CN117808718B - Method and system for improving medical image data quality based on Internet - Google Patents
Method and system for improving medical image data quality based on Internet Download PDFInfo
- Publication number
- CN117808718B CN117808718B CN202410228859.1A CN202410228859A CN117808718B CN 117808718 B CN117808718 B CN 117808718B CN 202410228859 A CN202410228859 A CN 202410228859A CN 117808718 B CN117808718 B CN 117808718B
- Authority
- CN
- China
- Prior art keywords
- medical image
- artifact
- image
- metal
- corrected
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000002184 metal Substances 0.000 claims abstract description 120
- 238000012937 correction Methods 0.000 claims abstract description 74
- 238000011156 evaluation Methods 0.000 claims abstract description 64
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 55
- 238000007781 pre-processing Methods 0.000 claims abstract description 32
- 238000012545 processing Methods 0.000 claims abstract description 32
- 238000001514 detection method Methods 0.000 claims abstract description 30
- 238000005457 optimization Methods 0.000 claims abstract description 26
- 238000009499 grossing Methods 0.000 claims description 18
- 230000008859 change Effects 0.000 claims description 15
- 238000001914 filtration Methods 0.000 claims description 14
- 230000009467 reduction Effects 0.000 claims description 13
- 238000006243 chemical reaction Methods 0.000 claims description 11
- 238000012544 monitoring process Methods 0.000 claims description 11
- 238000004364 calculation method Methods 0.000 claims description 5
- 230000002159 abnormal effect Effects 0.000 claims description 3
- 239000002131 composite material Substances 0.000 claims description 2
- 238000013507 mapping Methods 0.000 claims description 2
- 230000008030 elimination Effects 0.000 abstract description 4
- 238000003379 elimination reaction Methods 0.000 abstract description 4
- 238000010586 diagram Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 8
- 238000011282 treatment Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000003902 lesion Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000001360 synchronised effect Effects 0.000 description 2
- 210000003484 anatomy Anatomy 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 238000004590 computer program Methods 0.000 description 1
- 238000002059 diagnostic imaging Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 230000004807 localization Effects 0.000 description 1
- 210000000056 organ Anatomy 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/30—Subject of image; Context of image processing
- G06T2207/30004—Biomedical image processing
Landscapes
- Image Processing (AREA)
Abstract
The embodiment of the invention relates to the technical field of medical images, and particularly discloses a method and a system for improving the quality of medical image data based on the Internet. According to the embodiment of the invention, the acquired basic medical image is acquired, and the basic medical image is subjected to image preprocessing to generate a preprocessed medical image; performing artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image; performing artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generating a corrected medical image after the evaluation reaches the standard; and performing image optimization on the corrected medical image to generate an optimized medical image. The method can perform image preprocessing, artifact detection and region marking, artifact correction and evaluation and image optimization on the acquired medical images, effectively eliminate metal artifacts in the medical images, and avoid other problems in the medical images after the elimination processing.
Description
Technical Field
The invention belongs to the technical field of medical images, and particularly relates to a method and a system for improving the quality of medical image data based on the Internet.
Background
Medical imaging refers to a technique and a processing procedure for acquiring an internal tissue image of a human body or a part of the human body in a non-invasive manner for medical treatment or medical research, and the internal tissue organ structure and the density of the human body are represented in an image manner for a diagnostician to judge according to information provided by the image, so that the health condition of the human body is evaluated.
In the prior art, due to various factors such as quality and performance of medical image equipment, selection of parameters and settings in a collection process, influence of medical image collection environment, misoperation of operators and the like, medical image data quality is easy to be low, analysis of medical image data is influenced, particularly, the quality of the medical image data is seriously influenced due to the existence of metal artifacts, but the prior art cannot effectively eliminate the metal artifacts in medical images, and medical images after elimination processing are easy to have other problems.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a system for improving medical image data quality based on the Internet, which aim to solve the problems in the background technology.
In order to achieve the above object, the embodiment of the present invention provides the following technical solutions:
The method for improving the quality of medical image data based on the Internet specifically comprises the following steps:
Acquiring an acquired basic medical image, performing image preprocessing on the basic medical image, and generating a preprocessed medical image;
performing artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image;
Performing artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generating a corrected medical image after the evaluation reaches the standard;
And performing image optimization on the corrected medical image to generate an optimized medical image.
As further defined by the technical solution of the embodiment of the present invention, the acquiring the acquired basic medical image, performing image preprocessing on the basic medical image, and generating a preprocessed medical image specifically includes the following steps:
Performing image acquisition and monitoring to obtain basic medical images;
noise removing is carried out on the basic medical image;
Gray scale adjustment is carried out on the basic medical image;
contrast enhancement is carried out on the basic medical image;
the pre-processed medical image after noise removal, gray scale adjustment and contrast enhancement is acquired.
As a further limitation of the technical solution of the embodiment of the present invention, the performing artifact detection on the preprocessed medical image, judging whether there is a metal artifact, and marking a metal artifact area when there is a metal artifact, and generating a marked medical image specifically includes the following steps:
carrying out artifact identification on the preprocessed medical image, and judging whether metal artifacts exist or not;
Generating an artifact positioning instruction when the metal artifact exists;
And marking the metal artifact region according to the artifact positioning instruction, and generating a marked medical image.
As a further limitation of the technical solution of the embodiment of the present invention, marking a metal artifact region according to the artifact positioning instruction, and generating a marked medical image specifically includes the following steps:
identifying abnormal edges and textures of the preprocessed medical image according to the artifact positioning instruction, and determining a metal artifact region;
analyzing the metal artifact area to determine the type of the metal artifact;
and performing preset marking operation of a metal artifact region on the preprocessed medical image according to the metal artifact type to generate a marked medical image.
