Method, device and equipment for marking section of ultrasonic image and readable storage medium

Abstract

The application discloses a kind of section marking method, device, ultrasonic medical equipment and readable storage medium of ultrasonic image, the method includes: obtaining the nodule section image collected by ultrasonic equipment;Wherein, nodule section image includes nodule region;Nodule section image is carried out image segmentation, and the blood vessel region in nodule section image is determined;Obtain the marking information of blood vessel region in nodule section image;Wherein, marking information includes position marking information;Marking information is displayed in nodule section image;The application is carried out image segmentation to nodule section image, determines the blood vessel region in nodule section image, can be segmented out the blood vessel region in nodule section image;By displaying marking information in nodule section image, the position of blood vessel region can be displayed in real time in the nodule section image collected by ultrasonic equipment, to guide doctor to choose the best puncture section away from blood vessel under ultrasonic guidance, to guide doctor to needle, improve puncture safety.

Description

Technical Field

[0001] This invention relates to the field of image recognition technology, and in particular to a method, apparatus, ultrasound medical device, and readable storage medium for cross-sectional marking of ultrasound images. Background Technology

[0002] Thyroid nodules are a common thyroid disease with an incidence rate of 19%-67%, of which 5%-15% are malignant. Thyroid fine-needle aspiration biopsy is an invasive procedure to determine the benign or malignant nature of thyroid tissue. Ultrasound-guided thyroid fine-needle aspiration is an invasive technique used to diagnose the benign or malignant nature of thyroid tissue. Its most common complications are perithyroid hemorrhage and hematoma formation, mostly caused by puncture of blood vessels during the procedure or improper compression after the procedure.

[0003] Currently, ultrasound-guided thyroid biopsy relies on the surgeon manually selecting the incision plane. This requires the operator to repeatedly switch to Color mode to ensure there are no large blood vessels along the needle path, guaranteeing a successful biopsy and obtaining thyroid nodule tissue or cytological fluid for pathological examination. Ultimately, this leads to a definitive diagnosis and guides treatment. Therefore, enabling surgeons to easily select the optimal incision plane under ultrasound guidance, thus improving biopsy safety, is a pressing issue that needs to be addressed. Summary of the Invention

[0004] The purpose of this invention is to provide a method, device, ultrasound medical device, and readable storage medium for marking sections of ultrasound images, so as to facilitate doctors in selecting the best section under ultrasound guidance, guide doctors in needle insertion, and improve puncture safety.

[0005] To solve the above-mentioned technical problems, the present invention provides a method for section marking of ultrasound images, comprising:

[0006] Acquire a cross-sectional image of a nodule obtained by an ultrasound device; wherein the cross-sectional image of the nodule includes the nodule region;

[0007] The nodule cross-sectional image is segmented to determine the vascular region in the nodule cross-sectional image;

[0008] Obtain the marking information of the vascular region in the nodule cross-sectional image; wherein, the marking information includes location marking information;

[0009] The marking information is displayed in the nodule cross-sectional image.

[0010] Optionally, the step of performing image segmentation on the nodule cross-sectional image to determine the vascular region in the nodule cross-sectional image includes:

[0011] Based on the pixel values ​​within the nodule cross-sectional image, the nodule cross-sectional image is segmented to determine the vascular region within the nodule cross-sectional image; wherein, the nodule cross-sectional image is an ultrasound image acquired by the ultrasound device in color mode.

[0012] Optionally, the step of segmenting the nodule cross-sectional image based on pixel values ​​within the nodule cross-sectional image to determine the vascular region in the nodule cross-sectional image includes:

[0013] Based on the pixel values ​​within the nodule cross-sectional image, feature analysis and semantic segmentation are performed on the nodule cross-sectional image to obtain the vascular region in the nodule cross-sectional image.

[0014] Optionally, the marking information further includes, when considering the proportion of blood vessel area, the step of obtaining marking information of the blood vessel region in the nodule cross-sectional image, including:

[0015] Calculate the vascular area corresponding to the vascular region;

[0016] The ratio of the blood vessel area to the nodule cross-sectional image is taken as the proportion of the blood vessel area.

[0017] Optionally, acquiring the nodule cross-sectional image obtained by the ultrasound device includes:

[0018] According to the acquired color mode start command, the ultrasound device is controlled to turn on the color mode and activate the grayscale blood flow function to acquire the nodule cross-sectional image collected by the ultrasound device.

