CN113520465B - Automatic measuring method for maximum depth of amniotic fluid - Google Patents
Automatic measuring method for maximum depth of amniotic fluid Download PDFInfo
- Publication number
- CN113520465B CN113520465B CN202110864327.3A CN202110864327A CN113520465B CN 113520465 B CN113520465 B CN 113520465B CN 202110864327 A CN202110864327 A CN 202110864327A CN 113520465 B CN113520465 B CN 113520465B
- Authority
- CN
- China
- Prior art keywords
- amniotic fluid
- depth
- maximum
- vertical direction
- pixel
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
- 210000004381 amniotic fluid Anatomy 0.000 title claims abstract description 179
- 238000000034 method Methods 0.000 title claims description 11
- 238000005259 measurement Methods 0.000 claims abstract description 61
- 238000000691 measurement method Methods 0.000 claims abstract description 7
- 230000011218 segmentation Effects 0.000 claims description 11
- 238000005516 engineering process Methods 0.000 claims description 4
- 238000012545 processing Methods 0.000 claims description 4
- 230000007797 corrosion Effects 0.000 claims description 3
- 238000005260 corrosion Methods 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 230000008030 elimination Effects 0.000 claims description 2
- 238000003379 elimination reaction Methods 0.000 claims description 2
- 239000012141 concentrate Substances 0.000 abstract description 3
- 230000003993 interaction Effects 0.000 abstract description 3
- 238000002604 ultrasonography Methods 0.000 abstract description 2
- 210000003754 fetus Anatomy 0.000 description 3
- 210000002826 placenta Anatomy 0.000 description 3
- 210000004291 uterus Anatomy 0.000 description 3
- 230000001605 fetal effect Effects 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 239000000523 sample Substances 0.000 description 2
- 210000003954 umbilical cord Anatomy 0.000 description 2
- 208000019914 Mental Fatigue Diseases 0.000 description 1
- 241001494479 Pecora Species 0.000 description 1
- 210000001015 abdomen Anatomy 0.000 description 1
- 230000009471 action Effects 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000002372 labelling Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012549 training Methods 0.000 description 1
Classifications
-
- 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
- A61B8/08—Detecting organic movements or changes, e.g. tumours, cysts, swellings
- A61B8/0866—Detecting organic movements or changes, e.g. tumours, cysts, swellings involving foetal diagnosis; pre-natal or peri-natal diagnosis of the baby
-
- 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
-
- 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
- A61B8/5269—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving detection or reduction of artifacts
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/20—Image enhancement or restoration using local operators
- G06T5/30—Erosion or dilatation, e.g. thinning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T5/00—Image enhancement or restoration
- G06T5/70—Denoising; Smoothing
-
- 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
- G06T7/11—Region-based segmentation
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20081—Training; Learning
-
- 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
- G06T2207/20—Special algorithmic details
- G06T2207/20084—Artificial neural networks [ANN]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A90/00—Technologies having an indirect contribution to adaptation to climate change
- Y02A90/30—Assessment of water resources
Landscapes
- Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- General Physics & Mathematics (AREA)
- Biophysics (AREA)
- Molecular Biology (AREA)
- Radiology & Medical Imaging (AREA)
- Medical Informatics (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Heart & Thoracic Surgery (AREA)
- Pathology (AREA)
- Surgery (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Artificial Intelligence (AREA)
- Computational Linguistics (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- Gynecology & Obstetrics (AREA)
- Pregnancy & Childbirth (AREA)
- Vascular Medicine (AREA)
- Quality & Reliability (AREA)
- Image Processing (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention discloses an automatic measurement method of the maximum amniotic fluid depth, which sequentially carries out amniotic fluid depth measurement on a current frame image scanned by ultrasound, judges whether the amniotic fluid depth of the current frame image is larger than the maximum amniotic fluid depth, if so, updates the value of the maximum amniotic fluid depth into the value of the amniotic fluid depth of the current frame image, and records the image corresponding to the maximum amniotic fluid depth, namely, records the current frame image; and outputting the maximum amniotic fluid depth and an image corresponding to the maximum amniotic fluid depth until the ultrasonic scanning is finished, wherein the image corresponding to the maximum amniotic fluid depth is the optimal section. The invention can automatically identify the optimal tangential plane and automatically measure the maximum depth of amniotic fluid, thereby freeing doctors from complex ultrasonic equipment interaction, enabling doctors to concentrate more on the accuracy and rapidity of the scanned part, and improving the overall efficiency and measurement accuracy of the maximum depth measurement of amniotic fluid.