As a further limitation of the technical solution of the embodiment of the present invention, the artifact correction and evaluation are performed on the marked medical image according to a plurality of preset correction algorithms, and after the evaluation reaches the standard, the generation of the corrected medical image specifically includes the following steps:
acquiring a plurality of preset correction algorithms, wherein the correction algorithms comprise an interpolation algorithm, a filtering algorithm and a learning algorithm;
Selecting a target algorithm from a plurality of correction algorithms according to the metal artifact type;
performing artifact correction and evaluation on the marked medical image through the target algorithm;
if the evaluation meets the standard, generating a corrected medical image;
and if the evaluation does not reach the standard, selecting other correction algorithms to perform artifact correction and evaluation until the evaluation reaches the standard.
As a further limitation of the technical solution of the embodiment of the present invention, the image optimization of the corrected medical image, and the generation of the optimized medical image specifically includes the following steps:
Smoothing the corrected medical image;
Performing contrast stretching and histogram equalization on the corrected medical image;
performing color balance adjustment on the corrected medical image;
After finishing smoothing, contrast stretching, histogram equalization and color balance adjustment, format conversion is performed according to a preset required format, and an optimized medical image is generated.
The system for improving the quality of medical image data based on the Internet comprises an image acquisition preprocessing unit, an image artifact detection unit, an image artifact correction unit and an image optimization processing unit, wherein:
the image acquisition preprocessing unit is used for acquiring an acquired basic medical image, preprocessing the basic medical image and generating a preprocessed medical image;
The image artifact detection unit is used for carrying out artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image;
The image artifact correction unit is used for carrying out artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generating a corrected medical image after the evaluation reaches the standard;
and the image optimization processing unit is used for performing image optimization on the corrected medical image and generating an optimized medical image.
As a further limitation of the technical solution of the embodiment of the present invention, the image acquisition preprocessing unit specifically includes:
the acquisition monitoring module is used for carrying out image acquisition monitoring to acquire basic medical images;
the noise removing module is used for removing noise from the basic medical image;
The gray scale adjustment module is used for gray scale adjustment of the basic medical image;
the contrast enhancement module is used for contrast enhancement of the basic medical image;
and the preprocessing image acquisition module is used for acquiring the preprocessing medical image after noise removal, gray level adjustment and contrast enhancement.
As a further limitation of the technical solution of the embodiment of the present invention, the image artifact detection unit specifically includes:
the artifact identification module is used for carrying out artifact identification on the preprocessed medical image and judging whether metal artifacts exist or not;
the instruction generation module is used for generating an artifact positioning instruction when the metal artifact exists;
and the region marking module is used for marking the metal artifact region according to the artifact positioning instruction and generating a marked medical image.
As a further limitation of the technical solution of the embodiment of the present invention, the image optimization processing unit specifically includes:
The smoothing processing module is used for carrying out smoothing processing on the corrected medical image;
the stretching and equalizing processing module is used for carrying out contrast stretching and histogram equalizing processing on the corrected medical image;
the color balance adjustment module is used for performing color balance adjustment on the corrected medical image;
And the format conversion module is used for carrying out format conversion according to a preset required format after finishing smoothing, contrast stretching, histogram equalization and color balance adjustment, and generating an optimized medical image.
Compared with the prior art, the invention has the beneficial effects that:
According to the embodiment of the invention, the acquired basic medical image is acquired, and the basic medical image is subjected to image preprocessing to generate a preprocessed medical image; performing artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image; performing artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generating a corrected medical image after the evaluation reaches the standard; and performing image optimization on the corrected medical image to generate an optimized medical image. The method can perform image preprocessing, artifact detection and region marking, artifact correction and evaluation and image optimization on the acquired medical images, effectively eliminate metal artifacts in the medical images, and avoid other problems in the medical images after the elimination processing.
Drawings
In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the following description will briefly introduce the drawings that are needed in the embodiments or the description of the prior art, and it is obvious that the drawings in the following description are only some embodiments of the present invention.
Fig. 1 shows a flowchart of a method provided by an embodiment of the present invention.
Fig. 2 shows a flowchart of generating a preprocessed medical image in a method according to an embodiment of the invention.
Fig. 3 shows a flowchart of generating a marked medical image in a method according to an embodiment of the invention.
Fig. 4 shows a flowchart of a method for marking a metal artifact area according to an embodiment of the present invention.
Fig. 5 shows a flowchart of artifact correction and evaluation in the method according to the embodiment of the present invention.
Fig. 6 shows a flowchart of generating an optimized medical image in a method provided by an embodiment of the invention.
Fig. 7 shows an application architecture diagram of a system provided by an embodiment of the present invention.
Fig. 8 is a block diagram illustrating a structure of an image acquisition preprocessing unit in the system according to an embodiment of the present invention.
Fig. 9 is a block diagram illustrating a structure of an image artifact detection unit in the system according to an embodiment of the present invention.
Fig. 10 is a block diagram illustrating a structure of an image optimization processing unit in the system according to an embodiment of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
It can be understood that in the prior art, due to various factors such as quality and performance of medical image equipment, selection of parameters and settings in the acquisition process, influence of medical image acquisition environment, misoperation of operators and the like, medical image data quality is easy to be low, follow-up analysis and processing of medical image data are affected, particularly, the quality of medical image data is seriously affected due to the existence of metal artifacts, but the prior art cannot effectively eliminate metal artifacts in medical images, and medical images after the processing are easy to have other problems.
In order to solve the problems, in the embodiment of the invention, the acquired basic medical image is acquired, and the basic medical image is subjected to image preprocessing to generate a preprocessed medical image; performing artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image; performing artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generating a corrected medical image after the evaluation reaches the standard; and performing image optimization on the corrected medical image to generate an optimized medical image. The method can perform image preprocessing, artifact detection and region marking, artifact correction and evaluation and image optimization on the acquired medical images, effectively eliminate metal artifacts in the medical images, and avoid other problems in the medical images after the elimination processing.
Fig. 1 shows a flowchart of a method provided by an embodiment of the present invention.
Specifically, the method for improving the quality of medical image data based on the Internet specifically comprises the following steps:
step S101, acquiring an acquired basic medical image, and performing image preprocessing on the basic medical image to generate a preprocessed medical image.
