阅读说明：本技术 智能辅助引导方法、超声诊断设备及存储介质 (Intelligent auxiliary guiding method, ultrasonic diagnosis device and storage medium ) 是由 莫若理 于 2019-11-09 设计创作，主要内容包括：本发明提供一种智能辅助引导方法,包括：获取检测指令,所述检测指令至少包括待检测对象信息；获取超声探头检测到的第一超声图像；基于所述待检测对象信息,获得所述待检测对象对应的三维参考模型；判断所述第一超声图像是否是所述待检测对象的标准切面图像,若否,则至少基于所述第一超声图像和所述三维参考模型,利用超声探头移动引导模型进行处理,生成用于所述超声探头移动的指示信息。(The invention provides an intelligent auxiliary guiding method, which comprises the following steps: acquiring a detection instruction, wherein the detection instruction at least comprises information of an object to be detected; acquiring a first ultrasonic image detected by an ultrasonic probe; obtaining a three-dimensional reference model corresponding to the object to be detected based on the information of the object to be detected; and judging whether the first ultrasonic image is a standard tangent plane image of the object to be detected, if not, processing by using an ultrasonic probe movement guide model at least based on the first ultrasonic image and the three-dimensional reference model to generate indication information for the movement of the ultrasonic probe.)

1. An intelligent auxiliary guiding method is characterized by comprising the following steps:

acquiring a detection instruction, wherein the detection instruction at least comprises information of an object to be detected;

acquiring a first ultrasonic image detected by an ultrasonic probe;

obtaining a three-dimensional reference model corresponding to the object to be detected based on the information of the object to be detected;

judging whether the first ultrasonic image is a standard section image of the object to be detected, if not,

processing with an ultrasound probe movement guidance model based on at least the first ultrasound image and the three-dimensional reference model to generate indication information for the ultrasound probe movement.

2. The method of claim 1, further comprising:

and guiding the ultrasonic probe to move based on the indication information to obtain an updated first ultrasonic image, judging whether the updated first ultrasonic image is the standard section image of the object to be detected, if not, processing by using an ultrasonic probe movement guide model at least based on the updated ultrasonic image and the three-dimensional reference model to generate indication information for the movement of the ultrasonic probe, and repeating the steps until the updated first ultrasonic image is the standard section image of the object to be detected.

3. The method of claim 1, wherein the determining whether the first ultrasound image is a standard sectional image of the object to be detected comprises:

processing by using a standard tangent plane matching model based on the three-dimensional reference model corresponding to the object to be detected and the first ultrasonic image to obtain a matching result;

when the matching result is not less than a preset first matching threshold value, determining that the first ultrasonic image is a standard tangent plane image,

and when the matching result is smaller than the preset first matching threshold value, determining that the first ultrasonic image is not a standard tangent plane image.

4. The method of claim 3, wherein the standard tangent plane matching model is a deep learning model,

the standard tangent plane matching model is obtained by the following method:

acquiring a first training set, wherein the first training set comprises a plurality of first sample ultrasonic images and marking data, detection objects of contents corresponding to the first sample ultrasonic images are the same, and the marking data at least comprises a matching result obtained based on a three-dimensional reference model of the detection objects;

and training the initial model by using the first training set to obtain a standard tangent plane matching model.

5. The method of claim 1, wherein the processing with an ultrasound probe movement guidance model based at least on the first ultrasound image to generate the indication information for the ultrasound probe movement comprises:

acquiring pose information of the ultrasonic probe, wherein the pose information at least comprises position information and/or angle information;

and processing the three-dimensional reference model and the first ultrasonic image corresponding to the object to be detected by using an ultrasonic probe movement guide model according to the pose information of the ultrasonic probe to obtain indication information for the movement of the ultrasonic probe.

