CN118261851A

CN118261851A - Ultrasonic image processing method, device, equipment and medium

Info

Publication number: CN118261851A
Application number: CN202211715329.7A
Authority: CN
Inventors: 王灵玄
Original assignee: Sonoscape Medical Corp
Current assignee: Sonoscape Medical Corp
Filing date: 2022-12-28
Publication date: 2024-06-28

Abstract

The application discloses an ultrasonic image processing method, an ultrasonic image processing device, ultrasonic image processing equipment and an ultrasonic image processing medium in the technical field of computers. According to the application, after the ultrasonic image of the ovarian cyst is obtained, the ultrasonic image is input into the cyst identification model, the inner cyst outline can be obtained, the cyst blood flow ratio is determined according to the inner cyst outline and the blood flow image corresponding to the ultrasonic image, and finally the blood flow evaluation result of the ovarian cyst is determined according to the cyst blood flow ratio. According to the scheme, artificial participation is not needed, the saccular blood flow ratio can be automatically calculated, and the blood flow evaluation result is automatically determined based on the saccular blood flow ratio. According to the method, the cyst blood flow evaluation result can be automatically and quantitatively calculated based on the ultrasonic image of the ovarian cyst for reference of doctors, so that the workload of the ultrasonic doctors can be reduced to a certain extent, and the evaluation accuracy of the cyst blood flow level is improved. The ultrasonic image processing device, the ultrasonic image processing equipment and the ultrasonic image processing medium have the same technical effects.

Description

Ultrasonic image processing method, device, equipment and medium

Technical Field

The present application relates to the field of computer technologies, and in particular, to a method, an apparatus, a device, and a medium for processing an ultrasonic image.

Background

At present, in a CW scanning mode, the ultrasonic equipment can display Doppler blood flow images of ovarian cysts, and doctors can manually evaluate the blood flow level of the cysts through the blood flow images and combining related guidelines, so that the benign and malignant degrees of the ovarian cysts are evaluated. However, the Doppler blood flow image of the ovarian cyst can make the edge of the cyst invisible, so that when a doctor evaluates the blood flow level of the cyst, the doctor needs to rely on the professional level and clinical experience to judge the size of the section area of the cyst, and the evaluation result of the blood flow level of the cyst is inaccurate.

Disclosure of Invention

Accordingly, the present application is directed to an ultrasonic image processing method, apparatus, device and medium, which can automatically determine the cyst blood flow ratio based on an ultrasonic image of an ovarian cyst, and automatically output a blood flow evaluation result of the ovarian cyst based on the cyst blood flow ratio for a doctor to refer to. The specific scheme is as follows:

to achieve the above object, in one aspect, the present application provides an ultrasound image processing method, including:

Acquiring an ultrasonic image of the ovarian cyst;

Inputting the ultrasonic image into a cyst identification model to obtain the inner outline of the cyst cavity;

Determining the blood flow ratio of the capsule cavity according to the inner outline of the capsule cavity and the blood flow image corresponding to the ultrasonic image;

and determining a blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

Optionally, inputting the ultrasonic image into a cyst identification model to obtain an inner cyst outline includes:

Inputting the ultrasonic image into the cyst identification model so that a feature extraction module in the cyst identification model extracts image features in the ultrasonic image, and a target segmentation module in the cyst identification model carries out mask segmentation based on the image features to obtain the inner cyst cavity contour.

Optionally, the determining the balloon cavity blood flow ratio according to the balloon cavity inner contour and the blood flow image corresponding to the ultrasonic image includes:

calculating the overlapping area of the inner outline of the capsule cavity and the blood flow area in the blood flow image;

and determining the ratio of the overlapping area to the area of the inner profile of the capsule cavity as the blood flow ratio of the capsule cavity.

Optionally, the method further comprises:

inputting the ultrasonic image into the cyst identification model so that a feature extraction module in the cyst identification model extracts image features in the ultrasonic image, and a target detection module in the cyst identification model obtains a cyst category, a cyst position and a cyst size based on the image features;

displaying the cyst category, the cyst location, and the cyst size in the ultrasound image.

