Medical image processing method and device, electronic equipment and storage medium

Abstract

The embodiment of the invention discloses a medical image processing method and device, electronic equipment and a storage medium. The method comprises the following steps: acquiring a target thyroid ultrasound image; the target thyroid ultrasound image is input into a thyroid image processing model which is trained in advance, a thyroid contour area of the thyroid ultrasound image and at least one reference thyroid nodule marking box are determined, and the thyroid image processing model which is trained in advance is obtained based on improved yo11 model training; and determining a target thyroid nodule labeling frame in the at least one reference thyroid nodule labeling frame according to a position relationship between the thyroid contour region and the at least one reference thyroid nodule labeling frame, and displaying the target thyroid nodule labeling frame in the target thyroid ultrasound image. According to the technical scheme of the embodiment of the invention, the thyroid nodule in the thyroid ultrasound image can be quickly and accurately identified, and objective reference can be provided for clinical diagnosis.

Description

Technical Field

[0001] The embodiments of the present invention relate to the field of image processing technology, and in particular to a medical image processing method, device, electronic device and storage medium. Background Art

[0002] Thyroid nodules are abnormal growths within the thyroid gland, and their diagnosis is crucial for timely treatment. Currently, ultrasound images play a key role in identifying thyroid nodules.

[0003] In the related technology, doctors often rely on observing thyroid ultrasound images and manually identifying and marking the location and size of thyroid nodules. However, this method relies on the doctor's experience and expertise, but has technical problems such as strong subjectivity, low efficiency and easy errors. Summary of the invention

[0004] The present invention provides a medical image processing method, device, electronic device and storage medium to achieve relatively fast and accurate identification of thyroid nodules in thyroid ultrasound images, which can provide an objective reference for clinical diagnosis.

[0005] According to one aspect of the present invention, a medical image processing method is provided, the method comprising:

[0006] Acquire ultrasound images of the target thyroid gland;

[0007] Inputting the target thyroid ultrasound image into a pre-trained thyroid image processing model to determine a thyroid contour area and at least one reference thyroid nodule annotation box of the thyroid ultrasound image, wherein the pre-trained thyroid image processing model is trained based on an improved YOLO11 model;

[0008] A target thyroid nodule marking frame in at least one of the reference thyroid nodule marking frames is determined according to a positional relationship between the thyroid contour area and at least one of the reference thyroid nodule marking frames, and the target thyroid nodule marking frame is displayed in the target thyroid ultrasound image.

[0009] Optionally, determining a target thyroid nodule marking frame in at least one reference thyroid nodule marking frame based on a positional relationship between the thyroid contour area and at least one reference thyroid nodule marking frame includes: for each reference thyroid nodule marking frame, when a center position of the reference thyroid nodule marking frame is located within the thyroid contour area, determining that a detection point corresponding to the reference thyroid nodule marking frame is a real nodule, and using the reference thyroid nodule marking frame as a target thyroid nodule marking frame.

[0010] Optionally, the medical image processing method further includes: when the center position of the reference thyroid nodule marking box is not located within the thyroid contour area, determining that the detection point corresponding to the reference thyroid nodule marking box is a false positive nodule, and deleting the reference thyroid nodule marking box.

[0011] Optionally, the improved yolo11 model adds a segmentation head for performing thyroid segmentation processing on thyroid ultrasound images based on the original yolo11 model.

[0012] Optionally, the loss function of the improved yolo11 model includes a first loss function and a second loss function, wherein the first loss function is used to calculate the loss value of the thyroid nodule annotation box, and the second loss function is used to calculate the loss value of the thyroid contour area.

[0013] Optionally, the medical image processing method also includes: acquiring sample data and expected data corresponding to the sample data, wherein the sample data is a thyroid ultrasound sample image, and the expected data is a thyroid contour area of ​​the thyroid ultrasound sample image or a thyroid contour area including a thyroid nodule annotation box; inputting the sample data into a pre-constructed improved yolo11 model to obtain an actual output result of the improved yolo11 model; adjusting the network parameters of the improved yolo11 model based on the expected data and the actual output result to obtain a trained thyroid image processing model.