Description
Technical Field
The invention relates to the technical field of image processing, in particular to an automatic measurement method for the maximum depth of amniotic fluid.
Background
Prenatal ultrasound amniotic fluid measurement is an important part of monitoring whether a fetus grows healthily in the uterus, which provides a non-invasive way to assess the condition of amniotic fluid. The current measurement method is to measure the maximum depth of amniotic fluid, i.e. the maximum vertical depth of a amniotic fluid pool. The sheep pool refers to a black area containing only amniotic fluid and not containing a fetus or umbilical cord. Vertical depth refers to the extension from the anterior wall of the uterus or the margin of the placenta down to the next solid area, which may be the fetal, placenta or the posterior wall of the uterus.
At present, the maximum amniotic fluid depth is measured by a doctor manually, and the process is as follows:
firstly, a doctor holds an ultrasonic probe to scan over the pregnant woman fetal position continuously, and a scanning angle suitable for observation and measurement is found.
Then, one hand is stabilized at the optimal angle, the other hand controls the ultrasonic equipment, and the ultrasonic scanning picture is frozen to obtain the optimal section.
Finally, the ultrasonic device is operated, and the measuring line of the maximum vertical depth in the optimal tangential plane, namely the measuring line of the maximum amniotic fluid depth, is drawn, wherein the measuring line of the maximum amniotic fluid depth in the optimal tangential plane is shown in figure 2.
The process is very time-consuming and complex, one hand of a doctor needs to operate the ultrasonic scanning probe, the abdomen of the pregnant woman is carefully searched for the optimal scanning section, the attention is highly concentrated during scanning, and the optimal scanning section which can flash is searched for; the other hand also controls the ultrasonic input device to freeze the optimal section and manually measure the section; the working strength is high, a doctor is required to have better medical experience and action coordination, and various errors, such as the error of judging the optimal section and the measurement error of the maximum amniotic fluid depth, are inevitably introduced.
Disclosure of Invention
In order to overcome the defects in the prior art, the invention provides the automatic measuring method for the maximum depth of the amniotic fluid, which can automatically identify the best and automatically measure the maximum depth of the amniotic fluid, so that doctors are liberated from complex ultrasonic equipment interaction, the doctors can concentrate more on the accuracy and the rapidity of the scanned part, and the overall efficiency and the measuring accuracy of the maximum depth measurement of the amniotic fluid are improved.
In order to achieve the above purpose, the present invention adopts the following technical scheme, including:
an automatic measurement method for the maximum depth of amniotic fluid comprises the following steps:
s1, defining the maximum depth of amniotic fluid as d max ，d max Initializing to 0;
s2, performing amniotic fluid depth measurement on the current frame image of ultrasonic scanning, namely the t frame image, to obtain the amniotic fluid depth d of the current frame image, namely the t frame image t ；
Judging amniotic fluid depth d of t-th frame image t Whether or not it is greater than the maximum depth d of amniotic fluid max If d t Greater than d max For the maximum depth d of amniotic fluid max Updating to obtain the maximum depth d of amniotic fluid max Is updated to the amniotic fluid depth d of the t-th frame image t Record the maximum depth d of amniotic fluid max Recording the t frame image of the corresponding image; if d t Less than or equal to d max The maximum depth d of amniotic fluid is not max Updating;
s3, according to the mode of the step S2, sequentially measuring the amniotic fluid depth of the next frame of image scanned by ultrasonic, and judging whether to perform maximum depth d on the amniotic fluid according to the amniotic fluid depth of the next frame of image max Updating until the ultrasonic scanning is finished, and outputting the maximum depth d of amniotic fluid max The maximum depth d of amniotic fluid max Corresponding image, the maximum depth d of amniotic fluid max The corresponding image is the best section.
