CN111047580A - Acoustic image quantitative analysis and comprehensive quantitative analysis method for ultrasonic molecular image research - Google Patents
Acoustic image quantitative analysis and comprehensive quantitative analysis method for ultrasonic molecular image research Download PDFInfo
- Publication number
- CN111047580A CN111047580A CN201911287472.9A CN201911287472A CN111047580A CN 111047580 A CN111047580 A CN 111047580A CN 201911287472 A CN201911287472 A CN 201911287472A CN 111047580 A CN111047580 A CN 111047580A
- Authority
- CN
- China
- Prior art keywords
- roi
- image
- ultrasonic
- gray value
- gray
- 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.)
- Granted
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/0002—Inspection of images, e.g. flaw detection
- G06T7/0012—Biomedical image inspection
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/12—Edge-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/181—Segmentation; Edge detection involving edge growing; involving edge linking
-
- 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
- G06T2207/10—Image acquisition modality
- G06T2207/10132—Ultrasound image
Abstract
The invention discloses a method for quantitatively analyzing an acoustic image and comprehensively and quantitatively analyzing the acoustic image for ultrasonic molecular image research, which takes an ultrasonic molecular image (comprising a conventional ultrasonic image and an ultrasonic contrast image) as a research object, and can realize quantitative analysis of gray values of various ROIs by carrying out statistical analysis on the intercepted gray values of various ROIs, thereby providing effective data support for ultrasonic medical detection and auxiliary diagnosis. Further by ROI position marking and loading, the same ROI can be marked at exactly the same position in the conventional ultrasound image and the ultrasound contrast image, respectively. Therefore, the method fills the blank of ultrasonic ROI gray value quantitative analysis, has simple system, easy use and high visualization degree, integrates image scaling treatment and any ROI mark, improves the precision and the effectiveness of ROI gray value analysis, and can be widely applied to a plurality of fields of ultrasonic medical image analysis, auxiliary diagnosis and the like.
Description
Technical Field
The invention belongs to the technical field of ultrasonic molecular images, relates to ultrasonic image analysis for ultrasonic molecular image research, particularly relates to the cross field of computer science and medical molecular image research, and particularly relates to a method and a system capable of realizing quantitative analysis of an acoustic image.
Background
With the progress of social science and technology and the improvement of the living standard of human beings, the attention degree of people to medical treatment and health is higher and higher, the rapid development of a medical imaging technology is greatly promoted, and the medical image is widely applied to various links such as medical diagnosis, preoperative planning, intraoperative guidance, postoperative monitoring and the like. The molecular image is taken as the leading-edge field of medical image technology development, is one of the most rapidly developed subjects in modern medicine due to the fact that the molecular image relates to multiple fields of biomedical engineering, computer science, molecular biology and the like, is expected to perform nondestructive and real-time imaging on cell and molecular levels in human physiology and pathological processes, and leads the human society to enter a new precise medical age.
The ultrasonic molecular image can convert a series of complex information change processes such as gene expression, biological signal transmission, disease occurrence and development and the like into visual sonograms for displaying by skillfully designing a molecular probe with specific function, and develops rapidly in recent years by virtue of the advantages of strong real-time performance, portability and no damage of an ultrasonic imaging technology. Although a lot of ultrasonic instruments can be used for ultrasonic molecular image research at present, only image enhancement processing technology is usually focused, quantitative analysis function is not deeply developed, an analysis system for accurately and quantitatively researching the biological information of an acoustic image is not available, and medical research and clinical application of ultrasonic molecular images are severely limited. Especially, the quantitative analysis of the gray value of the region of interest (ROI) in the image has important value for exploring biological information of living tissue molecules and cell levels, and further has far-reaching significance for realizing early-stage sub-clinical diagnosis and treatment of diseases. In addition, by utilizing the characteristic that the ultrasonic contrast agent generates harmonic waves, the ultrasonic instrument can respectively obtain a gray level image of common ultrasound and an enhanced image of ultrasonic contrast by respectively receiving and processing echo signals of fundamental waves and harmonic waves. Therefore, if the contrast analysis of the gray scale image and the contrast enhanced image generated in the ultrasonic contrast process can be realized, a more effective basis can be provided for molecular image diagnosis and research of diseases.
The presently known sonogram processing techniques also suffer from the following problems: (1) most of the ROI-like image capturing methods can only be selected in a regular rectangular, circular, oval or other capturing modes, and the capturing modes can not completely cover the ROI or capture the area outside the ROI, so that analysis is influenced; (2) the sound image processing technology adopts a mouse punctuation mode to realize ROI selection, but the punctuations are connected in a straight line mode, so the ROI selection is not smooth and accurate enough, and the analysis is influenced; (3) the traditional image ROI intercepting system can only intercept and analyze the size of an original image, but the ROI is a small part in the whole image, so that the accurate interception of the ROI is influenced, and the subsequent image analysis is influenced; (4) in the conventional image processing, the same ROI in the conventional ultrasonic image and the ultrasonic contrast image cannot be contrasted and analyzed, and more molecular information can be provided for the image diagnosis and scientific research of diseases by contrastingly analyzing the same ROI in the conventional ultrasonic image and the ultrasonic contrast image.
Therefore, it is desirable to develop a method and a system for performing quantitative analysis on an acoustic image, so as to solve various accuracy problems in the conventional ultrasound image processing.
Disclosure of Invention
Aiming at the problem that the existing ultrasonic molecular imaging technology can not realize quantitative analysis, thereby limiting the application of the technology in medical research and clinical application, the method and the system for quantitatively analyzing the sound image for ultrasonic molecular imaging research are provided, the quantitative analysis of the gray value of the ultrasonic molecular image is realized, effective image data is provided for the medical research and the clinical application, and the comparison of the same ROI in a conventional ultrasonic image and an ultrasonic contrast image in the ultrasonic molecular image is realized.
The object of study aimed by the invention is an ultrasonic image obtained by ultrasonic molecular imaging, and the ultrasonic image is a conventional ultrasonic image or an ultrasonic contrast image. The same processing procedure can be adopted for the two types of ultrasonic images, and based on the processing procedure, the application provides two realizable schemes:
(1) the first is a sound image quantitative analysis method, which realizes the gray value quantitative analysis of the conventional ultrasonic image or/and the ultrasonic contrast image;
(2) the second is a sound image comprehensive quantitative analysis method, which comprises the steps of analyzing a conventional ultrasonic image, finding and marking an ROI, then carrying out quantitative gray value analysis on the ROI of the conventional ultrasonic image, positioning the same ROI region on an ultrasonic contrast image through marked ROI position information, carrying out quantitative gray value analysis on the region, and finally realizing quantitative contrast analysis on the same ROI of the conventional ultrasonic image and the ultrasonic contrast image.
