CN-115457161-B - Medical image metal artifact verification method, device, equipment and storage medium

CN115457161BCN 115457161 BCN115457161 BCN 115457161BCN-115457161-B

Abstract

The application discloses a method and a device for verifying metal artifacts of medical images, electronic equipment and a storage medium, wherein the method comprises the steps of identifying a visit image sequence with metal artifact labels, wherein the visit image sequence comprises a plurality of image sequences, acquiring a plain image sequence with the metal artifact labels from the visit image sequence, and verifying metal artifact images of corresponding target image sequences in the visit image sequence based on sequence number ranges of the metal artifact images in the plain image sequence, wherein the layer thickness of the target image sequence is larger than that of the plain image sequence, and/or the target image sequence is an enhanced image sequence. The method can realize metal artifact verification on each image sequence in the visit image sequence, and provides possibility for intelligent auditing images.

Inventors

CUI YAXUAN
XIA XIAOLEI
ZHANG JUNJIE
NIE LING
HUO ZHIMIN

Assignees

上海太美数字科技有限公司

Dates

Publication Date: 20260512
Application Date: 20221018

Claims (7)

1. A method for verifying a metal artifact of a medical image, the method comprising: identifying a visit image sequence with a metal artifact tag, wherein the visit image sequence comprises a plurality of image sequences; Acquiring a plain scan image sequence with a metal artifact label from the visit image sequence; Verifying a metal artifact image of a corresponding target image sequence in the access image sequence based on a sequence number range of the metal artifact image in the plain image sequence, wherein the layer thickness of the target image sequence is larger than that of the plain image sequence, and/or the target image sequence is an enhanced image sequence; When the layer thickness of the target image sequence is larger than that of the plain image sequence, the method specifically comprises the steps of calculating the layer thickness proportion of the plain image sequence and the target image sequence, mapping the sequence number range of the metal artifact image in the plain image sequence to the target image sequence based on the layer thickness proportion, and determining a non-metal artifact image belonging to a real metal artifact image in the target image sequence as a false negative metal artifact image; When the target image sequence is an enhanced image sequence, the method specifically comprises the steps of mapping a sequence number range of metal artifact images in the plain image sequence to the target image sequence to determine a real metal artifact image of the target image sequence, and determining metal artifact images which do not belong to the real metal artifact image in the target image sequence as high-density contrast agent artifact images.
2. The method according to claim 1, characterized in that it comprises in particular: And mapping the sequence number range of the metal artifact image in the plain image sequence to the target image sequence by using a tail-removing method.
3. The method for verifying metal artifacts in medical images according to any one of claims 1 to 2, wherein verifying the metal artifact image of the corresponding target image sequence in the access image sequence based on the sequence number range of the metal artifact image in the pan image sequence specifically comprises: Acquiring position information and position information of a plurality of image sequences in the visit image sequence; inquiring an image sequence which is the same as the part of the flat scanning image sequence in the visit image sequence based on the part information; based on the position information, confirming whether the positions of the image sequences with the same parts and the flat scanning image sequences are the same, if so, And confirming that the image sequences with the same parts are corresponding target image sequences in the visit image sequences.
4. The method of checking for metal artifacts in medical images according to any one of claims 1 to 2, characterized in that before identifying the sequence of access images with metal artifact tags, the method further comprises: Judging whether each image slice of the plurality of image sequences comprises an image slice with CT value larger than a first set threshold value or not, if so, Judging whether the number of pixels of which the CT value is larger than a first set threshold value in the image slice is larger than a second set threshold value, if so, And determining the image slice as a metal artifact image, and marking a metal artifact label for an image sequence and a visit image sequence to which the image slice belongs.
5. A medical image metal artifact verification device, comprising: the identification module is used for identifying a visit image sequence with a metal artifact label, wherein the visit image sequence comprises a plurality of image sequences; the acquisition module is used for acquiring a plain scan image sequence with a metal artifact label from the visit image sequence; The verification module is used for verifying the metal artifact image of the corresponding target image sequence in the visit image sequence based on the sequence number range of the metal artifact image in the plain image sequence, wherein the layer thickness of the target image sequence is larger than that of the plain image sequence, and/or the target image sequence is an enhanced image sequence; When the layer thickness of the target image sequence is larger than that of the plain image sequence, the verification module is specifically used for calculating the layer thickness ratio of the plain image sequence and the target image sequence, mapping the sequence number range of the metal artifact image in the plain image sequence to the target image sequence based on the layer thickness ratio, and determining the non-metal artifact image belonging to the real metal artifact image in the target image sequence as a false negative metal artifact image; when the target image sequence is an enhanced image sequence, the verification module is specifically configured to map a sequence number range of a metal artifact image in the plain image sequence to the target image sequence to determine a real metal artifact image of the target image sequence, and determine a metal artifact image in the target image sequence, which does not belong to the real metal artifact image, as a high-density contrast agent artifact image.
6. An electronic device, comprising: at least one processor, and A memory storing instructions that, when executed by the at least one processor, cause the at least one processor to perform the method of verifying medical image metal artifacts of any one of claims 1 to 4.
7. A machine-readable storage medium storing executable instructions that, when executed, cause the machine to perform the method of verifying for medical image metal artifacts of any one of claims 1 to 4.