In step S2, the amniotic fluid depth measurement is performed on the current frame image of the ultrasonic scanning, namely the t frame image, to obtain the amniotic fluid depth d of the t frame image t The method comprises the steps of carrying out a first treatment on the surface of the The specific modes are as follows:
s21, recognizing an ultrasonic scanned t frame image, and recognizing an amniotic fluid region; wherein, the pixel value of the pixel point on the amniotic fluid area, namely the amniotic fluid pixel point, is 1, and the pixel value of the pixel point on the non-amniotic fluid area, namely the non-amniotic fluid pixel point, is 0;
s22, accumulating pixel values of the pixel points in the same vertical direction in the amniotic fluid region to obtain total pixel values in all vertical directions respectively;
the x-axis direction in the image coordinate system is the horizontal direction; the vertical direction refers to a direction perpendicular to the x-axis; the pixel points in the same vertical direction are the pixel points corresponding to the same abscissa; the total pixel value in each vertical direction is the total pixel value of each abscissa;
s23, sequentially judging each vertical direction according to the sequence from the large pixel total value to the small pixel total value in the vertical direction, and judging whether the direction is the measurement direction of the maximum amniotic fluid depth or not until the measurement direction and the measurement line of the maximum amniotic fluid depth are found out; wherein the length of the measuring line of the maximum amniotic fluid depth is the amniotic fluid depth d of the t-th frame image t ；
The determination mode for a certain vertical direction is as follows:
s231, respectively finding out a pixel point with a first pixel value of 1 and a pixel point with a last pixel value of 1 from top to bottom in the vertical direction, wherein the pixel point with the first pixel value of 1 is a measurement starting point in the vertical direction, the pixel point with the last pixel value of 1 is a measurement end point in the vertical direction, and the measurement line in the vertical direction can be obtained according to the measurement starting point and the measurement end point in the vertical direction;
s232, calculating the distance between the measurement end point in the vertical direction and the lower boundary of the ultrasonic scanning area, if the distance is smaller than a set distance threshold t1, the measurement direction of the maximum amniotic fluid depth in the vertical direction is not the measurement direction of the maximum amniotic fluid depth, and ending the judgment in the vertical direction to directly judge the next vertical direction; if the distance is not smaller than the set distance threshold t1, judging the next step;
s233, judging whether a pixel point with a pixel value of 0 exists on the vertical measuring line from the measuring starting point to the measuring end point in the vertical direction, if the pixel point with the pixel value of 0 exists on the vertical measuring line, the vertical measuring direction is not the measuring direction of the maximum amniotic fluid depth, and ending the judgment in the vertical direction, and directly judging the next vertical direction; if no pixel point with the pixel value of 0 exists on the measuring line in the vertical direction, judging in the next step;
s234, drawing a rectangular frame by taking the vertical measuring line as a central line, wherein the length of the rectangular frame is the length of the vertical measuring line, the width of the rectangular frame is W, counting the pixel values of the pixel points in the rectangular frame, and if the number of the pixel points with the pixel value of 0 in the rectangular frame exceeds a set number threshold t2, judging the vertical direction not to be the measuring direction of the maximum amniotic fluid depth, ending the judgment of the vertical direction, and directly judging the next vertical direction; if the number of the pixel points with the pixel value of 0 in the rectangular frame does not exceed the set number threshold t2, the vertical direction is the measurement direction of the maximum amniotic fluid depth, and the measurement line in the vertical direction is the measurement line of the maximum amniotic fluid depth; wherein the length of the measuring line of the maximum amniotic fluid depth is the amniotic fluid depth d of the t-th frame image t 。
In step S21, recognizing the t frame image of ultrasonic scanning, and recognizing the amniotic fluid region; the specific modes are as follows:
s211, classifying each pixel point of the t frame image by adopting a semantic segmentation network, wherein the pixel points are divided into amniotic fluid pixel points and non-amniotic fluid pixel points, the pixel value of the amniotic fluid pixel points is 1, and the pixel value of the non-amniotic fluid pixel points is 0; after semantic segmentation, a plurality of discrete amniotic fluid areas are obtained;
s212, performing noise point elimination and boundary smoothing treatment on the plurality of discrete amniotic fluid areas by adopting an image processing technology of corrosion expansion;
s213, searching the connected domain of the plurality of discrete amniotic fluid regions, wherein the largest searched connected domain is the finally identified amniotic fluid region.