The invention provides an acoustic image quantitative analysis method for ultrasonic molecular image research, which comprises the following steps:
s1 image preprocessing: the ultrasonic image to be processed is enlarged or reduced to meet the set size;
s2 ROI truncation: moving along the boundary of a region to be extracted of the preprocessed ultrasonic image, recording a plurality of moving track points, connecting the recorded track points into a closed region, and performing ROI interception on the region to obtain an ROI region matched with the shape of the region to be extracted;
s3 obtaining gray value characteristic parameters of the ROI: and filtering the gray value between the intercepted minimum circumscribed rectangular region of the ROI region and the ROI region to obtain the gray value of the ROI region, and then performing statistical analysis on the gray value of the ROI region to obtain the gray value characteristic parameter of the ROI region.
In step S1 of the above quantitative analysis method for an ultrasound image used in ultrasound molecular imaging research, an ultrasound image to be analyzed is selected from ultrasound images obtained by ultrasound molecular imaging. Because the region of interest ROI (region of interest) in the ultrasound image is larger or smaller in the ultrasound image, in order to more accurately intercept the ROI of real interest in the next step, the ultrasound image to be processed may be enlarged or reduced to meet the set size, so as to obtain the ultrasound image subjected to zoom processing.
In step S2 of the above method for quantitatively analyzing an acoustic image for ultrasound molecular image research, since the ROI region with a shape matching the region to be extracted may be a regular rectangular region or an irregular arbitrary shape region, the ROI cutting method provided by the present invention includes a rectangular cutting method or a non-rectangular arbitrary shape cutting method. The rectangular shape intercepting mode is that a rectangular closed region is constructed by taking the moving distance as a diagonal line, and the rectangular closed region is the ROI region; the non-rectangular arbitrary shape intercepting mode is that firstly a plurality of moving track points are obtained in a mode of moving along the boundary of the region to be extracted on an ultrasonic image, and then the recorded track points are connected into a closed region, namely the ROI region matched with the shape of the region to be extracted. And after the ROI intercepting mode is selected, the ROI is sketched out from the zoomed ultrasonic image and intercepted to the display area, and the interception of the ROI is completed. For ease of analysis, the ROI may be clipped to an interface for displaying the ROI alone (i.e., the ROI display interface), thereby facilitating viewing against the other.
In step S3 of the method for quantitatively analyzing an acoustic image for ultrasound molecular image research, after the screenshot is determined, the method of the present invention performs statistical analysis on the captured ROI gray value to obtain the gray value characteristic parameter. The gray value characteristic parameters comprise a gray average value, a gray maximum value and a gray minimum value. If the intercepted rectangular ROI is in a rectangular shape, extracting the gray value of the whole rectangular ROI, and completing statistical analysis; if the non-rectangular ROI in any shape is intercepted, the filtering of the gray value of the peripheral image outside the ROI area within the minimum circumscribed rectangular area of the intercepted ROI area is automatically realized in a manner of judging the gray value, so that the gray value of the non-rectangular ROI in any shape is reserved.
The gray average value, the gray maximum value and the gray minimum value are obtained in the following modes:
(1)
in the formula, Grayvalue [ i ] represents the ith gray scale value, and N represents the number of gray scale values in ROI.
(2) Maximum value of ROI
＝Max{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(3) Gray minimum of ROI
＝Min{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
In the invention, the gray value of the peripheral image outside any ROI and inside the minimum rectangular region is determined in the following manner of judging the gray value (namely, the gray value between the minimum circumscribed rectangular region of the ROI region and the ROI region is intercepted), and is filtered out: firstly, extracting any non-rectangular ROI boundary contour, acquiring a minimum circumscribed rectangle of the ROI boundary contour according to the non-rectangular ROI boundary contour, and extracting a gray value of a minimum circumscribed rectangle region from a preprocessed ultrasonic image.
The invention provides a sonogram comprehensive quantitative analysis method for ultrasonic molecular image research, which comprises the following steps:
s1' quantitative analysis of conventional ultrasound images:
s11' image preprocessing: the conventional ultrasonic image to be processed is amplified or reduced to meet the set size;
s12' ROI truncation: performing ROI interception on the preprocessed conventional ultrasonic image to obtain an ROI area matched with the shape of the area to be extracted;
s13' ROI labeling: marking and storing ROI regional position information of a conventional ultrasonic image;
s14' obtaining the gray value characteristic parameters of the ROI: performing statistical analysis on the gray value of the ROI area of the intercepted conventional ultrasonic image to obtain the characteristic parameter of the gray value of the ROI area of the conventional ultrasonic image;
s2' quantitative analysis of ultrasound contrast images:
s21' image preprocessing: carrying out amplification or reduction processing on an ultrasonic contrast image to be processed until the size meets the set size;
s22' ROI loading: the method comprises the steps that the marked ROI area position information of the conventional ultrasonic image is loaded into an ultrasonic contrast image, so that the ROI area consistent with the ROI area in the conventional ultrasonic image is determined on the ultrasonic contrast image;
s23' obtaining the gray value characteristic parameters of the ROI: performing statistical analysis on the determined gray value of the ROI area of the ultrasonic contrast image to obtain a characteristic parameter of the gray value of the ROI area;
s3' quantitative contrast analysis of gray value characteristic parameters: and carrying out quantitative contrast analysis on the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image to obtain the change trend of the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image.
According to the comprehensive quantitative analysis method for the sonogram for the ultrasonic molecular imaging research, the object to be processed in the conventional ultrasonic image quantitative analysis is a conventional ultrasonic image obtained from ultrasonic molecular imaging. Because the region of interest ROI (region of interest) in the ultrasound image is larger or smaller in the ultrasound image, in order to more accurately intercept the ROI of real interest in the next step, the ultrasound image to be processed may be enlarged or reduced to meet the set size, so as to obtain the ultrasound image subjected to zoom processing.
In the above comprehensive quantitative analysis method for sonogram for ultrasound molecular imaging research, steps S11 '-S12' in the conventional quantitative analysis of ultrasound image are the same as the steps S1-S2 in the first quantitative analysis method for sonogram for ultrasound molecular imaging research, and are not repeated herein. The marking and saving of the ROI region position information of the conventional ultrasound image in step S13' is to locate the same ROI region in the ultrasound contrast image. Step S14' is the same as step S3 of the sonogram quantitative analysis method for ultrasound molecular imaging research, and will not be described herein.
In the above comprehensive quantitative analysis method for sonogram used for ultrasound molecular imaging research, the operation of step S21' in the quantitative analysis for ultrasound contrast image is the same as that of step S1 in the first quantitative analysis method for sonogram used for ultrasound molecular imaging research, and thus the description thereof is omitted. In step S22', the marked ROI region position information of the conventional ultrasound image is loaded into the ultrasound contrast image, so that the ROI region corresponding to the ROI region in the conventional ultrasound image can be given on the ultrasound contrast image. Step S23 'is the same as the operation of step S14' given above and will not be described here.