6. The method of claim 5, wherein the ultrasound probe movement guidance model is a deep learning model,

the ultrasonic probe movement guiding model is obtained by the following method:

acquiring a second training set, wherein the second training set comprises a plurality of second sample ultrasonic images and marking data, detection objects of contents corresponding to the second sample ultrasonic images are the same, and the marking data at least comprises pose information of an ultrasonic probe corresponding to the second sample ultrasonic images and indication information of ultrasonic probe movement obtained based on a three-dimensional reference model of the detection objects;

and training the initial model by using the second training set to obtain an ultrasonic probe movement guiding model.

7. The method of claim 1, the indication information comprising at least one of a path of movement, a distance of movement, a rotation angle for an ultrasound probe.

8. The method of claim 1, further comprising:

and judging whether the object to be detected has a next target detection position, if so, determining indication information of the ultrasonic probe moving to the next target detection position according to the pose information of the ultrasonic probe.

9. An ultrasonic diagnostic apparatus characterized by comprising:

a storage medium storing a computer program;

a processor for executing the computer program to implement the steps of the intelligent assisted boot method according to any of claims 1 to 8.

10. A computer storage medium comprising, in combination,

the computer storage medium has stored therein a computer program which, when being executed by a processor, is adapted to carry out the steps of the intelligent assisted booting method according to one of claims 1 to 8.

Technical Field

The present invention relates to a guidance method, and more particularly, to an intelligent auxiliary guidance method, an ultrasonic diagnostic apparatus, and a storage medium.

Background

Medical ultrasonic detection is a conventional tomographic plane imaging technology, and can reflect a tissue tomographic interface image of a human body to a doctor for the doctor to diagnose and judge the health condition of a patient. In the detection process, in order to detect a part to be diagnosed, a doctor needs to place an ultrasonic probe on a part corresponding to a human body, then adjust the position or the angle of the probe by observing a display screen, and finally obtain an ultrasonic image of a required standard tangent plane.

Disclosure of Invention

The invention aims to overcome the defects in the prior art and provides an intelligent auxiliary guiding method and ultrasonic diagnostic equipment applying the method; can make things convenient for the doctor to operate, improve work efficiency. The embodiment of the invention adopts the technical scheme that:

acquiring a detection instruction, wherein the detection instruction at least comprises information of an object to be detected; acquiring a first ultrasonic image detected by an ultrasonic probe; obtaining a three-dimensional reference model corresponding to the object to be detected based on the information of the object to be detected; and judging whether the first ultrasonic image is a standard tangent plane image of the object to be detected, if not, processing by using an ultrasonic probe movement guide model at least based on the first ultrasonic image and the three-dimensional reference model to generate indication information for the movement of the ultrasonic probe.

In some embodiments, further comprising: and guiding the ultrasonic probe to move based on the indication information to obtain an updated first ultrasonic image, judging whether the updated first ultrasonic image is the standard section image of the object to be detected, if not, processing by using an ultrasonic probe movement guide model at least based on the updated ultrasonic image and the three-dimensional reference model to generate indication information for the movement of the ultrasonic probe, and repeating the steps until the updated first ultrasonic image is the standard section image of the object to be detected.

In some embodiments, the determining whether the first ultrasound image is a standard sectional image of the object to be detected includes: processing by using a standard tangent plane matching model based on the three-dimensional reference model corresponding to the object to be detected and the first ultrasonic image to obtain a matching result; and when the matching result is not smaller than a preset first matching threshold, determining that the first ultrasonic image is a standard tangent plane image, and when the matching result is smaller than the preset first matching threshold, determining that the first ultrasonic image is not the standard tangent plane image.

In some embodiments, the standard tangent plane matching model is a deep learning model, and the standard tangent plane matching model is obtained by the following method: acquiring a first training set, wherein the first training set comprises a plurality of first sample ultrasonic images and marking data, detection objects of contents corresponding to the first sample ultrasonic images are the same, and the marking data at least comprises a matching result obtained based on a three-dimensional reference model of the detection objects; and training the initial model by using the first training set to obtain a standard tangent plane matching model.