In the embodiment of the invention, the acquired basic medical image is acquired through image acquisition monitoring, noise removal is carried out on the basic medical image through modes such as median filtering, gaussian filtering and self-adaptive filtering, electronic noise, motion artifacts and the like in the basic medical image are reduced, gray scale adjustment is carried out on the basic medical image through modes such as histogram equalization and contrast stretching, the deviation of gray scale values in the medical image is reduced, the gray scale value of the image is enabled to be in a certain range, subsequent artifact detection and correction are better carried out, contrast enhancement is carried out on the basic medical image through modes such as histogram prescribing and contrast limiting self-adaptive histogram prescribing, the difference between different tissues in the medical image is improved, and finally the preprocessed medical image after noise removal, gray scale adjustment and contrast enhancement is acquired.
Specifically, fig. 2 shows a flowchart of generating a preprocessed medical image in the method provided by the embodiment of the invention.
In a preferred embodiment of the present invention, the acquiring the acquired basic medical image, performing image preprocessing on the basic medical image, and generating a preprocessed medical image specifically includes the following steps:
Step S1011, performing image acquisition monitoring to acquire a basic medical image;
Step S1012, performing noise removal on the basic medical image;
step S1013, gray scale adjustment is carried out on the basic medical image;
Step S1014, performing contrast enhancement on the basic medical image;
in step S1015, the preprocessed medical image after noise removal, gray scale adjustment and contrast enhancement is obtained.
Further, the method for improving the quality of medical image data based on the internet further comprises the following steps:
Step S102, performing artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image.
In the embodiment of the invention, the pre-processing medical image is subjected to artifact detection, obvious artifact differences existing in the pre-processing medical image are identified, whether metal artifacts exist or not is judged, an artifact positioning instruction is generated when the metal artifacts exist are judged, at the moment, the image processing technology is utilized to extract the difference edges, textures and other characteristics of the image according to the artifact positioning instruction, and the artifact position is determined. Meanwhile, according to the nature and the morphology of the artifact, the type of the metal artifact is identified, and then according to the type of the metal artifact, the metal artifact area is marked (the pixel value of the artifact area can be set to a special value, or a mark frame is drawn on the image, and the like, the metal artifact area is marked in the preprocessed medical image), so that the marked medical image is generated.
Specifically, fig. 3 shows a flowchart of generating a labeled medical image in the method provided by the embodiment of the invention.
In a preferred embodiment of the present invention, the performing artifact detection on the preprocessed medical image, determining whether there is a metal artifact, and marking a metal artifact area when there is a metal artifact, and generating a marked medical image specifically includes the following steps:
Step S1021, performing artifact identification on the preprocessed medical image, and judging whether metal artifacts exist or not;
step S1022, when metal artifact exists, generating an artifact positioning instruction;
Step S1023, marking the metal artifact area according to the artifact positioning instruction, and generating a marked medical image.
Specifically, fig. 4 shows a flowchart of marking a metal artifact area in the method provided by the embodiment of the present invention.
In a preferred embodiment of the present invention, the marking the metal artifact area according to the artifact positioning instruction, and generating the marked medical image specifically includes the following steps:
Step S10231, identifying abnormal edges and textures of the preprocessed medical image according to the artifact positioning instruction, and determining a metal artifact region;
step S10232, analyzing the metal artifact area to determine the type of the metal artifact;
Step S10232 includes the following sub-steps:
Step S10232a, extracting the characteristics of the metal artifact area to obtain shape characteristics, size characteristics, brightness characteristics and texture characteristics;
Step S10232b, according to the shape feature, the size feature, the brightness feature and the texture feature, respectively searching and confirming the shape feature association degree, the size feature association degree, the brightness feature association degree and the texture feature association degree corresponding to one current metal artifact type in a preset metal artifact feature database; step S10232c, calculating a type of relevance index according to the shape feature relevance, the size feature relevance, the brightness feature relevance and the texture feature relevance of the metal artifact region;
The number of the type relevance indexes is also multiple because the number of the metal artifact types is multiple, and each metal artifact type is correspondingly calculated to obtain a type relevance index.
In this step, the calculation formula of the type association index is expressed as:
；
wherein, Representing type relevance index,/>Reference value representing type association index,/>Weight factor representing shape feature relevance term,/>Representing shape feature association degree,/>A reference value representing the degree of association of the shape features,Weight factor representing size feature relevance term,/>Representing the degree of association of size features,/>Reference value representing degree of association of size features,/>Weight factor representing luminance feature relevance term,/>Representing the degree of association of luminance features,/>Reference value representing the degree of association of luminance features,/>Weight factor representing texture feature relevance term,/>The degree of association of the texture features is indicated,A reference value representing the degree of association of the texture features.
Step S10232d, selecting the metal artifact type corresponding to the maximum type association index from the multiple type association indexes to determine the metal artifact type of the current metal artifact area.
It can be appreciated that if the type association index is the largest, the corresponding metal artifact type may be determined to be the metal artifact type of the current metal artifact region.
Step S10233, performing preset marking operation of the metal artifact area on the preprocessed medical image according to the metal artifact type, and generating a marked medical image.
Further, the method for improving the quality of medical image data based on the internet further comprises the following steps:
step S103, artifact correction and evaluation are carried out on the marked medical image according to a plurality of preset correction algorithms, and after the evaluation reaches the standard, a corrected medical image is generated.
In the embodiment of the invention, a plurality of preset correction algorithms including an interpolation algorithm, a filtering algorithm, a learning algorithm and the like are acquired, a target algorithm is selected from the plurality of correction algorithms according to the metal artifact type, artifact correction and evaluation are further carried out on the marked medical image through the target algorithm, and different treatments are carried out according to different evaluation results. Specific: if the evaluation meets the standard, generating a corrected medical image; if the evaluation does not reach the standard, other correction algorithms are selected, and artifact correction and evaluation are performed on the marked medical image again until the evaluation reaches the standard.
