Focus sign processing method, device and equipment and computer readable storage medium

Abstract

The invention discloses a focus sign processing method, apparatus and device, and a computer readable storage medium. The method comprises the steps of obtaining the diagnosis difficulty of a target focus; determining a difficult sign of the target focus according to the diagnosis difficulty and focus information of the target focus; and performing enhancement processing on the difficult sign to obtain a target sign, and performing diagnosis on the target focus again based on the target sign. The accuracy of focus diagnosis can be improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and particularly relates to a method, apparatus, device and computer-readable storage medium for processing lesion signs. Background Art

[0002] Lesion signs refer to specific manifestations or characteristics of a lesion area observed through imaging examinations in medical imaging. These signs can help doctors identify lesions for disease diagnosis. However, during the generation of medical images, the images of not all areas are very clear, resulting in certain inaccurate factors in some lesion signs, which affect the accuracy of lesion diagnosis. Summary of the Invention

[0003] Embodiments of the present invention provide a method, apparatus, device and computer-readable storage medium for processing lesion signs, aiming to effectively improve the accuracy of processing lesion signs.

[0004] In a first aspect, embodiments of the present invention provide a method for processing lesion signs, and the method for processing lesion signs includes:

[0005] Obtain the diagnostic difficulty of a target lesion;

[0006] Determine the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion;

[0007] Perform enhancement processing on the difficult signs to obtain target signs, and re-diagnose the target lesion based on the target signs.

[0008] Optionally, the obtaining the diagnostic difficulty of the target lesion includes:

[0009] Obtain the type and / or degree of the target lesion;

[0010] Determine the diagnostic difficulty according to the type and / or degree of the target lesion.

[0011] Optionally, the determining the diagnostic difficulty according to the type and / or degree of the target lesion and the ambiguous zone of benign and malignant definition corresponding to the target lesion includes:

[0012] Obtain the confidence level corresponding to the degree of the target lesion;

[0013] Determine the relationship between the confidence level and the ambiguous zone of benign and malignant definition corresponding to the target lesion;

[0014] Determine the diagnostic difficulty according to the type of the target lesion, the degree of the target lesion and / or the relationship.

[0015] Optionally, determining the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion includes:

[0016] If the diagnostic difficulty indicates that the target lesion is a lesion to be enhanced, determine the difficult signs of the target lesion according to the lesion information of the target lesion.

[0017] Optionally, determining the difficult signs of the target lesion according to the lesion information of the target lesion includes:

[0018] Obtain a preset sign relationship, where the preset sign relationship includes the corresponding relationship between different preset lesion information and different preset difficult signs;

[0019] Determine the difficult signs of the target lesion according to the preset difficult signs corresponding to the preset lesion information that matches the lesion information of the target lesion in the preset sign relationship.

[0020] Optionally, performing enhancement processing on the difficult signs to obtain target signs includes:

[0021] Obtain a medical image including the target lesion;

[0022] Determine a target image area associated with the difficult signs from the medical image;

[0023] Perform image enhancement processing on the target image area, and obtain the target signs based on the target image area after image enhancement processing.

[0024] Optionally, performing enhancement processing on the difficult signs to obtain target signs includes:

[0025] Construct a local three-dimensional model corresponding to the difficult signs to perform enhancement processing on the difficult signs;

[0026] Determine the target signs based on the local three-dimensional model.

[0027] In a second aspect, an embodiment of the present invention provides a lesion sign processing device, and the lesion sign processing device includes:

[0028] An acquisition module, configured to acquire the diagnostic difficulty of a target lesion;

[0029] A determination module, configured to determine the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion;

[0030] An enhancement module, configured to perform enhancement processing on the difficult signs to obtain target signs, so as to re-diagnose the target lesion based on the target signs.

[0031] In a third aspect, an embodiment of the present invention further provides a lesion sign processing device, including a processor and a memory. The memory stores a computer program, and when the computer program is executed by the processor, the processor is caused to execute the steps of any one of the lesion sign processing methods provided by the embodiments of the present invention.

[0032] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium. The computer-readable storage medium includes a computer program, and when the computer program runs on an electronic device, the computer program is used to cause the electronic device to execute the steps of any one of the lesion sign processing methods provided by the embodiments of the present invention.

[0033] The present invention obtains the diagnostic difficulty of a target lesion; according to the diagnostic difficulty and the lesion information of the target lesion, determines the difficult signs of the target lesion; performs enhancement processing on the difficult signs to obtain target signs, so as to re-diagnose the target lesion based on the target signs. In this way, by screening out the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion, and then performing enhancement processing on the difficult signs, target signs with more information content than the difficult signs are obtained, and then the target lesion is re-diagnosed according to the target signs, which can improve the accuracy of lesion diagnosis. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present invention, and those skilled in the art can also obtain other drawings without creative efforts based on these drawings.