In some embodiments, said processing with an ultrasound probe movement guidance model based on at least said first ultrasound image, generating indication information for said ultrasound probe movement, comprises: acquiring pose information of the ultrasonic probe, wherein the pose information at least comprises position information and/or angle information; and processing the three-dimensional reference model and the first ultrasonic image corresponding to the object to be detected by using an ultrasonic probe movement guide model according to the pose information of the ultrasonic probe to obtain indication information for the movement of the ultrasonic probe.

In some embodiments, the ultrasound probe movement guidance model is a deep learning model, the ultrasound probe movement guidance model being obtained by: acquiring a second training set, wherein the second training set comprises a plurality of second sample ultrasonic images and marking data, detection objects of contents corresponding to the second sample ultrasonic images are the same, and the marking data at least comprises pose information of an ultrasonic probe corresponding to the second sample ultrasonic images and indication information of ultrasonic probe movement obtained based on a three-dimensional reference model of the detection objects; and training the initial model by using the second training set to obtain an ultrasonic probe movement guiding model.

In some embodiments, the indication information comprises at least one of a movement path, a movement distance, a rotation angle for the ultrasound probe.

In some embodiments, further comprising: and judging whether the object to be detected has a next target detection position, if so, determining indication information of the ultrasonic probe moving to the next target detection position according to the pose information of the ultrasonic probe.

An embodiment of the present invention further provides an ultrasound diagnostic apparatus, including: a storage medium storing a computer program; a processor for executing the computer program to implement the steps of the intelligent assisted boot method of any of the above.

An embodiment of the present invention further provides a computer storage medium, where a computer program is stored, and when the computer program is executed by a processor, the computer program is used to implement the steps of any one of the above-mentioned intelligent auxiliary booting methods.

The embodiment of the invention has the advantages that: whether an ultrasonic image acquired by the ultrasonic probe is a standard tangent plane or not is judged through the standard tangent plane matching model, the specific position of the ultrasonic probe on the object to be detected is obtained through the deep learning model, and indication information for guiding the ultrasonic probe is generated, so that the ultrasonic probe is driven to correct the pose, the examination difficulty of a doctor is reduced, the operation time of the doctor is shortened, and the quality of the ultrasonic image can be effectively ensured.

Drawings

Fig. 1 is a flowchart illustrating an intelligent assisted guidance method 100 according to an embodiment of the invention.

Fig. 2 is a flowchart of another intelligent assisted booting method 200 according to an embodiment of the invention.

Fig. 3 is a flowchart of a standard tangent plane matching determination method 300 according to an embodiment of the invention.

FIG. 4 is a flowchart of a standard tangent plane matching model training method 400 according to an embodiment of the invention.

Fig. 5 is a flowchart of an ultrasound probe movement guidance model training method 500 according to an embodiment of the present invention.

Detailed Description

In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.

In an embodiment of the present invention, an intelligent auxiliary guiding method is provided, which can be applied to an ultrasonic diagnostic apparatus, for example, a handheld ultrasonic diagnostic apparatus. As illustrated in fig. 1, the method 100 may include:

step 110: and acquiring a detection instruction, wherein the detection instruction at least comprises information of an object to be detected.

In some embodiments, an operator (e.g., a doctor) may input a detection instruction through an input device (e.g., a touch screen, a mouse, a keyboard, etc.), information of the detection instruction may include at least information of an object to be detected, and the object to be detected may include a human body part, an organ, a tissue, etc. to be detected. For example, the examination site may include, but is not limited to, heart, kidney, liver, blood vessels, gall bladder, uterus, breast, fetus, thyroid, and the like. In some embodiments, the detection instruction may include a plurality of objects to be detected, for example, the object to be detected includes a heart and a kidney.

Step 120: a first ultrasound image detected by an ultrasound probe is acquired.