[0014] Optionally, before inputting the target thyroid ultrasound image into a pre-trained thyroid image processing model, the medical image method further includes: performing image preprocessing on the target thyroid ultrasound image, wherein the image preprocessing includes at least one of image enhancement processing, image scaling processing and image normalization processing.

[0015] According to another aspect of the present invention, a medical image processing device is provided. The device comprises:

[0016] An image acquisition module, used for acquiring an ultrasonic image of a target thyroid gland;

[0017] An image processing module, used for inputting the target thyroid ultrasound image into a pre-trained thyroid image processing model, determining a thyroid contour area and at least one reference thyroid nodule annotation frame of the thyroid ultrasound image, wherein the pre-trained thyroid image processing model is obtained by training based on an improved YOLO11 model;

[0018] The image display module is used to determine a target thyroid nodule marking frame in at least one of the reference thyroid nodule marking frames according to the positional relationship between the thyroid contour area and at least one of the reference thyroid nodule marking frames, and display the target thyroid nodule marking frame in the target thyroid ultrasound image.

[0019] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising:

[0020] at least one processor; and

[0021] a memory communicatively connected to the at least one processor; wherein,

[0022] The memory stores a computer program that can be executed by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the medical image processing method described in any embodiment of the present invention.

[0023] According to another aspect of the present invention, a computer-readable storage medium is provided, wherein the computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the medical image processing method described in any embodiment of the present invention when executed.

[0024] The technical solution of the embodiment of the present invention is to obtain a target thyroid ultrasound image; input the target thyroid ultrasound image into a pre-trained thyroid image processing model to determine the thyroid contour area and at least one reference thyroid nodule annotation box of the thyroid ultrasound image, wherein the pre-trained thyroid image processing model is obtained by training based on the improved yolo11 model; determine a target thyroid nodule annotation box in at least one reference thyroid nodule annotation box according to the positional relationship between the thyroid contour area and at least one reference thyroid nodule annotation box, and display the target thyroid nodule annotation box in the target thyroid ultrasound image. The technical solution of the embodiment of the present invention can achieve relatively fast and accurate identification of thyroid nodules in thyroid ultrasound images, and can provide an objective reference for clinical diagnosis.

[0025] It should be understood that the contents described in this section are not intended to identify the key or important features of the embodiments of the present invention, nor are they intended to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.

[0027] Figure 1 A schematic diagram of a flow chart of a medical image processing method provided by an embodiment of the present invention;

[0028] Figure 2 A schematic diagram of a network structure of a medical image processing model provided by an embodiment of the present invention;

[0029] Figure 3 A schematic diagram of the structure of a medical image processing device provided by an embodiment of the present invention;

[0030] Figure 4 A schematic diagram of the structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0031] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work should fall within the scope of protection of the present invention.

[0032] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and are not necessarily used to describe a specific order or sequence. It should be understood that the data used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions, for example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units that are clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0033] It is understandable that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and relevant provisions.

[0034] Figure 1A flow chart of a medical image processing method provided in an embodiment of the present invention is provided. This embodiment is applicable to the case of processing medical images. The method can be executed by a medical image processing device. The medical image processing device can be implemented in the form of hardware and / or software. The medical image processing device can be configured in an electronic device such as a computer or a server.

[0035] like Figure 1 As shown, the method of this embodiment includes:

[0036] S110, obtaining a target thyroid ultrasound image.

[0037] The target thyroid ultrasound image may be understood as a thyroid ultrasound image for which thyroid nodules are to be identified.

[0038] In the embodiment of the present invention, there are multiple ways to obtain the target thyroid ultrasound image. As an optional implementation of the embodiment of the present invention, a high-frequency probe can be used to lightly sweep both sides of the patient's neck to obtain the thyroid ultrasound image.

[0039] As another optional implementation of the embodiment of the present invention, in response to an image upload operation for a thyroid ultrasound image, an uploaded thyroid ultrasound image can be obtained. Thus, the uploaded thyroid ultrasound image can be determined as a target thyroid ultrasound image; wherein the image upload operation can be understood as an operation for uploading a target thyroid ultrasound image.

