CN113995435A - Ultrasound image-based measurement device, ultrasound image-based measurement method, ultrasound image-based measurement medium, and electronic device - Google Patents
Ultrasound image-based measurement device, ultrasound image-based measurement method, ultrasound image-based measurement medium, and electronic device Download PDFInfo
- Publication number
- CN113995435A CN113995435A CN202111242249.XA CN202111242249A CN113995435A CN 113995435 A CN113995435 A CN 113995435A CN 202111242249 A CN202111242249 A CN 202111242249A CN 113995435 A CN113995435 A CN 113995435A
- Authority
- CN
- China
- Prior art keywords
- scale
- target
- target object
- key points
- scale key
- 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.)
- Withdrawn
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B8/00—Diagnosis using ultrasonic, sonic or infrasonic waves
- A61B8/44—Constructional features of the ultrasonic, sonic or infrasonic diagnostic device
- A61B8/4411—Device being modular
-
- 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
- A61B8/5223—Devices using data or image processing specially adapted for diagnosis using ultrasonic, sonic or infrasonic waves involving processing of medical diagnostic data for extracting a diagnostic or physiological parameter from medical diagnostic data
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Medical Informatics (AREA)
- Surgery (AREA)
- Pathology (AREA)
- Radiology & Medical Imaging (AREA)
- Biophysics (AREA)
- Biomedical Technology (AREA)
- Heart & Thoracic Surgery (AREA)
- Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Nuclear Medicine, Radiotherapy & Molecular Imaging (AREA)
- Animal Behavior & Ethology (AREA)
- General Health & Medical Sciences (AREA)
- Public Health (AREA)
- Veterinary Medicine (AREA)
- Physiology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ultra Sonic Daignosis Equipment (AREA)
Abstract
The invention provides a measuring device, a measuring method, a medium and an electronic device based on an ultrasonic image. The apparatus comprises: an ultrasonic image acquisition module for acquiring a target ultrasonic image; the scale key point acquisition module is used for acquiring scale key points in the target ultrasonic image; the scale acquisition module is used for acquiring a scale of the target ultrasonic image according to the on-graph distance between the scale key points and the actual distance; the target object detection module is used for detecting a target object in the target ultrasonic image; the object size measuring module is used for acquiring the actual size of the target object according to the on-graph size and the scale of the target object; and the superposition display module is used for superposing and displaying the scale key points, the scale, the detection result of the target object and/or the actual size of the target object in the target ultrasonic image. The device can automatically acquire the actual size of the target object, the process basically does not need manual participation, and the efficiency is high.
Description
Technical Field
The present invention relates to a measurement device, and more particularly, to a measurement device, a measurement method, a measurement medium, and an electronic device based on an ultrasound image.
Background
Ultrasonic imaging is to scan human body with ultrasonic sound beam, and receive and process reflected signal to obtain image of internal organs. In practical applications, the ultrasound imaging method is often used to determine the position, size, and shape of an organ, determine the range and physical properties of a lesion, and the like. For example, in the case of ultrasound detection of thyroid, breast, liver and gall bladder, etc., nodules or other lesions are found, the size of the lesion needs to be evaluated.
In the prior art, ultrasonic images displayed by ultrasonic equipment of different manufacturers have different sizes and different size ratios with real organs of a human body, and medical staff needs to visually observe the proportional relationship between the ultrasonic images and the real human body by experience and identify the size of a focus by visual observation after the focus is identified. Even if some ultrasonic equipment provided by some manufacturers can display the reference scale lines while displaying images, the display modes and display positions of the ultrasonic equipment of different manufacturers are different, and the scaling of the ultrasonic equipment relative to a real human body is different, so that medical staff is required to learn to know the image display characteristics of the equipment before using one ultrasonic equipment, otherwise, the evaluation on the lesion size of a patient is possibly inaccurate. This method is inefficient and is prone to measurement errors caused by human subjective factors such as doctor experience.
Disclosure of Invention
In view of the above-mentioned drawbacks of the prior art, an object of the present invention is to provide an ultrasound image-based measurement apparatus, a method, a medium, and an electronic apparatus, which solve the above-mentioned problems in the prior art.
To achieve the above and other related objects, a first aspect of the present invention provides an ultrasound image-based measuring apparatus, comprising: an ultrasonic image acquisition module for acquiring a target ultrasonic image; the scale key point acquisition module is used for acquiring scale key points in the target ultrasonic image; the scale acquisition module is used for acquiring a scale of the target ultrasonic image according to the on-graph distance and the actual distance between the scale key points; a target object detection module for detecting a target object in the target ultrasound image; the object size measuring module is used for acquiring the actual size of the target object according to the on-graph size of the target object and the scale; and the superposition display module is used for superposing and displaying the scale key points, the scale, the detection result of the target object and/or the actual size of the target object in the target ultrasonic image.