In some embodiments, the operator may place an ultrasound probe on the object to be detected, thereby causing the ultrasound diagnostic apparatus to acquire the first ultrasound image. It will be appreciated that in order to speed up the detection of the object to be detected, the operator may place the ultrasound probe at a position on the surface of the body that corresponds approximately to the object to be detected, although the placement position need not be precise.

Step 130: and acquiring a three-dimensional reference model corresponding to the object to be detected based on the information of the object to be detected.

In some embodiments, a three-dimensional reference model corresponding to a pre-stored object to be detected may be obtained according to the information of the object to be detected. For example, when the object to be detected is a heart, a pre-stored three-dimensional reference model of the heart is acquired. In some embodiments, the three-dimensional reference model may include standard slice ultrasound image data from different angles of the object to be detected. In some embodiments, the three-dimensional reference model may further include pose information of the ultrasound probe corresponding to each detection point of the object to be detected, where the pose information includes position information and/or angle information, and the position information may be represented according to a coordinate position, for example, by using a cartesian coordinate system.

Step 140: and judging whether the first ultrasonic image is a standard tangent plane image of the object to be detected, if not, processing by using an ultrasonic probe movement guide model at least based on the first ultrasonic image and the three-dimensional reference model to generate indication information for the movement of the ultrasonic probe.

In some embodiments, a predetermined algorithm may be used to determine whether the first ultrasound image is a standard sectional image, which is described in detail in fig. 3-4 and will not be described herein again.

Step 150: when the first ultrasonic image is not the standard tangent plane image of the object to be detected, the ultrasonic probe movement guiding model can be utilized for processing, and indication information for the ultrasonic probe movement is generated.

In some embodiments, pose information of the ultrasound probe may be acquired, the pose information including at least position information and/or angle information; and processing the three-dimensional reference model and the first ultrasonic image corresponding to the object to be detected by using an ultrasonic probe movement guide model according to the pose information of the ultrasonic probe to obtain indication information for the movement of the ultrasonic probe.

In some embodiments, the indication information comprises at least one of a movement path, a movement distance, a rotation angle for the ultrasound probe. In some embodiments, the indication information may indicate a direction and a rotation angle at which the ultrasound probe moves to a detection position where a standard slice image may be acquired, for example, the indication information is: to the right and to the clockwise. In some embodiments, the ultrasound probe includes a navigation indicator thereon, which may include but is not limited to a vibrator, an LED indicator light, a projection light, and the indication information may be transmitted to the ultrasound probe, which may output the indication information in the form of an indicator light or played with voice, projected to a target location, and the like.

The ultrasound probe movement guidance model may be a deep learning model whose input data is the first ultrasound image and the three-dimensional reference model and whose output data is indication information guiding the ultrasound probe movement. For the ultrasound probe movement guidance model, reference may be made to the related description of fig. 4, which is not described herein again.

As shown in fig. 2, the booting method 200 may further include:

step 260: and based on the indication information, guiding the ultrasonic probe to move to obtain an updated first ultrasonic image, judging whether the updated first ultrasonic image is the standard section image of the object to be detected, if not, processing by using an ultrasonic probe movement guide model at least based on the updated ultrasonic image and the three-dimensional reference model to generate indication information for the movement of the ultrasonic probe, and repeating the steps until the updated first ultrasonic image is the standard section image of the object to be detected.

As shown in fig. 3, the method 300 for determining whether the first ultrasound image is a standard sectional image of the object to be detected may specifically include:

step 310: and processing by using a standard tangent plane matching model based on the three-dimensional reference model corresponding to the object to be detected and the first ultrasonic image to obtain a matching result.

In some embodiments, the standard tangent plane matching model is a deep learning model, the input data is a three-dimensional reference model and a first ultrasonic image of the object to be detected, and the output data is a matching result of the first ultrasonic image with respect to the standard tangent plane image of the object to be detected. The matching result may be a continuous value, e.g., 0.1, 0.9, and the matching result may be a binary result, e.g., 0 or 1,0 indicating a matching failure and 1 indicating a matching success. The details of the standard matching model are described in fig. 4, and will not be described herein.