The invention has the advantages that:
(1) The invention can automatically identify the optimal section and automatically measure the maximum depth of amniotic fluid, thereby freeing doctors from complex ultrasonic equipment interaction, enabling doctors to concentrate more on the accuracy and rapidity of the scanned part, reducing the working strength of ultrasonic scanning and improving the overall efficiency of the maximum depth measurement of amniotic fluid.
(2) The automatic identification of the optimal section and the automatic measurement of the maximum depth of the amniotic fluid can greatly reduce errors generated in manual operation, avoid the phenomenon of error increase caused by long-time work and mental fatigue, and improve the measurement precision of the maximum depth of the amniotic fluid.
Drawings
Fig. 1 is a flowchart of an automatic measuring method of the maximum amniotic fluid depth according to the present invention.
Fig. 2 is a schematic view of a measurement line of the maximum amniotic fluid depth in the optimal section.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
As shown in fig. 1, an automatic measurement method for the maximum depth of amniotic fluid comprises the following steps:
s1, defining the maximum depth of amniotic fluid as d max ，d max Initializing to 0;
s2, starting from the first frame image of ultrasonic scanning, performing amniotic fluid depth measurement on the current frame image of ultrasonic scanning, namely the t frame image, to obtain amniotic fluid depth d of the current frame image, namely the t frame image t ；
Judging amniotic fluid depth d of t-th frame image t Whether or not it is greater than the maximum depth d of amniotic fluid max If d t Greater than d max For the maximum depth d of amniotic fluid max Updating to obtain the maximum depth d of amniotic fluid max Is updated to the amniotic fluid depth d of the t-th frame image t Record the maximum depth d of amniotic fluid max Recording the t frame image of the corresponding image; if d t Less than or equal to d max The maximum depth d of amniotic fluid is not max Updating;
s3, according to the mode of the step S2, sequentially measuring the amniotic fluid depth of the next frame of image of the ultrasonic scanning, and judging according to the amniotic fluid depth of the next frame of imageWhether to make the amniotic fluid have the maximum depth d max Updating until the ultrasonic scanning is finished, and outputting the maximum depth d of amniotic fluid max The maximum depth d of amniotic fluid max Corresponding image, the maximum depth d of amniotic fluid max The corresponding image is the best section.
In step S2, the amniotic fluid depth measurement is performed on the current frame image of the ultrasonic scanning, namely the t frame image, to obtain the amniotic fluid depth d of the t frame image t The method comprises the steps of carrying out a first treatment on the surface of the The specific modes are as follows:
s21, recognizing an ultrasonic scanned t frame image, and recognizing an amniotic fluid region; the pixel value of the pixel point on the amniotic fluid area, namely the amniotic fluid pixel point, is 1, and the pixel value of the pixel point on the non-amniotic fluid area, namely the non-amniotic fluid pixel point, is 0.
The method for identifying the amniotic fluid region in step S21 is specifically as follows:
s211, classifying each pixel point of the t frame image by adopting a semantic segmentation network, wherein the pixel points are divided into amniotic fluid pixel points and non-amniotic fluid pixel points, the pixel value of the amniotic fluid pixel points is 1, and the pixel value of the non-amniotic fluid pixel points is 0; because the placenta is not only amniotic fluid, but also a fetus and an umbilical cord, and because of factors such as amniotic fluid turbidity, a plurality of discrete amniotic fluid areas are obtained after semantic segmentation;
the semantic segmentation network refers to: a depth network which can automatically divide and identify the content in the image is realized through the depth neural network; the semantic segmentation technology can realize classification of each pixel point in the image;
in the embodiment, a Unet network is adopted to identify the image, and the amniotic fluid region is identified; the Unet network is obtained by training an ultrasonic image with the polygonal labeling information of amniotic fluid.
S212, eliminating noise points of a smaller discrete amniotic fluid area and smoothing the boundary of a larger discrete amniotic fluid area by adopting image processing technologies such as corrosion and expansion;
in this embodiment, the segmentation map, which is an image after semantic segmentation, is corroded and expanded by using cv2.erode and cv2.dialite functions in opencv.
