CN112819773A - Ultrasonic image quantitative evaluation method - Google Patents
Ultrasonic image quantitative evaluation method Download PDFInfo
- Publication number
- CN112819773A CN112819773A CN202110117779.5A CN202110117779A CN112819773A CN 112819773 A CN112819773 A CN 112819773A CN 202110117779 A CN202110117779 A CN 202110117779A CN 112819773 A CN112819773 A CN 112819773A
- Authority
- CN
- China
- Prior art keywords
- lung
- line
- ultrasonic
- intensity
- ultrasonic image
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0833—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures
- A61B8/085—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving detecting or locating foreign bodies or organic structures for locating body or organic structures, e.g. tumours, calculi, blood vessels, nodules
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/52—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/5215—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/60—Analysis of geometric attributes
- G06T7/62—Analysis of geometric attributes of area, perimeter, diameter or volume
-
- 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
-
- 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
- G06T2207/30061—Lung
-
- 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
- G06T2207/30168—Image quality inspection
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Radiology & Medical Imaging (AREA)
- Theoretical Computer Science (AREA)
- Surgery (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Molecular Biology (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Vascular Medicine (AREA)
- Quality & Reliability (AREA)
- Geometry (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention relates to an ultrasonic image quantitative evaluation method, which comprises the following steps: firstly, preprocessing the acquired lung ultrasonic image; secondly, carrying out image segmentation on the lung ultrasonic image; thirdly, carrying out quantitative analysis index extraction on the lung ultrasonic image; and fourthly, carrying out multi-parameter joint analysis on the lung ultrasonic image. The invention adopts a method of carrying out quantitative analysis on the ultrasonic image, extracts parameters related to the pleural line, the B line and the lung parenchyma change, and finally obtains the classification result of the lung lesion degree by comprehensively utilizing all quantitative analysis indexes by utilizing a multi-parameter joint analysis method, thereby providing a noninvasive/quantitative lung ultrasonic image quantitative evaluation method for clinic so as to be better applied to the rapid lesion screening, the grading diagnosis and the disease follow-up of a large-range crowd and the intensive care at the bedside.
Description
Technical Field
The invention relates to an ultrasonic image quantitative evaluation method, in particular to an ultrasonic image quantitative evaluation method for evaluating lung lesions.
Background
In the process of definite diagnosis and treatment of lung diseases, it is extremely important to accurately evaluate the degree of lung lesions in time. Clinically, Computed Tomography (CT) is often used for pulmonary imaging, but its use in conventional screening is limited due to CT's having ionizing radiation. In addition, difficulties in transporting critical patients, increased risk of infection, etc. limit their use in intensive care.
The ultrasonic diagnosis has the advantages of no wound, no ionizing radiation, real time, high cost performance and the like, and can be used as a rapid and convenient clinical screening tool and a bedside detection tool. In the clinical practice related to severe medicine, specific B-mode image expressions such as pleural line thickening, rupture, B-line fusion, lung consolidation and other characteristics are closely related to the pathological condition of the lung, so that the risk degree of the lung disease can be evaluated based on the characteristics. However, the current clinical ultrasonic diagnosis based on the B ultrasonic image has the problems of strong subjectivity, incapability of giving quantitative results and the like.
Some semi-quantitative assessment methods, i.e., scoring systems, exist today that score based on different ultrasound image representations to semi-quantitatively assess the severity of lung disease. However, such methods still rely on the subjective judgment of the doctor or operator. In addition, some artificial intelligence-based assessment methods have proved to have great application potential and show good assessment effect, but such assessment methods have the disadvantages of requiring a large number of labeled samples (clinically difficult to obtain) and being poor in interpretability.
Therefore, it is urgently needed to provide a noninvasive/quantitative lung ultrasound image quantitative evaluation method for clinical application in rapid lesion screening and grading diagnosis of a large-scale population.
Disclosure of Invention
In view of the above problems, an object of the present invention is to provide a method for quantitatively evaluating an ultrasound image for evaluating a lung lesion, in which an index sensitive to a lung lesion is extracted by quantitatively analyzing an ultrasound image, and a plurality of indexes are comprehensively analyzed by multi-parameter joint analysis, so that a degree of a lung lesion can be non-invasively and quantitatively evaluated.
In order to achieve the purpose, the invention adopts the following technical scheme: a method of quantitative assessment of ultrasound images, comprising: firstly, preprocessing the acquired lung ultrasonic image; secondly, carrying out image segmentation on the lung ultrasonic image; thirdly, carrying out quantitative analysis index extraction on the lung ultrasonic image; and fourthly, carrying out multi-parameter joint analysis on the lung ultrasonic image.