According to the comprehensive quantitative analysis method for the sonogram for the ultrasonic molecular image research, the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image are subjected to quantitative comparative analysis, so that the change trend of the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image is obtained. The variation trend can reflect the difference of expression on the signal path of different molecule levels (such as disease molecule and normal molecule), thereby providing effective basis of molecule level for the image diagnosis and differential diagnosis of disease.
The method for quantitatively analyzing the sonogram and comprehensively and quantitatively analyzing the sonogram for the ultrasonic molecular image research has the following beneficial effects:
(1) the invention takes the ultrasonic molecular image (including the conventional ultrasonic image and the ultrasonic contrast image) as a research object, and can realize the quantitative analysis of the gray values of various ROIs by carrying out the statistical analysis on the intercepted gray values of various ROIs, thereby providing effective data support for the ultrasonic medical detection and the auxiliary diagnosis.
(2) According to the invention, the closed region is formed by moving the track points to intercept any ROI, so that the ROI is accurately positioned and analyzed, and the ultrasonic image detection and analysis effect is improved.
(3) According to the invention, the original ultrasound image is firstly amplified or reduced, so that the ROI can be marked and intercepted more accurately.
(4) According to the invention, the same ROI can be marked at the completely same position in a conventional ultrasonic image and an ultrasonic contrast image respectively through ROI position marking and loading, and different gray characteristic signals and change trends of different molecules in two image modes can be found through carrying out gray value quantitative analysis and comparison on the same ROI.
(5) The method for reflecting the expression difference on the molecular level signal path of the disease by using the signal processing and image analysis technology is expected to provide an effective basis for molecular level for the image diagnosis and differential diagnosis of the disease.
(6) The invention fills the blank of ultrasonic ROI gray value quantitative analysis, has simple system, easy use and high visualization degree, integrates image scaling treatment and any ROI mark, improves the precision and the effectiveness of ROI gray value analysis, and can be widely applied to a plurality of fields of ultrasonic medical image analysis, auxiliary diagnosis and the like.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other embodiments and drawings can be obtained according to the embodiments shown in the drawings without creative efforts.
Fig. 1 is a schematic flow chart of an acoustic image quantitative analysis method for ultrasonic molecular imaging research according to the present invention.
Fig. 2 is a schematic flow chart of an acoustic image comprehensive quantitative analysis method for ultrasonic molecular imaging research provided by the invention.
Fig. 3 is a flow chart of a conventional ultrasonic image quantitative analysis method according to the present invention.
Fig. 4 is a flow chart of the quantitative analysis method of the ultrasonic contrast image according to the invention.
Fig. 5 is a conventional ultrasound image loaded in example 2, wherein (a) is an original conventional ultrasound image, (b) is a conventional ultrasound image enlarged by 2.5 times, (c) is a conventional ultrasound image obtained by an arbitrary ROI cutting method, (d) is a cut-out arbitrary ROI display image and an analysis result, (e) is a conventional ultrasound image obtained by a rectangular ROI cutting, and (f) is a cut-out rectangular ROI display image and an analysis result.
Fig. 6 is the loaded ultrasound contrast image of example 2, wherein (a) is the original ultrasound contrast image, (b) is the ultrasound contrast image after 2.5 times enlargement, (c) is the ultrasound contrast image obtained by arbitrary ROI cutting, (d) is the cut single ROI display image and analysis result, (e) is the ultrasound contrast image obtained by rectangular ROI cutting, (f) is the cut single ROI display image and analysis result.
Detailed Description
The technical solutions of the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings, and it is to be understood that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
The study object aimed at in this embodiment may be a conventional ultrasound image or an ultrasound contrast image, and the method for quantitatively analyzing an acoustic image for ultrasound molecular imaging study, as shown in fig. 1, includes the following steps:
s1 image preprocessing: and (4) carrying out amplification or reduction processing on the ultrasonic image to be processed until the size meets the set size.
And selecting the ultrasonic image with better definition from the ultrasonic images obtained by ultrasonic molecular imaging as the ultrasonic image to be analyzed and processed.
Since the ROI in the ultrasound image can be large or small, in order to divide the ROI more accurately, the original ultrasound image may be first enlarged or reduced. In this embodiment, the mouse position is used as the center, the enlargement and reduction are realized by judging the movement of the mouse rolling wheel, if the mouse rolling wheel rolls forward, the loaded image is enlarged by a certain multiple by using the mouse position as the center, and if the mouse rolling wheel rolls backward, the loaded image is reduced by a certain multiple by using the mouse position as the center. Thereby realizing that the ROI with any size can be presented with the proper size.
S2 ROI truncation: and performing ROI interception on the preprocessed ultrasonic image to obtain an ROI area matched with the shape of the area to be extracted.
The ROI to be extracted in the image is usually in an irregular shape, so the ROI intercepting mode provided by the invention comprises a rectangular shape intercepting mode or a non-rectangular arbitrary shape intercepting mode. If it is desired to analyze only the gray values of the ROI and the peripheral region roughly, a rectangular shape clipping method (abbreviated as "rectangular ROI") may be selected, and if it is desired to acquire only the gray values of the irregular ROI matching the shape of the region to be extracted accurately without the gray values of the peripheral region, a non-rectangular arbitrary shape clipping method (abbreviated as "arbitrary ROI") may be selected.
The following two ROI interception methods are explained in detail:
(i) if the ROI clipping mode is selected as "rectangular ROI", in this embodiment, the position of the mouse when the left button is pressed, the position of the mouse moved after the mouse is pressed, and the position of the mouse when the left button is lifted on the image are recorded, so that a closed rectangular region, which is the rectangular ROI, is formed by using the movement distance as a diagonal line. To facilitate viewing of the contrast, the image of the rectangular region may be truncated to the ROI display interface.
(ii) If the ROI intercepting mode is selected to be any ROI, in the embodiment, when a left mouse button is pressed down on the picture, track points moved by the mouse are recorded at a high speed, the dense track points are connected into a line, when the left mouse button is lifted up on the picture, the track points are recorded, and the recorded track points are connected into a closed area, namely, any ROI. To facilitate cross-viewing, the image of the irregular trace points can be truncated to the ROI display interface.
In order to reduce the post-calculation processing, the determination operation may be further performed on the selected ROI in this embodiment. After the screenshot is realized through the rectangular ROI or the arbitrary ROI, if the screenshot result is satisfied, the screenshot determination is finished by clicking the rectangular ROI determination or the arbitrary ROI determination; and if the screenshot result is not satisfied, clicking a cancel button to cancel the screenshot, and selecting a new screenshot mode to complete new screenshot analysis.