[0019] Optionally, before acquiring the nodule cross-sectional image obtained by the ultrasound device, the method further includes:

[0020] Based on the acquired section recognition instruction, target recognition is performed on the real-time ultrasound images acquired by the ultrasound equipment to determine the target region in the real-time ultrasound images; wherein, the target region includes nodule regions;

[0021] Obtain prompt information for identifying the target region in the real-time ultrasound image; wherein, the prompt information includes location prompt information;

[0022] The prompt information is displayed in the real-time ultrasound image to indicate the area to be scanned further.

[0023] Optionally, when the identified target area further includes the tracheal region and the arteriovenous region, displaying the prompt information in the real-time ultrasound image includes:

[0024] The prompt information is displayed in real time on the real-time ultrasound image to indicate areas where nodules are clearly visible and avoid the trachea and arteries / veins for further scanning.

[0025] Optionally, acquiring the nodule cross-sectional image obtained by the ultrasound device includes:

[0026] Based on the vascular marking instructions obtained by the ultrasound equipment during scanning within the area, the nodule cross-sectional image is acquired.

[0027] Optionally, the step of performing target recognition on the real-time ultrasound image acquired by the ultrasound device according to the acquired section recognition instruction, and determining the target region in the real-time ultrasound image, includes:

[0028] According to the section recognition instruction, a preset neural network model is used to perform target recognition on the real-time ultrasound image to determine the target region in the real-time ultrasound image.

[0029] The present invention also provides a section marking device for ultrasound images, comprising:

[0030] An image acquisition module is used to acquire cross-sectional images of nodules obtained by ultrasound equipment; wherein, the cross-sectional images of nodules include nodule regions;

[0031] The image segmentation module is used to segment the nodule cross-sectional image and determine the blood vessel region in the nodule cross-sectional image;

[0032] A marker acquisition module is used to acquire marker information of the vascular region in the nodule cross-sectional image; wherein, the marker information includes location marker information;

[0033] A marker display module is used to display the marker information in the nodule cross-sectional image.

[0034] The present invention also provides an ultrasound medical device, comprising:

[0035] Memory, used to store computer programs;

[0036] A processor is configured to implement the steps of the ultrasound image section marking method as described above when executing the computer program.

[0037] Furthermore, the present invention also provides a readable storage medium storing a computer program that, when executed by a processor, implements the steps of the ultrasound image section marking method as described above.

[0038] The present invention provides a method for cross-sectional marking of ultrasound images, comprising: acquiring a cross-sectional image of a nodule acquired by an ultrasound device; wherein the cross-sectional image of the nodule includes a nodule region; performing image segmentation on the cross-sectional image of the nodule to determine the vascular region in the cross-sectional image of the nodule; acquiring marking information of the vascular region in the cross-sectional image of the nodule; wherein the marking information includes location marking information; and displaying the marking information in the cross-sectional image of the nodule.

[0039] As can be seen, this invention, by segmenting the nodule cross-sectional image, identifies the vascular region within it, thus enabling the segmentation of the vascular region. By displaying marking information in the nodule cross-sectional image, the location of the vascular region can be indicated in real-time within the nodule cross-sectional image acquired by the ultrasound device. This allows doctors to conveniently select the optimal puncture section away from the blood vessel under ultrasound guidance, thereby guiding needle insertion and improving puncture safety. Furthermore, this invention also provides an ultrasound image section marking device, an ultrasound medical device, and a readable storage medium, which also possess the aforementioned beneficial effects. Attached Figure Description

[0040] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on the provided drawings without creative effort.

[0041] Figure 1 A flowchart illustrating a method for cross-sectional marking of an ultrasound image provided in an embodiment of the present invention;

[0042] Figure 2 A flowchart of another method for cross-sectional marking of ultrasound images provided in an embodiment of the present invention.

[0043] Figure 3 A structural block diagram of a section marking device for ultrasound images provided in an embodiment of the present invention;

[0044] Figure 4 This is a schematic diagram of the structure of an ultrasound medical device provided in an embodiment of the present invention;

[0045] Figure 5 This is a schematic diagram of the specific structure of an ultrasound medical device provided in an embodiment of the present invention. Detailed Implementation

[0046] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0047] Please refer to Figure 1 , Figure 1 A flowchart illustrating a method for cross-sectional marking of ultrasound images provided in an embodiment of the present invention. The method may include:

[0048] Step 101: Acquire a cross-sectional image of the nodule from an ultrasound device; wherein the cross-sectional image of the nodule includes the nodule region.

[0049] It is understandable that the nodule cross-sectional image in this step can be a cross-sectional image (i.e., ultrasound image) containing the nodule region acquired by ultrasound equipment, which is an ultrasound image that needs to be marked with vascular area indication.