The method for quantitatively evaluating an ultrasound image preferably includes the step of preprocessing the acquired ultrasound image of the lung, including: 1) performing depth-direction pixel interpolation on the lung ultrasonic images to enable the lung ultrasonic images acquired at different depths to have the same pixel size; 2) intensity normalization is carried out on each frame of lung ultrasonic image by using the maximum intensity value of each frame, and the influence of time gain on the ultrasonic echo intensity is eliminated; 3) the attenuation compensation method is used to compensate for the acoustic attenuation in the ultrasound images of the lungs.
The method for quantitatively evaluating an ultrasound image preferably includes the step of performing image segmentation on an ultrasound image of a lung, including: the pleural line region, the B line region and the lung consolidation region are segmented from the lung ultrasound image.
The method for quantitatively evaluating an ultrasound image preferably includes the step of performing quantitative analysis index extraction on a lung ultrasound image, including: 1) extracting quantitative analysis indexes related to thickness, an ultrasonic echo signal reflection intensity mean value, an ultrasonic echo signal reflection intensity standard deviation, roughness and scatterer distribution from a pleural line region; 2) extracting quantitative analysis indexes related to the number, the accumulated width, the accumulated emission intensity, the attenuation coefficient and the scatterer distribution from the B line area; 3) and extracting quantitative analysis indexes related to the area, the average value of the intensity of the internal echo signals, the standard deviation of the intensity of the internal echo signals and the distribution of the scatterers from the lung real variation region.
The method for quantitatively evaluating an ultrasound image preferably includes, in step 1), the following steps:
thickness: firstly, determining a brightness peak point of a pleural line area by searching the maximum value of each row of ultrasonic echo signals in a lung ultrasonic image, then searching the row of ultrasonic echo signals from the brightness peak point up and down, finding out a set threshold position where the brightness peak value is attenuated to the brightness peak point, respectively defining the position as an upper boundary and a lower boundary of the pleural line, defining the vertical distance between the upper boundary and the lower boundary as the thickness, traversing all brightness peak points of the pleural line area, sequentially obtaining corresponding thicknesses, and then averaging the thicknesses to reflect the pleural line thickness of the lung;
the mean value of the reflection intensity of the ultrasonic echo signal: calculating the average value or the median value of the brightness peak values at different positions of the pleural line, wherein the average value is used for reflecting the reflection intensity average value of the ultrasonic echo signals;
③ standard deviation of reflection intensity of ultrasonic echo signal: calculating the standard deviation of the brightness peak values at different positions of the pleural line, and reflecting the standard deviation of the reflection intensity of the ultrasonic echo signal;
fourthly, roughness: acquiring the vertical distance from the upper boundary of the pleural line to the position of the brightness peak, performing low-pass filtering on the vertical distance, and solving a standard deviation of a filtered distance signal to reflect the pleural line roughness of the lung;
scattering particle distribution: fitting parameters related to scatterer distribution by using the extracted ultrasonic echo signals in the pleural line region according to a scatterer statistical distribution model, wherein the Nakagami distribution model is as follows:
wherein r is the ultrasonic echo signal intensity of the pleural line region, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
The method for quantitatively evaluating an ultrasound image preferably includes, in step 2), the following steps:
the number of the first step: axially selecting a series of brightness peak points in a B line area, defining the brightness peak points as B line peak values, then scanning left and right from the B line peak values of each line of the ultrasonic image to the positions of set threshold values with brightness attenuated into the brightness peak values, respectively defining the brightness peak points as the left boundary and the right boundary of the B line, positioning one B line according to the left boundary and the right boundary, and counting B line total items contained in the B line area to reflect the number of the B lines;
cumulative width: defining the average horizontal distance between the left boundary and the right boundary of the B line as the width of the B line, and accumulating the widths of different B lines to reflect the accumulated width of the B line of the lung;
cumulative emission intensity: for each B line, selecting a rectangular frame with the same height to contain the corresponding B line, adding the brightness values of the ultrasonic images which are positioned in the rectangular frame and between the left boundary and the right boundary of the B line to be used as the average emission intensity of each B line, and adding the average emission intensities of all B lines in one ultrasonic image to reflect the B line emission intensity of the whole lung;