For example: when artifact correction and evaluation are performed through a filtering algorithm, a proper filter (a commonly used filter comprises a Gaussian filter, a median filter, a mean filter and the like) is selected according to the type of metal artifact, a metal artifact region of a marked medical image is processed through the selected filter (pixels around each pixel are calculated, an original pixel value is replaced by a calculation result to achieve the purpose of eliminating or reducing the artifact), then the image quality is further improved through modes of contrast stretching, histogram equalization and the like, and finally, the corrected image is evaluated to determine whether the correction effect reaches the expectation.
Specifically, fig. 5 shows a flowchart of artifact correction and evaluation in the method provided by the embodiment of the present invention.
In a preferred embodiment of the present invention, artifact correction and evaluation are performed on the marked medical image according to a plurality of preset correction algorithms, and after the evaluation reaches the standard, the generation of the corrected medical image specifically includes the following steps:
step S1031, obtaining a plurality of preset correction algorithms, wherein the correction algorithms comprise an interpolation algorithm, a filtering algorithm and a learning algorithm;
Step S1032, selecting a target algorithm from a plurality of correction algorithms according to the metal artifact type;
step S1033, performing artifact correction and evaluation on the labeled medical image through the target algorithm;
When artifact correction and evaluation are carried out on the marked medical image, the method for judging whether the evaluation is qualified comprises the following steps:
step S1033a, obtaining artifact reduction degree, signal-to-noise ratio difference value, contrast difference value and integrity change value of the marked medical image before and after artifact correction; wherein artifact reduction refers to the artifact intensity, size, and visibility of the image in the same area before and after correction, and the evaluation is more likely to be considered acceptable if the artifact is significantly reduced or almost completely eliminated. The signal-to-noise ratio difference and the contrast difference refer to the difference in signal-to-noise ratio and the difference in contrast of the marked medical image before and after correction. An integrity change value refers to the correction process not introducing new artifacts or distortions nor destroying or changing the anatomy in the image.
Step S1033b, according to the artifact reduction degree, the signal-to-noise ratio difference value, the contrast difference value, and the integrity change value, searching in a corresponding preset mapping table to obtain an artifact reduction degree score, a signal-to-noise ratio change item score, a contrast change item score, and an integrity change item score, respectively;
Step S1033c, calculating to obtain a corrected comprehensive score according to the artifact reduction degree score, the signal-to-noise ratio variation item score, the contrast variation item score and the integrity variation item score;
Wherein, the calculation formula of the corrected comprehensive score is expressed as follows:
；
wherein, Representing the corrected composite score,/>Reference value representing corrected integrated score,/>Weight factor representing artifact reduction degree term,/>Representing artifact reduction degree term score,/>Weighting factor representing signal-to-noise ratio variation term,/>Representing signal to noise ratio variation term score,/>Weight factor representing contrast variation term,/>Representing contrast variation term score,/>Weight factor representing an integrity change term,/>Representing the integrity change term score.
And step S1033d, when the corrected comprehensive score is judged to be larger than the preset comprehensive score, determining that the evaluation reaches the standard.
Step S1034, if the evaluation meets the standard, generating a corrected medical image;
step S1035, if the evaluation does not reach the standard, selecting other correction algorithms to perform artifact correction and evaluation until the evaluation reaches the standard.
Further, the method for improving the quality of medical image data based on the internet further comprises the following steps:
step S104, performing image optimization on the corrected medical image to generate an optimized medical image.
In the embodiment of the invention, the corrected medical image is subjected to smoothing treatment, filtering or blurring treatment, noise or distortion is reduced, the image is smoother and more natural, the corrected medical image is subjected to contrast stretching or histogram equalization, the contrast and brightness of the image are adjusted, the corrected medical image is more in accordance with the diagnosis requirement of a doctor, the color balance of the corrected medical image is adjusted, the colors of different tissues or lesions are more true and natural, the image readability is improved, and after the smoothing treatment, the contrast stretching, the histogram equalization and the color balance adjustment are completed, format conversion is performed according to a preset requirement format, so that the optimized medical image is generated.
Specifically, fig. 6 shows a flowchart of generating an optimized medical image in the method provided by the embodiment of the invention.
In a preferred embodiment of the present invention, the image optimization of the corrected medical image, and the generation of the optimized medical image specifically includes the following steps:
Step S1041, performing a smoothing process on the corrected medical image;
Step S1042, performing contrast stretching and histogram equalization on the corrected medical image;
Step S1043, performing color balance adjustment on the corrected medical image;
Step S1044, after finishing the smoothing process, the contrast stretching, the histogram equalization and the color balance adjustment, performing format conversion according to a preset required format to generate an optimized medical image.
Further, fig. 7 shows an application architecture diagram of the system provided by the embodiment of the present invention.
In another preferred embodiment of the present invention, a system for improving quality of medical image data based on internet specifically includes:
the image acquisition preprocessing unit 101 is configured to acquire an acquired basic medical image, perform image preprocessing on the basic medical image, and generate a preprocessed medical image.
In the embodiment of the invention, the image acquisition preprocessing unit 101 acquires the acquired basic medical image through image acquisition monitoring, performs noise removal on the basic medical image through modes such as median filtering, gaussian filtering and self-adaptive filtering, reduces electronic noise, motion artifacts and the like in the basic medical image, performs gray scale adjustment on the basic medical image through modes such as histogram equalization, contrast stretching and the like, reduces the deviation of gray scale values in the medical image, enables the gray scale values of the image to be in a certain range, better performs subsequent artifact detection and correction, performs contrast enhancement on the basic medical image through modes such as histogram specification and contrast-limited self-adaptive histogram specification, improves the difference between different tissues in the medical image, and finally acquires the preprocessed medical image after noise removal, gray scale adjustment and contrast enhancement.
Specifically, fig. 8 shows a block diagram of an image acquisition preprocessing unit 101 in the system according to the embodiment of the present invention.
In a preferred embodiment of the present invention, the image capturing preprocessing unit 101 specifically includes:
The acquisition monitoring module 1011 is used for performing image acquisition monitoring to acquire basic medical images;
a noise removal module 1012, configured to perform noise removal on the basic medical image;
The gray scale adjustment module 1013 is configured to perform gray scale adjustment on the basic medical image;
A contrast enhancement module 1014 for contrast enhancing the underlying medical image;
The preprocessed image acquisition module 1015 is configured to acquire preprocessed medical images after noise removal, gray scale adjustment, and contrast enhancement.