Description

Medical image metal artifact verification method, device, equipment and storage medium Technical Field The application belongs to the technical field of computer data processing, and particularly relates to a method, a device, equipment and a storage medium for checking metal artifacts of medical images. Background The medical image film reading system (MEDICAL IMAGING READING SYSTEM, MIRS) provides a multi-scene comprehensive solution for medical image film reading, and realizes informatization and intellectualization of the whole business process from image management to film reading management. In the whole business process, the intelligent film reading platform is used as a film reading tool of the image, can carry out intelligent statistical management on the upper serve of process nuclear film reading of the image, and follows the image state and the film reading progress in real time, is a core component part of the MIRS, and one key requirement of the intelligent image checking function is verification of metal artifacts possibly existing in the image. The information disclosed in this background section is only for enhancement of understanding of the general background of the application and should not be taken as an acknowledgement or any form of suggestion that this information forms the prior art already known to a person of ordinary skill in the art. Disclosure of Invention The application aims to provide a method for verifying metal artifacts of medical images, which is used for solving the problem that the metal artifacts possibly existing in the images need to be verified in an intelligent auditing image function. To achieve the above object, the present application provides a method for verifying metal artifacts in medical images, the method comprising: identifying a visit image sequence with a metal artifact tag, wherein the visit image sequence comprises a plurality of image sequences; Acquiring a plain scan image sequence with a metal artifact label from the visit image sequence; and verifying the metal artifact image of the corresponding target image sequence in the access image sequence based on the sequence number range of the metal artifact image in the plain image sequence, wherein the layer thickness of the target image sequence is larger than that of the plain image sequence, and/or the target image sequence is an enhanced image sequence. In one embodiment, when the layer thickness of the target image sequence is greater than the sweep image sequence, the method specifically includes: Calculating the layer thickness ratio of the flat scanning image sequence and the target image sequence; And mapping a sequence number range of the metal artifact image in the plain image sequence to the target image sequence based on the layer thickness proportion so as to determine a real metal artifact image of the target image sequence. In one embodiment, the method further comprises: and determining a non-metal artifact image belonging to the real metal artifact image in the target image sequence as a false negative metal artifact image. In one embodiment, the method specifically includes: And mapping the sequence number range of the metal artifact image in the plain image sequence to the target image sequence by using a tail-removing method. In one embodiment, when the target image sequence is an enhanced image sequence, the method specifically includes: Mapping the sequence number range of the metal artifact image in the plain image sequence to the target image sequence to determine a real metal artifact image of the target image sequence; and determining the metal artifact image which does not belong to the real metal artifact image in the target image sequence as a high-density contrast agent artifact image. In an embodiment, based on a sequence number range of the metal artifact image in the pan image sequence, verifying the metal artifact image of the corresponding target image sequence in the view image sequence specifically includes: Acquiring position information and position information of a plurality of image sequences in the visit image sequence; inquiring an image sequence which is the same as the part of the flat scanning image sequence in the visit image sequence based on the part information; based on the position information, confirming whether the positions of the image sequences with the same parts and the flat scanning image sequences are the same, if so, And confirming that the image sequences with the same parts are corresponding target image sequences in the visit image sequences. In an embodiment, before identifying the sequence of access images with metal artifact tags, the method further comprises: Judging whether each image slice of the plurality of image sequences comprises an image slice with CT value larger than a first set threshold value or not, if so, Judging whether the number of pixels of which the CT value is larger than a first set threshold value in the imag