attenuation coefficient: for a B line, drawing a curve of the brightness peak value changing along with the axial depth, calculating the slope of the curve by utilizing linear fitting to represent the attenuation coefficient of the B line, and averaging the attenuation coefficients of all B lines in an ultrasonic image to reflect the average attenuation coefficient of the B line of the lung;
scattering particle distribution: and fitting parameters related to the scatterer distribution by using the extracted ultrasonic echo signals in the B line region according to a scatterer statistical distribution model, wherein the Nakagami distribution model is as follows:
in the formula, r is the ultrasonic echo signal intensity of the B line area, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
The method for quantitatively evaluating an ultrasound image preferably includes, in step 2), the following steps:
area: segmenting the boundary of the lung compaction change region by using a manual or automatic segmentation algorithm, and counting the number of pixels in the boundary range of the lung compaction change region to be used as the area of the lung compaction change region;
the average value of the internal echo signal intensity: extracting echo signals in the lung real change region, and solving the average value of the intensity of the echo signals;
③ standard deviation of internal echo signal intensity: extracting an ultrasonic echo signal in the lung real change region, solving a standard deviation of the echo signal, and reflecting the uniformity of the echo in the lung real change region;
scattering electron distribution: fitting parameters related to the scatterer distribution by using the extracted ultrasonic echo signals in the lung real change region according to a scatterer statistical distribution model, wherein the Nakagami distribution model is as follows:
in the formula, r is the intensity of an ultrasonic echo signal in a lung consolidation area, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
The method for quantitatively evaluating an ultrasound image preferably includes the step of performing multi-parameter joint analysis on a lung ultrasound image, including: and (3) performing comprehensive analysis on all quantitative analysis indexes obtained in the third step of extraction by using a multi-parameter joint analysis or machine learning method to realize noninvasive quantitative grading of lung lesions.
Due to the adoption of the technical scheme, the invention has the following advantages: the invention adopts a method of carrying out quantitative analysis on an ultrasonic image, extracts parameters related to the pleural line, the B line and the lung parenchyma change, and finally obtains a classification result of lung lesion degrees by comprehensively utilizing all quantitative analysis indexes by utilizing a multi-parameter joint analysis method, thereby providing a noninvasive/quantitative lung lesion degree evaluation method for clinic so as to be better applied to the rapid lesion screening, the grading diagnosis and the disease follow-up of a large-range population and the intensive care bedside monitoring. The proposed method is equally suitable for non-invasive quantitative assessment of other signal types (RF signals) and various lung diseases (such as pneumonia, pulmonary edema, pulmonary fibrosis, etc.).
Drawings
Fig. 1 is a schematic flow chart of a method according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all 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.
As shown in fig. 1, the method for quantitatively evaluating an ultrasound image provided by this embodiment includes the following steps:
firstly, preprocessing an acquired ultrasonic image:
in this embodiment, the acquired ultrasound image is a lung ultrasound image acquired in a standard format (such as DICOM format) by an ultrasound system according to a unified standard operation procedure (for example, outco measures in radiology, OMERACT criterion), and then the lung ultrasound image is preprocessed by pixel interpolation, intensity normalization, acoustic attenuation compensation, and the like, so as to eliminate the influence of variable parameters such as acquisition depth, time gain compensation, gain, and the like on the result in the imaging process, specifically:
1) performing depth-direction pixel interpolation on the ultrasonic images to enable the ultrasonic images acquired at different depths to have the same pixel size;
2) intensity normalization is carried out on each frame of ultrasonic image by using the maximum intensity value of each frame, and the influence of time gain on the ultrasonic echo intensity is eliminated;
3) the acoustic attenuation in the ultrasound image is compensated using an attenuation compensation method, such as an optimum power spectral shift estimation method.
Secondly, carrying out image segmentation on the ultrasonic image:
in this embodiment, the pleural line region (the acoustic interface between the intercostal soft tissue and the air in the lung due to the high mismatch of acoustic impedances), the B-line region (discrete hyperechoic artifact extending perpendicularly from the pleural line to the bottom of the image), and the lung consolidation region (the disappearance of air in the lung due to atelectasis and alveolar effusion, with the lung tissue exhibiting substantial changes) are segmented from the lung ultrasound image using manual or region, boundary, mathematical morphology, wavelet theory, or neural network based image segmentation algorithms.