S3 obtaining gray value characteristic parameters of the ROI: and performing statistical analysis on the intercepted ROI gray value to obtain a gray value characteristic parameter of the ROI.
After the ROI screenshot is finally determined, the embodiment further performs statistical analysis on the intercepted gray value of the ROI to obtain a gray value characteristic parameter. The gray value characteristic parameters comprise a gray average value, a gray maximum value and a gray minimum value.
For the ROIs obtained by different ROI interception methods, the corresponding gray value statistical analysis methods are also different:
(i) for the rectangular ROI obtained in step S2, the present embodiment extracts the gray value of the entire rectangular ROI from the preprocessed ultrasound image, and then performs the statistical analysis according to the following formula:
(1)
in the formula, Grayvalue [ i ] represents the ith gray scale value, and N represents the number of gray scale values in ROI.
(2) Maximum value of ROI
＝Max{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(3) Gray minimum of ROI
＝Min{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(ii) For any ROI obtained in step S2, filtering the gray values of the peripheral image except for the ROI by determining the gray values to leave the gray values of any ROI region, and then performing statistical analysis according to the following formula:
(1)
in the formula, Grayvalue [ i ] represents the ith gray scale value, and N represents the number of gray scale values in ROI.
(2) Maximum value of ROI
＝Max{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(3) Gray minimum of ROI
＝Min{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
In this embodiment, the gray values of the peripheral image outside any ROI and within the minimum rectangular region are determined and filtered out in the following manner: firstly, extracting any ROI boundary contour, acquiring a minimum circumscribed rectangle of the ROI boundary contour according to the ROI boundary contour, and extracting a gray value of a minimum circumscribed rectangle region from a preprocessed ultrasonic image, wherein the gray value distribution in the minimum circumscribed rectangle region is equivalent to a two-dimensional lattice, so that the gray value between any ROI and the minimum circumscribed rectangle region can be set to be 255, the extracted gray value of 255 in the minimum circumscribed rectangle region is removed, and the residual gray value is the gray value of any ROI region.
The present embodiment further provides a system for implementing the above method for quantitatively analyzing an acoustic image for ultrasound molecular imaging research, including:
the preprocessing module is used for carrying out amplification or reduction processing on the ultrasonic image to be processed until the size meets the set size;
the ROI intercepting module is used for carrying out ROI intercepting on the preprocessed ultrasonic image to obtain an ROI area matched with the shape of the area to be extracted;
and the gray value analysis module is used for carrying out statistical analysis on the intercepted gray value of the ROI area to obtain the characteristic parameter of the gray value of the ROI area.
The sonogram quantitative analysis system for ultrasonic molecular image research can be operated in an ultrasonic instrument provided with a Windows operating system, and can also be operated in various computer systems provided with the Windows operating system. The system can set a desktop shortcut, and the system can be accessed to execute the operation through the shortcut.
Example 2
The study object of this embodiment may be a conventional ultrasound image and an ultrasound contrast image, and the purpose of this embodiment is to implement the gray-level quantitative analysis and comparison of the two same ROIs, and the employed sonogram comprehensive quantitative analysis method for ultrasound molecular imaging study, as shown in fig. 2, includes the following steps:
s1' quantitative analysis of conventional ultrasound image, as shown in fig. 3, comprises the following sub-steps:
s11' image preprocessing: and (4) carrying out amplification or reduction processing on the conventional ultrasonic image to be processed to meet the set size.
And selecting a conventional ultrasonic image with better definition from ultrasonic images obtained by ultrasonic molecular imaging as the conventional ultrasonic image to be analyzed and processed.
Since the ROI in the conventional ultrasound image can be large or small, in order to divide the ROI more accurately, the original conventional ultrasound image may be enlarged or reduced. In this embodiment, the mouse position is used as the center, the enlargement and reduction are realized by judging the movement of the mouse rolling wheel, if the mouse rolling wheel rolls forward, the loaded image is enlarged by a certain multiple by using the mouse position as the center, and if the mouse rolling wheel rolls backward, the loaded image is reduced by a certain multiple by using the mouse position as the center. Thereby realizing that the ROI with any size can be presented with the proper size.
S12' ROI truncation: and performing ROI interception on the preprocessed conventional ultrasonic image to obtain an ROI area matched with the shape of the area to be extracted.
The ROI to be extracted in the image is usually in an irregular shape, so the ROI intercepting mode provided by the invention comprises a rectangular shape intercepting mode or a non-rectangular arbitrary shape intercepting mode. If it is desired to analyze only the gray values of the ROI and the peripheral region roughly, a rectangular shape clipping method (abbreviated as "rectangular ROI") may be selected, and if it is desired to acquire only the gray values of the irregular ROI matching the shape of the region to be extracted accurately without the gray values of the peripheral region, a non-rectangular arbitrary shape clipping method (abbreviated as "arbitrary ROI") may be selected.
The two ROI-intercepting manners have been explained in detail in the foregoing embodiment 1, and are not described herein again.
In order to reduce the post-calculation processing, the determination operation may be further performed on the selected ROI in this embodiment. After the screenshot is realized through the rectangular ROI or the arbitrary ROI, if the screenshot result is satisfied, the screenshot determination is finished by clicking the rectangular ROI determination or the arbitrary ROI determination; and if the screenshot result is not satisfied, clicking a cancel button to cancel the screenshot, and selecting a new screenshot mode to complete new screenshot analysis.
S13' ROI labeling: the ROI region location information of the conventional ultrasound image is marked and saved.
In order to realize the comparative analysis of the same ROI in different ultrasonic images, the embodiment adds the functions of 'marker saving' and 'marker loading'. Through 'mark saving', the position information of the current ROI is saved, the ROI position data is saved in an Excel data saving mode, a data saving path can be freely selected, and calling is facilitated.
S14' obtaining the gray value characteristic parameters of the ROI: and performing statistical analysis on the ROI area gray value of the intercepted conventional ultrasonic image to obtain the gray value characteristic parameters of the ROI area of the conventional ultrasonic image.
After the ROI screenshot is finally determined, the embodiment further performs statistical analysis on the intercepted gray value of the ROI to obtain a gray value characteristic parameter. The gray value characteristic parameters comprise a gray average value, a gray maximum value and a gray minimum value.
For ROIs obtained by different ROI clipping methods, the corresponding gray value statistical analysis methods are also different, and the gray average value, the gray maximum value, and the gray minimum value can be calculated by referring to the method provided in embodiment 1.
S2' quantitative analysis of ultrasound contrast images, as shown in fig. 4, comprising the following sub-steps:
s21' image preprocessing: and carrying out amplification or reduction processing on the ultrasonic contrast image to be processed until the size meets the set size.
This step S21 'is the same as the operation of step S11' given earlier and will not be described further herein.