In an embodiment of the first aspect, the scale key point obtaining module processes the target ultrasound image by using a neural network model to obtain the scale key point.
In an embodiment of the first aspect, the target object detection module includes: a target object obtaining unit, configured to segment the target ultrasound image to obtain a model of the target object; and the target parameter acquiring unit is used for acquiring target parameters according to the model of the target object, wherein the target parameters are used for reflecting the on-graph size of the target object.
In an embodiment of the first aspect, the target object detection module includes: a detection frame acquisition unit configured to acquire a detection frame of the target object according to the target ultrasound image; and the target parameter acquiring unit is used for acquiring target parameters according to the detection frame of the target object, wherein the target parameters are used for reflecting the on-graph size of the target object.
In an embodiment of the first aspect, the scale obtaining module includes: the scale key point identification unit is used for identifying the scale key points according to the vertical coordinates of the scale key points; the on-graph distance acquiring unit is used for acquiring the on-graph distance between the scale key points according to the marks of the scale key points; and the scale obtaining unit is used for obtaining the scale of the target ultrasonic image according to the on-graph distance between the scale key points and the actual distance.
In an embodiment of the first aspect, the scale key point identification unit includes: the scale key point sequencing subunit is used for sequencing the scale key points according to the vertical coordinates of the scale key points; and the scale key point identification subunit is used for sequentially identifying the scale key points according to the sequencing result of the scale key points.
In an embodiment of the first aspect, the scale obtaining unit obtains the scale according to an on-graph distance and an actual distance between two key points of the scale, or the scale obtaining unit obtains the scale according to an average on-graph distance and an average actual distance between a plurality of key points of the scale.
A second aspect of the present invention provides an ultrasound image-based measurement method, the method including: acquiring a target ultrasonic image; acquiring scale key points in the target ultrasonic image; obtaining a scale of the target ultrasonic image according to the on-graph distance and the actual distance between the scale key points; detecting a target object in the target ultrasound image; acquiring the actual size of the target object according to the on-graph size of the target object and the scale; and displaying the scale key points, the scale, the detection result of the target object and/or the actual size of the target object in an overlapping manner in the target ultrasonic image.
A third aspect of the invention provides a computer-readable storage medium having stored thereon a computer program which, when being executed by a processor, carries out the ultrasound image-based measurement method of the second aspect of the invention.
A fourth aspect of the present invention provides an electronic apparatus, comprising: a memory storing a computer program; and the processor is in communication connection with the memory and executes the ultrasonic image-based measurement method according to the second aspect of the invention when the computer program is called.
As described above, the ultrasound image-based measurement apparatus according to one or more embodiments of the present invention has the following advantageous effects:
the ultrasonic image-based measuring equipment can acquire the scale of the target ultrasonic image based on the scale key points in the target ultrasonic image, and the actual size of the target object can be obtained based on the scale and the on-graph size of the target object. The process basically does not need manual participation, has high efficiency, and can avoid measurement errors caused by artificial subjective reasons.
In addition, the measurement device based on the ultrasonic image can be externally connected to different ultrasonic devices, and the ultrasonic images output by the ultrasonic devices can be processed as long as the ultrasonic images can be acquired, so that the measurement device based on the ultrasonic images can be used in connection with the ultrasonic devices.
Drawings
FIG. 1A is a schematic diagram of an ultrasound-image-based measurement apparatus according to an embodiment of the present invention.
FIG. 1B is a diagram illustrating an example of a target ultrasound image for an ultrasound image-based measurement apparatus according to an embodiment of the present invention.
FIG. 2 is a flowchart illustrating a method for training a first neural network model in an embodiment of an ultrasound-based measurement apparatus according to the present invention.
Fig. 3A is a schematic structural diagram of a target object detection module of an ultrasound image-based measurement apparatus according to an embodiment of the invention.
FIG. 3B is a flowchart illustrating a method for training a second neural network model of the ultrasound-based measurement device according to an embodiment of the present invention.
Fig. 3C is a schematic structural diagram of a target object detection module in another embodiment of the ultrasound-image-based measurement apparatus according to the present invention.
Fig. 4A is a schematic structural diagram of a scale obtaining module of the ultrasound-image-based measurement apparatus according to an embodiment of the invention.
Fig. 4B is a schematic structural diagram of a scale key point identification unit of the ultrasound-image-based measurement apparatus according to an embodiment of the present invention.
FIG. 4C is a diagram illustrating an exemplary result of marking scale key points of the ultrasound-based measurement device according to an embodiment of the present invention.