Further, the system for improving the quality of medical image data based on the internet further comprises:
The image artifact detection unit 102 is configured to perform artifact detection on the preprocessed medical image, determine whether there is a metal artifact, and mark a metal artifact region when there is a metal artifact, and generate a marked medical image.
In the embodiment of the present invention, the image artifact detection unit 102 identifies an obvious artifact difference existing in the preprocessed medical image by performing artifact detection on the preprocessed medical image, determines whether the preprocessed medical image has a metal artifact, generates an artifact positioning instruction when the preprocessed medical image has the metal artifact, extracts features such as a difference edge and a texture of the image according to the artifact positioning instruction, and determines an artifact position, and simultaneously identifies a metal artifact type according to the nature and the morphology of the artifact, and marks a metal artifact region (a pixel value of the artifact region can be set as a special value, or marks a metal artifact region in the preprocessed medical image by drawing a mark frame on the image, etc.), so as to generate a marked medical image.
Specifically, fig. 9 is a block diagram illustrating a structure of the image artifact detection unit 102 in the system according to the embodiment of the present invention.
In a preferred embodiment of the present invention, the image artifact detection unit 102 specifically includes:
The artifact identification module 1021 is configured to perform artifact identification on the preprocessed medical image, and determine whether there is a metal artifact;
An instruction generation module 1022 for generating artifact localization instructions when having metal artifacts;
The region marking module 1023 is configured to mark a metal artifact region according to the artifact positioning instruction, and generate a marked medical image.
Further, the system for improving the quality of medical image data based on the internet further comprises:
The image artifact correction unit 103 is configured to perform artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generate a corrected medical image after the evaluation reaches the standard.
In the embodiment of the present invention, the image artifact correction unit 103 obtains a plurality of preset correction algorithms, including an interpolation algorithm, a filtering algorithm, a learning algorithm, and the like, and selects a target algorithm from the plurality of correction algorithms according to the metal artifact type, and further performs artifact correction and evaluation on the marked medical image through the target algorithm, and performs different processes according to different evaluation results, specifically: if the evaluation meets the standard, generating a corrected medical image; if the evaluation does not reach the standard, other correction algorithms are selected, and artifact correction and evaluation are performed on the marked medical image again until the evaluation reaches the standard.
The image optimization processing unit 104 is configured to perform image optimization on the corrected medical image, and generate an optimized medical image.
In the embodiment of the present invention, the image optimization processing unit 104 performs smoothing processing on the corrected medical image, reduces noise or distortion by performing filtering or blurring processing, makes the image smoother and more natural, performs contrast stretching or histogram equalization on the corrected medical image, adjusts the contrast and brightness of the image to make the image more in line with the diagnosis requirement of a doctor, performs color balance adjustment on the corrected medical image, makes the color of different tissues or lesions more true and natural, improves the readability of the image, and performs format conversion according to a preset requirement format after the smoothing processing, the contrast stretching, the histogram equalization and the color balance adjustment are completed, thereby generating an optimized medical image.
Specifically, fig. 10 shows a block diagram of the image optimization processing unit 104 in the system according to the embodiment of the present invention.
In a preferred embodiment of the present invention, the image optimization processing unit 104 specifically includes:
A smoothing module 1041, configured to smooth the corrected medical image;
the stretching and equalizing processing module 1042 is used for performing contrast stretching and histogram equalizing processing on the corrected medical image;
the color balance adjustment module 1043 is configured to perform color balance adjustment on the corrected medical image;
The format conversion module 1044 is configured to perform format conversion according to a preset required format after finishing smoothing, contrast stretching, histogram equalization and color balance adjustment, so as to generate an optimized medical image.
It should be understood that, although the steps in the flowcharts of the embodiments of the present invention are shown in order as indicated by the arrows, these steps are not necessarily performed in order as indicated by the arrows. The steps are not strictly limited to the order of execution unless explicitly recited herein, and the steps may be executed in other orders. Moreover, at least some of the steps in various embodiments may include multiple sub-steps or stages that are not necessarily performed at the same time, but may be performed at different times, nor do the order in which the sub-steps or stages are performed necessarily performed in sequence, but may be performed alternately or alternately with at least a portion of the sub-steps or stages of other steps or other steps.
Those skilled in the art will appreciate that all or part of the processes in the methods of the above embodiments may be implemented by a computer program for instructing relevant hardware, where the program may be stored in a non-volatile computer readable storage medium, and where the program, when executed, may include processes in the embodiments of the methods described above. Any reference to memory, storage, database, or other medium used in embodiments provided herein may include non-volatile and/or volatile memory. The nonvolatile memory can include Read Only Memory (ROM), programmable ROM (PROM), electrically Programmable ROM (EPROM), electrically Erasable Programmable ROM (EEPROM), or flash memory. Volatile memory can include Random Access Memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in a variety of forms such as Static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double Data Rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (SYNCHLINK) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM), among others.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be considered as the scope of the description.
The foregoing examples illustrate only a few embodiments of the invention and are described in detail herein without thereby limiting the scope of the invention. It should be noted that it will be apparent to those skilled in the art that several variations and modifications can be made without departing from the spirit of the invention, which are all within the scope of the invention. Accordingly, the scope of protection of the present invention is to be determined by the appended claims.
The foregoing description of the preferred embodiments of the invention is not intended to be limiting, but rather is intended to cover all modifications, equivalents, and alternatives falling within the spirit and principles of the invention.