[0035] Figure 1 is a flowchart of an embodiment of the lesion sign processing method provided by an embodiment of the present invention;

[0036] Figure 2 is a schematic diagram of sign enhancement processing of the lesion sign processing method provided by an embodiment of the present invention;

[0037] Figure 3 is a schematic structural diagram of the lesion sign processing device provided by an embodiment of the present invention;

[0038] Figure 4 is a schematic structural diagram of the lesion sign processing device provided by an embodiment of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0039] Next, the technical solutions in the embodiments of the present invention will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative efforts belong to the scope of protection of the present invention. At the same time, in the description of the embodiments of the present invention, terms such as "first" and "second" are only used for distinguishing descriptions and cannot be understood as indicating or implying relative importance. Thus, the features defined with "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present invention, the meaning of "a plurality" is two or more, unless otherwise specifically defined.

[0040] The embodiments of the present invention provide a method, device, equipment and computer-readable storage medium for processing lesion signs.

[0041] Specifically, this embodiment will be described from the perspective of the lesion sign processing device. The lesion sign processing device can be specifically integrated in the lesion sign processing equipment. That is, the lesion sign processing method in the embodiments of the present invention can be executed by the lesion sign processing equipment, and the lesion sign processing equipment can be a medical device (such as a magnetic resonance imaging device, etc.), a terminal device (such as a computer, etc.).

[0042] The following will be described in detail with reference to the accompanying drawings. In this embodiment, the execution subject is the lesion sign processing equipment as an example. It should be noted that the description order of the following embodiments does not limit the preferred order of the embodiments. Although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in a different order from that shown in the drawings.

[0043] According to the description of the background technology of the present invention, lesion signs refer to specific manifestations or characteristics of the lesion area observed through imaging examinations in medical imaging. These signs can help doctors identify lesions for disease diagnosis. However, in the process of generating medical images, the images of not all regions are very clear, resulting in certain inaccurate factors in some lesion signs, which affect the accuracy of lesion diagnosis.

[0044] To solve the above problems, the present invention discloses a method for processing lesion signs. Please refer to Figure 1 , the specific process of the method for processing lesion signs can be as follows: Step S10 to Step S30, where:

[0045] Step S10, obtain the diagnostic difficulty of the target lesion;

[0046] In this embodiment, a lesion refers to an area in a body tissue or organ that has undergone pathological changes, which may be caused by infections, inflammations, tumors, injuries, or other pathological processes. Lesions can be local or systemic, and they can be visible or detected by medical imaging techniques (such as X-rays, CTs, MRIs, ultrasounds, etc.). Medical images are obtained by scanning a target tissue area on a target object using one or more medical devices, and the target object can be an organism with biological characteristics, such as a human body, a pet, etc. By performing lesion detection and other processing on the target medical images, it can be determined whether the target medical images contain the target lesions. If the target medical images do not contain the target lesions, it can be determined that the target medical images are normal; if the target medical images contain the target lesions, it can be determined that the target medical images are abnormal.

[0047] In this embodiment, the target lesion refers to the target lesion obtained through primary diagnosis based on medical images. The diagnostic difficulty of diagnosing the target lesion involves multiple factors, including the characteristics of the lesion, the experience of the doctor, and the diagnostic tools and techniques used.

[0048] In one embodiment, obtaining the diagnostic difficulty of the target lesion includes:

[0049] Obtaining the type and / or degree of the target lesion;

[0050] Determining the diagnostic difficulty according to the type and / or degree of the target lesion.

[0051] In this embodiment, the type of the target lesion is information that differentiates this lesion from other lesions. The type of the target lesion can reflect the commonness, confusion-proneness, etc. of the target lesion. According to the type of the target lesion, it can be determined whether the target lesion is a common lesion or a confusion-prone lesion. According to whether the target lesion is a common lesion and / or a confusion-prone lesion, the diagnostic difficulty of the target lesion can be determined.

[0052] It can be understood that when the target lesion is an uncommon lesion, the diagnostic difficulty of the target lesion will be relatively large. When the target lesion is a confusion-prone lesion, the diagnostic difficulty of the target lesion will also be relatively large.

[0053] The degree of the target lesion is information that characterizes the benign or malignant degree of the target lesion. According to the degree of the target lesion, the diagnostic result of diagnosing the target lesion can be reflected, and the diagnostic difficulty of the lesion can also be determined according to the degree of the target lesion.

[0054] In one embodiment, determining the diagnostic difficulty according to the type and / or degree of the target lesion, and the fuzzy zone of benign and malignant definition corresponding to the target lesion includes:

[0055] Obtain the confidence level corresponding to the degree of the target lesion;

[0056] Determine the relationship between the confidence level and the benign-malignant boundary ambiguity zone corresponding to the target lesion;

[0057] Determine the diagnostic difficulty according to the type of the target lesion, the degree of the target lesion, and / or the relationship.