FIG. 5 is a flowchart illustrating an ultrasound image based measurement method according to an embodiment of the present invention.
Fig. 6 is a schematic structural diagram of an electronic device according to an embodiment of the invention.
Description of the element reference numerals
Ultrasound image-based measuring device
10 ultrasonic image acquisition module
11 scale key point acquisition module
12 scale acquisition module
121-scale key point identification unit
1211 scale key point sorting subunit
1212 scale key point identification subunit
122 distance on graph obtaining unit
123 scale acquisition unit
13 target object detection module
131 target object acquisition unit
132 target parameter acquiring unit
133 detection frame acquisition unit
134 target parameter acquisition unit
14 object size measuring module
15 superimposed display module
600 electronic device
610 memory
620 processor
630 display
S21-S24
S31-S34
S51-S56
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the drawings only show the components related to the present invention rather than being drawn according to the number, shape and size of the components in actual implementation, and the type, number and proportion of the components in actual implementation may be changed arbitrarily, and the layout of the components may be more complicated. Moreover, in this document, relational terms such as "first," "second," and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions.
In an embodiment of the present invention, referring to fig. 1A, an ultrasound image-based measurement apparatus 1 includes an ultrasound image obtaining module 10, a scale key point obtaining module 11, a scale obtaining module 12, a target object detecting module 13, an object size measuring module 14, and an overlay display module 15.
The ultrasound image acquisition module 10 is used for acquiring a target ultrasound image. Specifically, the ultrasound image acquisition module 10 may be communicatively connected to an ultrasound device, and acquire an ultrasound image output by the ultrasound device as the target ultrasound image. The ultrasound image acquisition module 10 is preferably capable of connecting to a plurality of different types of ultrasound devices and acquiring ultrasound images output by the ultrasound devices in different display modes, different display positions and/or different scales as the target ultrasound image.
The scale key point obtaining module 11 is connected to the ultrasound image obtaining module 10, and is configured to obtain a scale key point in the target ultrasound image. For example, please refer to fig. 1B, which is an exemplary diagram of a target ultrasound image related to the present embodiment, wherein the target ultrasound image includes an image body and a scale key point, and the scale key point is a point in the target ultrasound image for indicating a scale, and is generally generated automatically by an ultrasound scanning device. Furthermore, for purposes of clarity of display, only one scale key point is identified in FIG. 1B, it being understood that the white point below the scale key point in the figure is also the scale key point.
The scale obtaining module 12 is connected to the scale key point obtaining module 11, and is configured to obtain a scale of the target ultrasound image according to the on-graph distance between the scale key points and the actual distance. Wherein the scale is, for example, a ratio of a distance on the graph between the key points of the scale to an actual distance.
The target object detection module 13 is configured to detect a target object in the target ultrasound image, and more specifically, to detect an on-map size of the target object in the target ultrasound image, wherein the target object is, for example, a thyroid nodule, and the size includes, but is not limited to, a length, a perimeter, an area, a volume, and the like.
The object size measuring module 14 is connected to the scale obtaining module 12 and the target object detecting module 13, and is configured to obtain an actual size of the target object according to the on-map size of the target object and the scale. For example, when the minimum detection frame is used to detect the target object and the minimum detection frame is a rectangle, the object size measurement module 14 may obtain the actual length and the actual width of the minimum detection frame according to the on-map length and the on-map width of the minimum detection frame, so as to obtain the actual radial size of the target object.
The overlay display module 15 is connected to the ultrasound image acquisition module 10, the scale key point acquisition module 11, the scale acquisition module 12, the target object detection module 13, and the object size measurement module 14, and is configured to overlay and display the scale key point, the scale, the detection result (e.g., a minimum detection frame, a lesion contour) of the target object, and/or the actual size of the target object in the target ultrasound image. The connection mode between the superposition display module 15 and the other modules includes direct connection and indirect connection through other modules. For example, the overlay display module 15 may be directly connected to the object size measurement module 14, or may be indirectly connected to the scale obtaining module 12 through the object size measurement module 14.
Preferably, the overlay display module 15 is further configured to determine a display position and/or a display manner of the scale key point, the scale, the detection result of the target object, and/or the actual size of the target object, so as to avoid occlusion between display contents. For example, the overlay display module 15 may display the scale key points, the scale, and the actual size of the target object on one side of the target ultrasound image.
As can be seen from the above description, the ultrasound image-based measurement apparatus of this embodiment can obtain the scale of the target ultrasound image based on the scale key points in the target ultrasound image, and obtain the actual size of the target object based on the scale and the on-map size of the target object. The process basically does not need manual participation, has high efficiency, and can avoid measurement errors caused by artificial subjective reasons.
