Management method and system for medical image desensitization data based on content uniqueness

Abstract

The invention discloses a management method for medical image desensitization data based on content uniqueness, and is applied to the management for the image desensitization data in the medical system. The management method is characterized by at least comprising the following steps: obtaining the source data of medical image desensitization and the desensitization data DICOM, calculating the SHA256 hash values of the two data and uniquely identifying and storing the two data in a database; deleting the tag data of the source data and the desensitization data DICOM, calculating the SHA256 hash value of the two image data separately, comparing the source data after deleting the tag and the desensitization data after deleting the tag to calculate the SHA256 hash value and storing the SHA256hash value as the accurate identifier corresponding to the source data and the desensitization data in the database when the two hash values are the same; and querying the corresponding source data according to each SHA256 value stored in the database.

Description

technical field [0001] The invention relates to the technical field of data management, in particular to a management method and system for medical image desensitization data based on content uniqueness. Background technique [0002] With the digital development of the medical field, medical imaging data is often exchanged and transmitted through the standard format of DICOM (Digital Imaging and Communications in Medicine). Patient and ethics-related tags were removed from the DICOM data before it was made available to researchers. Conversely, if necessary, there is also a need to reversely retrieve the corresponding original data from the desensitized data used in scientific research to query sensitive information such as patients. Therefore, the current mainstream desensitization data management method is based on various IDs of image data, such as inspection IDs, image sequence IDs, etc., or a certain combination of multiple non-sensitive information IDs (sensitive IDs i...

AI Technical Summary

Problems solved by technology

The current mainstream method is to select one or more related ID combinations from the original DICOM image data and desensitized data to make the mapping relationship. The disadvantage is that if the label or ID of the desensitized data is changed, it will be lost. With these ID information, the corresponding relationship between the original data and the desensitized data can no longer be restored.

Images