Image automatic annotation model construction method, system and application

Abstract

The invention discloses an automatic image annotation model construction method and system and application. The method comprises the steps that (1) a plurality of images are collected and annotated to obtain an original sample set; constructing an original annotation model according to the to-be-annotated image; (2) training the original labeling model by using samples in the original sample set to obtain an original automatic labeling model; and (3) automatically annotating the to-be-annotated image by using the original automatic annotation model, judging whether the annotation result of the annotated image is accurate or not, if so, not updating the original automatic annotation model, if not, correcting the annotation of the annotated image, storing the corrected annotated image into the original sample set, and returning to the step (2). According to the method, a small-order-of-magnitude sample size is adopted, heavy-sample-free expansion and model optimization are carried out on a labeling model in detection, the model accuracy and the environment applicability are improved, the accuracy of a model judgment result is ensured, and the model training time/workload can be greatly shortened.

Description

technical field [0001] The invention relates to the field of image processing, in particular to a method, system and application for constructing an image automatic labeling model. Background technique [0002] Deep learning has achieved great success in the fields of natural image processing and recognition, and has also made great progress in traditional image processing algorithms in medical imaging. Using deep learning technology to automatically segment and identify tissues and organs from medical imaging data can greatly improve the work efficiency of doctors. [0003] For example, when it comes to the automatic processing of human spine images, it has automatic labeling requirements for vertebral segment recognition and positioning, and it is necessary to build an automatic labeling model for human spine images. The entire labeling model construction process includes offline collection of raw data, offline manual labeling of raw data, depth Learn the process of label...

AI Technical Summary

Problems solved by technology

[0005] In addition, due to different detection individuals, due to gender, age, race and other factors, the bones are different, and the images collected by different detection equipment, such as sharpness, black and white contrast, tissue edge blurring, etc., are also different, here collectively referred to as Due to image differences caused by environmental factors, the model obtained in the original training environment will not be able to fit the data distribution well in the new detection environment, and there will be insufficient generalization of the model, resulting in the recognition of tissues and organs in the image by the labeling model with decreased positioning accuracy

Images