Thirdly, performing quantitative analysis index extraction on the ultrasonic image:
1) for pleural line region
Thickness: firstly, determining a brightness peak point of a pleural line region by searching the maximum value of each row of ultrasonic echo signals in an ultrasonic image, then searching the row of ultrasonic echo signals up and down from the brightness peak point, finding out the position of a set threshold (for example, 75%) where the brightness peak value is attenuated to the brightness peak point, respectively defining the position as the upper boundary and the lower boundary of the pleural line, defining the vertical distance between the upper boundary and the lower boundary as the thickness, traversing all the brightness peak points in the pleural line region, sequentially obtaining corresponding thicknesses, and then averaging the thicknesses to reflect the pleural line thickness of the lung;
the mean value of the reflection intensity of the ultrasonic echo signal: calculating the average value or the median value of the brightness peak values at different positions of the pleural line, wherein the average value is used for reflecting the reflection intensity average value of the ultrasonic echo signals;
③ standard deviation of reflection intensity of ultrasonic echo signal: calculating the standard deviation of the brightness peak values at different positions of the pleural line, and reflecting the standard deviation of the reflection intensity of the ultrasonic echo signal;
fourthly, roughness: acquiring the vertical distance from the upper boundary of the pleural line to the position of the brightness peak, performing low-pass filtering on the vertical distance, and solving a standard deviation of a filtered distance signal to reflect the pleural line roughness of the lung;
scattering particle distribution: parameters related to scatterer distribution are fitted using the extracted ultrasound echo signals in the pleural line region according to a scatterer statistical distribution model (in the present embodiment, a Nakagami distribution model is used), where the Nakagami distribution model is as follows:
wherein r is the ultrasonic echo signal intensity of the pleural line region, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
2) For B line region
The number of the first step: similar to pleural line positioning, a series of brightness peak points are axially selected in a B line area and defined as B line peaks, then scanning left and right from the B line peaks of each line of an ultrasonic image to the positions of set thresholds (for example, 75%) where brightness is attenuated to the brightness peak points, respectively defining the positions as left boundaries and right boundaries of the B lines, positioning one B line according to the left boundary and the right boundary, and counting B line total items contained in the B line area to reflect the number of the B lines;
cumulative width: defining the average horizontal distance between the left boundary and the right boundary of the B line as the width of the B line, and accumulating the widths of different B lines to reflect the accumulated width of the B line of the lung;
cumulative emission intensity: for each B line, selecting a rectangular frame with the same height (2 mm in the embodiment) to contain the corresponding B line, adding the brightness values of the ultrasonic images positioned in the rectangular frame and between the left boundary and the right boundary of the B line to obtain the average emission intensity of each B line, and adding the average emission intensities of all B lines in one ultrasonic image to reflect the overall B line emission intensity of the lung;
attenuation coefficient: for a B line, drawing a curve of the brightness peak value changing along with the axial depth, calculating the slope of the curve by utilizing linear fitting to represent the attenuation coefficient of the B line, and averaging the attenuation coefficients of all B lines in an ultrasonic image to reflect the average attenuation coefficient of the B line of the lung;
scattering particle distribution: fitting parameters related to scatterer distribution by using the extracted ultrasonic echo signal in the B-line region according to a scatterer statistical distribution model (in this embodiment, a Nakagami distribution model is used), wherein the Nakagami distribution model is as follows:
in the formula, r is the ultrasonic echo signal intensity of the B line area, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
3) For areas of lung consolidation
Area: segmenting the boundary of the lung compaction change region by using a manual or automatic segmentation algorithm, and counting the number of pixels in the boundary range of the lung compaction change region to be used as the area of the lung compaction change region;
the average value of the internal echo signal intensity: extracting echo signals in the lung real change region, and solving the average value of the intensity of the echo signals;
③ standard deviation of internal echo signal intensity: extracting an ultrasonic echo signal in the lung real change region, solving a standard deviation of the echo signal, and reflecting the uniformity of the echo in the lung real change region;
scattering electron distribution: fitting parameters related to the scatterer distribution by using the extracted ultrasonic echo signals in the lung real change region according to a scatterer statistical distribution model (in the embodiment, a Nakagami distribution model is adopted), wherein the Nakagami distribution model is as follows:
in the formula, r is the intensity of an ultrasonic echo signal in a lung consolidation area, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; t (n) represents a Gamma function with respect to a shape parameter n.
Fourthly, carrying out multi-parameter joint analysis on the ultrasonic image:
and (3) performing comprehensive analysis on all quantitative analysis indexes obtained in the three steps by using a multi-parameter joint analysis or machine learning (such as a support vector machine, a decision tree, a random forest and the like) method, realizing noninvasive quantitative grading of lung lesions, and finally obtaining a classification result of the lung lesion degree.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A method for quantitative evaluation of ultrasound images, comprising:
firstly, preprocessing the acquired lung ultrasonic image;
secondly, carrying out image segmentation on the lung ultrasonic image;
thirdly, carrying out quantitative analysis index extraction on the lung ultrasonic image;
and fourthly, carrying out multi-parameter joint analysis on the lung ultrasonic image.