[0040] As another optional implementation of the embodiment of the present invention, at least one or two candidate thyroid ultrasound images may be displayed, and after receiving an image selection operation for the candidate thyroid ultrasound images, the selected candidate thyroid ultrasound image may be determined, so that the selected candidate thyroid ultrasound image may be determined as the target thyroid ultrasound image.

[0041] S120: Input the target thyroid ultrasound image into a pre-trained thyroid image processing model to determine a thyroid contour area and at least one reference thyroid nodule annotation box of the thyroid ultrasound image.

[0042] Among them, the thyroid contour area can be understood as the area where the contour of the thyroid gland in the target thyroid ultrasound image is located. The reference thyroid nodule annotation box can be understood as the thyroid nodule annotation box obtained after the first annotation of the thyroid nodules in the target thyroid ultrasound image by the pre-trained thyroid image processing model. In an embodiment of the present invention, the number of reference thyroid nodule annotation boxes may be one, two, or more than two. In an embodiment of the present invention, when the number of reference thyroid nodule annotation boxes is one, the position of the reference thyroid nodule annotation box may be located within the thyroid contour area or outside the thyroid contour area. When the number of reference thyroid nodule annotation boxes is multiple, the positions of some reference thyroid nodule annotation boxes may be located within the thyroid contour area, and the positions of the remaining reference thyroid nodule annotation boxes may be located outside the thyroid contour area; alternatively, the positions of all reference thyroid nodule annotation boxes may be located within the thyroid contour area; alternatively, the positions of all reference thyroid nodule annotation boxes may be located outside the thyroid contour area.

[0043] In an embodiment of the present invention, the pre-trained thyroid image processing model may be obtained by training based on an improved yolo11 model. The improved yolo11 model may be an original yolo11 model with an additional segmentation head for thyroid segmentation processing of thyroid ultrasound images. Figure 2 , the network structure of the improved yolo11 model may include a segmentation head (SegmentHead) for performing thyroid segmentation processing on thyroid ultrasound images and the network structure of the original yolo11 model. Among them, the segmentation head may include a preset number of segmentation units. Among them, the segmentation unit may include an upsample layer (Upsample layer), a convolution layer (Conv layer), and a connection layer (Concat layer). In an embodiment of the present invention, the preset number can be set according to actual needs and is not specifically limited here. Exemplarily, the segmentation head may include 3 segmentation units. The network structure of the original yolo11 model may include Backbone, Neck, and Detect Head. Among them, Neck can be used between backbone and detection head for better fusion and feature extraction. In an embodiment of the present invention, the loss function of the improved yolo11 model may include a first loss function and a second loss function. Among them, the first loss function can be used to calculate the loss value of the thyroid nodule annotation box. The second loss function can be used to calculate the loss value of the thyroid contour area.

[0044] Optionally, the second loss function can be:

[0045]

[0046] Among them, the loss result of the second loss function can be expressed as L dice . Y can be expressed as the actual contour area of ​​the thyroid gland. It can be represented as the desired contour area of ​​the thyroid gland.

[0047] In an embodiment of the present invention, a method for obtaining a pre-trained thyroid image processing model may specifically include: first obtaining sample data and expected data corresponding to the sample data, wherein the sample data may be a thyroid ultrasound sample image, and the expected data may be a thyroid contour area of ​​the thyroid ultrasound sample image or a thyroid contour area including a thyroid nodule annotation box. That is to say, in an embodiment of the present invention, the expected data corresponding to the thyroid ultrasound sample image may be the thyroid contour area of ​​the thyroid ultrasound sample image; or, it may be the thyroid contour area of ​​the thyroid ultrasound sample image and a thyroid nodule annotation box located within the thyroid contour area. The advantage of such processing is that it can provide richer training data and improve the generalization of the model.

[0048] Based on this, the sample data can be input into the pre-built improved yolo11 model to obtain the actual output result of the improved yolo11 model. Then, the network parameters of the improved yolo11 model can be adjusted based on the expected data and the actual output result to obtain a trained thyroid image processing model. Wherein, the network parameters of the improved yolo11 model are adjusted based on the expected data and the actual output result to obtain a trained thyroid image processing model. Specifically, the model loss function of the improved yolo11 model is calculated based on the expected data and the actual output result. Thereby, the network parameters of the improved yolo11 model can be adjusted based on the calculation result of the loss function. When the result of the model loss function converges, a trained thyroid image processing model can be obtained.