S213, searching for the connected domain of the plurality of discrete amniotic fluid regions, wherein the largest searched connected domain is the finally identified amniotic fluid region;
in this embodiment, all connected domains on the segmentation map are found by using the cv2.findcontours function in opencv, and the area of each connected domain is calculated according to cv2.contourarea, so as to find out the largest connected domain, i.e. amniotic fluid region.
S22, accumulating pixel values of the pixel points in the same vertical direction in the amniotic fluid region to obtain total pixel values in all vertical directions respectively;
the x-axis direction in the two-dimensional image coordinate system is the horizontal direction; the vertical direction refers to a direction perpendicular to the x-axis; in this embodiment, the pixel points in the same vertical direction refer to the pixel points corresponding to the same abscissa; the total pixel value in each vertical direction is the total pixel value of each abscissa.
S23, sequentially judging each vertical direction according to the sequence from the large pixel total value to the small pixel total value in the vertical direction, and judging whether the direction is the measurement direction of the maximum amniotic fluid depth or not until the measurement direction and the measurement line of the maximum amniotic fluid depth are found out; wherein the length of the measuring line of the maximum amniotic fluid depth is the amniotic fluid depth d of the t-th frame image t 。
The determination mode for a certain vertical direction is as follows:
s231, respectively finding out a pixel point with a first pixel value of 1 and a pixel point with a last pixel value of 1 from top to bottom in the vertical direction, wherein the pixel point with the first pixel value of 1 is a measurement starting point in the vertical direction, the pixel point with the last pixel value of 1 is a measurement end point in the vertical direction, and the measurement line in the vertical direction can be obtained according to the measurement starting point and the measurement end point in the vertical direction;
s232, calculating the distance between the measurement end point in the vertical direction and the lower boundary of the ultrasonic scanning area, if the distance is smaller than a set distance threshold t1, the measurement line in the vertical direction is not the measurement direction of the maximum amniotic fluid depth, the measurement line in the vertical direction is not the measurement line of the maximum amniotic fluid depth, the judgment in the vertical direction is ended, and the judgment in the next vertical direction is directly carried out; if the distance is not smaller than the set distance threshold t1, judging the next step; in this embodiment, the distance threshold t1 is 5 pixels, i.e. 5 pixels.
S233, judging whether a pixel point with a pixel value of 0 exists on the vertical measuring line from the measuring starting point to the measuring end point in the vertical direction, namely judging whether the vertical measuring line is segmented, if the pixel point with the pixel value of 0 exists on the vertical measuring line, namely the vertical measuring line is segmented, the vertical measuring line is not the measuring direction of the maximum amniotic fluid depth, the vertical measuring line is not the measuring line of the maximum amniotic fluid depth, and the judgment in the vertical direction is ended, so that the judgment in the next vertical direction is directly carried out; if no pixel point with the pixel value of 0 exists on the measuring line in the vertical direction, the next step is judged.
S234, drawing a rectangular frame by taking the vertical measuring line as a central line, wherein the length of the rectangular frame is the length of the vertical measuring line, the width of the rectangular frame is W, counting the pixel values of the pixel points in the rectangular frame, if the number of the pixel points with the pixel value of 0 in the rectangular frame exceeds a set number threshold t2, the vertical measuring line is not the measuring line of the maximum amniotic fluid depth, and ending the judgment of the vertical direction to directly judge the next vertical direction; if the number of the pixel points with the pixel value of 0 in the rectangular frame does not exceed the set number threshold t2, the vertical direction is the measurement direction of the maximum amniotic fluid depth, and the measurement line in the vertical direction is the measurement line of the maximum amniotic fluid depth; wherein the length of the measuring line of the maximum amniotic fluid depth is the amniotic fluid depth d of the t-th frame image t The method comprises the steps of carrying out a first treatment on the surface of the The width W of the rectangular frame takes a value of 5pixel; the value of the quantity threshold t2 is 10pixel.