Optionally, the training process of the cyst identification model includes:

obtaining a training sample; the training sample comprises: cyst category information, cyst location information, and cyst inner contour information;

Amplifying the training sample to obtain a training set;

And training the initial neural network model by using the training set to obtain the cyst identification model.

Optionally, the amplifying the training sample to obtain a training set includes:

And performing horizontal overturning, vertical overturning, mirror image filling rotation, mosaic enhancement, affine transformation, random contrast enhancement, random brightness enhancement and/or image clipping on the training sample to obtain the training set.

Optionally, the method further comprises:

If a plurality of cyst blood flow ratios are calculated for the same ovarian cyst, selecting one with the largest numerical value from the cyst blood flow ratios, and executing the step of determining the blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

Optionally, the determining the blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio comprises:

Comparing the cyst lumen blood flow ratio with a plurality of thresholds preset based on cyst assessment guidelines to obtain a comparison result;

and taking the corresponding blood flow grade in the cyst assessment guide as the blood flow assessment result according to the comparison result.

In still another aspect, the present application also provides an ultrasound image processing apparatus, including:

the acquisition module is used for acquiring an ultrasonic image of the ovarian cyst;

the detection module is used for inputting the ultrasonic image into a cyst identification model to obtain the inner outline of the cyst cavity;

the determining module is used for determining the blood flow ratio of the capsule cavity according to the inner outline of the capsule cavity and the blood flow image corresponding to the ultrasonic image;

And the evaluation module is used for determining a blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

Optionally, the detection module is specifically configured to:

Optionally, the determining module is specifically configured to:

Optionally, the detection module is further configured to:

inputting the ultrasonic image into the cyst identification model so that a feature extraction module in the cyst identification model extracts image features in the ultrasonic image, and a target detection module in the cyst identification model obtains a cyst category, a cyst position and a cyst size based on the image features; displaying the cyst category, the cyst location, and the cyst size in the ultrasound image.

Optionally, the cyst identification system further comprises a model training module, wherein the model training module can train to obtain a cyst identification model, and specifically comprises the following steps:

The sample acquisition unit is used for acquiring training samples; the training sample comprises: cyst category information, cyst location information, and cyst inner contour information;

the sample amplification unit is used for amplifying the training samples to obtain a training set;

and the training unit is used for training the initial neural network model by utilizing the training set to obtain the cyst identification model.

Optionally, the sample amplification unit is specifically configured to:

Optionally, the method further comprises:

And the selection module is used for selecting one with the largest numerical value from the plurality of the cyst blood flow ratios if the plurality of the cyst blood flow ratios are calculated for the same ovarian cyst, and executing the step of determining the blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

Optionally, the evaluation module is specifically configured to:

In yet another aspect, the present application also provides an electronic device including a processor and a memory; wherein the memory is for storing a computer program that is loaded and executed by the processor to implement the method of any of the preceding claims.

Optionally, the electronic device comprises an ultrasonic diagnostic device and/or an ultrasonic workstation.

In yet another aspect, the present application further provides a storage medium having stored therein computer executable instructions that, when loaded and executed by a processor, implement a method as in any of the preceding claims.

According to the application, after the ultrasonic image of the ovarian cyst is obtained, the ultrasonic image is input into the cyst identification model, the inner cyst outline can be obtained, the cyst blood flow ratio is determined according to the inner cyst outline and the blood flow image corresponding to the ultrasonic image, and finally the blood flow evaluation result of the ovarian cyst is determined according to the cyst blood flow ratio. According to the scheme, artificial participation is not needed, the saccular blood flow ratio can be automatically calculated, and the blood flow evaluation result is automatically determined based on the saccular blood flow ratio. Therefore, the application does not aim at subjective assessment of the cyst blood flow grade by doctors, but enables equipment to automatically and quantitatively calculate the cyst blood flow assessment result based on the ultrasonic image of the ovarian cyst for reference by the doctors. Of course, after the cyst blood flow level can be subjectively estimated by a doctor, the result output by the equipment is compared, so that the comprehensive cyst blood flow estimation result is given, the workload of the ultrasonic doctor can be reduced to a certain extent, and the cyst blood flow level estimation efficiency and accuracy are improved.