2. The method for quantitatively evaluating an ultrasound image according to claim 1, wherein the step of preprocessing the acquired ultrasound image of the lung comprises:
1) performing depth-direction pixel interpolation on the lung ultrasonic images to enable the lung ultrasonic images acquired at different depths to have the same pixel size;
2) intensity normalization is carried out on each frame of lung ultrasonic image by using the maximum intensity value of each frame, and the influence of time gain on the ultrasonic echo intensity is eliminated;
3) the attenuation compensation method is used to compensate for the acoustic attenuation in the ultrasound images of the lungs.
3. The method for quantitatively evaluating an ultrasound image according to claim 1, wherein the step of image-segmenting the ultrasound image of the lung comprises: the pleural line region, the B line region and the lung consolidation region are segmented from the lung ultrasound image.
4. The method for quantitatively evaluating an ultrasonic image according to claim 3, wherein the step of performing quantitative analysis index extraction on the lung ultrasonic image comprises:
1) extracting quantitative analysis indexes related to thickness, an ultrasonic echo signal reflection intensity mean value, an ultrasonic echo signal reflection intensity standard deviation, roughness and scatterer distribution from a pleural line region;
2) extracting quantitative analysis indexes related to the number, the accumulated width, the accumulated emission intensity, the attenuation coefficient and the scatterer distribution from the B line area;
3) and extracting quantitative analysis indexes related to the area, the average value of the intensity of the internal echo signals, the standard deviation of the intensity of the internal echo signals and the distribution of the scatterers from the lung real variation region.
5. The method for quantitatively evaluating an ultrasonic image according to claim 4, wherein the step 1) comprises the following steps:
thickness: firstly, determining a brightness peak point of a pleural line area by searching the maximum value of each row of ultrasonic echo signals in a lung ultrasonic image, then searching the row of ultrasonic echo signals from the brightness peak point up and down, finding out a set threshold position where the brightness peak value is attenuated to the brightness peak point, respectively defining the position as an upper boundary and a lower boundary of the pleural line, defining the vertical distance between the upper boundary and the lower boundary as the thickness, traversing all brightness peak points of the pleural line area, sequentially obtaining corresponding thicknesses, and then averaging the thicknesses to reflect the pleural line thickness of the lung;
the mean value of the reflection intensity of the ultrasonic echo signal: calculating the average value or the median value of the brightness peak values at different positions of the pleural line, wherein the average value is used for reflecting the reflection intensity average value of the ultrasonic echo signals;
③ standard deviation of reflection intensity of ultrasonic echo signal: calculating the standard deviation of the brightness peak values at different positions of the pleural line, and reflecting the standard deviation of the reflection intensity of the ultrasonic echo signal;
fourthly, roughness: acquiring the vertical distance from the upper boundary of the pleural line to the position of the brightness peak, performing low-pass filtering on the vertical distance, and solving a standard deviation of a filtered distance signal to reflect the pleural line roughness of the lung;
scattering particle distribution: fitting parameters related to scatterer distribution by using the extracted ultrasonic echo signals in the pleural line region according to a scatterer statistical distribution model, wherein the Nakagami distribution model is as follows:
wherein r is the ultrasonic echo signal intensity of the pleural line region, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
6. The method for quantitatively evaluating an ultrasonic image according to claim 4, wherein the step 2) comprises the following steps:
the number of the first step: axially selecting a series of brightness peak points in a B line area, defining the brightness peak points as B line peak values, then scanning left and right from the B line peak values of each line of the ultrasonic image to the positions of set threshold values with brightness attenuated into the brightness peak values, respectively defining the brightness peak points as the left boundary and the right boundary of the B line, positioning one B line according to the left boundary and the right boundary, and counting B line total items contained in the B line area to reflect the number of the B lines;