Claims (6)
1. The method for improving the quality of medical image data based on the Internet is characterized by comprising the following steps of:
Acquiring an acquired basic medical image, performing image preprocessing on the basic medical image, and generating a preprocessed medical image;
performing artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image;
Performing artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generating a corrected medical image after the evaluation reaches the standard;
Performing image optimization on the corrected medical image to generate an optimized medical image;
The method for acquiring the acquired basic medical image, carrying out image preprocessing on the basic medical image, and generating the preprocessed medical image specifically comprises the following steps:
Performing image acquisition and monitoring to obtain basic medical images;
noise removing is carried out on the basic medical image;
Gray scale adjustment is carried out on the basic medical image;
contrast enhancement is carried out on the basic medical image;
Acquiring a preprocessed medical image after noise removal, gray level adjustment and contrast enhancement;
The artifact correction and evaluation are carried out on the marked medical image according to a plurality of preset correction algorithms, and the generation of the corrected medical image after the evaluation reaches the standard specifically comprises the following steps:
acquiring a plurality of preset correction algorithms, wherein the correction algorithms comprise an interpolation algorithm and a filtering algorithm;
Selecting a target algorithm from a plurality of correction algorithms according to the metal artifact type;
performing artifact correction and evaluation on the marked medical image through the target algorithm;
if the evaluation meets the standard, generating a corrected medical image;
if the evaluation does not reach the standard, other correction algorithms are selected for artifact correction and evaluation until the evaluation reaches the standard;
The step of performing artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts, and generating a marked medical image specifically comprises the following steps:
carrying out artifact identification on the preprocessed medical image, and judging whether metal artifacts exist or not;
Generating an artifact positioning instruction when the metal artifact exists;
Marking a metal artifact region according to the artifact positioning instruction, and generating a marked medical image;
Marking a metal artifact region according to the artifact positioning instruction, and generating a marked medical image specifically comprises the following steps:
identifying abnormal edges and textures of the preprocessed medical image according to the artifact positioning instruction, and determining a metal artifact region;
analyzing the metal artifact area to determine the type of the metal artifact;
performing preset marking operation of a metal artifact region on the preprocessed medical image according to the metal artifact type to generate a marked medical image;
The method for analyzing the metal artifact area and determining the metal artifact type comprises the following steps:
extracting the characteristics of the metal artifact area to obtain shape characteristics, size characteristics, brightness characteristics and texture characteristics;
According to the shape feature, the size feature, the brightness feature and the texture feature, respectively searching and confirming the shape feature association degree, the size feature association degree, the brightness feature association degree and the texture feature association degree corresponding to one current metal artifact type in a preset metal artifact feature database;
calculating to obtain a type of relevance index according to the shape feature relevance, the size feature relevance, the brightness feature relevance and the texture feature relevance of the metal artifact region;
The calculation formula of the type association index is expressed as:
；
wherein, Representing type relevance index,/>Reference value representing type association index,/>Weight factor representing shape feature relevance term,/>Representing shape feature association degree,/>Reference value representing degree of association of shape features,/>Weight factor representing size feature relevance term,/>Representing the degree of association of size features,/>Reference value representing degree of association of size features,/>Weight factor representing luminance feature relevance term,/>Representing the degree of association of luminance features,/>Reference value representing the degree of association of luminance features,/>Weight factor representing texture feature relevance term,/>Representing texture feature association degree,/>A reference value representing a degree of association of texture features;
And selecting the metal artifact type corresponding to the maximum type relevance index from the multiple type relevance indexes to determine the metal artifact type of the current metal artifact area.
2. The internet-based method for improving the quality of medical image data according to claim 1, wherein the method for judging whether the evaluation is acceptable when the artifact correction and evaluation are performed on the marked medical image comprises the following steps:
obtaining artifact reduction degree, signal-to-noise ratio difference value, contrast difference value and integrity change value of the marked medical image before and after artifact correction;
According to the artifact reduction degree, the signal-to-noise ratio difference value, the contrast difference value and the integrity change value, respectively searching in a corresponding preset mapping table to obtain an artifact reduction degree item score, a signal-to-noise ratio change item score, a contrast change item score and an integrity change item score;
calculating according to the artifact reduction degree score, the signal-to-noise ratio variation item score, the contrast variation item score and the integrity variation item score to obtain a corrected comprehensive score;
Wherein, the calculation formula of the corrected comprehensive score is expressed as follows:
；
wherein, Representing the corrected composite score,/>Reference value representing corrected integrated score,/>Weight factor representing artifact reduction degree term,/>Representing artifact reduction degree term score,/>Weighting factor representing signal-to-noise ratio variation term,/>Representing signal to noise ratio variation term score,/>Weight factor representing contrast variation term,/>Representing contrast variation term score,/>Weight factor representing an integrity change term,/>Representing an integrity change item score;
And when the corrected comprehensive score is judged to be larger than the preset comprehensive score, determining that the evaluation reaches the standard.
3. The internet-based method for improving the quality of medical image data according to claim 2, wherein the performing image optimization on the corrected medical image to generate an optimized medical image specifically comprises the following steps:
Smoothing the corrected medical image;
Performing contrast stretching and histogram equalization on the corrected medical image;
performing color balance adjustment on the corrected medical image;
After finishing smoothing, contrast stretching, histogram equalization and color balance adjustment, format conversion is performed according to a preset required format, and an optimized medical image is generated.
4. An internet-based system for improving the quality of medical image data, which is characterized by applying the internet-based method for improving the quality of medical image data according to any one of claims 1 to 3, wherein the system comprises an image acquisition preprocessing unit, an image artifact detection unit, an image artifact correction unit and an image optimization processing unit, wherein:
the image acquisition preprocessing unit is used for acquiring an acquired basic medical image, preprocessing the basic medical image and generating a preprocessed medical image;
The image artifact detection unit is used for carrying out artifact detection on the preprocessed medical image, judging whether the preprocessed medical image has metal artifacts, and marking a metal artifact area when the preprocessed medical image has the metal artifacts to generate a marked medical image;
The image artifact correction unit is used for carrying out artifact correction and evaluation on the marked medical image according to a plurality of preset correction algorithms, and generating a corrected medical image after the evaluation reaches the standard;
and the image optimization processing unit is used for performing image optimization on the corrected medical image and generating an optimized medical image.