[0049] On the basis of the above embodiment, the model loss function of the improved yolo11 model can be constructed based on the first loss function and the second loss function. Furthermore, the first weight factor of the first loss function and the second weight factor of the second loss function can be pre-set. Thus, a model loss function can be constructed according to the first loss function, the first weight factor, the second loss function and the second weight factor. It should be noted that the sum of the first weight factor and the second weight factor is 1, and the specific value can be set according to actual needs, which is not specifically limited here.

[0050] Based on the above embodiment, the method may further include: testing and verifying the trained thyroid image processing model. The benefit of doing so is that the reliability of the thyroid image processing model can be enhanced.

[0051] Before inputting the target thyroid ultrasound image into a pre-trained thyroid image processing model, the method may further include: performing image preprocessing on the target thyroid ultrasound image, wherein the image preprocessing may include at least one of image enhancement processing, image scaling processing, and image normalization processing.

[0052] In the embodiment of the present invention, image enhancement processing is performed on the target thyroid ultrasound image, which can improve the image quality of the target thyroid ultrasound image, highlight key features, and make the image clearer.

[0053] In the embodiment of the present invention, the target thyroid ultrasound image is subjected to image scaling processing. When the size of the target thyroid ultrasound image is reduced, the computing resources required for subsequent image processing and analysis can be reduced, thereby improving processing efficiency. When the size of the target thyroid ultrasound image is enlarged, the details can be made clearer, thereby facilitating image segmentation and labeling.

[0054] In the embodiment of the present invention, the target thyroid ultrasound image may be normalized by the following formula:

[0055]

[0056] Wherein, X represents a single pixel value of the target thyroid ultrasound image. xmin can be expressed as the minimum value of the pixel of the target thyroid ultrasound image. xmax can be expressed as the maximum value of the pixel of the target thyroid ultrasound image.

[0057] Optionally, the single pixel value of the target thyroid ultrasound image may be a grayscale value of a single pixel of the target thyroid ultrasound image. The minimum value of the target thyroid ultrasound image pixel may be a minimum grayscale value of the target thyroid ultrasound image pixel. The maximum value of the target thyroid ultrasound image pixel may be a maximum grayscale value of the target thyroid ultrasound image pixel.

[0058] S130 . Determine a target thyroid nodule labeling frame in at least one of the reference thyroid nodule labeling frames according to a positional relationship between the thyroid contour region and at least one of the reference thyroid nodule labeling frames.

[0059] The target thyroid nodule labeling frame can be understood as a thyroid nodule labeling frame that corresponds to the target thyroid ultrasound image and needs to be displayed. In the embodiment of the present invention, the number of target thyroid nodule labeling frames can be one, two, or more than two.

[0060] In an embodiment of the present invention, determining a target thyroid nodule marking frame in at least one of the reference thyroid nodule marking frames based on the positional relationship between the thyroid contour area and at least one of the reference thyroid nodule marking frames may include: for each of the reference thyroid nodule marking frames, when the center position of the reference thyroid nodule marking frame is located within the thyroid contour area, determining that a detection point corresponding to the reference thyroid nodule marking frame is a real nodule, and using the reference thyroid nodule marking frame as a target thyroid nodule marking frame.

[0061] Based on the above embodiment, the method may further include: when the center position of the reference thyroid nodule marking box is not located within the thyroid contour area, it can be determined that the detection point corresponding to the reference thyroid nodule marking box is a false positive nodule, and the reference thyroid nodule marking box is deleted.