Correspondingly, the ultrasonic image processing device, the ultrasonic image processing equipment and the ultrasonic image processing medium have the same technical effects.

Drawings

In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present application, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.

FIG. 1 is a flow chart of an ultrasound image processing method provided by the application;

FIG. 2 is a schematic diagram of a cyst identification model provided by the application;

FIG. 3 is a flowchart of another ultrasound image processing method provided by the present application;

FIG. 4 is a schematic view of an ultrasonic image processing apparatus according to the present application;

FIG. 5 is a diagram of a server according to the present application;

fig. 6 is a diagram of a terminal structure according to the present application.

Detailed Description

The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. It will be apparent that the described embodiments are only some, but not all, embodiments of the application. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application. In addition, in the embodiments of the present application, "first", "second", etc. are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence.

At present, the edge of the cyst is invisible due to the Doppler blood flow image of the ovarian cyst, so that a doctor needs to automatically judge the size of the section area of the cyst according to the professional level and clinical experience when evaluating the blood flow level of the cyst, and the evaluation result of the blood flow level of the cyst is inaccurate.

In view of the problems existing at present, the application provides an ultrasonic image processing scheme which can quantitatively and automatically evaluate the blood flow evaluation result of the ovarian cyst for reference by doctors, and can reduce the workload of the ultrasonic doctors to a certain extent and improve the evaluation efficiency and accuracy of the blood flow level of the cyst.

Fig. 1 is a flowchart of an ultrasonic image processing method according to an embodiment of the present application. The following description will be given by taking an application to an electronic device as an example. The electronic device may be a terminal device such as an ultrasonic device or a personal computer, or may be a server. As shown in fig. 1, the ultrasonic image processing method may include the steps of:

S101, acquiring an ultrasonic image of the ovarian cyst.

In this embodiment, the ultrasound image may be a frame of image data acquired by the ultrasound probe in real time, or may be a continuous image frame acquired within a period of time. In the case of consecutive image frames, the method provided by the present embodiment is performed for each frame of image data. In this embodiment, the ultrasound image is specifically: the ultrasound device images the resulting image in B mode.

S102, inputting the ultrasonic image into a cyst identification model to obtain the inner outline of the cyst cavity.

In this embodiment, the cyst identification model may be obtained by using any structure of network training. In one example, the cyst identification model includes: a feature extraction module and a target segmentation module. The feature extraction module is used for extracting image features from the ultrasonic image; the target segmentation module is used for carrying out mask segmentation based on the image characteristics so as to determine the intracavitary outline of the ovarian cyst. In one embodiment, inputting an ultrasound image into a cyst identification model yields an inner cyst lumen contour, comprising: inputting the ultrasonic image into a cyst identification model so that a feature extraction module in the cyst identification model extracts image features in the ultrasonic image, and a target segmentation module in the cyst identification model performs mask segmentation based on the image features to obtain an intracapsular contour.

S103, determining the blood flow ratio of the capsule cavity according to the outline of the capsule cavity and the blood flow image corresponding to the ultrasonic image.

It should be noted that the blood flow image corresponding to the ultrasound image may be obtained based on a doppler imaging mode (CW mode) of the ultrasound apparatus. Specifically, in the doppler imaging mode, the ultrasound device may generate a corresponding blood flow image based on the echo signal, and more specifically, the blood flow image generation process may refer to the related art. That is to say: for the same scan site, a blood flow image of the site may be obtained in CW mode, while an ultrasound image of the site may be obtained in B mode. Then for the same ovarian cyst, a blood flow image of the ovarian cyst can be obtained in a CW mode, and an ultrasonic image of the ovarian cyst can be obtained in a B mode, wherein the blood flow image of the ovarian cyst can be considered to correspond to the ultrasonic image thereof.