Step 320: and when the matching result is not smaller than a preset first matching threshold value, determining that the first ultrasonic image is a standard tangent plane image.

A first matching threshold may be obtained in advance, for example, the first matching threshold is set to 0.8, and when the matching result is 0.9, the first ultrasound image is determined to be a standard tangent plane image.

Step 330: and when the matching result is smaller than the preset first matching threshold value, determining that the first ultrasonic image is not a standard tangent plane image.

In some embodiments, the first matching threshold is set to 0.8, and when the matching result is 0.7, it is determined that the first ultrasound image is not a standard section image.

As illustrated in fig. 4, the standard tangent plane matching model may be obtained by the method 400:

step 410: acquiring a first training set, wherein the first training set comprises a plurality of first sample ultrasonic images and marking data, detection objects of contents corresponding to the first sample ultrasonic images are the same, and the marking data at least comprises a matching result obtained based on a three-dimensional reference model of the detection objects.

In some embodiments, the ultrasound image data of the same detected object should be included in the first training set, for example, the content in the first sample ultrasound image corresponds to the heart of the human body.

In some embodiments, a preset matching algorithm may be used to calculate a similarity between the first sample ultrasound image and the standard tangent plane of the object to be detected, and the similarity is used as a matching result. The matching algorithm may include, but is not limited to, mean absolute difference algorithm (MAD), sum of absolute difference algorithm (SAD), sum of squared error algorithm (SSD), mean sum of squared error algorithm (MSD), normalized product correlation algorithm (NCC), Sequential Similarity Detection Algorithm (SSDA), hadamard transform algorithm (SATD).

Step 420: and training the initial model by using the first training set to obtain a standard tangent plane matching model.

As shown in fig. 5, the ultrasound probe movement guidance model is obtained by the method 500:

step 510: and acquiring a second training set, wherein the second training set comprises a plurality of second sample ultrasonic images and marking data, detection objects of contents corresponding to the second sample ultrasonic images are the same, and the marking data at least comprises pose information of an ultrasonic probe corresponding to the second sample ultrasonic images and indication information of ultrasonic probe movement obtained based on a three-dimensional reference model of the detection objects.

In some embodiments, the ultrasound image data of the same kind of test object is included in the second training set, for example, the contents in the second sample ultrasound image correspond to the thyroid of the human body.

Step 520: and training the initial model by using the second training set to obtain an ultrasonic probe movement guiding model.

In some embodiments, it may also be determined whether the object to be detected has a next target detection position, and if so, the indication information that the ultrasonic probe moves to the next target detection position is determined according to the pose information of the ultrasonic probe.

As another embodiment of the present invention, a storage medium is provided, wherein the storage medium stores at least one program instruction for being loaded and executed by a processor to implement the intelligent assisted booting method as described above.

It should be understood that the storage medium provided by the present invention can store the program instructions for executing the intelligent auxiliary guiding method described above, thereby enabling the doctor to quickly start the diagnosis work and improving the work efficiency.

As another embodiment of the present invention, there is provided an ultrasonic diagnostic apparatus including a processor and a storage medium, the processor being configured to load and execute program instructions on the storage medium. The storage medium stores at least one program instruction for being loaded and executed by a processor to implement the ultrasound parameter intelligent control method as described above.

The ultrasonic diagnosis device provided by the invention adopts the storage medium and stores the program instruction for executing the ultrasonic parameter intelligent control method, so that a doctor can quickly start diagnosis work and the work efficiency is improved.

Finally, it should be noted that the above embodiments are only for illustrating the technical solutions of the present invention and not for limiting, and although the present invention has been described in detail with reference to examples, it should be understood by those skilled in the art that modifications or equivalent substitutions may be made on the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, which should be covered by the claims of the present invention.