S22' ROI loading: by loading the marked ROI area position information of the conventional ultrasonic image into the ultrasonic contrast image, the ROI area which is consistent with the ROI area in the conventional ultrasonic image is determined on the ultrasonic contrast image.
In this embodiment, the previously saved ROI trajectory data file is called by the "mark loading" function, and the position information of the ROI region of the marked conventional ultrasound image is loaded into the ultrasound contrast image, so that the mark of the same ROI as that in the conventional ultrasound image is determined on the ultrasound contrast image.
S23' obtaining the gray value characteristic parameters of the ROI: and carrying out statistical analysis on the determined ROI regional gray value of the ultrasonic contrast image to obtain a gray value characteristic parameter of the ROI region.
The method for statistically analyzing the ROI gray level in the ultrasound contrast image is the same as the method for statistically analyzing the ROI gray level in the conventional ultrasound image, and is not described herein again.
S3' quantitative contrast analysis of gray value characteristic parameters: and carrying out quantitative contrast analysis on the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image to obtain the change trend of the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image.
And carrying out quantitative contrast analysis on the gray characteristic parameters of the same ROI region of the conventional ultrasonic image and the contrast ultrasonic image to obtain the change trend of the gray characteristic parameters of the same ROI region of the conventional ultrasonic image and the contrast ultrasonic image, including different changes of gray values and gray values along with time. The variation trend can reflect the difference of expression on the signal path of different molecule levels (such as disease molecule and normal molecule), valuable molecular diagnosis information is extracted, and effective basis of molecular level is provided for the image diagnosis and differential diagnosis of diseases.
The conventional ultrasound image and the ultrasound contrast image acquired by the ultrasound molecular imaging are processed in accordance with the above-mentioned steps S1 '-S3', respectively.
(I) conventional ultrasound image
The method for analyzing the ultrasonic image quantitative analysis method for the ultrasonic molecular image research by using the conventional ultrasonic image as a processing object comprises the following steps:
s11' image preprocessing: and (4) carrying out amplification or reduction processing on the ultrasonic image to be processed until the size meets the set size.
In this embodiment, the original conventional ultrasound image is as shown in fig. 5 (a). The original conventional ultrasound image in fig. 5(a) is magnified by 2.5 times by the rolling of the mouse wheel, and the conventional ultrasound image is shown in fig. 5 (b). As can be seen from the figure, the ROI lesion area is clearer in the enlarged conventional ultrasonic image.
S12' ROI truncation: and performing ROI interception on the preprocessed conventional ultrasonic image to obtain an ROI area matched with the shape of the area to be extracted.
Two ROI truncation approaches have been explained in detail above. The enlarged image obtained in step S11' is subjected to ROI truncation according to the operation method given previously:
(i) if the ROI clipping mode is selected as "rectangular ROI", in this embodiment, the position of the mouse when the left button is pressed, the position of the mouse moved after the mouse is pressed, and the position of the mouse when the left button is lifted on the image are recorded, so that a closed rectangular region, which is the rectangular ROI, is formed by using the movement distance as a diagonal line. To facilitate viewing of the contrast, the image of the rectangular region may be truncated to the ROI display interface. The effect of using the "rectangular ROI" clipping approach is shown in FIGS. 5(e) and (f).
(ii) If the ROI intercepting mode is selected to be any ROI, in the embodiment, when a left mouse button is pressed down on the picture, track points moved by the mouse are recorded at a high speed, the dense track points are connected into a line, when the left mouse button is lifted up on the picture, the track points are recorded, and the recorded track points are connected into a closed area, namely, any ROI. To facilitate cross-viewing, the image of the irregular trace points can be truncated to the ROI display interface. The effect of using the "arbitrary ROI" clipping approach is shown in FIGS. 5(c) and (d).
After the screenshot is realized through the rectangular ROI or the arbitrary ROI, if the screenshot result is satisfied, the screenshot determination is finished by clicking the rectangular ROI determination or the arbitrary ROI determination; and if the screenshot result is not satisfied, clicking a cancel button to cancel the screenshot, and selecting a new screenshot mode to complete new screenshot analysis.
S13' ROI labeling: the ROI region location information of the conventional ultrasound image is marked and saved.
In order to realize the comparative analysis of the same ROI in different ultrasonic images, the embodiment adds the functions of 'marker saving' and 'marker loading'. Through 'mark saving', the position information of the current ROI is saved, the ROI position data is saved in an Excel data saving mode, a data saving path can be freely selected, and calling is facilitated.
S14' obtaining the gray value characteristic parameters of the ROI: and performing statistical analysis on the ROI area gray value of the intercepted conventional ultrasonic image to obtain the gray value characteristic parameters of the ROI area of the conventional ultrasonic image.
Aiming at the ROIs obtained by different ROI interception modes, the corresponding gray value statistical analysis method is as follows:
(i) for the rectangular ROI obtained in step S2, the present embodiment extracts the gray value of the entire rectangular ROI, and then performs the statistical analysis according to the following formula:
(1)
in the formula, Grayvalue [ i ] represents the ith gray scale value, and N represents the number of gray scale values in ROI.
(2) Maximum value of ROI
＝Max{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(3) Gray minimum of ROI
＝Min{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
The statistical analysis of the rectangular ROI in fig. 5(f) was performed by the above method, and the average value of the gradations was 29.35, the maximum value of the gradations was 92, and the minimum value of the gradations was 0.
(ii) For any ROI obtained in step S2, firstly, the gray values of the peripheral image within the minimum bounding rectangle region of any ROI and outside the ROI region are filtered out by the manner of determining the gray values given above, so as to leave the gray values of the ROI region in any shape, and then the statistical analysis is completed according to the following formula:
(1)
in the formula, Grayvalue [ i ] represents the ith gray scale value, and N represents the number of gray scale values in ROI.
(2) Maximum value of ROI
＝Max{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(3) Gray minimum of ROI
＝Min{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
Statistical analysis of any ROI in fig. 5(d) was performed by the above method, and the mean value of the gray scale was 30.85, the maximum value of the gray scale was 96, and the minimum value of the gray scale was 1.
From the quantitative analysis result of the gray value parameters of the rectangular ROI and any ROI, it can be obviously seen that the positioning of any ROI is more accurate, the gray value parameters can more truly reflect the characteristics of the sound image signals of the ROI, and the interference of peripheral image signals on the diagnosis and differential diagnosis of diseases is avoided.
(II) ultrasound contrast imaging
The method for analyzing the ultrasonic contrast image by adopting the quantitative analysis method of the sonogram for the ultrasonic molecular image research comprises the following steps:
s21' image preprocessing: and carrying out amplification or reduction processing on the ultrasonic contrast image to be processed until the size meets the set size.
In the present embodiment, the original ultrasound contrast image is as shown in fig. 6 (a). The original ultrasound contrast image in fig. 6(a) is magnified by 2.5 times by the rolling of the mouse wheel, and the ultrasound contrast image is shown in fig. 6 (b). As can be seen from the figure, the ROI lesion area is clearer in the magnified ultrasound contrast image.