In an embodiment of the present invention, the ultrasound image measuring apparatus 1 further includes a housing, and the hardware structures corresponding to the modules of the ultrasound image measuring apparatus 1 are disposed in the housing. In addition, the housing has a communication interface through which the ultrasound image acquisition module 10 is communicatively connected to an ultrasound device to acquire the target ultrasound image from the ultrasound device. In this way, the ultrasound image measuring device 1 can be used with an ultrasound device immediately after being connected, that is, as long as the ultrasound image measuring device 1 is externally connected to the ultrasound device, the ultrasound image measuring device 1 can process an ultrasound image output by the ultrasound device, so as to obtain a corresponding scale key point, a scale, a detection result of a target object and/or an actual size of the target object, and display the detection result.
In an embodiment of the present invention, the scale key point obtaining module 11 processes the target ultrasound image by using a first neural network model to obtain the scale key point, where the first neural network model is a trained neural network model.
Optionally, referring to fig. 2, the training method of the first neural network model in this embodiment includes:
s21, constructing a neural network initial model, wherein the neural network initial model is used for extracting scale key points in the ultrasonic image, and for example, deep learning network models such as U-Net or V-Net can be adopted.
S22, acquiring first training data, where the first training data is an ultrasound image labeled with scale key points, and the labeling of the scale key points may be implemented by manual or other methods, which is not limited in the present invention.
S23, training the neural network initial model by using the first training data to obtain the first neural network model.
And S24, testing the first neural network model.
It should be understood that the above scheme of obtaining the scale key points through the first neural network model is only a preferred scheme of the present invention, and other algorithms or manual marks may also be used in practical applications to obtain the scale key points, which is not limited by the present invention.
Referring to fig. 3A, in an embodiment of the present invention, a structure of the target object detection module 13 includes a target object obtaining unit 131 and a target parameter obtaining unit 132.
The target object obtaining unit 131 is configured to segment the target ultrasound image to obtain a model of the target object.
Optionally, the target object obtaining unit 131 processes the target ultrasound image by using a second neural network model to segment the target ultrasound image, so as to obtain a model of the target object.
Referring to fig. 3B, in this embodiment, the method for implementing the training of the second neural network model includes:
s31, constructing a neural network initial model, wherein the neural network initial model is used for realizing a segmentation algorithm for the target object in the embodiment, and for example, deep learning models such as U-Net or V-Net can be adopted.
S32, obtaining second training data, where the second training data is an ultrasound image labeled with the target object binary segmentation mask, and the labeling of the binary segmentation mask may be implemented by manual or other methods, which is not limited in the present invention.
S33, training the neural network initial model by using the second training data to obtain the second neural network model.
S34, testing the second neural network model.
It should be noted that, the target object obtaining unit 131 obtains the model of the target object by using the second neural network model is only one possible way of the embodiment, but the invention is not limited thereto.
The target parameter obtaining unit 132 is connected to the target object obtaining unit 131, and is configured to obtain a target parameter according to a model of the target object, where the target parameter is used to reflect an on-map size of the target object. The target parameters include, but are not limited to, length, perimeter, area, volume, and the like.
Alternatively, the target parameter acquiring unit 132 may acquire a manually marked parameter value as the target parameter.
Alternatively, the target parameter acquiring unit 132 may acquire the target parameter by using a conventional algorithm such as key point detection.
Alternatively, the target parameter acquiring unit 132 may acquire, as the target parameters, a maximum diameter and a minimum diameter of a model of the target object obtained after image segmentation.
Referring to fig. 3C, in an embodiment of the invention, another structure of the target object detection module 13 includes a detection frame obtaining unit 133 and a target parameter obtaining unit 134.
The detection frame acquiring unit 133 is configured to acquire a detection frame of the target object according to the target ultrasound image. Specifically, the detection frame obtaining unit 133 may process the target ultrasound image by using a trained deep learning model, a trained neural network model, and the like to obtain a detection frame of the target object, may also obtain the detection frame of the target object according to a labeling result input by a user, and may also obtain a boundary of the target object according to the model of the target object to further obtain the detection frame of the target object according to a pixel point on the boundary.
In addition, the detection frame of the target object may have any shape, and the detection frame of the target object entirely contains the target object. Preferably, the detection frame of the target object is a minimum detection frame (or referred to as a minimum bounding box) of the target object, the minimum detection frame fully contains the target object, and the minimum detection frame is preferably a polygon, and is further preferably a rectangle.
The target parameter obtaining unit 134 is connected to the detection frame obtaining unit 133, and is configured to obtain a target parameter according to the detection frame of the target object, where the target parameter is used to reflect an on-map size of the target object. For example, the target parameter acquiring unit 134 may acquire geometric dimensions such as a width, a height, an area, and a circumference of the detection frame as the target parameters.