cumulative width: defining the average horizontal distance between the left boundary and the right boundary of the B line as the width of the B line, and accumulating the widths of different B lines to reflect the accumulated width of the B line of the lung;
cumulative emission intensity: for each B line, selecting a rectangular frame with the same height to contain the corresponding B line, adding the brightness values of the ultrasonic images which are positioned in the rectangular frame and between the left boundary and the right boundary of the B line to be used as the average emission intensity of each B line, and adding the average emission intensities of all B lines in one ultrasonic image to reflect the B line emission intensity of the whole lung;
attenuation coefficient: for a B line, drawing a curve of the brightness peak value changing along with the axial depth, calculating the slope of the curve by utilizing linear fitting to represent the attenuation coefficient of the B line, and averaging the attenuation coefficients of all B lines in an ultrasonic image to reflect the average attenuation coefficient of the B line of the lung;
scattering particle distribution: and fitting parameters related to the scatterer distribution by using the extracted ultrasonic echo signals in the B line region according to a scatterer statistical distribution model, wherein the Nakagami distribution model is as follows:
in the formula, r is the ultrasonic echo signal intensity of the B line area, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
7. The method for quantitatively evaluating an ultrasonic image according to claim 4, wherein the step 2) comprises the following steps:
area: segmenting the boundary of the lung compaction change region by using a manual or automatic segmentation algorithm, and counting the number of pixels in the boundary range of the lung compaction change region to be used as the area of the lung compaction change region;
the average value of the internal echo signal intensity: extracting echo signals in the lung real change region, and solving the average value of the intensity of the echo signals;
③ standard deviation of internal echo signal intensity: extracting an ultrasonic echo signal in the lung real change region, solving a standard deviation of the echo signal, and reflecting the uniformity of the echo in the lung real change region;
scattering electron distribution: fitting parameters related to the scatterer distribution by using the extracted ultrasonic echo signals in the lung real change region according to a scatterer statistical distribution model, wherein the Nakagami distribution model is as follows:
in the formula, r is the intensity of an ultrasonic echo signal in a lung consolidation area, and r is more than or equal to 0; n is a shape parameter, and n > 0; omega is a scale parameter, and omega is more than 0; Γ (n) represents a Gamma function with respect to the shape parameter n.
8. The method for quantitative assessment of ultrasound images as claimed in claim 4, wherein said step of performing a multi-parameter joint analysis on ultrasound images of the lung comprises: and (3) performing comprehensive analysis on all quantitative analysis indexes obtained in the third step of extraction by using a multi-parameter joint analysis or machine learning method to realize noninvasive quantitative grading of lung lesions.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110117779.5A CN112819773B (en) | 2021-01-28 | 2021-01-28 | Ultrasonic image quantitative evaluation system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110117779.5A CN112819773B (en) | 2021-01-28 | 2021-01-28 | Ultrasonic image quantitative evaluation system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN112819773A true CN112819773A (en) | 2021-05-18 |
| CN112819773B CN112819773B (en) | 2022-05-17 |
Family
ID=75860096
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110117779.5A Active CN112819773B (en) | 2021-01-28 | 2021-01-28 | Ultrasonic image quantitative evaluation system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112819773B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113267521A (en) * | 2021-07-20 | 2021-08-17 | 杭州盾源聚芯半导体科技有限公司 | Silicon product surface processing damage depth detection method and automatic detection system |
| CN113440167A (en) * | 2021-06-28 | 2021-09-28 | 南京大学 | Lung ultrasonic signal feature identification method based on RF signal |