[0062] In an embodiment of the present invention, there are multiple ways to determine whether the center position of the reference thyroid nodule annotation box is located within the thyroid contour area, which are not specifically limited here. As an optional implementation of an embodiment of the present invention, the boundary points of the thyroid contour can be obtained first. Then, the minimum circumscribed rectangle or ellipse of the thyroid contour can be calculated to determine the position and range of the thyroid gland. Afterwards, the center coordinates of the reference thyroid nodule annotation box can be calculated. Then, it can be determined whether the center coordinates are located within the minimum circumscribed rectangle or ellipse of the thyroid contour. If so, it can be determined that the reference thyroid nodule annotation box is located within the thyroid contour area; otherwise, it can be determined that the center position of the reference thyroid nodule annotation box is not located within the thyroid contour area.

[0063] As another optional implementation of an embodiment of the present invention, the distance from the center point of the reference thyroid nodule annotation box to each point on the thyroid contour can be calculated. Then, the minimum value of the distance can be determined, that is, the shortest distance from the center point to the thyroid contour. Based on this, a threshold value can be set in advance, and the threshold value can be adjusted according to actual conditions. If the shortest distance is less than or equal to the threshold value, it can be determined that the reference thyroid nodule annotation box is located within the thyroid contour area; otherwise, it can be determined that the center position of the reference thyroid nodule annotation box is not located within the thyroid contour area.

[0064] S140, displaying the target thyroid nodule marking frame in the target thyroid ultrasound image.

[0065] Specifically, after the target thyroid nodule marking frame is determined, the target thyroid nodule marking frame may be displayed in the target thyroid ultrasound image.

[0066] The technical solution of the embodiment of the present invention is to obtain a target thyroid ultrasound image; input the target thyroid ultrasound image into a pre-trained thyroid image processing model to determine the thyroid contour area and at least one reference thyroid nodule annotation box of the thyroid ultrasound image, wherein the pre-trained thyroid image processing model is obtained by training based on the improved yolo11 model; determine a target thyroid nodule annotation box in at least one reference thyroid nodule annotation box according to the positional relationship between the thyroid contour area and at least one reference thyroid nodule annotation box, and display the target thyroid nodule annotation box in the target thyroid ultrasound image. The technical solution of the embodiment of the present invention can achieve relatively fast and accurate identification of thyroid nodules in thyroid ultrasound images, and can provide an objective reference for clinical diagnosis.

[0067] Figure 3 FIG. 1 is a schematic diagram of the structure of a medical image processing device provided by an embodiment of the present invention. Figure 3 As shown, the device includes: an image acquisition module 210, an image processing module 220 and an image display module 230.

[0068] Among them, the image acquisition module 210 is used to acquire a target thyroid ultrasound image; the image processing module 220 is used to input the target thyroid ultrasound image into a pre-trained thyroid image processing model to determine the thyroid contour area and at least one reference thyroid nodule labeling box of the thyroid ultrasound image, and the pre-trained thyroid image processing model is obtained by training based on the improved yolo11 model; the image display module 230 is used to determine a target thyroid nodule labeling box in at least one of the reference thyroid nodule labeling boxes based on the positional relationship between the thyroid contour area and at least one of the reference thyroid nodule labeling boxes, and display the target thyroid nodule labeling box in the target thyroid ultrasound image.

[0069] The technical solution of the embodiment of the present invention is to acquire a target thyroid ultrasound image through an image acquisition module; input the target thyroid ultrasound image into a pre-trained thyroid image processing model through an image processing module to determine the thyroid contour area and at least one reference thyroid nodule annotation box of the thyroid ultrasound image, wherein the pre-trained thyroid image processing model is obtained by training based on the improved yolo11 model; and determine the target thyroid nodule annotation box in at least one reference thyroid nodule annotation box according to the positional relationship between the thyroid contour area and at least one reference thyroid nodule annotation box through an image display module, and display the target thyroid nodule annotation box in the target thyroid ultrasound image. The technical solution of the embodiment of the present invention can realize relatively fast and accurate identification of thyroid nodules in thyroid ultrasound images, and can provide an objective reference for clinical diagnosis.

[0070] Optionally, the image display module 230 is used to determine, for each reference thyroid nodule marking box, when the center position of the reference thyroid nodule marking box is located within the thyroid contour area, that the detection point corresponding to the reference thyroid nodule marking box is a real nodule, and use the reference thyroid nodule marking box as the target thyroid nodule marking box.