Wherein, the saccular cavity blood flow ratio specifically means: the cyst blood flow area is the proportion of the cyst total area. Thus in one embodiment, determining the balloon blood flow ratio from the balloon inner contour and the corresponding blood flow image of the ultrasound image comprises: calculating the overlapping area of the inner outline of the capsule cavity and the blood flow area in the blood flow image; the ratio of the overlapping area to the area of the inner profile of the balloon is determined as the balloon blood flow ratio. Wherein, calculate the area of overlapping of the area of the intracavitary outline and blood flow area in the blood flow image, include: and (3) counting the occupied area of pixel points of the inner outline of the cyst cavity, and counting the occupied area of pixel points of all blood flows in the blood flow image, wherein the intersection of the two areas is the overlapping area, namely the size of the blood flow area in the cyst.

S104, determining a blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

It should be noted that, the number of evaluation guidelines for evaluating the blood flow level of ovarian cyst is numerous, the threshold value of each level may be set based on the level set by any evaluation guideline, and then the cyst blood flow ratio is compared with the corresponding threshold value, so as to determine the blood flow evaluation result based on the comparison result. For example: in this evaluation guideline of O-RADS, there is: level 1 is no blood flow information; level 2 is a small amount of blood flow information; level 3 is more blood flow information; level 4 is rich blood flow information. From this, 3 thresholds can be set: A. b, C, A < B < C. When the cyst blood flow ratio is smaller than A, the cyst blood flow grade is considered to be 1 grade; when the cyst blood flow ratio is between A and B, the cyst blood flow grade is considered to be 2; when the cyst blood flow ratio is between B and C, the cyst blood flow grade is considered to be 3; when the cyst blood flow ratio is greater than C, the cyst blood flow rating is considered to be class 4. Of course, when the result evaluation is performed in combination with other types of evaluation guidelines, the threshold setting and comparison may be performed accordingly. Thus in one embodiment, determining a blood flow assessment of an ovarian cyst based on a luminal blood flow ratio comprises: comparing the cyst lumen blood flow ratio with a plurality of thresholds preset based on cyst assessment guidelines to obtain a comparison result; and determining a blood flow evaluation result according to the comparison result.

In this embodiment, the cyst identification model may also detect cyst category, cyst location, cyst size, and the like. Wherein the cyst categories are still classified according to the corresponding cyst assessment guidelines. In one embodiment, inputting an ultrasonic image into a cyst identification model to enable a feature extraction module in the cyst identification model to extract image features in the ultrasonic image, and a target detection module in the cyst identification model obtains a cyst category, a cyst position and a cyst size based on the image features; the cyst category, cyst location, and cyst size are displayed in the ultrasound image for the physician to observe the cyst.

In one embodiment, the training process of the cyst identification model includes: obtaining a training sample; the training samples include: cyst category information, cyst location information, and cyst inner contour information; amplifying a training sample to obtain a training set; and training the initial neural network model by using the training set to obtain the cyst identification model. Amplifying the training sample to obtain a training set, wherein the amplifying comprises the following steps: the training samples are subjected to horizontal overturning, vertical overturning, mirror image filling rotation, mosaic enhancement, affine transformation, random contrast enhancement, random brightness enhancement and/or image clipping to obtain a training set, so that the sample size can be increased, and the model training precision is improved.

The method provided by the present embodiment may be performed for each of the successive image frames output by the ultrasound apparatus. In one example, for multiple ultrasound images of the same ovarian cyst output by the ultrasound device, multiple luminal blood flow ratios are calculated according to the present embodiment, and then one of these luminal blood flow ratios may be selected to evaluate the blood flow level of the ovarian cyst. In one embodiment, the method further comprises: if a plurality of cyst blood flow ratios are calculated for the same ovarian cyst, selecting one with the largest numerical value from the plurality of cyst blood flow ratios, and executing the step of determining the blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