The above embodiments are merely preferred embodiments of the present invention and are not intended to limit the present invention, and any modifications, equivalent substitutions and improvements made within the spirit and principles of the present invention should be included in the scope of the present invention.
Claims (2)
1. An automatic measurement method for the maximum depth of amniotic fluid is characterized by comprising the following steps:
s1, defining the maximum depth of amniotic fluid as d max ，d max Initializing to 0;
s2, performing amniotic fluid depth measurement on the current frame image of ultrasonic scanning, namely the t frame image, to obtain the amniotic fluid depth d of the current frame image, namely the t frame image t ；
Judging amniotic fluid depth d of t-th frame image t Whether or not it is greater than the maximum depth d of amniotic fluid max If d t Greater than d max For the maximum depth d of amniotic fluid max Updating to obtain the maximum depth d of amniotic fluid max Is updated to the amniotic fluid depth d of the t-th frame image t Record the maximum depth d of amniotic fluid max Recording the t frame image of the corresponding image; if d t Less than or equal to d max The maximum depth d of amniotic fluid is not max Updating;
s3, according to the mode of the step S2, sequentially measuring the amniotic fluid depth of the next frame of image scanned by ultrasonic, and judging whether to perform maximum depth d on the amniotic fluid according to the amniotic fluid depth of the next frame of image max Updating until the ultrasonic scanning is finished, and outputting the maximum depth d of amniotic fluid max The maximum depth d of amniotic fluid max Corresponding image, the maximum depth d of amniotic fluid max The corresponding image is the optimal section;
in step S2, the amniotic fluid depth measurement is performed on the current frame image of the ultrasonic scanning, namely the t frame image, to obtain the amniotic fluid depth d of the t frame image t The method comprises the steps of carrying out a first treatment on the surface of the The specific modes are as follows:
s21, recognizing an ultrasonic scanned t frame image, and recognizing an amniotic fluid region; wherein, the pixel value of the pixel point on the amniotic fluid area, namely the amniotic fluid pixel point, is 1, and the pixel value of the pixel point on the non-amniotic fluid area, namely the non-amniotic fluid pixel point, is 0;
s22, accumulating pixel values of the pixel points in the same vertical direction in the amniotic fluid region to obtain total pixel values in all vertical directions respectively;
the x-axis direction in the image coordinate system is the horizontal direction; the vertical direction refers to a direction perpendicular to the x-axis; the pixel points in the same vertical direction are the pixel points corresponding to the same abscissa; the total pixel value in each vertical direction is the total pixel value of each abscissa;
s23, sequentially judging each vertical direction according to the sequence from the large pixel total value to the small pixel total value in the vertical direction, and judging whether the direction is the measurement direction of the maximum amniotic fluid depth or not until the measurement direction and the measurement line of the maximum amniotic fluid depth are found out; wherein the length of the measuring line of the maximum amniotic fluid depth is the amniotic fluid depth d of the t-th frame image t ；
The determination mode for a certain vertical direction is as follows:
s231, respectively finding out a pixel point with a first pixel value of 1 and a pixel point with a last pixel value of 1 from top to bottom in the vertical direction, wherein the pixel point with the first pixel value of 1 is a measurement starting point in the vertical direction, the pixel point with the last pixel value of 1 is a measurement end point in the vertical direction, and the measurement line in the vertical direction can be obtained according to the measurement starting point and the measurement end point in the vertical direction;
s232, calculating the distance between the measurement end point in the vertical direction and the lower boundary of the ultrasonic scanning area, if the distance is smaller than a set distance threshold t1, the measurement direction of the maximum amniotic fluid depth in the vertical direction is not the measurement direction of the maximum amniotic fluid depth, and ending the judgment in the vertical direction to directly judge the next vertical direction; if the distance is not smaller than the set distance threshold t1, judging the next step;