[0071] Optionally, the device also includes a marking box deletion module; wherein the marking box deletion module is used to determine that the detection point corresponding to the reference thyroid nodule marking box is a false positive nodule and delete the reference thyroid nodule marking box when the center position of the reference thyroid nodule marking box is not within the thyroid contour area.

[0072] Optionally, the improved yolo11 model adds a segmentation head for performing thyroid segmentation processing on thyroid ultrasound images based on the original yolo11 model.

[0073] Optionally, the loss function of the improved yolo11 model includes a first loss function and a second loss function, wherein the first loss function is used to calculate the loss value of the thyroid nodule annotation box, and the second loss function is used to calculate the loss value of the thyroid contour area.

[0074] Optionally, the device further includes a model training module; wherein the model training module is used to:

[0075] Acquire sample data and expected data corresponding to the sample data, wherein the sample data is a thyroid ultrasound sample image, and the expected data is a thyroid contour area of ​​the thyroid ultrasound sample image or a thyroid contour area including a thyroid nodule annotation box;

[0076] Input the sample data into a pre-built improved yolo11 model to obtain an actual output result of the improved yolo11 model;

[0077] Based on the expected data and the actual output result, the network parameters of the improved yolo11 model are adjusted to obtain a trained thyroid image processing model.

[0078] Optionally, the device also includes an image preprocessing module; wherein the image preprocessing module is used to perform image preprocessing on the target thyroid ultrasound image before inputting the target thyroid ultrasound image into a pre-trained thyroid image processing model, wherein the image preprocessing includes at least one of image enhancement processing, image scaling processing and image normalization processing.

[0079] The medical image processing device provided in the embodiment of the present invention can execute the medical image processing method provided in any embodiment of the present invention, and has the corresponding functional modules and beneficial effects of the execution method.

[0080] It is worth noting that the various units and modules included in the above-mentioned medical image processing device are only divided according to functional logic, but are not limited to the above-mentioned division, as long as the corresponding functions can be achieved; in addition, the specific names of the functional units are only for the convenience of distinguishing each other, and are not used to limit the protection scope of the embodiments of the present invention.

[0081] Figure 4 A schematic diagram of the structure of an electronic device 10 that can be used to implement an embodiment of the present invention is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processing, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely examples and are not intended to limit the implementation of the present invention described and / or required herein.

[0082] like Figure 4As shown, the electronic device 10 includes at least one processor 11, and a memory connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc., wherein the memory stores a computer program that can be executed by at least one processor, and the processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 to the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the electronic device 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other through a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0083] A number of components in the electronic device 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a disk, an optical disk, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the electronic device 10 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks.

[0084] The processor 11 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 performs the various methods and processes described above, such as a medical image processing method.

[0085] In some embodiments, the medical image processing method may be implemented as a computer program, which is tangibly contained in a computer-readable storage medium, such as a storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the medical image processing method described above may be performed. Alternatively, in other embodiments, the processor 11 may be configured to perform the medical image processing method in any other appropriate manner (e.g., by means of firmware).

[0086] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), load programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0087] Computer programs for implementing the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that when the computer program is executed by the processor, the functions / operations specified in the flow chart and / or block diagram are implemented. The computer program may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0088] In the context of the present invention, a computer-readable storage medium may be a tangible medium that may contain or store a computer program for use by or in combination with an instruction execution system, device or equipment. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, devices or equipment, or any suitable combination of the foregoing. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0089] To provide interaction with a user, the systems and techniques described herein may be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or trackball) through which the user can provide input to the electronic device. Other types of devices may also be used to provide interaction with the user; for example, the feedback provided to the user may be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user may be received in any form (including acoustic input, voice input, or tactile input).

[0090] The systems and techniques described herein may be implemented in a computing system that includes backend components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes frontend components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such backend components, middleware components, or frontend components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), a blockchain network, and the Internet.

[0091] A computing system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The client and server relationship is generated by computer programs running on the corresponding computers and having a client-server relationship with each other. The server may be a cloud server, also known as a cloud computing server or cloud host, which is a host product in the cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and VPS services.