Therefore, after the ultrasonic image of the ovarian cyst is obtained, the ultrasonic image is input into the cyst identification model, the inner cyst outline can be obtained, the cyst blood flow ratio is determined according to the inner cyst outline and the blood flow image corresponding to the ultrasonic image, and finally the blood flow evaluation result of the ovarian cyst is determined according to the cyst blood flow ratio. According to the scheme, artificial participation is not needed, the saccular blood flow ratio can be automatically calculated, and the blood flow evaluation result is automatically determined based on the saccular blood flow ratio. Therefore, the application does not aim at subjective assessment of the cyst blood flow grade by doctors, but enables equipment to automatically and quantitatively calculate the cyst blood flow assessment result based on the ultrasonic image of the ovarian cyst for reference by the doctors. Of course, after the cyst blood flow level can be subjectively estimated by a doctor, the result output by the equipment is compared, so that the comprehensive cyst blood flow estimation result is given, the workload of the ultrasonic doctor can be reduced to a certain extent, and the cyst blood flow level estimation accuracy is improved.

The following embodiment realizes a cyst identification model based on convolutional neural network CNN design. The implementation steps of the solution described in this embodiment and those related to other embodiments may be referred to each other.

Referring to fig. 2, the convolutional neural network CNN includes: backbone network for feature extraction, target detection network and target segmentation network.

The backbone network comprises a plurality of feature extraction layers, after an ultrasonic image of the ovarian cyst is input into the backbone network, a first feature extraction layer outputs a feature image based on the ultrasonic image, then each feature extraction layer can further extract features with higher semantics on the basis of the feature image output by the upper layer, the features are repeated in this way, and the feature image output by the last feature extraction layer is the image feature. The ultrasound image is a cyst section image, which can be an RGB type image or optical flow information recorded in sequence. From the optical flow class information, it can be determined that: the change condition of the same pixel point in the front and back frame images. Feature maps and image features include, but are not limited to: cyst edge information, cyst outline information, gray information and the like.

The target detection network takes the image characteristics as input, and can extract the information of the area where the cyst is located, wherein the information comprises the relative position information of the cyst in the image and the cyst type label, so that the target detection network can detect the information of the cyst type, the position, the size and the like. The object segmentation network takes image features as input and can perform object mask segmentation so as to output the inner outline information of the capsule cavity.

It can be seen that the embodiment transmits the extracted image features to the target detection module and the target segmentation module, and the two modules are independently calculated in parallel. The target detection module is mainly used for detecting information such as the area where the cyst is located, the size of the cyst and the like, and the target segmentation module is used for segmenting an interested area of the area where the cyst is located and determining a target area where the inner outline of the cyst is located.

After determining the target region of the lumen contour, the blood flow region in the currently detected ultrasound image may be calculated from the Doppler blood flow information of the image. Typically, the blood flow region of an ultrasound image is transmitted in a two-dimensional image. And then calculating the overlapping area of the target area where the inner outline of the capsule cavity is positioned and the blood flow area in the image, wherein the percentage of the overlapping area to the area of the inner outline of the capsule cavity is the evaluation value of the blood flow of the capsule cavity. The determination of blood flow level is then made against a threshold set based on the evaluation guideline. For example: in this evaluation guideline of O-RADS, there is: level 1 is no blood flow information; level 2 is a small amount of blood flow information; level 3 is more blood flow information; level 4 is rich blood flow information. From this, 3 thresholds can be set: A. b, C, A < B < C. When the percentage of the overlapped area to the inner outline area of the cyst cavity is smaller than A, the cyst blood flow grade is considered to be 1 grade; when the overlapping area accounts for the percentage of the inner outline area of the cyst cavity between A and B, the cyst blood flow grade is considered to be 2; when the overlapping area accounts for the percentage of the inner outline area of the cyst cavity to be between B and C, the cyst blood flow grade is considered to be 3; when the percentage of the overlapping area to the inner contour area of the cyst lumen is greater than C, the cyst blood flow rating is considered to be class 4. And calculating the IOU of the blood flow two-dimensional image and the inner outline of the capsule cavity, so as to obtain the percentage of the blood flow area in the capsule cavity to the total area of the capsule cavity.

During training of the initial convolutional neural network, the training samples can be amplified in a mode of horizontal overturning, vertical overturning, mirror image filling rotation, mosaic enhancement, affine transformation, random contrast enhancement, random brightness enhancement, image clipping and the like, so that the training sample quantity and model training accuracy are improved. Wherein each sample comprises: cyst detection frame, boundary, segmentation label, cyst class etc. the crowd of different ages, different regions can be covered to sample data to increase sample diversity.