s233, judging whether a pixel point with a pixel value of 0 exists on the vertical measuring line from the measuring starting point to the measuring end point in the vertical direction, if the pixel point with the pixel value of 0 exists on the vertical measuring line, the vertical measuring direction is not the measuring direction of the maximum amniotic fluid depth, and ending the judgment in the vertical direction, and directly judging the next vertical direction; if no pixel point with the pixel value of 0 exists on the measuring line in the vertical direction, judging in the next step;
s234, drawing a rectangular frame by taking the vertical measuring line as a central line, wherein the length of the rectangular frame is the length of the vertical measuring line, the width of the rectangular frame is W, counting the pixel values of the pixel points in the rectangular frame, and if the number of the pixel points with the pixel value of 0 in the rectangular frame exceeds a set number threshold t2, judging the vertical direction not to be the measuring direction of the maximum amniotic fluid depth, ending the judgment of the vertical direction, and directly judging the next vertical direction; if the number of the pixel points with the pixel value of 0 in the rectangular frame does not exceed the set number threshold t2, the vertical direction is the measurement direction of the maximum amniotic fluid depth, and the measurement line in the vertical direction is the measurement line of the maximum amniotic fluid depth; wherein the length of the measuring line of the maximum amniotic fluid depth is the amniotic fluid depth d of the t-th frame image t 。
2. The automatic measurement method of the maximum amniotic fluid depth according to claim 1, wherein in step S21, the t-th frame image of the ultrasonic scanning is identified, and the amniotic fluid region is identified; the specific modes are as follows:
s211, classifying each pixel point of the t frame image by adopting a semantic segmentation network, wherein the pixel points are divided into amniotic fluid pixel points and non-amniotic fluid pixel points, the pixel value of the amniotic fluid pixel points is 1, and the pixel value of the non-amniotic fluid pixel points is 0; after semantic segmentation, a plurality of discrete amniotic fluid areas are obtained;
s212, performing noise point elimination and boundary smoothing treatment on the plurality of discrete amniotic fluid areas by adopting an image processing technology of corrosion expansion;
s213, searching the connected domain of the plurality of discrete amniotic fluid regions, wherein the largest searched connected domain is the finally identified amniotic fluid region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110864327.3A CN113520465B (en) | 2021-07-29 | 2021-07-29 | Automatic measuring method for maximum depth of amniotic fluid |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110864327.3A CN113520465B (en) | 2021-07-29 | 2021-07-29 | Automatic measuring method for maximum depth of amniotic fluid |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113520465A CN113520465A (en) | 2021-10-22 |
| CN113520465B true CN113520465B (en) | 2023-11-24 |
Family
ID=78089650
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110864327.3A Active CN113520465B (en) | 2021-07-29 | 2021-07-29 | Automatic measuring method for maximum depth of amniotic fluid |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113520465B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1986006606A1 (en) * | 1985-05-08 | 1986-11-20 | International Biomedics, Inc. | Apparatus for non-invasively measuring the volume of urine in a human bladder |
| US6480732B1 (en) * | 1999-07-01 | 2002-11-12 | Kabushiki Kaisha Toshiba | Medical image processing device for producing a composite image of the three-dimensional images |
| CN102949206A (en) * | 2011-08-26 | 2013-03-06 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for three-dimensional ultrasound imaging |
| CN104546000A (en) * | 2015-01-05 | 2015-04-29 | 深圳市大深生物医学工程转化研究院 | Shape feature-based ultrasonic image bladder volume measuring method and device |
| JP2016083192A (en) * | 2014-10-27 | 2016-05-19 | 日立アロカメディカル株式会社 | Ultrasonic diagnostic equipment |
| CN107518920A (en) * | 2017-09-30 | 2017-12-29 | 深圳开立生物医疗科技股份有限公司 | Ultrasonic image processing method and device, supersonic diagnostic appts and storage medium |
| KR20210002197A (en) * | 2019-06-27 | 2021-01-07 | 고려대학교 산학협력단 | Method for automatic measurement of amniotic fluid volume based on artificial intelligence model |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6676605B2 (en) * | 2002-06-07 | 2004-01-13 | Diagnostic Ultrasound | Bladder wall thickness measurement system and methods |