It should be noted that the two schemes listed above for acquiring the target parameter are only alternatives of the present invention, but the present invention is not limited to this, and other methods may be used to acquire the target parameter in practical applications, for example, the target parameter may be acquired by contouring, displaying meridian lines, and the like.
Referring to fig. 4A, in an embodiment of the present invention, the scale obtaining module 12 includes a scale key point identification unit 121, an on-graph distance obtaining unit 122, and a scale obtaining unit 123.
The scale key point identification unit 121 is connected to the scale key point acquisition module 11, and configured to identify the scale key points according to the ordinate of the scale key points, where the identification of the scale key points is used to mark longitudinal relative positions between the scale key points, and distances on a longitudinal graph between different scale key points can be obtained according to the identification. For example, if the two scale key points are labeled as a and b, respectively, the distance between the two is a-b, wherein a and b are preferably positive integers.
The on-graph distance acquiring unit 122 is connected to the scale key point identifying unit 121, and configured to acquire the longitudinal on-graph distance between the scale key points according to the identification of the scale key points.
The scale obtaining unit 123 is connected to the on-graph distance obtaining unit 122, and is configured to obtain a scale of the target ultrasound image according to the longitudinal on-graph distance between the scale key points and the longitudinal actual distance. The longitudinal actual distance of the scale key points can be obtained according to the positions, numbers and/or coordinates of the scale key points.
It should be noted that the longitudinal direction in this embodiment refers to a direction substantially parallel to the key point connecting line of the scale.
Optionally, in this embodiment, the scale obtaining module further includes a preprocessing unit, and the preprocessing unit is configured to preprocess the scale key points to delete the abnormal points therein. For example, if the abscissa of a certain scale key point is greatly different from the average of the abscissas of the other scale key points, the scale key point can be regarded as the abnormal point and deleted. The scale key point identification unit 121 is connected to the scale key point acquisition module 11 through the preprocessing unit, and the scale acquisition unit 123 is connected to the scale key point acquisition module 11 through the preprocessing unit. By the method, the scale of the target image can be acquired by the scale acquiring unit only according to the distance on the graph between the key points of the normal scale and the actual distance, and the accuracy of the acquired scale is improved.
Optionally, referring to fig. 4B, the scale key point identification unit 121 includes a scale key point sorting subunit 1211 and a scale key point identification subunit 1212.
The scale key point sorting subunit 1211 is connected to the scale key point obtaining module 11, and configured to sort the scale key points according to the ordinate of the scale key points, for example, the scale key points may be sorted according to a sequence from large to small or from small to large of the ordinate.
The scale key point identification subunit 1212 is connected to the scale key point sorting subunit 1211 and configured to sequentially identify the scale key points according to the sorting of the scale key points. For example, when the key point sorting subunit 1211 sorts the scale key points in order of ascending ordinate, the scale key point identification subunit 1212 may sequentially identify the scale key points as 0, 1, …, N, where N is a positive integer. The result of identifying the scale key points in this embodiment is shown in fig. 4C, for example.
In an embodiment of the invention, the scale obtaining unit 124 may obtain the scale according to an on-graph distance and an actual distance between two key points of the scale, or the scale obtaining unit 124 may obtain the scale according to an average on-graph distance and an average actual distance between a plurality of key points of the scale. In addition, the scale obtaining unit 124 may also obtain the scale by using other methods, which is not limited in the present invention.
In practical application, omission easily occurs in the process of acquiring scale key points, which may cause that the scale key point acquisition module cannot acquire all scale key points, and further may cause errors in the acquired scale. To address this problem, in an embodiment of the present invention, the object dimension measuring module determines a scale of the target ultrasound image according to the following formula:
wherein L is the scale of the target ultrasonic image Li,jThe longitudinal actual distance between the ith scale key point and the jth scale key point, that is, the longitudinal actual distance between the ith scale key point and the jth scale key point, the distance value can be obtained according to the ordinate of the two scale key points,/m,nIs the longitudinal direction between the mth scale key point and the nth scale key pointThe distance value to the actual distance, i.e. the actual distance in the longitudinal direction of the mth scale key point and the nth scale key point, can be derived from the ordinate of these two scale key points, i ═ j ± 1 and/or m ═ n ± 1, and,
f is a rounding function, which can be a rounding function, an upward rounding function, a downward rounding function, etc., max (l)m,n,li,j) Is 1m,nAnd li,jLarger value in between, min (l)m,n,li,j) Is 1m,nAnd li,jThe smaller value in between. For example, for the labeling result shown in fig. 4C, if i is 2, j is m is 3, and n is 4, then
At this time, the scale is
For example, as for the identification result shown in fig. 4C, if i is 1, j is 2, m is 3, and n is 4, then
At this time, the scale is
As described above, the object size measurement module in this embodiment can obtain the value of one scale from any two scale key point pairs (i, j) and (m, n) that satisfy the condition of i ═ j ± 1 and/or m ═ n ± 1. Based on this, the object size measurement module preferably obtains values of a plurality of scales according to different scale key point pairs, and averages the values as the scale of the target ultrasound image.