[0058] In this embodiment, it is possible to determine the degree of difficulty in defining the benign or malignant nature of the target lesion according to whether the degree of the target lesion is on the boundary of differentiating between benign and malignant. Obtain the confidence level corresponding to the degree of the target lesion. The confidence level is a numerical value used to determine the degree of the target lesion. In some embodiments, when the confidence level reaches a threshold, it can be determined that the degree of the target lesion is malignant. In some embodiments, the magnitude of the confidence level can be directly associated with the degree of the target lesion. For example, the greater the confidence level, the greater the malignant degree of the target lesion. It can be seen that the confidence level is the main basis for judging whether the degree of the target lesion is benign or malignant, and correspondingly, there will be a benign-malignant boundary ambiguity zone. According to the relationship between the confidence level and the benign-malignant boundary ambiguity zone corresponding to the target lesion, it can be determined whether the degree of the target lesion is ambiguous, and further, the diagnostic difficulty of the target lesion can be determined.

[0059] In some embodiments, when the confidence level corresponding to the degree of the target lesion is in the benign-malignant boundary ambiguity zone, it indicates that the degree of the target lesion is difficult to define, and the diagnostic difficulty of the target lesion will be relatively large.

[0060] In some embodiments, the diagnostic difficulty of the target lesion can be determined according to each of the type of the target lesion, the degree of the target lesion, and the relationship between the confidence level corresponding to the degree of the target lesion and the benign-malignant boundary ambiguity zone corresponding to the target lesion. Furthermore, according to at least one of the type of the target lesion, the degree of the target lesion, and the relationship between the confidence level corresponding to the degree of the target lesion and the benign-malignant boundary ambiguity zone corresponding to the target lesion, the diagnostic difficulty of the target lesion can be determined by means of weighted summation.

[0061] In one example, the confidence level is a specific numerical value. When the confidence level tends to indicate benignancy, it shows that the degree of the target lesion is a benign lesion, and further observation is required in the follow-up. When the confidence level tends to indicate malignancy, it shows that the target lesion is a malignant lesion and further diagnosis and treatment are needed. Obtain the benign-malignant demarcation threshold corresponding to the target lesion. This benign-malignant demarcation threshold is a preset confidence level for distinguishing whether the degree of the target lesion is benign or malignant. When the confidence level of the target lesion is lower than the benign-malignant demarcation threshold, it indicates that the degree of the target lesion is benign. When the confidence level of the target lesion is higher than the benign-malignant demarcation threshold, it indicates that the degree of the target lesion is malignant; or, when the confidence level of the target lesion is lower than the benign-malignant demarcation threshold, it indicates that the degree of the target lesion is malignant. When the confidence level of the target lesion is higher than the benign-malignant demarcation threshold, it indicates that the degree of the target lesion is benign. Based on the benign-malignant demarcation threshold and the preset bandwidth, the benign-malignant fuzzy zone corresponding to the target lesion can be determined. According to the confidence level of the degree of the target lesion, calculate the distance between the confidence level of the degree of the target lesion and the benign-malignant fuzzy zone corresponding to the target lesion. This distance represents the relationship between the confidence level and the benign-malignant fuzzy zone corresponding to the target lesion, and also represents the degree of confusion in the qualitative determination of the degree of the target lesion. Furthermore, the diagnostic difficulty of the target lesion can be determined. When the distance is smaller, the qualitative determination of the degree of the target lesion is more likely to be confused, and the diagnostic difficulty of the target lesion is greater. On the contrary, when the distance is larger, the qualitative determination of the degree of the target lesion is less likely to be confused, and the diagnostic difficulty of the target lesion is smaller.

[0062] Step S20, according to the diagnostic difficulty and the lesion information of the target lesion, determine the difficult signs of the target lesion.

[0063] In the embodiment, according to the diagnostic difficulty of the target lesion, it can be determined whether the target lesion needs to be enhanced to improve the diagnostic accuracy. According to the lesion information of the target lesion, it can be determined which difficult signs of the target lesion need to be enhanced for processing to obtain a target diagnosis and re-diagnose to improve the diagnostic efficiency. The target lesion specifically has a variety of lesion signs. The lesion signs are specific image features of the lesion based on the lesion image. The difficult signs refer to the imaging manifestations that are uncommon, difficult to identify or interpret among the target signs. These signs often require more advanced diagnostic techniques and clinical experience to accurately interpret. The difficult signs are at least one of the lesion signs of the target lesion.