[0050] Specifically, the method for obtaining the nodule cross-sectional image acquired by the ultrasound device in this step can be set by the designer according to the practical scenario and user needs. For example, the processor can directly receive the original ultrasound image acquired by the ultrasound probe in the ultrasound device and use the original ultrasound image as the nodule cross-sectional image; the processor can also receive the original ultrasound image acquired by the ultrasound probe in the ultrasound device and preprocess the original ultrasound image to obtain the preprocessed nodule cross-sectional image; this embodiment does not impose any restrictions on this.

[0051] Correspondingly, the specific process for obtaining the nodule cross-sectional image acquired by the ultrasound device in this step can be set by the designer according to the practical scenario and user needs. For example, the processor can obtain the nodule cross-sectional image acquired by the ultrasound device according to the acquired vascular marking instruction; that is, the processor can use the ultrasound image acquired by the ultrasound device as the nodule cross-sectional image after acquiring the vascular marking instruction. Correspondingly, if image segmentation of the nodule cross-sectional image requires ultrasound images acquired by the ultrasound device in color mode (i.e., nodule cross-sectional images), the aforementioned vascular marking instruction can be directly set as a color mode activation instruction. For example, in this step, the processor can control the ultrasound device to turn on color mode (Color mode) according to the acquired color mode activation instruction to acquire the nodule cross-sectional image acquired by the ultrasound device. That is, the nodule cross-sectional image is an ultrasound image acquired by the ultrasound device in color mode. In order to facilitate the doctor's viewing of the displayed nodule cross-sectional image and avoid repeated activation of color mode, in this step, the processor can control the ultrasound device to turn on color mode and activate the grayscale blood flow function (B Flow function) according to the acquired color mode activation instruction to acquire the nodule cross-sectional image acquired by the ultrasound device. That is, the nodule cross-sectional image is an ultrasound image acquired by the ultrasound device in color mode with the grayscale blood flow function activated.

[0052] It should be noted that in this step, the processor can acquire ultrasound images (i.e., nodule cross-sectional images) collected by the ultrasound device within the nodule area. For example, the doctor can operate the ultrasound probe of the ultrasound device to the nodule area and activate the Color mode to control the ultrasound device to turn on the color mode and perform a scan, displaying the blood vessels around the nodule. At the same time, the BFlow function is activated so that the processor of the ultrasound device can acquire the nodule cross-sectional images obtained by the ultrasound probe of the ultrasound device.

[0053] Correspondingly, to facilitate doctors in determining the extent of nodules, the processor can perform real-time target recognition on each frame of ultrasound image (i.e., real-time ultrasound image) acquired by the ultrasound device before this step, displaying and prompting the area where the identified target (such as nodules, trachea, and arteries and veins) is located in the ultrasound image. This allows doctors to determine the area of ​​the nodule that is relatively clear and avoids the trachea and arteries and veins based on the displayed target area. In other words, in this embodiment, before step 101, the process may also include: performing target recognition on the real-time ultrasound image acquired by the ultrasound device according to the acquired section recognition instruction to determine the target area in the real-time ultrasound image; acquiring prompt information about the target area in the real-time ultrasound image; and displaying the prompt information in the real-time ultrasound image. The target area includes the nodule area, and the prompt information includes location prompt information.

[0054] Step 102: Perform image segmentation on the nodule cross-sectional image to determine the vascular region in the nodule cross-sectional image.

[0055] Understandably, in this step, the processor can segment the vascular region in the nodule cross-section image by image segmentation, thereby determining the location and extent of the vascular region in the nodule cross-section image.

[0056] Specifically, the method by which the processor performs image segmentation on the nodule cross-sectional image to determine the vascular region within it in this step can be set by the designer according to the practical scenario and user needs. For example, since the color difference between blood vessels and other tissues is significant in the color mode of ultrasound equipment, this embodiment can utilize this characteristic to perform image segmentation calculations using pixel values ​​within the color mode area to distinguish blood vessels from other tissues. In other words, in this step, the processor can perform image segmentation on the nodule cross-sectional image based on the pixel values ​​within the image to determine the vascular region within it. The nodule cross-sectional image is an ultrasound image acquired by the ultrasound equipment in color mode. Specifically, the nodule cross-sectional image can be an ultrasound image acquired by the ultrasound equipment in color mode with the grayscale blood flow function activated. The processor can also use other methods to perform image segmentation on the nodule cross-sectional image to determine the vascular region, as long as the processor can segment and determine the vascular region within the nodule cross-sectional image; this embodiment does not impose any restrictions on this.

[0057] Step 103: Obtain the labeling information of the vascular region in the nodule cross-sectional image; wherein, the labeling information includes location labeling information.