Therefore, the convolutional neural network CNN provided in this embodiment can output information such as the intracavitary outline, the cyst category, the position, the size and the like, and then the scheme determines the percentage of the intracavitary blood flow and the intracavitary outline area based on the intracavitary outline and the blood flow two-dimensional image, and performs the blood flow level assessment by comparing with the threshold value set based on the assessment guideline. If necessary, the section of the continuous multi-frame cyst collected by the ultrasonic probe can be evaluated to accurately detect the blood flow level of the same cyst frame by frame.

In one embodiment, an embodiment may be provided in which the imaging method is applied to an ultrasound apparatus of a medical institution, a scientific research institution, or the like. The ultrasonic equipment is connected with the control terminal in a wired or wireless mode. The ultrasound device includes a probe, a host, and a display. The control terminal can be a panel special for controlling the ultrasonic equipment, and can also be a mobile phone, a tablet and the like for doctors to use.

Referring to fig. 3, a specific imaging and display process may include:

step 1: the physician scans the ovarian position using the probe.

Step 2: the method comprises the steps that a host of ultrasonic equipment performs ultrasonic imaging based on echo data obtained in a scanning process in a B mode, and inputs ultrasonic images into a cyst identification model for each frame of ultrasonic image to obtain the inner outline of a cyst cavity; determining the blood flow ratio of the capsule cavity according to the outline of the capsule cavity and the blood flow image corresponding to the ultrasonic image; and determining a blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

Step 3: and the host of the ultrasonic equipment transmits the ultrasonic image, the blood flow evaluation result and the like to the display, and finally, the display of the ultrasonic image and the blood flow evaluation result is carried out on the display. Wherein, can annotate on the ultrasonic image: cyst outline, diameter, location, etc.

Therefore, the present embodiment automatically and quantitatively calculates the cyst blood flow evaluation result based on the ultrasonic image of the ovarian cyst, so as to be referred by doctors. Of course, after the cyst blood flow level can be subjectively estimated by a doctor, the result output by the equipment is compared, so that the comprehensive cyst blood flow estimation result is given, the workload of the ultrasonic doctor can be reduced to a certain extent, and the cyst blood flow level estimation accuracy is improved.

An ultrasound image processing apparatus according to an embodiment of the present application is described below, and the implementation steps of the ultrasound image processing apparatus described below and the above embodiment may be referred to each other.

Referring to fig. 4, the present embodiment provides an ultrasound image processing apparatus, including:

an acquisition module 401, configured to acquire an ultrasound image of an ovarian cyst;

The detection module 402 is used for inputting an ultrasonic image into the cyst identification model to obtain the inner outline of the cyst cavity;

a determining module 403, configured to determine a balloon cavity blood flow ratio according to the balloon cavity inner contour and a blood flow image corresponding to the ultrasound image;

and the evaluation module 404 is used for determining the blood flow evaluation result of the ovarian cyst according to the cyst blood flow ratio.

In one embodiment, the detection module is specifically configured to:

Inputting the ultrasonic image into a cyst identification model so that a feature extraction module in the cyst identification model extracts image features in the ultrasonic image, and a target segmentation module in the cyst identification model performs mask segmentation based on the image features to obtain an intracapsular contour.

In one embodiment, the determining module is specifically configured to:

The ratio of the overlapping area to the area of the inner profile of the balloon is determined as the balloon blood flow ratio.

In one embodiment, the evaluation module is specifically configured to:

and determining a blood flow evaluation result according to the comparison result.

In one embodiment, the detection module is further configured to:

Inputting the ultrasonic image into a cyst identification model so that a feature extraction module in the cyst identification model extracts image features in the ultrasonic image, and a target detection module in the cyst identification model obtains a cyst category, a cyst position and a cyst size based on the image features; the cyst category, cyst location, and cyst size are displayed in the ultrasound image.