[0064] In this embodiment, according to the lesion information, the difficult signs that are prone to problems can be determined from the target lesion. The lesion information refers to the relevant information set for the target lesion, such as the lesion name, lesion type, etc. In this embodiment, it also includes whether the target lesion is a common lesion, whether the target lesion is an easily confused lesion, and whether the degree of the target lesion is a lesion with a fuzzy demarcation.

[0065] In one embodiment, determining the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion includes:

[0066] If the diagnostic difficulty indicates that the target lesion is a lesion to be enhanced, determine the difficult signs of the target lesion according to the lesion information of the target lesion.

[0067] In this embodiment, if the diagnostic difficulty of the target lesion indicates that the target lesion is a lesion to be enhanced, then determine the difficult signs of the target lesion according to the lesion information of the target lesion. The diagnostic difficulty of the target lesion can be a specific value. When the diagnostic difficulty of the target lesion is greater than the preset threshold, it can be determined that the diagnostic difficulty of the target lesion indicates that the target lesion is a lesion to be enhanced. Furthermore, it is necessary to determine the difficult signs to be enhanced of the target lesion according to the lesion relationship of the target lesion to improve the efficiency of determining the difficult signs to be enhanced.

[0068] In one embodiment, determining the difficult signs of the target lesion according to the lesion information of the target lesion includes:

[0069] Obtain a preset sign relationship, where the preset sign relationship includes the corresponding relationship between different preset lesion information and different preset difficult signs;

[0070] Determine the difficult signs of the target lesion according to the preset difficult signs corresponding to the preset lesion information that matches the lesion information of the target lesion in the preset sign relationship.

[0071] In this embodiment, if the diagnostic difficulty of the target lesion indicates that the target lesion is a lesion to be enhanced, then obtain a preset sign relationship. The preset sign relationship includes the corresponding relationship between different preset lesion information and different preset difficult signs. For example, for common lesions, the corresponding associated preset difficult sign is the edge, and for easily confused lesions, the corresponding associated preset difficult sign is the texture. Determine the preset difficult sign corresponding to the preset lesion information that matches the lesion information of the target lesion in the preset sign relationship as the difficult sign of the target lesion.

[0072] In this embodiment, the diagnostic difficulty is used to evaluate whether to process the signs of the target lesion to re-diagnose the target lesion, and the lesion information of the target lesion is used to query the difficult signs in the target lesion. The processing efficiency of the signs of the target lesion can be improved.

[0073] Step S30, perform enhancement processing on the difficult signs to obtain target signs, and re-diagnose the target lesion based on the target signs.

[0074] In this embodiment, enhancing the difficult signs to obtain the target signs is equivalent to processing the difficult signs with more information. The obtained target signs are of the same type as the difficult signs, but are more accurate and have a higher dimension. Refer to Figure 2 , after enhancing the difficult signs, the contrast is higher than that before enhancement, and it is easier to observe the lesion image features. The target signs can replace the original difficult signs of the target lesion, and all the lesion signs of the updated target lesion can be used to re-diagnose the target lesion, thereby improving the accuracy for the target lesion.

[0075] Specifically, the process of re-diagnosing the target lesion based on the target signs first involves using advanced image processing techniques, such as deep learning and three-dimensional reconstruction, to accurately identify and segment the lesion. Through the enhancement process, the features of the lesion are highlighted for further analysis. Subsequently, combined with a machine learning model, especially a convolutional neural network, the key features of the lesion are automatically extracted, which are crucial for classifying the malignancy of the lesion. Finally, the doctor can comprehensively consider these technical results and clinical information to make a more accurate diagnosis of the lesion, thereby providing a more effective treatment plan for the patient. This process not only improves the accuracy of the diagnosis but also makes personalized medicine possible.

[0076] In some embodiments, enhancing the difficult signs to obtain the target signs includes: obtaining a medical image containing the target lesion, determining a target image region associated with the difficult signs from the medical image, enhancing the target image region, increasing the information related to the target image region, and then obtaining the target signs based on the enhanced target image region.

[0077] In one embodiment, enhancing the difficult signs to obtain the target signs includes:

[0078] obtaining a medical image containing the target lesion;

[0079] determining a target image region associated with the difficult signs from the medical image;

[0080] performing image enhancement on the target image region and obtaining the target signs based on the enhanced target image region.

[0081] In this embodiment, image enhancement processing is performed on the target image region. Image enhancement processing refers to a processing algorithm that improves the visual effect of an image or extracts useful information in the image, so as to better analyze and interpret it. These methods enhance certain features of the image by modifying the image data while trying to maintain the authenticity and non-distortion of the image. The goals of image enhancement can be to improve the contrast, clarity, color saturation of the image, or to highlight specific details in the image for easy manual observation or automatic analysis.