[0058] It should be noted that the marking information for the vascular region in this step can be information used to mark and display the vascular region in the nodule cross-sectional image. The specific content of the marking information for the vascular region in this embodiment can be set by the designer according to the practical scenario and user needs. For example, the marking information may include information for marking and displaying the location of the vascular region in the nodule cross-sectional image (i.e., location marking information), so as to mark and display the location marking information in the displayed nodule cross-sectional image and prompt the doctor about the location of the vascular region in the nodule cross-sectional image; the marking information may also include information for marking and displaying the extent of the vascular region in the nodule cross-sectional image (i.e., extent marking information), such as the vascular area and / or the percentage of the vascular area.

[0059] Specifically, the method by which the processor obtains the marking information of the vascular region in the nodule cross-section image in this step can be set by the designer according to the practical scenario and user needs. For example, when the marking information includes location marking information, the processor can obtain the location of the vascular region based on the determined vascular region in the nodule cross-section image; based on the location of the vascular region, it can obtain the location marking information of the vascular region in the nodule cross-section image, such as the display position of the marking box, the display position of the corner box, or the display position of the color coverage, etc.; when the marking information includes the proportion of vascular area, the processor can calculate the vascular area corresponding to the vascular region based on the determined vascular region in the nodule cross-section image; and use the quotient of the vascular area and the nodule cross-section image as the proportion of vascular area.

[0060] Step 104: Display the marking information in the nodule cross-sectional image.

[0061] Understandably, in this step, the processor can mark and display vascular area information in the nodule cross-sectional image displayed on the monitor, such as the corner box or marking box (such as a rectangle) corresponding to the vascular area, to prompt the doctor to locate the vascular position in the cross-section (i.e., nodule cross-sectional image) within each nodule range being scanned, making it easier to select the best puncture section away from the blood vessel.

[0062] Specifically, in this step, the processor can mark and display the real-time image segmentation information obtained in the nodule cross-sectional image displayed on the monitor. That is, in this embodiment, the processor can perform real-time image segmentation on the nodule cross-sectional image acquired in real time by the ultrasound device, obtain the corresponding marking information, and display the corresponding marking information in real time on the nodule cross-sectional image displayed on the monitor, so as to prompt the doctor to find the location of blood vessels in the cross-section (i.e., nodule cross-sectional image) within the range of each nodule scanned by the doctor.

[0063] In this embodiment, the present invention performs image segmentation on the nodule cross-sectional image to determine the vascular region in the nodule cross-sectional image, and can segment the vascular region in the nodule cross-sectional image; by displaying marking information in the nodule cross-sectional image, the location of the vascular region can be displayed in real time in the nodule cross-sectional image acquired by the ultrasound device, so that doctors can conveniently select the best puncture section away from the blood vessel under ultrasound guidance, thereby guiding doctors to insert the needle and improving puncture safety.

[0064] Please refer to Figure 2 , Figure 2 A flowchart illustrating another method for cross-sectional marking of ultrasound images provided in an embodiment of the present invention. The method may include:

[0065] Step 201: Based on the acquired section recognition instruction, perform target recognition on the real-time ultrasound image acquired by the ultrasound equipment to determine the target region in the real-time ultrasound image; wherein, the target region includes the nodule region.

[0066] Understandably, in this step, the processor can, during the ultrasound scanning process of the ultrasound equipment, perform target recognition on the ultrasound images (i.e., real-time ultrasound images) acquired in real time by the acquired control plane recognition function, and determine the area of ​​the target in the real-time ultrasound image (i.e., the target area). For example, when a physician operates the ultrasound equipment to perform an ultrasound scan, he can activate the plane recognition function to perform real-time target recognition on each frame of ultrasound image scanned after the plane recognition function is activated, so as to indicate the area where each target is located in the real-time ultrasound image.

[0067] In this step, the target region to be identified can be the region where the target of the target recognition algorithm is located. The specific number and type of the target regions to be identified in this embodiment can be set by the designer according to the practical scenario and user needs. For example, the target regions to be identified can include nodule regions, that is, the target to be identified can include nodules in the image. The target regions to be identified can also include tracheal regions and arteriovenous regions, that is, the target to be identified can also include trachea and arteriovenous vessels in the image. For example, when the method provided in this embodiment is applied to ultrasound-guided thyroid puncture, the processor in this embodiment can identify and display prompts on the regions where nodules, trachea and arteriovenous vessels are located in each frame of ultrasound image in the ultrasound scan after the thyroid section recognition function is activated, so that the physician can determine the region where the nodule is relatively clear and avoids the trachea and arteriovenous vessels according to the prompts.