S22' ROI loading: by loading the marked ROI area position information of the conventional ultrasonic image into the ultrasonic contrast image, the ROI area which is consistent with the ROI area in the conventional ultrasonic image is determined on the ultrasonic contrast image.
In this embodiment, the ROI trajectory data file saved in the conventional ultrasound image before is called by the "mark loading" function, and the position information of the ROI region of the marked conventional ultrasound image is loaded into the ultrasound contrast image, so that the mark of the same ROI as that in the conventional ultrasound image is determined on the ultrasound contrast image.
(i) If the ROI clipping mode is selected as "rectangular ROI" at the time, the effect after loading the ROI mark in the ultrasound contrast image is shown in FIGS. 6(e) and (f).
(ii) If the ROI clipping mode is selected as "arbitrary ROI", the effect after loading the ROI mark in the ultrasound contrast image is shown in FIGS. 6(c) and (d).
S23' obtaining the gray value characteristic parameters of the ROI: and carrying out statistical analysis on the determined ROI regional gray value of the ultrasonic contrast image to obtain a gray value characteristic parameter of the ROI region.
Aiming at the ROIs obtained by different ROI interception modes, the corresponding gray value statistical analysis method is as follows:
(i) for the rectangular ROI obtained in step S22', the present embodiment extracts the gray value of the entire rectangular ROI, and then performs the statistical analysis according to the following formula:
(1)
in the formula, Grayvalue [ i ] represents the ith gray scale value, and N represents the number of gray scale values in ROI.
(2) Maximum value of ROI
＝Max{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(3) Gray minimum of ROI
＝Min{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
The statistical analysis of the rectangular ROI in fig. 6(f) was performed by the above method, and the average value of the gray scale was 31.83 and the maximum value of the gray scale was 187.
(ii) For any ROI obtained in step S22', the gray values of the peripheral image of any ROI region within the minimum bounding rectangle region of any ROI are filtered out by the manner of determining the gray values given above, so as to leave the gray values of any ROI region, and then the statistical analysis is completed according to the following formula:
(1)
in the formula, Grayvalue [ i ] represents the ith gray scale value, and N represents the number of gray scale values in ROI.
(2) Maximum value of ROI
＝Max{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
(3) Gray minimum of ROI
＝Min{Grayvalue[1]、Grayvalue[2]、…、Grayvalue[i]、…Grayvalue[N]}。
Statistical analysis of any ROI in fig. 6(d) was performed by the above method, and the average value of the gray scale was 27.71, the maximum value of the gray scale was 176, and the minimum value of the gray scale was 1.
From the quantitative analysis result of the gray value parameters of the rectangular ROI and any ROI, it can be obviously seen that the positioning of any ROI is more accurate, the gray value parameters can more truly reflect the characteristics of the sound image signals of the ROI, and the interference of peripheral image signals on the diagnosis and differential diagnosis of diseases is avoided.
Quantitative contrast analysis of gray value characteristic parameters: the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image are subjected to quantitative contrast analysis, so that the change trend of the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image can be obtained, and an effective basis of a molecular level is provided for image diagnosis and differential diagnosis of diseases.
The embodiment further provides a system for implementing the above method for comprehensive quantitative analysis of sonograms for ultrasound molecular imaging research, including:
conventional ultrasound image quantitative analysis subsystem:
the first preprocessing module is used for amplifying or reducing the conventional ultrasonic image to be processed to meet the set size;
the ROI intercepting module is used for carrying out ROI intercepting on the preprocessed conventional ultrasonic image to obtain an ROI area matched with the shape of the area to be extracted;
the ROI marking module marks and stores the ROI regional position information of the conventional ultrasonic image;
the first gray value analysis module is used for carrying out statistical analysis on the gray value of the ROI area of the intercepted conventional ultrasonic image to obtain the characteristic parameter of the gray value of the ROI area of the conventional ultrasonic image;
an ultrasonic contrast image quantitative analysis subsystem:
the second preprocessing module is used for amplifying or reducing the ultrasonic contrast image to be processed to meet the set size;
the ROI determining module is used for determining an ROI (region of interest) region consistent with the ROI region in the conventional ultrasonic image on the ultrasonic contrast image by loading the position information of the marked ROI region of the conventional ultrasonic image into the ultrasonic contrast image;
the second gray value analysis module is used for carrying out statistical analysis on the determined gray value of the ROI of the ultrasonic contrast image to obtain a characteristic parameter of the gray value of the ROI;
and the contrast analysis module is used for carrying out quantitative contrast analysis on the same ROI regional gray characteristic parameters of the conventional ultrasonic image and the contrast ultrasonic image to obtain the change trend of the same ROI regional gray characteristic parameters of the conventional ultrasonic image and the contrast ultrasonic image.
The sonogram comprehensive quantitative analysis system for ultrasonic molecular image research can be operated in an ultrasonic instrument provided with a Windows operating system, and can also be operated in various computer systems provided with the Windows operating system. The system can set a desktop shortcut, and the system can be accessed to execute the operation through the shortcut.
In conclusion, the sonogram quantitative analysis and comprehensive quantitative analysis method for ultrasonic molecular image research provided by the invention has the following advantages:
(1) the sonogram quantitative analysis method for ultrasonic molecular image research can be realized by adopting C # window application program programming, and the executed program can be conveniently copied and transplanted to any personal computer and ultrasonic workstation provided with a Windows system;
(2) the invention can realize local amplification and reduction of the image aiming at the ROIs with different sizes, so that the ROIs can be more accurately intercepted by the mark, thereby improving the analysis precision of the gray value;
(3) the invention can realize two ROI intercepting modes of rectangular ROI and non-rectangular optional ROI, so that all ROI intercepting requirements can be met; the "rectangular ROI" is suitable for rough analysis of gray values, and the "arbitrary ROI" is suitable for precise analysis of gray values;
(4) in the invention, the arbitrary ROI intercepting mode adopts a mode of recording the moving track of the mouse at a high speed, so that the marked track is finer and smoother, and the marked ROI is more accurate;
(5) the position of the ROI in the original image is marked, and meanwhile, the interface of the intercepted ROI is displayed on the ROI display interface, so that the contrast and the viewing are convenient;
(6) in the gray value analysis process, the gray values except the ROI are automatically filtered by judging whether the ROI interception mode is 'rectangular ROI' or 'any ROI', so that the accurate statistical analysis of the ROI gray values can be realized;
(7) the ROI mark storage and loading functions in the invention can be adopted to mark the same ROI at the same position on the ultrasonic contrast image respectively, so that the gray value contrast analysis of the ROI of the ultrasonic contrast image can be completed; as the part of the attached drawings in the specification, a common image and a contrast image in the ultrasonic contrast are respectively loaded and analyzed, quantitative analysis is respectively realized by adopting any ROI and a rectangular ROI, and the quantitative analysis of the same ROI in the two images of the ultrasonic contrast can be realized.