| US8131098B2 (en) * | 2007-07-06 | 2012-03-06 | Panasonic Corporation | Image processing device, image processing method, image processing system, program, storage medium, and integrated circuit |
| TWI502545B (en) * | 2013-06-25 | 2015-10-01 | Method of storing a content of a three-dimensional image |
-
2021
- 2021-07-29 CN CN202110864327.3A patent/CN113520465B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO1986006606A1 (en) * | 1985-05-08 | 1986-11-20 | International Biomedics, Inc. | Apparatus for non-invasively measuring the volume of urine in a human bladder |
| US6480732B1 (en) * | 1999-07-01 | 2002-11-12 | Kabushiki Kaisha Toshiba | Medical image processing device for producing a composite image of the three-dimensional images |
| CN102949206A (en) * | 2011-08-26 | 2013-03-06 | 深圳迈瑞生物医疗电子股份有限公司 | Method and device for three-dimensional ultrasound imaging |
| JP2016083192A (en) * | 2014-10-27 | 2016-05-19 | 日立アロカメディカル株式会社 | Ultrasonic diagnostic equipment |
| CN104546000A (en) * | 2015-01-05 | 2015-04-29 | 深圳市大深生物医学工程转化研究院 | Shape feature-based ultrasonic image bladder volume measuring method and device |
| CN107518920A (en) * | 2017-09-30 | 2017-12-29 | 深圳开立生物医疗科技股份有限公司 | Ultrasonic image processing method and device, supersonic diagnostic appts and storage medium |
| KR20210002197A (en) * | 2019-06-27 | 2021-01-07 | 고려대학교 산학협력단 | Method for automatic measurement of amniotic fluid volume based on artificial intelligence model |
Non-Patent Citations (2)
| Title |
|---|
| Deep Learning in Medical Ultrasound Analysis: A Review;Shengfeng Liu，等;《Engineering》;第5卷(第2期);全文 * |
| 王明师.《Python编程实践》.北京航空航天大学出版社,2021,69. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN113520465A (en) | 2021-10-22 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| WO2022141882A1 (en) | Lesion recognition model construction apparatus and system based on historical pathological information | |
| CN108186051B (en) | Image processing method and system for automatically measuring double-apical-diameter length of fetus from ultrasonic image | |
| CN110448335B (en) | Method and device for fully automatically measuring head circumference of fetus based on ultrasonic image | |
| TWI501754B (en) | An image recognition system and method of | |
| US8831311B2 (en) | Methods and systems for automated soft tissue segmentation, circumference estimation and plane guidance in fetal abdominal ultrasound images | |
| US20110158490A1 (en) | Method and apparatus for extracting and measuring object of interest from an image | |
| KR101926015B1 (en) | Apparatus and method processing image | |
| CN111374708B (en) | Fetal heart rate detection method, ultrasonic imaging device and storage medium | |
| CN111047608A (en) | Distance-AttU-Net-based end-to-end mammary ultrasound image segmentation method | |
| CN110163907B (en) | Method and device for measuring thickness of transparent layer of fetal neck and storage medium | |
| WO2020215485A1 (en) | Fetal growth parameter measurement method, system, and ultrasound device | |
| CN109948622B (en) | Method and device for detecting head and neck body aneurysm and computer readable storage medium | |
| TWI574671B (en) | Analysis method for breast image and electronic apparatus thereof | |
| CN113520465B (en) | Automatic measuring method for maximum depth of amniotic fluid | |
| CN110580697B (en) | Video image processing method and system for measuring thickness of fetal nape transparency from ultrasonic video image | |
| CN114399493A (en) | Automatic detection and display method for ultrasonic brain abnormal area | |
| CN108364289B (en) | IVOCT image vulnerable plaque automatic detection method | |
| CN113570594A (en) | Method and device for monitoring target tissue in ultrasonic image and storage medium | |
| CN112734743A (en) | Automatic measuring method and device for fetal head circumference | |
| CN109636843B (en) | Amniotic fluid index measurement method, ultrasonic imaging equipment and storage medium | |
| Mori et al. | Analysis of endometrium form by using LBP for female infertility | |
| Khan et al. | Automatic measurement of biparietal diameter with a portable ultrasound device | |
| CN115813433A (en) | Follicle measuring method based on two-dimensional ultrasonic imaging and ultrasonic imaging system | |
| CN110916724A (en) | B-ultrasonic image fetal head circumference detection method based on closed loop shortest path | |
| CN111476790A (en) | Method and device for enhancing display of puncture needle in ultrasonic puncture |
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 |