Digital pathological image annotation method and system

Abstract

The invention provides a digital pathological image annotation method and system. The method comprises the steps that a standard graphic annotation tool based on a pathological term base is adopted to annotate a to-be-annotated digital pathological image; format management is performed on pathological annotation information on the annotated digital pathological image based on an XML format; and the annotated digital pathological image is allocated to at least three persons for review, the annotated digital pathological image passing review is stored in an annotation database, and data in the annotation database is transmitted to a machine learning sample base for machine learning. A professional, normalized and systematic digital pathological image annotation solution is provided, a user can utilize various terminal devices to perform annotation, retrieval, uploading and downloading, annotation efficiency can be improved, and formation of a uniform and collaborative pathological image annotation mechanism is promoted.

Description

Technical field [0001] The present invention relates to the technical field of image processing, in particular to a method and system for marking digital pathological images. Background technique [0002] The annotation and information entry of pathological images are important tools and channels for pathologists to accumulate professional diagnostic experience. The rich and valuable professional data and information contained in it can provide a lot of reference for intelligent pathological diagnosis, pathological information teaching, and scientific research related to pathological diagnosis. information. [0003] With the development of information technology, scientific research related to digital pathology diagnosis, especially the research of digital pathology images based on deep learning, requires a large amount of digital pathology image annotation information and classification sample data, but the current digital pathology image annotation information is very scarce . ...

AI Technical Summary

Problems solved by technology

[0003] With the development of information technology, scientific research related to digital pathological diagnosis, especially digital pathological image research based on deep learning, requires a large amount of digital pathological image annotation information and classified sample data. However, the current digital pathological image annotation information is very scarce.

The digital pathological image annotation information among medical units cannot be shared, and the lack of a systematic and professional pathological image annotation database seriously limits the further application of scientific methods such as deep learning and data mining in the research of intelligent pathological diagnosis.

[0004] At the same time, the digital pathology image annotation methods of various medical institutions are usually self-contained, lacking a unified annotation specification, which is not conducive to the collaboration and data sharing of digital pathology image annotation, thus limiting the efficiency of annotation and the full application of annotation information

[0005] In the medical image labeling method proposed by the patent "A Method, Device and System for Labeling Medical Images" with the application number of 2013104394563, various labels are freely provided by each user. The labels are not standardized and professional, and cannot add types (professional entry) and other semantic annotation information, and there is no method for batch exporting the annotation area data of the annotated medical image, the annotation information cannot form a professional medical image annotation database, and cannot further play a greater role and value

In the patent "A digital pathological slice labeling method and labeling device" with the application number 2015109671608, in the digital pathological slice labeling method, the only types of labeling that users can provide are graphic labeling and text description labeling. The main significance of this patent is that Annotated pathological slices can be easily viewed by other users or users. It is only suitable for individual or small-scale users, and cannot be used for collaborative work and data sharing of digital pathological image annotation. Features of specialization

Images