According to the above description, the method provided by the embodiment can avoid the problem that the obtained scale is not accurate enough due to omission of the scale key points, and is beneficial to further improving the accuracy of the result.
In an embodiment of the present invention, the target object is a thyroid nodule, and the ultrasound image-based measurement device can obtain an upper and lower diameter, a width diameter, and a height diameter of the thyroid nodule according to an ultrasound image of the thyroid nodule, and further obtain an aspect ratio of the thyroid nodule, where the aspect ratio is the height diameter/the width diameter. The malignancy degree of the thyroid nodule can be obtained based on the upper and lower diameters, the width diameter, the height diameter and the aspect ratio of the thyroid nodule, the process basically does not need manual participation, the efficiency is high, and errors caused by artificial subjective factors cannot occur.
Based on the above description of the measurement device, the invention also provides a measurement method based on the ultrasonic image. Specifically, referring to fig. 5, in an embodiment of the invention, the method for ultrasound image based measurement includes:
and S51, acquiring the target ultrasonic image.
And S52, acquiring scale key points in the target ultrasonic image.
And S53, acquiring a scale of the target ultrasonic image according to the on-graph distance and the actual distance between the scale key points.
S54, detecting a target object in the target ultrasonic image.
And S55, acquiring the actual size of the target object according to the on-graph size of the target object and the scale.
And S56, displaying the scale key points, the scale, the detection result of the target object and/or the actual size of the target object in an overlapping mode in the target ultrasonic image.
It should be noted that, in the embodiment, the steps S51 to S56 correspond to the corresponding modules in the ultrasound image-based measurement apparatus 1 shown in fig. 1A one-to-one, and redundant description is not repeated herein for saving the description.
In addition, the above reference numerals S51 to S54 are only used to identify different steps, and are not used to limit the execution order among the steps, and the execution order of the steps may be adjusted according to specific requirements in practical applications, for example, step S54 may be executed first, and then steps S52 and S53 may be executed, or step S54 and step S52 may be executed at the same time.
Based on the above description of the measurement apparatus, the present invention also provides a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the ultrasound image-based measurement method shown in fig. 5.
Based on the above description of the measuring device, the invention also provides an electronic device. Referring to fig. 6, in an embodiment of the present invention, the electronic device 600 includes a memory 610 and a processor 620, wherein the memory 610 stores a computer program, and the processor 620 is communicatively connected to the memory 610, and when the computer program is invoked, the ultrasound image-based measurement method shown in fig. 5 is implemented.
Optionally, the electronic device 600 further comprises a display 630, and the display 630 is communicatively connected to the memory 610 and the processor 620 and is used for displaying a GUI interactive interface related to the ultrasound image-based measurement method.
The protection scope of the ultrasound image-based measurement method of the present invention is not limited to the execution sequence of the steps illustrated in this embodiment, and all the solutions implemented by the steps addition, subtraction and step replacement of the prior art according to the principles of the present invention are included in the protection scope of the present invention.
The invention also provides a measuring device based on an ultrasound image, which can implement the measuring method based on an ultrasound image, but the implementation hardware of the measuring method based on an ultrasound image of the invention includes but is not limited to the structure of the measuring device based on an ultrasound image listed in this embodiment, and all the structural modifications and replacements of the prior art made according to the principle of the invention are included in the protection scope of the invention.
The measuring equipment based on the ultrasonic image can acquire the scale of the target ultrasonic image based on the scale key points in the target ultrasonic image, and the actual size of the target object can be acquired based on the scale and the minimum detection frame of the target object. The process basically does not need manual participation, has high efficiency, and can avoid measurement errors caused by artificial subjective reasons.
In addition, in consideration of the fact that the scale obtained by the measurement device is not accurate enough due to the fact that problems such as omission or misrecognition exist in the acquired scale key points in the measurement process, the measurement device based on the ultrasonic image can delete abnormal points existing in the scale key points by the aid of the preprocessing unit, and therefore errors caused by misrecognition are avoided. And, the scale obtaining module can pass
The scale is determined by the formula, so that errors caused by missing key points of the scale are avoided. Therefore, the ultrasonic image-based measuring device of the invention has good accuracy.