[0082] Image enhancement processing can adopt image enhancement techniques, including zero-padding, gray-level transformation, smoothing filtering, sharpening filtering, frequency-domain method, super-resolution reconstruction, image denoising, image inpainting, etc. Gray-level transformation realizes image enhancement by performing non-linear transformation on the gray values of the image, including logarithmic transformation and power-law transformation, etc. Smoothing filtering reduces the noise of the image by averaging the gray values of adjacent pixels. Common smoothing filters include mean filter and median filter. Sharpening filtering improves the clarity of the image by enhancing the edge information of the image. Common sharpening filters include Laplacian filter and high-pass filter. The frequency-domain method performs signal enhancement in the transform domain of the image. Common methods include low-pass filtering, high-pass filtering, and homomorphic filtering, etc. Super-resolution reconstruction: Generates a high-resolution image from a low-resolution image to enhance the details and clarity of the image. Common methods include interpolation-based methods, learning-based methods, and sparse representation-based methods. Image denoising: Removes the noise in the image and retains the useful image information. Common methods include Gaussian filtering, median filtering, non-local means filtering, and deep learning-based methods. Image inpainting: Fills in the missing or damaged parts of the image to make the image complete. Common methods include texture synthesis-based methods and deep learning-based methods. These methods can be used alone or in combination to meet different image enhancement requirements and improve the image quality.

[0083] Zero-padding is a method of expanding an image, and the expanded part is filled with 0. The specific operations include randomly generating an expansion factor, generating an expanded image template, placing the original image at a specified position in the image template, and recalculating the coordinates of the rectangle containing the target. Or image enhancement processing can adopt deep learning-based image enhancement techniques, such as generative adversarial networks. According to the characteristics of the difficult signs, a suitable enhancement processing can be selected, and the parameters of the enhancement processing, such as the expansion factor, enhancement level, etc., can be set according to specific requirements. After the enhancement processing, the effect of the enhanced image is also evaluated. Based on the target image region after image enhancement processing, the target signs are determined, so as to ensure that the difficult signs are effectively enhanced and the accuracy of the target signs is improved.

[0084] Further, the enhancement processing of the difficult signs to obtain the target signs includes:

[0085] Construct a local three-dimensional model corresponding to the difficult sign to enhance the difficult sign;

[0086] Determine the target sign based on the local three-dimensional model.

[0087] In this embodiment, three-dimensional reconstruction can be performed on the image region corresponding to the difficult sign of the target lesion, which involves computer tomography or magnetic resonance imaging data in medical imaging. Obtain data such as computer tomography or magnetic resonance imaging data associated with the tissue region where the difficult sign of the target lesion is located. Through these data, a local three-dimensional model of the tissue region where the difficult sign of the target lesion is located can be constructed as the local three-dimensional model corresponding to the difficult sign.

[0088] In some embodiments, a medical image containing the target lesion can also be obtained, and the target image region associated with the difficult sign can be determined from the medical image. The target image region is processed to construct a local three-dimensional model from two dimensions to three dimensions to obtain the local three-dimensional model corresponding to the difficult sign. Three-dimensional reconstruction software or algorithms, such as voxel-based methods or surface-based reconstruction techniques, can be used to extract three-dimensional structure information from two-dimensional image data. This step may be implemented using professional medical image processing software or customized algorithms.

[0089] After constructing the local three-dimensional model corresponding to the difficult sign, more information corresponding to the difficult sign can be obtained, thereby enhancing the difficult sign. Based on the enhanced difficult sign, that is, the local three-dimensional model corresponding to the difficult sign, the characteristics of the target lesion, such as shape, edge, density, etc., can be more clearly identified. Using the local three-dimensional model, the spatial structure of the lesion and its relationship with the surrounding tissues can be further analyzed, thereby further improving the accuracy of diagnosing the target lesion.

[0090] In one embodiment, if the diagnostic difficulty indicates that the target lesion is a lesion to be enhanced, the associated lesion signs of the target lesion can also be obtained based on the associated medical image of the target lesion to enhance the target lesion to be enhanced. Based on the target sign obtained by enhancing the difficult sign and the associated lesion signs, the target lesion is jointly diagnosed to further improve the diagnostic accuracy of the target lesion.

[0091] In this embodiment, the associated medical images of the target lesion can be first subjected to lesion recognition to determine the associated lesions in the associated medical images. Then, the associated lesions are compared with the target lesion. If the associated lesions match the target lesion, it indicates that the associated lesions in the associated medical images and the target lesion are the same lesion. In this case, the associated lesion signs corresponding to the associated lesions are obtained, and these associated lesion signs can be used as the newly added lesion signs of the target lesion to enhance the target lesion. The associated medical images and the target medical image where the target lesion is located can be medical images obtained by different acquisition methods at different acquisition times within the same detection cycle. The same detection cycle indicates that the associated medical images are referable to the target medical image and can be used to optimize and enhance difficult signs. The associated medical images and the target medical image are also medical images obtained for the same target tissue area by different acquisition methods. Since the associated medical images and the target medical images are images acquired based on different acquisition methods, the information within the target tissue area included in different medical images is different and may include information such as liver tissue, blood vessels, and lesions. Therefore, they also contain different-dimensional information about the same lesion. Furthermore, the associated medical images can be used to enhance the target lesion. And because the medical images within the same detection cycle are stored associatively, it is more convenient to obtain the associated medical images, which can further improve the efficiency of lesion sign processing.