[0068] Specifically, the method by which the processor performs target recognition on the real-time ultrasound images acquired by the ultrasound equipment according to the acquired section recognition instructions in this step can be set by the designer according to the practical scenario and user needs. For example, the processor can use a pre-set neural network model (i.e., a preset neural network model) to perform target recognition on the real-time ultrasound images according to the section recognition instructions, and determine the target region in the real-time ultrasound images. The preset neural network model can be a neural network model trained based on deep learning. For example, the processor can use a preset detection algorithm to perform feature learning on a certain number of image data labeled with the target to obtain the feature of the foreground target category and location information, and train the preset neural network model. The preset detection algorithm can be YOLOv5 (a target detection algorithm), or other detection algorithms such as YOLOv4 (a target detection algorithm). This embodiment does not impose any restrictions on this.

[0069] Step 202: Obtain prompt information for identifying the target region in the real-time ultrasound image; wherein, the prompt information includes location prompt information.

[0070] It should be noted that the prompt information for identifying the target area in this step can be information that displays the target area in the real-time ultrasound image. This embodiment does not limit the specific content of the prompt information for identifying the target area. For example, the prompt information may include information for displaying the location of the target area in the real-time ultrasound image (i.e., location prompt information), so as to prompt the doctor on the location of each target area in the real-time ultrasound image by marking the location prompt information in the displayed real-time ultrasound image.

[0071] Specifically, the method by which the processor obtains the prompt information of the target area in the real-time ultrasound image in this step can be set by the designer according to the practical scenario and user needs. For example, when the prompt information includes location prompt information, the processor can obtain the location of the target area and the type of the target based on the identified target area in the real-time ultrasound image; based on the location of the target area and the type of the target, it can obtain the location prompt information of the target area in the real-time ultrasound image, such as the display position of the target text and directional symbols corresponding to each target area.

[0072] Step 203: Display prompts in the real-time ultrasound images to indicate the area to be scanned further.

[0073] Understandably, in this step, the processor can display prompts for identifying the target area in the real-time ultrasound images displayed on the monitor. These prompts can guide the doctor to further scan the area using the ultrasound equipment. For example, pointing to the corresponding target text in the target area with a directional symbol can indicate to the doctor the location of the target in each ultrasound image (i.e., the real-time ultrasound image) being scanned, making it easier for the doctor to scan the ultrasound images within the nodule area.

[0074] Specifically, the target area is identified as including the nodule area, trachea area, and arteriovenous area. That is, when the target is identified as including the nodule, trachea, and arteriovenous area, the processor can display prompt information in real time on the real-time ultrasound image displayed on the monitor. The prompt information can be used to indicate the area of ​​the nodule that is clear and avoids the trachea and arteriovenous area for further scanning. This allows the doctor to operate the ultrasound equipment to perform further scanning in the area of ​​the nodule that is clear and avoids the trachea and arteriovenous area, and complete the acquisition of the nodule cross-sectional image.

[0075] Step 204: Based on the color mode start command obtained by the ultrasound equipment during scanning within the area, control the ultrasound equipment to turn on the color mode and start the grayscale blood flow function to acquire the nodule cross-sectional image collected by the ultrasound equipment.

[0076] It is understandable that in this step, the processor can control the ultrasound device to turn on the color mode and activate the grayscale blood flow function according to the obtained color mode start command, and use the ultrasound image obtained by the ultrasound device as the nodule cross-sectional image. That is, the nodule cross-sectional image can be the ultrasound image acquired by the ultrasound device in color mode and with the grayscale blood flow function activated.

[0077] In other words, doctors can determine the area of ​​the nodule that is relatively clear and avoids the trachea and arteries and veins based on the real-time ultrasound images and prompts displayed. They can then operate the ultrasound equipment to scan the ultrasound images within that area, activate the color mode to display the blood vessels around the nodule, and activate the grayscale blood flow function to acquire cross-sectional images of the nodule.

[0078] Step 205: Based on the pixel values ​​in the nodule section image, perform image segmentation on the nodule section image to determine the vascular region in the nodule section image.

[0079] In this step, taking advantage of the significant color difference between blood vessels and other tissues in color mode, the nodule cross-section image is segmented based on the pixel values ​​of the nodule cross-section image acquired in color mode, thereby obtaining the blood vessel region in the nodule cross-section image.

[0080] Specifically, this embodiment does not limit the specific method by which the processor performs image segmentation on the nodule cross-section image based on pixel values ​​to determine the vascular region in the nodule cross-section image. For example, the processor can perform feature analysis and semantic segmentation on the nodule cross-section image based on pixel values ​​to obtain the vascular region in the nodule cross-section image, i.e., image segmentation is performed using feature analysis and semantic segmentation. The processor can also use other methods for image segmentation. As long as the processor can determine the vascular region in the nodule cross-section image based on pixel values, this embodiment does not impose any restrictions on this.