| CN113647983A (en) * | 2021-09-08 | 2021-11-16 | 南京云石医疗科技有限公司 | Ultrasonic color blood flow imaging control method |
| CN114081537A (en) * | 2021-11-12 | 2022-02-25 | 江西微润芯璟科技有限公司 | Skin tissue fluid positioning method and system based on ultrasonic detection |
| CN116188499A (en) * | 2023-05-04 | 2023-05-30 | 北京易优联科技有限公司 | Segmentation method for lung ultrasonic image |
| CN116269507A (en) * | 2023-05-23 | 2023-06-23 | 中日友好医院(中日友好临床医学研究所) | Method and device for classifying hyperuricemia and gouty nephropathy and electronic equipment |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102740762A (en) * | 2010-01-22 | 2012-10-17 | 不列颠哥伦比亚癌症分社 | Apparatus and methods for characterization of lung tissue by Raman spectroscopy |
| CN104021547A (en) * | 2014-05-17 | 2014-09-03 | 清华大学深圳研究生院 | Three dimensional matching method for lung CT |
| US20170086794A1 (en) * | 2015-09-29 | 2017-03-30 | General Electric Company | Method and system for enhanded visualization and selection of a representative ultrasound image by automatically detecting b lines and scoring images of an ultrasound scan |
| CN108805209A (en) * | 2018-06-14 | 2018-11-13 | 清华大学深圳研究生院 | A kind of Lung neoplasm screening method based on deep learning |
| US20190000425A1 (en) * | 2017-06-28 | 2019-01-03 | Tokitae Llc | Devices, systems, and methods for diagnosis of pulmonary conditions through detection of b-lines in lung sonography |
| WO2019150333A1 (en) * | 2018-02-05 | 2019-08-08 | Sensoriumlab Sp. Z O.O. | A method of measuring pleural effusion |
| CN110338843A (en) * | 2019-08-02 | 2019-10-18 | 无锡海斯凯尔医学技术有限公司 | Tissue-estimating method, apparatus, equipment and computer readable storage medium |
| CN110604593A (en) * | 2019-08-12 | 2019-12-24 | 清华大学 | Acoustic imaging calculation method and device for reconstructing parameters of human thorax |
| US20200046314A1 (en) * | 2018-08-07 | 2020-02-13 | Butterfly Network, Inc. | Methods and apparatuses for ultrasound imaging of lungs |
| CN111587089A (en) * | 2018-01-10 | 2020-08-25 | 皇家飞利浦有限公司 | Ultrasound system for detecting lung consolidation |
| CN111643118A (en) * | 2020-06-10 | 2020-09-11 | 北京核信锐视安全技术有限公司 | New coronary pneumonia risk prompting device, method and system based on ultrasonic imaging |
| WO2021003711A1 (en) * | 2019-07-10 | 2021-01-14 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging apparatus and method and device for detecting b-lines, and storage medium |
| US20210298715A1 (en) * | 2018-07-27 | 2021-09-30 | Koninklijke Philips N.V. | Devices, systems, and methods for lung pulse detection in ultrasound |
-
2021
- 2021-01-28 CN CN202110117779.5A patent/CN112819773B/en active Active
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102740762A (en) * | 2010-01-22 | 2012-10-17 | 不列颠哥伦比亚癌症分社 | Apparatus and methods for characterization of lung tissue by Raman spectroscopy |
| CN104021547A (en) * | 2014-05-17 | 2014-09-03 | 清华大学深圳研究生院 | Three dimensional matching method for lung CT |
| US20170086794A1 (en) * | 2015-09-29 | 2017-03-30 | General Electric Company | Method and system for enhanded visualization and selection of a representative ultrasound image by automatically detecting b lines and scoring images of an ultrasound scan |
| US20190000425A1 (en) * | 2017-06-28 | 2019-01-03 | Tokitae Llc | Devices, systems, and methods for diagnosis of pulmonary conditions through detection of b-lines in lung sonography |
| CN111587089A (en) * | 2018-01-10 | 2020-08-25 | 皇家飞利浦有限公司 | Ultrasound system for detecting lung consolidation |
| WO2019150333A1 (en) * | 2018-02-05 | 2019-08-08 | Sensoriumlab Sp. Z O.O. | A method of measuring pleural effusion |
| CN108805209A (en) * | 2018-06-14 | 2018-11-13 | 清华大学深圳研究生院 | A kind of Lung neoplasm screening method based on deep learning |
| US20210298715A1 (en) * | 2018-07-27 | 2021-09-30 | Koninklijke Philips N.V. | Devices, systems, and methods for lung pulse detection in ultrasound |
| US20200046314A1 (en) * | 2018-08-07 | 2020-02-13 | Butterfly Network, Inc. | Methods and apparatuses for ultrasound imaging of lungs |
| WO2021003711A1 (en) * | 2019-07-10 | 2021-01-14 | 深圳迈瑞生物医疗电子股份有限公司 | Ultrasonic imaging apparatus and method and device for detecting b-lines, and storage medium |
| CN110338843A (en) * | 2019-08-02 | 2019-10-18 | 无锡海斯凯尔医学技术有限公司 | Tissue-estimating method, apparatus, equipment and computer readable storage medium |
| CN110604593A (en) * | 2019-08-12 | 2019-12-24 | 清华大学 | Acoustic imaging calculation method and device for reconstructing parameters of human thorax |
| CN111643118A (en) * | 2020-06-10 | 2020-09-11 | 北京核信锐视安全技术有限公司 | New coronary pneumonia risk prompting device, method and system based on ultrasonic imaging |
Non-Patent Citations (3)
| Title |
|---|