[0092] In the above disclosed embodiments, the diagnostic difficulty of the target lesion is obtained; according to the diagnostic difficulty and the lesion information of the target lesion, the difficult signs of the target lesion are determined; the difficult signs are enhanced to obtain target signs, so as to rediagnose the target lesion based on the target signs. In this way, by screening out the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion, and then enhancing the difficult signs, target signs with more information content than the difficult signs are obtained. Furthermore, rediagnosing the target lesion based on the target signs can improve the accuracy of lesion diagnosis.

[0093] This embodiment also provides a lesion sign processing device, which can be specifically integrated in a lesion sign processing device. For example, as Figure 3 shown, the lesion sign processing device may include:

[0094] An acquisition module 1001, configured to obtain the diagnostic difficulty of the target lesion;

[0095] A determination module 1002, configured to determine the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion;

[0096] An enhancement module 1003, configured to enhance the difficult signs to obtain target signs, so as to rediagnose the target lesion based on the target signs.

[0097] Optionally, obtaining the diagnostic difficulty of the target lesion includes:

[0098] Obtaining the type of the target lesion and / or the degree of the target lesion;

[0099] Determining the diagnostic difficulty according to the type of the target lesion and / or the degree of the target lesion.

[0100] Optionally, determining the diagnostic difficulty according to the type of the target lesion and / or the degree of the target lesion, and the benign and malignant boundary fuzzy zone corresponding to the target lesion includes:

[0101] Obtaining the confidence level corresponding to the degree of the target lesion;

[0102] Determining the relationship between the confidence level and the benign and malignant boundary fuzzy zone corresponding to the target lesion;

[0103] Determining the diagnostic difficulty according to the type of the target lesion, the degree of the target lesion and / or the relationship.

[0104] Optionally, determining the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion includes:

[0105] If the diagnostic difficulty indicates that the target lesion is a lesion to be enhanced, determining the difficult signs of the target lesion according to the lesion information of the target lesion.

[0106] Optionally, determining the difficult signs of the target lesion according to the lesion information of the target lesion includes:

[0107] Obtaining a preset sign relationship, where the preset sign relationship includes the corresponding relationship between different preset lesion information and different preset difficult signs;

[0108] Determining the difficult signs of the target lesion according to the preset difficult signs corresponding to the preset lesion information matching the lesion information of the target lesion in the preset sign relationship.

[0109] Optionally, performing enhancement processing on the difficult signs to obtain target signs includes:

[0110] Obtaining a medical image including the target lesion;

[0111] Determining a target image area associated with the difficult signs from the medical image;

[0112] Performing image enhancement processing on the target image area, and obtaining the target signs based on the target image area after the image enhancement processing.

[0113] Optionally, enhancing the difficult sign to obtain a target sign includes:

[0114] Constructing a local three-dimensional model corresponding to the difficult sign to enhance the difficult sign;

[0115] Determining the target sign based on the local three-dimensional model.

[0116] In this embodiment, the diagnostic difficulty of the target lesion is obtained; according to the diagnostic difficulty and the lesion information of the target lesion, the difficult sign of the target lesion is determined; the difficult sign is enhanced to obtain a target sign, so as to re-diagnose the target lesion based on the target sign. In this way, after screening out the difficult sign of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion, and then enhancing the difficult sign, a target sign with more information than the difficult sign is obtained, and then the target lesion is re-diagnosed according to the target sign, which can improve the accuracy of lesion diagnosis.

[0117] For the specific implementation of each of the above operations, reference may be made to the previous embodiments and will not be elaborated herein.

[0118] Those of ordinary skill in the art can understand that all or part of the steps in the above method can be completed by instructing relevant hardware (such as a processor) through a program, and the program can be stored in a computer-readable storage medium, such as a read-only memory, a magnetic disk or an optical disc, etc. Optionally, all or part of the steps of the above embodiments can also be implemented using one or more integrated circuits. Correspondingly, each module / unit in the above embodiments can be implemented in the form of hardware, for example, by an integrated circuit to implement its corresponding function, or can be implemented in the form of a software function module, for example, by a processor executing a program / instruction stored in a memory to implement its corresponding function. The present application is not limited to any specific form of combination of hardware and software.