[0081] Step 206: Obtain the labeling information of the vascular region in the nodule cross-sectional image; wherein, the labeling information includes location labeling information and the proportion of vascular area.

[0082] This step is similar to step 103, and will not be described again here.

[0083] Understandably, in this step, the processor can acquire in real time the location markers and the proportion of blood vessel area in the cross-sectional images of each nodule acquired by the ultrasound equipment, and thus display the nodule cross-sectional images and corresponding markers on the monitor in real time. Since the monitor can display the proportion of blood vessel area and location markers in the cross-sectional images of the nodule in real time, it can avoid the need for doctors to repeatedly turn the color mode on and off, thus making the operation more convenient for doctors.

[0084] Step 207: Display the marking information in the nodule cross-sectional image.

[0085] Understandably, in this step, the processor can mark the location information of the blood vessel area and the proportion of the blood vessel area in the nodule cross-sectional image displayed in real time on the monitor. This is to prompt the doctor to identify the location and proportion of the blood vessels in each cross-section (i.e., nodule cross-sectional image) within the area where the nodule is clearly visible and avoids the trachea and arteries and veins. This makes it easier to select the best puncture section that is far away from the blood vessels or has a smaller proportion of blood vessels. As a result, the doctor can easily operate the ultrasound equipment to scan within the area where the nodule is clearly visible and avoids the trachea and arteries and veins, and select the best puncture section that is far away from the blood vessels or has a smaller proportion of blood vessels.

[0086] In this embodiment, the present invention performs target recognition on real-time ultrasound images acquired by an ultrasound device according to the acquired section recognition instruction, determines the target area in the real-time ultrasound image, and can identify the area where the target is located in the real-time ultrasound image. By displaying prompt information of the target area, doctors can select a section with a clearer nodule based on the prompt. By displaying marking information in the nodule section image, the location and area ratio of the blood vessel area can be displayed in real time in the nodule section image acquired by the ultrasound device. This allows doctors to conveniently select the best puncture section that is far away from the blood vessel or has a small proportion of blood vessel under ultrasound guidance, thereby guiding doctors to insert the needle and improving puncture safety.

[0087] Corresponding to the above method embodiments, this invention also provides a section marking device for ultrasound images. The section marking device for ultrasound images described below and the section marking method for ultrasound images described above can be referred to in correspondence.

[0088] Please refer to Figure 3 , Figure 3 A structural block diagram of a section marking device for ultrasound images provided in an embodiment of the present invention. The device may include:

[0089] The image acquisition module 10 is used to acquire cross-sectional images of nodules collected by ultrasound equipment; wherein, the cross-sectional images of nodules include the nodule region;

[0090] Image segmentation module 20 is used to segment the nodule cross-sectional image and determine the vascular region in the nodule cross-sectional image;

[0091] The marker acquisition module 30 is used to acquire marker information of the vascular region in the nodule cross-sectional image; wherein, the marker information includes location marker information;

[0092] The marker display module 40 is used to display marker information in the nodule cross-sectional image.

[0093] In some embodiments, the image segmentation module 20 may include:

[0094] The pixel value determination submodule is used to perform image segmentation on the nodule cross-sectional image based on the pixel values ​​within the nodule cross-sectional image, and to determine the vascular region in the nodule cross-sectional image; wherein, the nodule cross-sectional image is an ultrasound image acquired by an ultrasound device in color mode.

[0095] In some embodiments, the pixel value determination submodule can be specifically used to perform feature analysis and semantic segmentation on the nodule cross-section image based on the pixel values ​​within the nodule cross-section image, to obtain the vascular region in the nodule cross-section image.

[0096] In some embodiments, when the marking information further includes the percentage of blood vessel area, the marking acquisition module 30 may include:

[0097] The area calculation submodule is used to calculate the area of ​​blood vessels corresponding to the blood vessel region;

[0098] The proportion calculation submodule is used to calculate the proportion of the blood vessel area by dividing the blood vessel area by the nodule cross-sectional image.

[0099] In some embodiments, the image acquisition module 10 may be specifically used to control the ultrasound device to turn on the color mode and activate the grayscale blood flow function according to the acquired color mode start command, so as to acquire the nodule cross-sectional image collected by the ultrasound device.