In one embodiment, the system further comprises a model training module, wherein the model training module can train to obtain a cyst identification model, and the system specifically comprises:

The sample acquisition unit is used for acquiring training samples; the training samples include: cyst category information, cyst location information, and cyst inner contour information;

In one embodiment, the sample amplification unit is specifically configured to:

the training samples are subjected to horizontal flipping, vertical flipping, mirror fill rotation, mosaic enhancement, affine transformation, random contrast enhancement, random brightness enhancement, and/or image cropping to obtain a training set.

In one embodiment, the method further comprises:

And the selection module is used for selecting one with the largest numerical value from the plurality of the cyst blood flow ratios if the plurality of cyst blood flow ratios are calculated for the same ovarian cyst, and executing the step in the evaluation module.

Therefore, the ultrasonic image processing device provided by the embodiment can automatically and quantitatively calculate the cyst blood flow evaluation result based on the ultrasonic image of the ovarian cyst for reference of doctors, so that the workload of the ultrasonic doctors can be reduced to a certain extent, and the evaluation accuracy of the cyst blood flow grade can be improved.

An electronic device provided in the embodiments of the present application is described below, and the implementation steps of the electronic device described below and the related embodiments may be referred to each other.

Further, the embodiment of the application also provides electronic equipment. The electronic device may be the server 50 shown in fig. 5 or the terminal 60 shown in fig. 6. Fig. 5 and 6 are block diagrams of electronic devices according to an exemplary embodiment, and the contents of the diagrams should not be construed as limiting the scope of use of the present application.

Fig. 5 is a schematic structural diagram of a server according to an embodiment of the present application. The server 50 may specifically include: at least one processor 51, at least one memory 52, a power supply 53, a communication interface 54, an input output interface 55, and a communication bus 56. Wherein the memory 52 is adapted to store a computer program that is loaded and executed by the processor 51 to implement the relevant steps in ultrasound image processing as disclosed in any of the previous embodiments.

In this embodiment, the power supply 53 is configured to provide an operating voltage for each hardware device on the server 50; the communication interface 54 can create a data transmission channel between the server 50 and an external device, and the communication protocol to be followed is any communication protocol applicable to the technical solution of the present application, which is not specifically limited herein; the input/output interface 55 is used for acquiring external input data or outputting external output data, and the specific interface type thereof may be selected according to the specific application needs, which is not limited herein.

The memory 52 may be a carrier for storing resources, such as a read-only memory, a random access memory, a magnetic disk, or an optical disk, and the resources stored thereon include an operating system 521, a computer program 522, and data 523, and the storage may be temporary storage or permanent storage.

The operating system 521 is used for managing and controlling various hardware devices on the Server 50 and the computer program 522 to implement the operation and processing of the data 523 in the memory 52 by the processor 51, which may be Windows Server, netware, unix, linux, etc. The computer program 522 may further include a computer program capable of performing other specific tasks in addition to the computer program capable of performing the ultrasound image processing method disclosed in any of the foregoing embodiments. The data 523 may include data such as application program developer information in addition to data such as application program update information.

Fig. 6 is a schematic structural diagram of a terminal according to an embodiment of the present application, and the terminal 60 may specifically include, but is not limited to, a smart phone, a tablet computer, a notebook computer, a desktop computer, or the like.

Generally, the terminal 60 in this embodiment includes: a processor 61 and a memory 62.

Processor 61 may include one or more processing cores, such as a 4-core processor, an 8-core processor, etc. The processor 61 may be implemented in at least one hardware form of DSP (DIGITAL SIGNAL Processing), FPGA (Field-Programmable gate array), PLA (Programmable Logic Array ). The processor 61 may also include a main processor, which is a processor for processing data in an awake state, also called a CPU (Central Processing Unit ), and a coprocessor; a coprocessor is a low-power processor for processing data in a standby state. In some embodiments, the processor 61 may integrate a GPU (Graphics Processing Unit, image processor) for rendering and drawing of content required to be displayed by the display screen. In some embodiments, the processor 61 may also include an AI (ARTIFICIAL INTELLIGENCE ) processor for processing computing operations related to machine learning.