[0119] As Figure 4 shown, Figure 4 is a schematic structural diagram of a lesion sign processing device provided by an embodiment of the present invention. The lesion sign processing device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored on the memory 1102 and executable on the processor. Among them, the processor 1101 is electrically connected to the memory 1102. Those skilled in the art can understand that the structural diagram of the lesion sign processing device shown in the figure does not constitute a limitation on the lesion sign processing device, and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0120] The processor 1101 is the control center of the lesion sign processing device 1100, connecting various parts of the entire lesion sign processing device 1100 through various interfaces and circuits. By running or loading software programs and / or units stored in the memory 1102, and invoking the data stored in the memory 1102, it executes various functions of the lesion sign processing device 1100 and processes data, thereby monitoring the entire lesion sign processing device 1100. The processor 1101 can be a central processing unit (CPU), a graphics processing unit (GPU), a network processor (NP), etc., and can implement or execute the various methods, steps, and logic block diagrams disclosed in the embodiments of the present invention.

[0121] In the embodiments of the present invention, the processor 1101 in the lesion sign processing device 1100 will load the instructions corresponding to the processes of one or more application programs into the memory 1102 according to the following steps, and the processor 1101 will run the application programs stored in the memory 1102 to implement various functions, such as:

[0122] Obtain the diagnostic difficulty of the target lesion;

[0123] Determine the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion;

[0124] Perform enhancement processing on the difficult signs to obtain target signs, and re-diagnose the target lesion based on the target signs.

[0125] For the specific implementation of each of the above operations, reference can be made to the previous embodiments, and details will not be elaborated here.

[0126] Optionally, as Figure 4 shown, the lesion sign processing device 1100 further includes: a touch display screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106, and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch display screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106, and the power supply 1107 respectively. Those skilled in the art can understand that Figure 4 the structure of the lesion sign processing device shown in

[0127] The touch display screen 1103 can be used to display a graphical user interface and receive operation instructions generated by a user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Among them, the display panel can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of the lesion sign processing device. These graphical user interfaces can be composed of graphics, text, icons, videos, and any combination thereof. Optionally, the display panel can be configured in the form of a liquid crystal display (LCD), an organic light-emitting diode (OLED), etc. The touch panel can be used to collect touch operations of the user on or near it (such as operations of the user using any suitable object or accessory such as a finger or a stylus on or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute the corresponding program. Optionally, the touch panel can include two parts: a touch detection device and a touch controller. Among them, the touch detection device detects the touch position of the user and detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into contact coordinates, and then sends it to the processor 1101, and can receive and execute the commands sent by the processor 1101. The touch panel can cover the display panel. After the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event. Subsequently, the processor 1101 provides a corresponding visual output on the display panel according to the type of touch event. In the embodiment of the present invention, the touch panel and the display panel can be integrated into the touch display screen 1103 to implement input and output functions. However, in some embodiments, the touch panel and the touch panel can be implemented as two independent components to implement input and output functions. That is, the touch display screen 1103 can also be used as a part of the input unit 1106 to implement the input function.

[0128] The radio frequency circuit 1104 can be used to transmit and receive radio frequency signals to establish wireless communication with a network device or other lesion sign processing devices through wireless communication, and transmit and receive signals with the network device or other lesion sign processing devices.

[0129] The audio circuit 1105 can be used to provide an audio interface between the user and the lesion sign processing device through a speaker and a microphone. The audio circuit 1105 can transmit the electrical signal converted from the received audio data to the speaker, which is then converted into a sound signal for output. On the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105, converted into audio data, and then the audio data is output to the processor 1101 for processing. After that, it is sent through the radio frequency circuit 1104 to, for example, another lesion sign processing device, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earphone jack to provide communication between the peripheral earphone and the lesion sign processing device.

[0130] The input unit 1106 can be used to receive input digital, character information or user characteristic information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal inputs related to user settings and function controls.

[0131] The power supply 1107 is used to supply power to each component of the lesion sign processing device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management system, so as to implement functions such as management of charging, discharging, and power consumption management through the power management system. The power supply 1107 may also include any components such as one or more DC or AC power supplies, a recharge system, a power failure detection circuit, a power converter or inverter, and a power status indicator.

[0132] Although Figure 4 not shown in the figure, the lesion sign processing device 1100 may also include a camera, a sensor, a Wi-Fi module, a Bluetooth module, etc., which will not be elaborated here.

[0133] In the above embodiments, the descriptions of each embodiment have their own emphases. For the parts not detailed in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0134] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructions, or by controlling relevant hardware through instructions. These instructions can be stored in a computer-readable storage medium and loaded and executed by a processor.