[0100] In some embodiments, the device may further include:

[0101] The target recognition module is used to perform target recognition on real-time ultrasound images acquired by ultrasound equipment according to the acquired section recognition instructions, and to determine the target region in the real-time ultrasound image; wherein, the target region includes nodule region;

[0102] The prompt acquisition module is used to acquire prompt information of the target region in real-time ultrasound images; wherein, the prompt information includes location prompt information;

[0103] The prompt display module is used to display prompt information in real-time ultrasound images to indicate the area to be scanned further.

[0104] In some embodiments, where the target area also includes the tracheal region and the arteriovenous region, the prompt display module may be specifically used to display prompt information in real time on the real-time ultrasound image, so as to use the prompt information to indicate the area of ​​the nodule that is clear and avoids the trachea and arteriovenous region for further scanning.

[0105] In some embodiments, the image acquisition module 10 may be specifically used to acquire nodule cross-sectional images based on vascular marking instructions acquired by the ultrasound device during scanning within a region.

[0106] In some embodiments, the target recognition module may be specifically used to perform target recognition on real-time ultrasound images using a preset neural network model according to the section recognition instruction, and to determine the target region in the real-time ultrasound images.

[0107] In this embodiment, the image segmentation module 20 performs image segmentation on the nodule section image to determine the vascular region in the nodule section image, and can segment the vascular region in the nodule section image; the marker display module 40 displays marker information in the nodule section image, which can display the location of the vascular region in real time in the nodule section image acquired by the ultrasound equipment, so that under ultrasound guidance, the doctor can conveniently select the best puncture section away from the blood vessel, thereby guiding the doctor to insert the needle and improving the safety of puncture.

[0108] Corresponding to the above method embodiments, this invention also provides an ultrasound medical device. The ultrasound medical device described below and the ultrasound image section marking method described above can be referred to each other.

[0109] Please refer to Figure 4 , Figure 4 This is a schematic diagram of the structure of an ultrasound medical device provided in an embodiment of the present invention. The device may include:

[0110] Memory D1 is used to store computer programs;

[0111] The processor D2 is used to implement the steps of the ultrasound image section marking method provided in the above method embodiments when executing a computer program.

[0112] Specifically, the ultrasound medical device in this embodiment can be a device that performs image processing within an ultrasound system, such as an ultrasound machine. The specific structure of the ultrasound medical device can be found in [reference needed]. Figure 5 , Figure 5 This is a schematic diagram illustrating the specific structure of an ultrasound medical device according to an embodiment of the present invention. The ultrasound medical device 310 varies considerably depending on its configuration or performance, and may include one or more central processing units (CPUs) 322 (e.g., one or more processors) and a memory 332, and one or more storage media 330 (e.g., one or more mass storage devices) for storing application programs 342 or data 344. The memory 332 and storage media 330 can be temporary or persistent storage. The program stored in the storage media 330 may include one or more modules (e.g., such as...). Figure 3The image acquisition module 10, image segmentation module 20, marker acquisition module 30, and marker display module 40 are shown in the diagram. Furthermore, the central processing unit 322 can be configured to communicate with the storage medium 330 and execute a series of instructions stored in the storage medium 330 on the ultrasound medical device 310.

[0113] The ultrasound medical device 310 may also include one or more power supplies 326, one or more wired or wireless network interfaces 350, one or more input / output interfaces 358, and / or one or more operating systems 341. Examples include Windows Server™, Mac OS X™, Unix™, Linux™, FreeBSD™, etc.

[0114] The steps in the ultrasound image section marking method described above can be implemented by the structure of the ultrasound medical device.

[0115] Corresponding to the above method embodiments, this invention also provides a readable storage medium. The readable storage medium described below corresponds to the ultrasound image section marking method described above.

[0116] A readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the ultrasound image section marking method provided in the above-described method embodiments.

[0117] Specifically, the readable storage medium can be a USB flash drive, a portable hard drive, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disk, or any other readable storage medium capable of storing program code.

[0118] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on its differences from other embodiments. Similar or identical parts between embodiments can be referred to interchangeably. For the apparatuses, devices, and readable storage media disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the descriptions are relatively simple; relevant details can be found in the method section.

[0119] The present invention has provided a detailed description of a method, apparatus, device, and readable storage medium for cross-sectional marking of ultrasound images. Specific examples have been used to illustrate the principles and implementation methods of the invention. The descriptions of these embodiments are merely illustrative of the method and its core ideas. It should be noted that those skilled in the art can make various improvements and modifications to the invention without departing from its principles, and these improvements and modifications also fall within the scope of protection of the claims.