Furthermore, the measurement device based on the ultrasound image can be externally connected to different ultrasound devices, and the ultrasound images output by the ultrasound devices can be processed as long as the ultrasound images can be acquired, so that the measurement device based on the ultrasound images can be used in connection with the ultrasound devices.
In conclusion, the present invention effectively overcomes various disadvantages of the prior art and has high industrial utilization value.
The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.
Claims (10)
1. An ultrasound image-based measurement device, characterized in that the device comprises:
an ultrasonic image acquisition module for acquiring a target ultrasonic image;
the scale key point acquisition module is used for acquiring scale key points in the target ultrasonic image;
the scale acquisition module is used for acquiring a scale of the target ultrasonic image according to the on-graph distance and the actual distance between the scale key points;
a target object detection module for detecting a target object in the target ultrasound image;
the object size measuring module is used for acquiring the actual size of the target object according to the on-graph size of the target object and the scale;
and the superposition display module is used for superposing and displaying the scale key points, the scale, the detection result of the target object and/or the actual size of the target object in the target ultrasonic image.
2. The apparatus of claim 1, wherein: the scale key point acquisition module utilizes a neural network model to process the target ultrasonic image so as to obtain the scale key points.
3. The apparatus of claim 1, wherein the target object detection module comprises:
a target object obtaining unit, configured to segment the target ultrasound image to obtain a model of the target object; and the target parameter acquiring unit is used for acquiring target parameters according to the model of the target object, wherein the target parameters are used for reflecting the on-graph size of the target object.
4. The apparatus of claim 1, wherein the target object detection module comprises:
a detection frame acquisition unit configured to acquire a detection frame of the target object according to the target ultrasound image;
and the target parameter acquiring unit is used for acquiring target parameters according to the detection frame of the target object, wherein the target parameters are used for reflecting the on-graph size of the target object.
5. The apparatus of claim 1, wherein the scale acquisition module comprises:
the scale key point identification unit is used for identifying the scale key points according to the vertical coordinates of the scale key points;
the on-graph distance acquiring unit is used for acquiring the on-graph distance between the scale key points according to the marks of the scale key points;
and the scale obtaining unit is used for obtaining the scale of the target ultrasonic image according to the on-graph distance between the scale key points and the actual distance.
6. The apparatus of claim 5, wherein the scale key point identification unit comprises:
the scale key point sequencing subunit is used for sequencing the scale key points according to the vertical coordinates of the scale key points;
and the scale key point identification subunit is used for sequentially identifying the scale key points according to the sequencing result of the scale key points.
7. The apparatus of claim 5 or 6, wherein: the scale acquiring unit acquires the scale according to the on-graph distance and the actual distance between the two scale key points, or the scale acquiring unit acquires the scale according to the average on-graph distance and the average actual distance between the plurality of scale key points.
8. An ultrasound image-based measurement method, the method comprising:
acquiring a target ultrasonic image;
acquiring scale key points in the target ultrasonic image;
obtaining a scale of the target ultrasonic image according to the on-graph distance and the actual distance between the scale key points;
detecting a target object in the target ultrasound image;
acquiring the actual size of the target object according to the on-graph size of the target object and the scale;
and displaying the scale key points, the scale, the detection result of the target object and/or the actual size of the target object in an overlapping manner in the target ultrasonic image.
9. A computer-readable storage medium having stored thereon a computer program, characterized in that: the computer program, when executed by a processor, implements the ultrasound image based measurement method of claim 8.
10. An electronic device, characterized in that the electronic device comprises:
a memory storing a computer program;
a processor, communicatively coupled to the memory, that executes the ultrasound image based measurement method of claim 8 when the computer program is invoked.