Therefore, the processing method and the system for the quantitative analysis of the acoustic image in the ultrasonic molecular image research can quickly and accurately realize the quantitative analysis of the ROI gray value, fill the blank of the conventional ultrasonic ROI gray value analysis, have the advantages of simplicity, easy use and high visualization degree, integrate the image scaling treatment and any ROI mark, improve the precision and the effectiveness of the ROI gray value analysis, and can be widely applied to the fields of ultrasonic medical image analysis, auxiliary diagnosis and the like.
It will be appreciated by those of ordinary skill in the art that the examples provided herein are intended to assist the reader in understanding the principles of the invention and are to be construed as being without limitation to such specifically recited examples and embodiments. Those skilled in the art can make various other specific changes and combinations based on the teachings of the present invention without departing from the spirit of the invention, and these changes and combinations are within the scope of the invention.
Claims (8)
1. A sonogram quantitative analysis method for ultrasonic molecular image research is characterized by comprising the following steps:
s1 image preprocessing: the ultrasonic image to be processed is enlarged or reduced to meet the set size;
s2 ROI truncation: moving along the boundary of a region to be extracted of the preprocessed ultrasonic image, recording a plurality of moving track points, connecting the recorded track points into a closed region, and performing ROI interception on the region to obtain an ROI region matched with the shape of the region to be extracted;
s3 obtaining gray value characteristic parameters of the ROI: and filtering the gray value between the intercepted minimum circumscribed rectangular region of the ROI region and the ROI region to obtain the gray value of the ROI region, and then performing statistical analysis on the gray value of the ROI region to obtain the gray value characteristic parameter of the ROI region.
2. The method for quantitatively analyzing an sonogram for ultrasonic molecular imaging research according to claim 1, wherein the ultrasonic image is a conventional ultrasonic image or an ultrasound contrast image obtained by ultrasonic molecular imaging.
3. The sonogram quantitative analysis method for ultrasound molecular imaging studies according to claim 1 or 2 wherein in step S3, the gray value characteristic parameters include a gray value mean, a gray value maximum and a gray value minimum.
4. A sonogram comprehensive quantitative analysis method for ultrasonic molecular image research is characterized by comprising the following steps:
s1' quantitative analysis of conventional ultrasound images:
s11' image preprocessing: the conventional ultrasonic image to be processed is amplified or reduced to meet the set size;
s12' ROI truncation: performing ROI interception on the preprocessed conventional ultrasonic image to obtain an ROI area matched with the shape of the area to be extracted;
s13' ROI labeling: marking and storing ROI regional position information of a conventional ultrasonic image;
s14' obtaining the gray value characteristic parameters of the ROI: performing statistical analysis on the gray value of the ROI area of the intercepted conventional ultrasonic image to obtain the characteristic parameter of the gray value of the ROI area of the conventional ultrasonic image;
s2' quantitative analysis of ultrasound contrast images:
s21' image preprocessing: carrying out amplification or reduction processing on an ultrasonic contrast image to be processed until the size meets the set size;
s22' ROI loading: the method comprises the steps that the marked ROI area position information of the conventional ultrasonic image is loaded into an ultrasonic contrast image, so that the ROI area consistent with the ROI area in the conventional ultrasonic image is determined on the ultrasonic contrast image;
s23' obtaining the gray value characteristic parameters of the ROI: performing statistical analysis on the determined gray value of the ROI area of the ultrasonic contrast image to obtain a characteristic parameter of the gray value of the ROI area;
s3' quantitative contrast analysis of gray value characteristic parameters: and carrying out quantitative contrast analysis on the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image to obtain the change trend of the gray characteristic parameters of the same ROI area of the conventional ultrasonic image and the contrast ultrasonic image.
5. The comprehensive quantitative analysis method for the sonogram used for the ultrasonic molecular imaging research according to claim 4 is characterized in that in step S12', the ROI cutting mode is any shape cutting mode, the ROI cutting mode moves along the boundary of the region to be extracted of the preprocessed ultrasonic image, a plurality of moving track points are recorded, then the recorded track points are connected into a closed region, and the ROI cutting is performed on the region, so as to obtain the ROI region matched with the shape of the region to be extracted.
6. The method according to claim 5, wherein in step S14', the gray value between the ROI area and the minimum bounding rectangle area is filtered to obtain the gray value of the ROI area, and the gray value of the ROI area is statistically analyzed to obtain the characteristic parameters of the gray value of the ROI area.
7. The method according to claim 5, wherein in step S23', the gray value between the ROI area and the minimum bounding rectangle area is filtered to obtain the gray value of the ROI area, and the gray value of the ROI area is statistically analyzed to obtain the characteristic parameters of the gray value of the ROI area.