Claims

1. A method for section marking in ultrasound images, characterized in that, include: Based on the acquired section recognition instructions, target recognition is performed on the real-time ultrasound images acquired by the ultrasound equipment to determine the target regions in the real-time ultrasound images; wherein, the target regions include nodule regions, tracheal regions, and arteriovenous regions; Obtain prompt information for identifying the target region in the real-time ultrasound image; wherein, the prompt information includes location prompt information; The prompt information is displayed in real time in the real-time ultrasound image to indicate areas where nodules are clearly visible and where the trachea and arteries and veins are avoided for further scanning. Acquire a cross-sectional image of the nodule within the area captured by the ultrasound device; wherein the cross-sectional image of the nodule includes the nodule region; The nodule cross-sectional image is segmented to determine the vascular region in the nodule cross-sectional image; Obtain the marking information of the vascular region in the nodule cross-sectional image; wherein, the marking information includes location marking information and range marking information; The marking information is displayed in the nodule section image to select the optimal puncture section away from blood vessels under ultrasound guidance.

2. The method for section marking of ultrasound images according to claim 1, characterized in that, The step of performing image segmentation on the nodule cross-sectional image to determine the vascular region in the nodule cross-sectional image includes: Based on the pixel values ​​within the nodule cross-sectional image, the nodule cross-sectional image is segmented to determine the vascular region within the nodule cross-sectional image; wherein, the nodule cross-sectional image is an ultrasound image acquired by the ultrasound device in color mode.

3. The method for section marking of ultrasound images according to claim 2, characterized in that, The step of segmenting the nodule cross-section image based on pixel values ​​to determine the vascular region in the nodule cross-section image includes: Based on the pixel values ​​within the nodule cross-sectional image, feature analysis and semantic segmentation are performed on the nodule cross-sectional image to obtain the vascular region in the nodule cross-sectional image.

4. The method for section marking of ultrasound images according to claim 1, characterized in that, The marking information also includes, when considering the proportion of blood vessel area, the marking information of the blood vessel region in the nodule cross-sectional image obtained includes: Calculate the vascular area corresponding to the vascular region; The ratio of the blood vessel area to the nodule cross-sectional image is taken as the proportion of the blood vessel area.

5. The method for section marking of ultrasound images according to claim 1, characterized in that, The acquisition of the nodule cross-sectional image obtained by the ultrasound equipment includes: According to the acquired color mode start command, the ultrasound device is controlled to turn on the color mode and activate the grayscale blood flow function to acquire the nodule cross-sectional image collected by the ultrasound device.

6. The method for section marking of ultrasound images according to claim 1, characterized in that, The acquisition of nodule cross-sectional images collected by the ultrasound device within the area includes: Based on the vascular marking instructions obtained by the ultrasound equipment during scanning within the area, the nodule cross-sectional image is acquired.

7. The method for section marking of ultrasound images according to claim 1, characterized in that, The step of performing target recognition on the real-time ultrasound images acquired by the ultrasound equipment according to the acquired section recognition instructions, and determining the target region in the real-time ultrasound images, includes: According to the section recognition instruction, a preset neural network model is used to perform target recognition on the real-time ultrasound image to determine the target region in the real-time ultrasound image.

8. A section marking device for ultrasound images, characterized in that, include: The target recognition module is used to perform target recognition on real-time ultrasound images acquired by the ultrasound equipment according to the acquired section recognition instructions, and to determine the target regions in the real-time ultrasound images; wherein, the target regions include nodule regions, tracheal regions and arteriovenous regions; The prompt acquisition module is used to acquire prompt information of the target region in the real-time ultrasound image; wherein, the prompt information includes location prompt information; The prompt display module is used to display the prompt information in the real-time ultrasound image, so as to use the prompt information to indicate the area of ​​nodules that are clear and avoid the trachea and arteries and veins for further scanning; An image acquisition module is used to acquire cross-sectional images of nodules collected by the ultrasound device within the area; wherein, the cross-sectional images of nodules include the nodule region; The image segmentation module is used to segment the nodule cross-sectional image and determine the blood vessel region in the nodule cross-sectional image; The marker acquisition module is used to acquire marker information of the vascular region in the nodule cross-sectional image; wherein, the marker information includes location marker information and range marker information; A marker display module is used to display the marker information in the nodule section image to select the optimal puncture section away from blood vessels under ultrasound guidance.

9. An ultrasonic medical device, characterized in that, include: Memory, used to store computer programs; A processor, configured to implement the steps of the section marking method for ultrasound images as described in any one of claims 1 to 7 when executing the computer program.

10. A readable storage medium, characterized in that, The readable storage medium stores a computer program that, when executed by a processor, implements the steps of the ultrasound image section marking method as described in any one of claims 1 to 7.

Images