Priority Applications (2)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111242249.XA CN113995435A (en) | 2021-10-25 | 2021-10-25 | Ultrasound image-based measurement device, ultrasound image-based measurement method, ultrasound image-based measurement medium, and electronic device |
| PCT/CN2022/070646 WO2023070946A1 (en) | 2021-10-25 | 2022-01-07 | Measurement device and method based on ultrasound image, and medium and electronic device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111242249.XA CN113995435A (en) | 2021-10-25 | 2021-10-25 | Ultrasound image-based measurement device, ultrasound image-based measurement method, ultrasound image-based measurement medium, and electronic device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113995435A true CN113995435A (en) | 2022-02-01 |
Family
ID=79923872
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111242249.XA Withdrawn CN113995435A (en) | 2021-10-25 | 2021-10-25 | Ultrasound image-based measurement device, ultrasound image-based measurement method, ultrasound image-based measurement medium, and electronic device |
Country Status (2)
| Country | Link |
|---|---|
| CN (1) | CN113995435A (en) |
| WO (1) | WO2023070946A1 (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937219A (en) * | 2023-03-14 | 2023-04-07 | 合肥合滨智能机器人有限公司 | Ultrasonic image part identification method and system based on video classification |
Family Cites Families (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH0739546A (en) * | 1993-07-27 | 1995-02-10 | Ge Yokogawa Medical Syst Ltd | Apparatus for ultrasonic examination |
| JP2004275362A (en) * | 2003-03-14 | 2004-10-07 | Fuji Photo Film Co Ltd | Method of calculating actual size of image, method of measuring image and method of outputting image, and device thereof |
| US8556816B2 (en) * | 2011-05-27 | 2013-10-15 | Samsung Medison Co., Ltd. | Providing a measuring item candidate group for measuring size of a target object in an ultrasound system |
| CN106023269B (en) * | 2016-05-16 | 2019-03-22 | 北京大学第一医院 | A kind of method and device for estimating wound area |
| CN106419821B (en) * | 2016-08-31 | 2018-06-08 | 北京大学第三医院 | A kind of method and apparatus that joint inner structure is measured under arthroscope |
| CN108062749B (en) * | 2017-12-12 | 2020-04-21 | 深圳大学 | Identification method and device for levator ani fissure hole and electronic equipment |
| CN109165645B (en) * | 2018-08-01 | 2023-04-07 | 腾讯科技（深圳）有限公司 | Image processing method and device and related equipment |
| CN113066093A (en) * | 2021-04-08 | 2021-07-02 | 南华大学附属第一医院 | Automatic segmentation and parting and thickness measuring method based on endometrial ultrasound image |
-
2021
- 2021-10-25 CN CN202111242249.XA patent/CN113995435A/en not_active Withdrawn
-
2022
- 2022-01-07 WO PCT/CN2022/070646 patent/WO2023070946A1/en unknown
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115937219A (en) * | 2023-03-14 | 2023-04-07 | 合肥合滨智能机器人有限公司 | Ultrasonic image part identification method and system based on video classification |
Also Published As
| Publication number | Publication date |
|---|---|
| WO2023070946A1 (en) | 2023-05-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP4825253B2 (en) | System and method for deformable object recognition | |
| US20180140282A1 (en) | Ultrasonic diagnostic apparatus and image processing method | |
| CN109191424B (en) | Breast mass detection and classification system and computer-readable storage medium | |
| CN110570350A (en) | two-dimensional follicle detection method and device, ultrasonic equipment and readable storage medium | |
| US8285013B2 (en) | Method and apparatus for detecting abnormal patterns within diagnosis target image utilizing the past positions of abnormal patterns | |
| US8831311B2 (en) | Methods and systems for automated soft tissue segmentation, circumference estimation and plane guidance in fetal abdominal ultrasound images | |
| JP2004094954A (en) | Hierarchical component based object recognition | |
| CN111652213A (en) | Ship water gauge reading identification method based on deep learning | |
| CN107993228B (en) | Vulnerable plaque automatic detection method and device based on cardiovascular OCT (optical coherence tomography) image | |
| CN111820948B (en) | Fetal growth parameter measuring method and system and ultrasonic equipment | |
| CN103767728A (en) | Image identification method and image identification system | |
| CN110378227B (en) | Method, device and equipment for correcting sample labeling data and storage medium | |
| CN109035227A (en) | The system that lung tumors detection and diagnosis is carried out to CT image | |
| CN110974306A (en) | System for discernment and location pancreas neuroendocrine tumour under ultrasonic endoscope | |
| CN113995435A (en) | Ultrasound image-based measurement device, ultrasound image-based measurement method, ultrasound image-based measurement medium, and electronic device | |
| CN114066887B (en) | Rice chalkiness area detection method, device, equipment and storage medium | |
| CN110084736A (en) | A kind of method of detecting watermarks and system based on SURF and pyramid algorith | |
| CN114360695A (en) | Mammary gland ultrasonic scanning analysis auxiliary system, medium and equipment | |
| Staal et al. | Automatic rib segmentation in CT data | |
| CN114820492A (en) | Method for detecting excess on circuit board | |
| CN114140518A (en) | Water level height monitoring method and device, electronic equipment and storage medium | |
| CN114332858A (en) | Focus detection method and device and focus detection model acquisition method | |
| TW514515B (en) | Method for obtaining boundary data, contour and boundary category of target image and positioning and guidance of image | |
| CN117689567B (en) | Ultrasonic image scanning method and device | |
| CN117456542B (en) | Image matching method, device, electronic equipment and storage medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20220201 |