8. The comprehensive quantitative analysis method for sonograms used in ultrasound molecular imaging studies according to any of claims 4-7, characterized in that said gray value characteristic parameters comprise a gray average value, a gray maximum value and a gray minimum value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911287472.9A CN111047580B (en) | 2019-12-14 | 2019-12-14 | Acoustic image quantitative analysis and comprehensive quantitative analysis method for ultrasonic molecular image research |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201911287472.9A CN111047580B (en) | 2019-12-14 | 2019-12-14 | Acoustic image quantitative analysis and comprehensive quantitative analysis method for ultrasonic molecular image research |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111047580A true CN111047580A (en) | 2020-04-21 |
| CN111047580B CN111047580B (en) | 2022-08-23 |
Family
ID=70236479
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201911287472.9A Active CN111047580B (en) | 2019-12-14 | 2019-12-14 | Acoustic image quantitative analysis and comprehensive quantitative analysis method for ultrasonic molecular image research |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111047580B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583209A (en) * | 2020-04-29 | 2020-08-25 | 上海杏脉信息科技有限公司 | Brain perfusion image feature point selection method, medium and electronic equipment |
| CN113425325A (en) * | 2021-06-24 | 2021-09-24 | 北京理工大学 | Preoperative liver three-dimensional ultrasonic splicing system and method |
Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030092991A1 (en) * | 2001-09-21 | 2003-05-15 | Sehgal Chandra M. | Method and apparatus to control microbubble destruction during contrast-enhanced ultrasound imaging, and uses therefor |
| US20100256495A1 (en) * | 2007-11-14 | 2010-10-07 | Koninklijke Philips Electronics N.V. | System and method for quantitative 3d ceus analysis |
| CN102551803A (en) * | 2011-12-31 | 2012-07-11 | 重庆安碧捷生物科技有限公司 | Ultrasonic contrast video analysis method and system |
| CN103156636A (en) * | 2011-12-15 | 2013-06-19 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging device and method |
| CN105701351A (en) * | 2016-01-15 | 2016-06-22 | 上海市第十人民医院 | Ultrasonic radiography characteristic automatic identification system and method based on artificial nerve network model |
| CN105879064A (en) * | 2016-04-08 | 2016-08-24 | 江南大学 | Examination indexes of SonoVue ultrasonic contrast technology in diagnosis and treatment of tumor angiogenesis mimicry |
| CN106456108A (en) * | 2015-08-10 | 2017-02-22 | 深圳迈瑞生物医疗电子股份有限公司 | System and method for ultrasonic elastography |
| US20170100101A1 (en) * | 2015-10-08 | 2017-04-13 | Samsung Medison Co., Ltd. | Ultrasound diagnosis method and apparatus for analyzing contrast enhanced ultrasound image |
| CN107506791A (en) * | 2017-08-07 | 2017-12-22 | 哈尔滨医科大学 | A kind of system classified to atherosclerotic plaque |
| CN107582097A (en) * | 2017-07-18 | 2018-01-16 | 中山大学附属第医院 | A kind of Aided intelligent decision-making learned based on multi-modal ultrasound group |
| CN108073930A (en) * | 2017-11-17 | 2018-05-25 | 维库（厦门）信息技术有限公司 | A kind of target detection and tracking based on multiple irregular ROI |
-
2019
- 2019-12-14 CN CN201911287472.9A patent/CN111047580B/en active Active
Patent Citations (11)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030092991A1 (en) * | 2001-09-21 | 2003-05-15 | Sehgal Chandra M. | Method and apparatus to control microbubble destruction during contrast-enhanced ultrasound imaging, and uses therefor |
| US20100256495A1 (en) * | 2007-11-14 | 2010-10-07 | Koninklijke Philips Electronics N.V. | System and method for quantitative 3d ceus analysis |
| CN103156636A (en) * | 2011-12-15 | 2013-06-19 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging device and method |
| CN102551803A (en) * | 2011-12-31 | 2012-07-11 | 重庆安碧捷生物科技有限公司 | Ultrasonic contrast video analysis method and system |
| CN106456108A (en) * | 2015-08-10 | 2017-02-22 | 深圳迈瑞生物医疗电子股份有限公司 | System and method for ultrasonic elastography |
| US20170100101A1 (en) * | 2015-10-08 | 2017-04-13 | Samsung Medison Co., Ltd. | Ultrasound diagnosis method and apparatus for analyzing contrast enhanced ultrasound image |
| CN105701351A (en) * | 2016-01-15 | 2016-06-22 | 上海市第十人民医院 | Ultrasonic radiography characteristic automatic identification system and method based on artificial nerve network model |
| CN105879064A (en) * | 2016-04-08 | 2016-08-24 | 江南大学 | Examination indexes of SonoVue ultrasonic contrast technology in diagnosis and treatment of tumor angiogenesis mimicry |
| CN107582097A (en) * | 2017-07-18 | 2018-01-16 | 中山大学附属第医院 | A kind of Aided intelligent decision-making learned based on multi-modal ultrasound group |
| CN107506791A (en) * | 2017-08-07 | 2017-12-22 | 哈尔滨医科大学 | A kind of system classified to atherosclerotic plaque |
| CN108073930A (en) * | 2017-11-17 | 2018-05-25 | 维库（厦门）信息技术有限公司 | A kind of target detection and tracking based on multiple irregular ROI |
Non-Patent Citations (3)
| Title |
|---|
| GUILLAUME RENAUD等: "Increasing specificity of contrast-enhanced ultrasound imaging using the interaction of quasi counter-propagating wavefronts: a proof of concept", 《IEEE TRANSACTIONS ON ULTRASONICS, FERROELECTRICS, AND FREQUENCY CONTROL》 * |
| 徐涛等: "脂肪肝超声图像的定量分析", 《天津大学学报》 * |
| 杨利静: "基于超声造影的颈动脉粥样硬化斑块量化分析", 《中国优秀硕士学位论文全文数据库医药卫生科技辑》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111583209A (en) * | 2020-04-29 | 2020-08-25 | 上海杏脉信息科技有限公司 | Brain perfusion image feature point selection method, medium and electronic equipment |
| CN113425325A (en) * | 2021-06-24 | 2021-09-24 | 北京理工大学 | Preoperative liver three-dimensional ultrasonic splicing system and method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111047580B (en) | 2022-08-23 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110060774B (en) | Thyroid nodule identification method based on generative confrontation network | |
| CN112529894B (en) | Thyroid nodule diagnosis method based on deep learning network | |
| CN111062955A (en) | Lung CT image data segmentation method and system | |
| CN102940510B (en) | Automatic focusing method for ultrasonic elastography | |
| Liu et al. | Automatic whole heart segmentation using a two-stage u-net framework and an adaptive threshold window | |
| CN111340827A (en) | Lung CT image data processing and analyzing method and system | |
| CN111047580B (en) | Acoustic image quantitative analysis and comprehensive quantitative analysis method for ultrasonic molecular image research | |
| CN111260701B (en) | Multi-mode retina fundus image registration method and device | |
| Chang et al. | 3-D snake for US in margin evaluation for malignant breast tumor excision using mammotome | |
| Assad et al. | Deep biomedical image classification using diagonal bilinear interpolation and residual network | |
| CN110838110A (en) | System for identifying benign and malignant tumor based on ultrasonic imaging | |
| Huang et al. | Extracting keyframes of breast ultrasound video using deep reinforcement learning | |
| CN103169506A (en) | Ultrasonic diagnosis device and method capable of recognizing liver cancer automatically | |
| CN108364289B (en) | IVOCT image vulnerable plaque automatic detection method | |
| Gupta | Real time wound segmentation/management using image processing on handheld devices | |
| Ren et al. | Application value of a deep convolutional neural network model for cytological assessment of thyroid nodules | |
| WO2023193175A1 (en) | Puncture needle real-time detection method and apparatus based on ultrasonic image | |
| CN112137693B (en) | Imaging method and device for four-dimensional ultrasonic guided puncture | |
| CN108416769B (en) | IVOCT image vulnerable plaque automatic detection method based on preprocessing | |
| Horng | An ultrasonic image evaluation system for assessing the severity of chronic liver disease | |
| Schwaiger et al. | Risk analysis for intraoperative liver surgery | |
| Swami et al. | An algorithmic detection of brain tumour using image filtering and segmentation of various radiographs | |
| Hernández-Muriel et al. | Hapan: Support tool for practicing regional anesthesia in peripheral nerves | |
| Stippel et al. | A tissue-specific adaptive texture filter for medical ultrasound images | |
| Pahl et al. | Cervix Segmentation in Ultrasound Data Based on Numerical Technique |
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 |