[0135] For this reason, an embodiment of the present invention provides a computer-readable storage medium, in which multiple computer programs are stored. These computer programs can be loaded by a processor to execute any one of the lesion sign processing methods provided by the embodiments of the present invention. These computer programs can execute the steps of the following lesion sign processing method:

[0136] Obtain the diagnostic difficulty of the target lesion;

[0137] Determine the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion;

[0138] Perform enhancement processing on the difficult signs to obtain target signs, so as to re-diagnose the target lesion based on the target signs.

[0139] For the specific implementation of each of the above operations, reference may be made to the previous embodiments, which will not be elaborated here.

[0140] Among them, the computer-readable storage medium may include: read-only memory (ROM, Read Only Memory), random access memory (RAM, Random Access Memory), magnetic disk or optical disk, etc.

[0141] Since the computer program stored in the computer-readable storage medium can execute any one of the lesion sign processing methods provided by the embodiments of the present invention, the beneficial effects that can be achieved by any one of the lesion sign processing methods provided by the embodiments of the present invention can be realized. For details, reference may be made to the previous embodiments, which will not be elaborated here.

[0142] In the above embodiments of the lesion sign processing device, computer-readable storage medium, lesion sign processing equipment, and computer program product, the descriptions of each embodiment have their own focuses. For the parts not elaborated in a certain embodiment, reference may be made to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and conciseness of description, the specific working processes and the beneficial effects that can be brought by the above-described lesion sign processing device, computer-readable storage medium, computer program product, lesion sign processing equipment and their corresponding units can refer to the description of the lesion sign processing method in the above embodiments, which will not be elaborated here specifically.

[0143] The above has introduced in detail a lesion sign processing method, a lesion sign processing device, a lesion sign processing equipment, a computer-readable storage medium, and a computer program product provided by the embodiments of the present invention. Specific examples are used in this article to elaborate on the principle and implementation manner of the present invention. The description of the above embodiments is only used to help understand the method and its core idea of the present invention; at the same time, for those skilled in the art, according to the idea of the present invention, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A method for treating lesion signs, characterized in that: The method for treating lesion signs comprises: The diagnostic difficulty of obtaining the target lesion; Determining the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion; The difficult signs are enhanced to obtain target signs, so as to re-diagnose the target lesion based on the target signs.

2. The method for treating lesion signs as claimed in claim 1, characterized in that: The diagnostic difficulty of obtaining the target lesion includes: Acquiring the type of the target lesion and / or the extent of the target lesion; The diagnostic difficulty is determined according to the type of the target lesion and / or the extent of the target lesion.

3. The method for treating lesion signs as claimed in claim 2, characterized in that: Determining the diagnostic difficulty according to the type of the target lesion and / or the extent of the target lesion, and the benign and malignant fuzzy zone corresponding to the target lesion, includes: Obtaining a confidence level corresponding to the extent of the target lesion; Determining the relationship between the confidence and the fuzzy zone of good-malignant demarcation corresponding to the target lesion; The diagnostic difficulty is determined according to the type of target lesion, the extent of the target lesion and / or the relationship.

4. The method for treating lesion signs as claimed in claim 1, characterized in that: Determining the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion includes: If the diagnostic difficulty indicates that the target lesion is a lesion to be enhanced, the difficult signs of the target lesion are determined according to the lesion information of the target lesion.

5. The method for treating lesion signs according to claim 1, characterized in that: Determining the difficult signs of the target lesion according to the lesion information of the target lesion includes: Acquiring a preset sign relationship, wherein the preset sign relationship includes a correspondence between different preset lesion information and different preset difficult signs; The difficult sign of the target lesion is determined according to the preset difficult sign corresponding to the preset lesion information matching the lesion information of the target lesion in the preset sign relationship.

6. The method for treating lesion signs according to claim 1, characterized in that: The step of performing enhancement processing on the difficult signs to obtain target signs includes: Acquiring a medical image containing the target lesion; Determine a target image region associated with the difficult sign from the medical image; The target image region is subjected to image enhancement processing, and the target sign is obtained based on the target image region after the image enhancement processing.

7. The method for treating lesion signs according to claim 6, characterized in that: The step of performing enhancement processing on the difficult signs to obtain target signs includes: Constructing a local three-dimensional model corresponding to the difficult signs to enhance the difficult signs; The target feature is determined based on the local three-dimensional model.

8. A lesion sign processing device, characterized in that: The lesion sign processing device comprises: An acquisition module, used to obtain the diagnostic difficulty of the target lesion; A determination module, configured to determine the difficult signs of the target lesion according to the diagnostic difficulty and the lesion information of the target lesion; The enhancement module is used to enhance the difficult signs to obtain target signs, so as to re-diagnose the target lesion based on the target signs.

9. A lesion sign processing device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the lesion sign 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 includes a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the lesion sign processing method according to any one of claims 1 to 7.

Images