5. The internet-based system for improving medical image data quality according to claim 4, wherein the image acquisition preprocessing unit specifically comprises:
the acquisition monitoring module is used for carrying out image acquisition monitoring to acquire basic medical images;
the noise removing module is used for removing noise from the basic medical image;
The gray scale adjustment module is used for gray scale adjustment of the basic medical image;
the contrast enhancement module is used for contrast enhancement of the basic medical image;
the preprocessing image acquisition module is used for acquiring the preprocessing medical image after noise removal, gray level adjustment and contrast enhancement;
The image artifact detection unit specifically includes:
the artifact identification module is used for carrying out artifact identification on the preprocessed medical image and judging whether metal artifacts exist or not;
the instruction generation module is used for generating an artifact positioning instruction when the metal artifact exists;
and the region marking module is used for marking the metal artifact region according to the artifact positioning instruction and generating a marked medical image.
6. The internet-based system for improving medical image data quality according to claim 5, wherein the image optimization processing unit specifically comprises:
The smoothing processing module is used for carrying out smoothing processing on the corrected medical image;
the stretching and equalizing processing module is used for carrying out contrast stretching and histogram equalizing processing on the corrected medical image;
the color balance adjustment module is used for performing color balance adjustment on the corrected medical image;
And the format conversion module is used for carrying out format conversion according to a preset required format after finishing smoothing, contrast stretching, histogram equalization and color balance adjustment, and generating an optimized medical image.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410228859.1A CN117808718B (en) | 2024-02-29 | 2024-02-29 | Method and system for improving medical image data quality based on Internet |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410228859.1A CN117808718B (en) | 2024-02-29 | 2024-02-29 | Method and system for improving medical image data quality based on Internet |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117808718A CN117808718A (en) | 2024-04-02 |
| CN117808718B true CN117808718B (en) | 2024-05-24 |
Family
ID=90431987
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410228859.1A Active CN117808718B (en) | 2024-02-29 | 2024-02-29 | Method and system for improving medical image data quality based on Internet |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117808718B (en) |
Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101822545A (en) * | 2010-05-11 | 2010-09-08 | 河南大学 | Method for eliminating motion artifacts in digital subtraction angiography and system thereof |
| CN104599239A (en) * | 2013-10-31 | 2015-05-06 | 通用电气公司 | Medical image metal artifact eliminating method and device |
| CN105225208A (en) * | 2015-10-14 | 2016-01-06 | 上海联影医疗科技有限公司 | A kind of computer tomography metal artifacts reduction method and device |
| CN106909947A (en) * | 2017-03-03 | 2017-06-30 | 中南大学 | CT image metal artifacts removing method and elimination system based on Mean Shift algorithms |
| CN109801343A (en) * | 2018-12-16 | 2019-05-24 | 西安电子科技大学 | Based on annular artifact bearing calibration, the CT control system for rebuilding front and back image |
| CN110337673A (en) * | 2017-01-05 | 2019-10-15 | 通用电气公司 | The estimation to the data used in tomography reconstruction based on deep learning |
| CN110335666A (en) * | 2019-05-22 | 2019-10-15 | 平安国际智慧城市科技股份有限公司 | Medical image appraisal procedure, device, computer equipment and storage medium |
| CN111798440A (en) * | 2020-07-11 | 2020-10-20 | 大连东软教育科技集团有限公司 | Medical image artifact automatic identification method, system and storage medium |
| CN111815521A (en) * | 2020-05-27 | 2020-10-23 | 南京国科医工科技发展有限公司 | Cone beam CT metal artifact correction algorithm based on prior image |
| CN112037146A (en) * | 2020-09-02 | 2020-12-04 | 广州海兆印丰信息科技有限公司 | Medical image artifact automatic correction method and device and computer equipment |
| CN113902824A (en) * | 2021-10-12 | 2022-01-07 | 哈尔滨工业大学 | Guide wire artifact removing method for intravascular optical coherence tomography |
| CN113902737A (en) * | 2021-11-23 | 2022-01-07 | 西南医科大学附属医院 | Detection method based on thyroid CT image abnormality |
| CN113936068A (en) * | 2020-07-14 | 2022-01-14 | 上海联影医疗科技股份有限公司 | Artifact correction method, artifact correction device and storage medium |
| CN115375787A (en) * | 2022-08-26 | 2022-11-22 | 苏州微创畅行机器人有限公司 | Artifact correction method, computer device and readable storage medium |
| CN115482183A (en) * | 2021-05-31 | 2022-12-16 | 上海联影医疗科技股份有限公司 | Image correction method and system |
| CN115700740A (en) * | 2021-07-22 | 2023-02-07 | 上海联影医疗科技股份有限公司 | Medical image processing method, apparatus, computer device and storage medium |
| CN116309923A (en) * | 2023-05-24 | 2023-06-23 | 吉林大学 | CT metal artifact eliminating method and system based on graph neural network |
| CN116434918A (en) * | 2021-12-30 | 2023-07-14 | 上海联影医疗科技股份有限公司 | Medical image processing method and computer readable storage medium |
| CN116721045A (en) * | 2023-08-09 | 2023-09-08 | 经智信息科技(山东)有限公司 | Method and device for fusing multiple CT images |
| CN116982999A (en) * | 2023-08-03 | 2023-11-03 | 华西精创医疗科技(成都)有限公司 | Multi-mode CT image homogenization auxiliary method and system |
| CN117542485A (en) * | 2023-11-21 | 2024-02-09 | 江苏瑞康成医疗科技有限公司 | Intelligent processing method and system for image inspection |
-
2024
- 2024-02-29 CN CN202410228859.1A patent/CN117808718B/en active Active