Memory 62 may include one or more computer-readable storage media, which may be non-transitory. Memory 62 may also include high-speed random access memory, as well as non-volatile memory, such as one or more magnetic disk storage devices, flash memory storage devices. In the present embodiment, the memory 62 is at least used for storing a computer program 621 that, when loaded and executed by the processor 61, is capable of implementing the relevant steps in the ultrasound image processing method performed by the terminal side as disclosed in any of the foregoing embodiments. In addition, the resources stored by the memory 62 may also include an operating system 622, data 623, and the like, and the storage manner may be transient storage or permanent storage. Wherein the operating system 622 may include Windows, unix, linux, etc. The data 623 may include, but is not limited to, update information of the application.

In some embodiments, the terminal 60 may further include a display 63, an input-output interface 64, a communication interface 65, a sensor 66, a power supply 67, and a communication bus 68.

Those skilled in the art will appreciate that the structure shown in fig. 6 is not limiting of the terminal 60 and may include more or fewer components than shown.

Further, the electronic device described in this embodiment may include an ultrasonic diagnostic device and/or an ultrasonic workstation. The ultrasonic workstation can be matched with various types of ultrasonic diagnostic equipment, and is equipment integrating functional modules of patient registration, image acquisition, diagnosis and editing, report printing, image post-processing, medical record inquiring, statistical analysis and the like. In general, an ultrasonic diagnostic device is connected with an ultrasonic workstation by a standard video cable, and the ultrasonic workstation is also connected with a printer and other devices.

A storage medium provided in the embodiments of the present application is described below, and the implementation steps of the storage medium and the embodiments described below may be referred to each other.

Further, the embodiment of the application also discloses a storage medium, wherein the storage medium stores computer executable instructions, and when the computer executable instructions are loaded and executed by a processor, the ultrasonic image processing method disclosed in any embodiment is realized. For specific steps of the method, reference may be made to the corresponding contents disclosed in the foregoing embodiments, and no further description is given here.

It should be noted that the foregoing is only a preferred embodiment of the present application, and is not intended to limit the present application, but any modification, equivalent replacement, improvement, etc. which fall within the spirit and principles of the present application should be included in the scope of the present application.

In this specification, each embodiment is described in a progressive manner, and each embodiment is mainly described in a different point from other embodiments, so that the same or similar parts between the embodiments are referred to each other.

The principles and embodiments of the present application have been described herein with reference to specific examples, the description of which is intended only to assist in understanding the methods of the present application and the core ideas thereof; meanwhile, as those skilled in the art will have variations in the specific embodiments and application scope in accordance with the ideas of the present application, the present description should not be construed as limiting the present application in view of the above.

Claims

1. An ultrasound image processing method, comprising:

Acquiring an ultrasonic image of the ovarian cyst;

2. The method of claim 1, wherein said inputting the ultrasound image into a cyst identification model results in a cyst inner contour comprising:

3. The method of claim 1, wherein said determining a balloon blood flow ratio from the balloon inner profile and the corresponding blood flow image of the ultrasound image comprises:

4. The method of claim 1, wherein said determining a blood flow assessment of said ovarian cyst from said luminal blood flow ratio comprises:

and determining the blood flow evaluation result according to the comparison result.

5. The method according to any one of claims 1 to 4, further comprising:

6. The method of any one of claims 1 to 4, wherein the training process of the cyst identification model comprises:

Amplifying the training sample to obtain a training set;

7. The method according to any one of claims 1 to 4, further comprising:

8. The method of any one of claims 1 to 4, wherein said determining a blood flow assessment of said ovarian cyst from said luminal blood flow ratio comprises:

9. An ultrasonic image processing apparatus, comprising:

10. An electronic device comprising a processor and a memory; wherein the memory is for storing a computer program to be loaded and executed by the processor to implement the method of any one of claims 1 to 8.

11. The electronic device of claim 10, wherein the electronic device comprises an ultrasonic diagnostic device and/or an ultrasonic workstation.

12. A storage medium having stored therein computer executable instructions which, when loaded and executed by a processor, implement the method of any one of claims 1 to 8.