| CARRER L,等: "Automatic pleural line extraction and COVID-19 scoring from lung ultrasound data", 《IEEE TRANSACTIONS ON ULTRASONICS, FERROELECTRICS, AND FREQUENCY CONTROL,》 * |
| DEMI L,等: "Determination of a potential quantitative measure of the state of the lung using lung ultrasound spectroscopy", 《SCIENTIFIC REPORTS》 * |
| 孙利芳，等: "新生儿重症监护患儿机械通气撤机失败的", 《中国中西医结合影像学杂志》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113440167A (en) * | 2021-06-28 | 2021-09-28 | 南京大学 | Lung ultrasonic signal feature identification method based on RF signal |
| CN113440167B (en) * | 2021-06-28 | 2022-06-10 | 南京大学 | Lung ultrasonic signal feature identification method based on RF signal |
| CN113267521A (en) * | 2021-07-20 | 2021-08-17 | 杭州盾源聚芯半导体科技有限公司 | Silicon product surface processing damage depth detection method and automatic detection system |
| CN113267521B (en) * | 2021-07-20 | 2021-11-05 | 杭州盾源聚芯半导体科技有限公司 | Silicon product surface processing damage depth detection method and automatic detection system |
| CN113647983A (en) * | 2021-09-08 | 2021-11-16 | 南京云石医疗科技有限公司 | Ultrasonic color blood flow imaging control method |
| CN114081537A (en) * | 2021-11-12 | 2022-02-25 | 江西微润芯璟科技有限公司 | Skin tissue fluid positioning method and system based on ultrasonic detection |
| CN114081537B (en) * | 2021-11-12 | 2023-08-25 | 江西中医药大学 | Skin tissue fluid positioning method and system based on ultrasonic detection |
| CN116188499A (en) * | 2023-05-04 | 2023-05-30 | 北京易优联科技有限公司 | Segmentation method for lung ultrasonic image |
| CN116269507A (en) * | 2023-05-23 | 2023-06-23 | 中日友好医院(中日友好临床医学研究所) | Method and device for classifying hyperuricemia and gouty nephropathy and electronic equipment |
| CN116269507B (en) * | 2023-05-23 | 2023-07-25 | 中日友好医院(中日友好临床医学研究所) | Method and device for classifying hyperuricemia and gouty nephropathy and electronic equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN112819773B (en) | 2022-05-17 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112819773B (en) | Ultrasonic image quantitative evaluation system | |
| US7689016B2 (en) | Automatic detection of critical dermoscopy features for malignant melanoma diagnosis | |
| JP5123954B2 (en) | Identification and analysis of lesions in medical images | |
| US20040170308A1 (en) | Method for automated window-level settings for magnetic resonance images | |
| US20080130964A1 (en) | Methods and Apparatus for Analysing Ultrasound Images | |
| Padmapriya et al. | Edge based image segmentation technique for detection and estimation of the bladder wall thickness | |
| JPH11312234A (en) | Image processing method including segmentation processing of multidimensional image and medical video apparatus | |
| GB2490477A (en) | Processing ultrasound images to determine diameter of vascular tissue lumen and method of segmenting an image of a tubular structure comprising a hollow core | |
| Anuradha et al. | Detection of oral tumor based on marker-controlled watershed algorithm | |
| Jeevakala et al. | A novel segmentation of cochlear nerve using region growing algorithm | |
| Srivatava et al. | Non-linear quality evaluation index for mammograms | |
| Malathi et al. | Statistical Measurement of Ultrasound Placenta Images Complicated by Gestational Diabetes Mellitus Using Segmentation Approach. | |
| IT202000009667A1 (en) | DEVICE AND METHOD FOR THE DIAGNOSIS OF A COVID-19 TYPE PNEUMONIA BY ANALYSIS OF ULTRASOUND IMAGES | |
| Naik et al. | Effect of despeckling filters on the segmentation of ultrasound common carotid artery images | |
| Santos et al. | Detection of pathologic liver using ultrasound images | |
| KR101046510B1 (en) | Ventricular Automated Segmentation Using Edge Classification and Zone Expansion Techniques | |
| Aditya et al. | Fetal weight and gender estimation using computer based ultrasound images analysis | |
| CN113440167B (en) | Lung ultrasonic signal feature identification method based on RF signal | |
| Georgieva et al. | Ultrasound image processing for improving diagnose of renal diseases | |
| WO2022234318A1 (en) | Device and method for the diagnosis of a pneumonia by frequency analysis of ultrasound signals | |
| Wulandari et al. | Automatic lung cancer detection using color histogram calculation | |
| MacGillivray et al. | A reliability study of fractal analysis of the skeletonised vascular network using the" box-counting" technique | |
| CN112807024B (en) | Ultrasonic image quantitative evaluation system | |
| Molinari et al. | Role of fuzzy pre-classifier for high performance LI/MA segmentation in B-mode longitudinal carotid ultrasound images | |
| Zayanthi et al. | Carotid artery boundary extraction using segmentation techniques: a comparative study |
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 |