[0092] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in the present invention can be executed in parallel, sequentially or in different orders, as long as the desired results of the technical solution of the present invention can be achieved, and this document does not limit this.

[0093] The above specific implementations do not constitute a limitation on the protection scope of the present invention. It should be understood by those skilled in the art that various modifications, combinations, sub-combinations and substitutions can be made according to design requirements and other factors. Any modification, equivalent substitution and improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.

Claims

1. A medical image processing method, characterized in that: The method comprises: Acquire ultrasound images of the target thyroid gland; Inputting the target thyroid ultrasound image into a pre-trained thyroid image processing model to determine a thyroid contour area and at least one reference thyroid nodule annotation box of the thyroid ultrasound image, wherein the pre-trained thyroid image processing model is trained based on an improved YOLO11 model; A target thyroid nodule marking frame in at least one of the reference thyroid nodule marking frames is determined according to a positional relationship between the thyroid contour area and at least one of the reference thyroid nodule marking frames, and the target thyroid nodule marking frame is displayed in the target thyroid ultrasound image.

2. The medical image processing method according to claim 1, characterized in that: Determining a target thyroid nodule labeling frame in at least one of the reference thyroid nodule labeling frames according to the positional relationship between the thyroid contour area and at least one of the reference thyroid nodule labeling frames comprises: For each reference thyroid nodule marking frame, when the center position of the reference thyroid nodule marking frame is located within the thyroid contour area, it is determined that the detection point corresponding to the reference thyroid nodule marking frame is a real nodule, and the reference thyroid nodule marking frame is used as the target thyroid nodule marking frame.

3. The medical image processing method according to claim 2, characterized in that: The method further comprises: When the center position of the reference thyroid nodule marking frame is not located within the thyroid contour area, the detection point corresponding to the reference thyroid nodule marking frame is determined to be a false positive nodule, and the reference thyroid nodule marking frame is deleted.

4. The medical image processing method according to claim 1, characterized in that: The improved yolo11 model adds a segmentation head for performing thyroid segmentation processing on thyroid ultrasound images based on the original yolo11 model.

5. The medical image processing method according to claim 4, characterized in that: The loss function of the improved yolo11 model includes a first loss function and a second loss function, wherein the first loss function is used to calculate the loss value of the thyroid nodule annotation box, and the second loss function is used to calculate the loss value of the thyroid contour area.

6. The medical image processing method according to claim 4, characterized in that: The method further comprises: Acquire sample data and expected data corresponding to the sample data, wherein the sample data is a thyroid ultrasound sample image, and the expected data is a thyroid contour area of ​​the thyroid ultrasound sample image or a thyroid contour area including a thyroid nodule annotation box; Input the sample data into a pre-built improved yolo11 model to obtain an actual output result of the improved yolo11 model; Based on the expected data and the actual output result, the network parameters of the improved yolo11 model are adjusted to obtain a trained thyroid image processing model.

7. The medical image processing method according to claim 1, characterized in that: Before inputting the target thyroid ultrasound image into the pre-trained thyroid image processing model, the method further includes: The target thyroid ultrasound image is subjected to image preprocessing, wherein the image preprocessing includes at least one of image enhancement processing, image scaling processing and image normalization processing.

8. A medical image processing device, characterized in that: Said include: An image acquisition module, used for acquiring an ultrasonic image of a target thyroid gland; An image processing module, used for inputting the target thyroid ultrasound image into a pre-trained thyroid image processing model, determining a thyroid contour area and at least one reference thyroid nodule annotation frame of the thyroid ultrasound image, wherein the pre-trained thyroid image processing model is obtained by training based on an improved YOLO11 model; The image display module is used to determine a target thyroid nodule marking frame in at least one of the reference thyroid nodule marking frames according to the positional relationship between the thyroid contour area and at least one of the reference thyroid nodule marking frames, and display the target thyroid nodule marking frame in the target thyroid ultrasound image.

9. An electronic device, characterized in that: The electronic device comprises: at least one processor; and a memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can perform the medical image processing method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores computer instructions, and the computer instructions are used to enable a processor to implement the medical image processing method according to any one of claims 1 to 7 when executed.

Images