field of information processing, in particular to an information labeling method, device and system for medical image data. Background technique [0002] Medical image data plays an important role in patient diagnosis, treatment, surgery planning, training and other scenarios. In recent years, the large-scale growth of digital medical images has provided a data basis for promoting the research and application of medical image processing technology represented by deep neural networks. However, the current medical image field lacks large-scale and reliable benchmark datasets, which affects the development of deep learning for medical image data. [0003] The reason for the lack of accurate and reliable benchmark data sets in the field of medical images is that due to the professionalism and complexity of medical images, different experts have great differences when manually labeling medical images, and the ...

AI Technical Summary

Problems solved by technology

However, there is currently a lack of large-scale and reliable benchmark datasets in the field of medical images, which affects the development of deep learning for medical image data.

[0003] The reason for the lack of accurate and reliable benchmark data sets in the field of medical images is that due to the professionalism and complexity of medical images, different experts have great differences when manually labeling medical images, and the labeling results are often different. Therefore, manual Annotating medical images is becoming increasingly difficult and expensive

It can be seen that the existing information labeling methods for medical image data are mainly manually marked by experts, which reduces the efficiency and quality of information labeling.

Images