Patent Citations (21)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101822545A (en) * | 2010-05-11 | 2010-09-08 | 河南大学 | Method for eliminating motion artifacts in digital subtraction angiography and system thereof |
| CN104599239A (en) * | 2013-10-31 | 2015-05-06 | 通用电气公司 | Medical image metal artifact eliminating method and device |
| CN105225208A (en) * | 2015-10-14 | 2016-01-06 | 上海联影医疗科技有限公司 | A kind of computer tomography metal artifacts reduction method and device |
| CN110337673A (en) * | 2017-01-05 | 2019-10-15 | 通用电气公司 | The estimation to the data used in tomography reconstruction based on deep learning |
| CN106909947A (en) * | 2017-03-03 | 2017-06-30 | 中南大学 | CT image metal artifacts removing method and elimination system based on Mean Shift algorithms |
| CN109801343A (en) * | 2018-12-16 | 2019-05-24 | 西安电子科技大学 | Based on annular artifact bearing calibration, the CT control system for rebuilding front and back image |
| CN110335666A (en) * | 2019-05-22 | 2019-10-15 | 平安国际智慧城市科技股份有限公司 | Medical image appraisal procedure, device, computer equipment and storage medium |
| CN111815521A (en) * | 2020-05-27 | 2020-10-23 | 南京国科医工科技发展有限公司 | Cone beam CT metal artifact correction algorithm based on prior image |
| CN111798440A (en) * | 2020-07-11 | 2020-10-20 | 大连东软教育科技集团有限公司 | Medical image artifact automatic identification method, system and storage medium |
| CN113936068A (en) * | 2020-07-14 | 2022-01-14 | 上海联影医疗科技股份有限公司 | Artifact correction method, artifact correction device and storage medium |
| CN112037146A (en) * | 2020-09-02 | 2020-12-04 | 广州海兆印丰信息科技有限公司 | Medical image artifact automatic correction method and device and computer equipment |
| CN115482183A (en) * | 2021-05-31 | 2022-12-16 | 上海联影医疗科技股份有限公司 | Image correction method and system |
| CN115700740A (en) * | 2021-07-22 | 2023-02-07 | 上海联影医疗科技股份有限公司 | Medical image processing method, apparatus, computer device and storage medium |
| CN113902824A (en) * | 2021-10-12 | 2022-01-07 | 哈尔滨工业大学 | Guide wire artifact removing method for intravascular optical coherence tomography |
| CN113902737A (en) * | 2021-11-23 | 2022-01-07 | 西南医科大学附属医院 | Detection method based on thyroid CT image abnormality |
| CN116434918A (en) * | 2021-12-30 | 2023-07-14 | 上海联影医疗科技股份有限公司 | Medical image processing method and computer readable storage medium |
| CN115375787A (en) * | 2022-08-26 | 2022-11-22 | 苏州微创畅行机器人有限公司 | Artifact correction method, computer device and readable storage medium |
| CN116309923A (en) * | 2023-05-24 | 2023-06-23 | 吉林大学 | CT metal artifact eliminating method and system based on graph neural network |
| CN116982999A (en) * | 2023-08-03 | 2023-11-03 | 华西精创医疗科技(成都)有限公司 | Multi-mode CT image homogenization auxiliary method and system |
| CN116721045A (en) * | 2023-08-09 | 2023-09-08 | 经智信息科技(山东)有限公司 | Method and device for fusing multiple CT images |
| CN117542485A (en) * | 2023-11-21 | 2024-02-09 | 江苏瑞康成医疗科技有限公司 | Intelligent processing method and system for image inspection |
Non-Patent Citations (3)
| Title |
|---|
| DuDoUFNet: Dual-Domain Under-to-Fully-Complete Progressive Restoration Network for Simultaneous Metal Artifact Reduction and Low-Dose CT Reconstruction;Bo Zhou;《 IEEE Transactions on Medical Imaging 》;20220711;第41卷(第12期);3587-3599 * |
| X光CT图像伪影校正算法研究;黄铜港;《中国优秀硕士学位论文全文数据库 (信息科技辑)》;20240215;第2024年卷(第02期);I138-965 * |
| 单能量去金属伪影算法重建联合重建技术在人工耳蜗CT成像质量中的评估;李嘉慧等;《中国耳鼻咽喉头颈外科》;20200728(第6期);333-337 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117808718A (en) | 2024-04-02 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105654436B (en) | A kind of backlight image enhancing denoising method based on prospect background separation | |
| CN112233135A (en) | Retinal vessel segmentation method in fundus image and computer-readable storage medium | |
| CN116630762B (en) | Multi-mode medical image fusion method based on deep learning | |
| CN112598607B (en) | Endoscope image blood vessel enhancement algorithm based on improved weighted CLAHE | |
| CN110956632A (en) | Method and device for automatically detecting pectoralis major region in molybdenum target image | |
| CN116843581B (en) | Image enhancement method, system, device and storage medium for multi-scene graph | |
| Liu et al. | Enhancement of low illumination images based on an optimal hyperbolic tangent profile | |
| CN117036310A (en) | DICOM image peripheral outline identification and extraction method | |
| CN116416175A (en) | Image fusion method based on self-adaptive edge-preserving smooth pyramid | |
| CN114863498A (en) | Hand vein infrared image enhancement and segmentation method based on AGC and Frangi | |
| Saroj | An efficient hybrid approach for medical images enhancement | |
| CN114418906A (en) | Image contrast enhancement method and system | |
| Yue et al. | Deep pyramid network for low-light endoscopic image enhancement | |
| CN117808718B (en) | Method and system for improving medical image data quality based on Internet | |
| CN117830134A (en) | Infrared image enhancement method and system based on mixed filtering decomposition and image fusion | |
| CN116563166A (en) | Image enhancement method, device, storage medium and equipment | |
| CN116452502A (en) | Medical image multi-stage enhancement method and system | |
| JP4127537B2 (en) | Image processing method, apparatus, and program | |
| CN107784677A (en) | Radioscopic image processing method, device, system and storage medium | |
| Kaur et al. | A Comparative Study of Image Enhancement Algorithms for Abdomen CT Images | |
| CN111489314A (en) | Image enhancement method and device and terminal equipment | |
| Khattar et al. | Investigation of Denoising Techniques for Removal of Hair and Noise from Dermoscopic Images | |
| CN116912305B (en) | Brain CT image three-dimensional reconstruction method and device based on deep learning | |
| CN110634107B (en) | Standardization method for enhancing brain magnetic resonance image brightness aiming at T1 | |
| CN118261794B (en) | Ultrasonic image processing method, device, equipment and computer readable storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |