Medical image screening method and device, equipment and storage medium

Abstract

The invention discloses a medical image screening method and device, equipment and a storage medium, relates to the technical field of image processing, and aims to solve the problem of low accuracy of image detection in a manual detection mode. The method comprises the steps of determining a first image meeting a medical propaganda theme requirement from a medical image database, determining a second image meeting a medical compliance rule from the first image, and outputting the second image to a medical propaganda system under the condition that a confirmation instruction for the second image input by a clinical auditor is received, the matching degree between the first image and the medical propaganda theme requirement is greater than or equal to the first matching degree, and the matching degree between the second image and the medical compliance rule is greater than or equal to the second matching degree.

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to a medical image screening method, device, equipment and storage medium. Background Art

[0002] As an intuitive and powerful communication medium, images play a vital role in medical publicity. As publicity work becomes increasingly diversified and digital, higher requirements are placed on the quality, compliance, and relevance of photographic data to medical topics.

[0003] In related technologies, when determining medical images for promotional purposes, the process typically involves manually filtering out images that are subjectively considered to match a product from a large amount of image data. These images are then processed (e.g., by color matching and composition adjustments) to ensure that the image promotional effect is close to the desired target. However, due to differences in expertise among personnel and the uncertainty of subjective understanding, manual screening and processing can easily lead to significant deviations from the desired image promotional effect. Therefore, the current accuracy of image detection using manual detection is relatively low. Summary of the Invention

[0004] The purpose of this application is to provide a medical image screening method, device, equipment and storage medium, aiming to solve the problem of low accuracy of image detection using manual detection.

[0005] To achieve the above objectives, this application adopts the following technical solutions: The present application provides a medical image screening method, which includes: determining a first image that meets the requirements of a medical publicity and promotion theme from a medical image database, where the degree of match between the first image and the requirements of the medical publicity and promotion theme is greater than or equal to a first degree of match; determining a second image that meets the medical compliance rules from the first image, where the degree of match between the second image and the medical compliance rules is greater than or equal to a second degree of match; and upon receiving a confirmation instruction for the second image input by a clinical reviewer, outputting the second image to a medical publicity and promotion system.

[0006] The medical image screening method provided in the embodiment of the present application has low detection accuracy due to the possibility of detection errors in manual detection. Therefore, the present application first sets the medical publicity theme requirements to screen the images in the medical image database for theme matching, and then sets medical compliance rules to screen the images that meet the medical publicity theme requirements for rule matching, so as to perform double screening on each image, avoid the possible errors in manual detection, and improve the detection accuracy; and the second image obtained by the double screening is manually reviewed to eliminate the images that may have publicity risks in the second image, thereby further improving the detection accuracy of the image.

[0007] In some embodiments, the above-mentioned determination of the first image that meets the requirements of the medical promotion theme from the medical image database includes: identifying the number of medical features and clinical scenes of each image in the medical image database, the medical features including at least one of pathological identification, anatomical structure markings, and diagnostic equipment features; analyzing the medical feature number threshold and clinical scene type corresponding to the medical promotion theme requirements; and determining an image whose number of medical features is greater than or equal to the medical feature number threshold and whose clinical scene belongs to the clinical scene type as the first image.

[0008] Based on this, this application compares the number of subject elements in each image that meet the requirements of the medical publicity theme, and determines whether the clinical scene of the image belongs to the clinical scene type, to ensure that the determined first image has a matching degree greater than the first matching degree with the medical publicity theme requirements, thereby meeting the medical publicity theme requirements.

[0009] In some embodiments, the above-mentioned determination of the second image that meets the medical compliance rules from the first image includes: identifying the medical content and acquisition process of each image in the first image; analyzing the publicity content rules and acquisition process specifications corresponding to the medical compliance rules; and determining the image whose medical content meets the publicity content rules and whose acquisition process meets the acquisition process specifications as the second image.

[0010] Based on this, this application ensures that the matching degree between the determined second image and the promotion content rules is greater than the second matching degree, thereby meeting the medical compliance rules, by judging whether the medical content of each first image complies with the medical content of the promotion content rules, and judging whether the acquisition process of each first image complies with the acquisition process specifications.

[0011] In some embodiments, the above-mentioned outputting of the second image to the medical publicity and promotion system when a confirmation instruction for the second image input by the clinical reviewer is received includes: displaying the number of medical features, clinical scenes, medical content and acquisition process of each image in the second image; and outputting the second image to the medical publicity and promotion system in response to the confirmation instruction input by the clinical reviewer.

[0012] Based on this, the present application further improves the accuracy of image detection by displaying detailed information of the second image determined by double screening so that clinical reviewers can confirm whether to adopt the second image.

[0013] In some embodiments, the medical image screening method provided in the embodiments of the present application may also include: after receiving the confirmation instruction for the second image input by the clinical reviewer, generating a medical label corresponding to each image in the second image, the medical label is used to indicate the number of medical features, clinical scene, medical content and acquisition process of the image.

[0014] Based on this, the present application generates a medical label for the finally determined image so that when the image is used again in the future, it can be determined directly based on the medical label without the need for re-detection, thereby improving the reuse efficiency of the image.

[0015] In some embodiments, the medical image screening method provided in the embodiments of the present application may also include: preprocessing the original medical image set to obtain qualified images that meet quality control conditions, and generating a medical image database based on the qualified images; the preprocessing includes: noise suppression and resolution standardization of the original images; and verifying the validity of the hospital identifier and acquisition time in the original images.

[0016] Exemplarily, the above-mentioned quality control conditions include at least one of the following: the clarity of the original image is greater than or equal to the preset clarity, the color reproduction of the original image is less than or equal to the preset color reproduction, the contrast of the original image is greater than or equal to the preset contrast, and the integrity of the original image is greater than or equal to the preset integrity.

[0017] Based on this, before double screening the image, the present application first detects the image quality to determine multiple original images that meet the quality control conditions, providing effective image data for subsequent image detection steps, and indirectly improving the accuracy of image detection.

[0018] The present application provides a medical image screening device, which includes: a determination unit, used to determine a first image that meets the requirements of a medical publicity and promotion theme from a medical image database, and the matching degree of the first image with the requirements of the medical publicity and promotion theme is greater than or equal to the first matching degree; the determination unit is also used to determine a second image that meets the medical compliance rules from the first image, and the matching degree of the second image with the medical compliance rules is greater than or equal to the second matching degree; an output unit is used to output the second image to a medical publicity and promotion system when receiving a confirmation instruction for the second image input by a clinical reviewer.

[0019] In some embodiments, the above-mentioned determination unit is specifically used to: identify the number of medical features and clinical scenarios of each image in the medical imaging database, where the medical features include at least one of pathological markers, anatomical structure markers, and diagnostic and treatment equipment features; analyze the medical feature number threshold and clinical scenario type corresponding to the medical promotion theme requirements; and determine an image whose number of medical features is greater than or equal to the medical feature number threshold and whose clinical scenario belongs to the clinical scenario type as the first image.

[0020] In some embodiments, the above-mentioned determination unit is specifically used to: identify the medical content and acquisition process of each image in the first image; analyze the promotion content rules and acquisition process specifications corresponding to the medical compliance rules; and determine the image whose medical content complies with the promotion content rules and whose acquisition process complies with the acquisition process specifications as the second image.

[0021] In some embodiments, the above-mentioned output unit is specifically used to: display the number of medical features, clinical scenarios, medical content and acquisition process of each image in the second image; and output the second image to the medical publicity and distribution system in response to the confirmation instruction input by the clinical reviewer.

[0022] In some embodiments, the medical image screening device provided in the embodiments of the present application also includes: a generation unit, which is used to generate a medical label corresponding to each image in the second image after receiving a confirmation instruction for the second image input by the clinical reviewer, and the medical label is used to indicate the number of medical features, clinical scenes, medical content and acquisition process of the image.

[0023] In some embodiments, the above-mentioned determination unit is also used to: pre-process the original medical image set to obtain qualified images that meet quality control conditions, and generate a medical image database based on the qualified images; the pre-processing includes: noise suppression and resolution standardization of the original images; and verification of the validity of the hospital identifier and acquisition time in the original images.

[0024] In some embodiments, the above-mentioned quality control conditions include at least one of the following: the clarity of the original image is greater than or equal to the preset clarity, the color reproduction of the original image is less than or equal to the preset color reproduction, the contrast of the original image is greater than or equal to the preset contrast, and the integrity of the original image is greater than or equal to the preset integrity.

[0025] The present application provides an electronic device, comprising: a processor; and a memory for storing processor-executable instructions; wherein the processor is configured to execute the instructions to implement the medical image screening method described above.

[0026] The present application provides a computer-readable storage medium, which stores instructions. When the instructions are executed on a terminal, the terminal executes the medical image screening method described above.

[0027] The present application provides a computer program product comprising instructions, which, when executed by a computer, enables the computer to perform the medical image screening method described above.

[0028] The present application provides a chip, which includes a processor and a communication interface. The communication interface and the processor are coupled, and the processor is used to run computer programs or instructions to implement the medical image screening method described above.

[0029] Specifically, the chip provided in the embodiment of the present application also includes a memory for storing computer programs or instructions. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] In order to more clearly illustrate the technical solutions of the embodiments of the present application, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without any creative work.

[0031] Figure 1 A schematic diagram of a medical image screening platform provided in an embodiment of the present application; Figure 2 A flow chart of a medical image screening method provided in an embodiment of the present application; Figure 3 A structural diagram of a medical image screening device provided in an embodiment of the present application; Figure 4 A structural diagram of an electronic device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0032] The following will be combined with the drawings in the embodiments of this application to clearly and completely describe the technical solutions in the embodiments of this application. Obviously, the embodiments described are only part of the embodiments of this application, not all of the embodiments. Based on the embodiments in this application, all other embodiments obtained by ordinary technicians in this field without making creative efforts are within the scope of protection of this application.

[0033] In the description of this application, it should be understood that the terms "upper," "lower," "left," "right," "front," "back," "inner," "outer," and the like, indicating directions or positional relationships, are based on the directions or relative positional relationships shown in the accompanying drawings and are intended solely to facilitate the description of this application and simplify the description. They do not indicate or imply that the devices or components referred to must have a specific direction, be constructed, or operate in a specific direction. Therefore, they should not be construed as limitations on this application. Unless otherwise specified, the above-mentioned directionality descriptions may be flexibly set in actual application, provided that the relative positional relationships shown in the accompanying drawings are met.

[0034] The terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of the technical features being referred to. Thus, a feature specified as "first" or "second" may explicitly or implicitly include one or more of such features. Throughout this application, unless otherwise specified, "plurality" means two or more.

[0035] In the description of this application, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," "connected," and "connected" should be understood broadly. For example, they may refer to fixed connections, detachable connections, or integral connections. They may be directly connected, indirectly connected through an intermediary, or internally connected between two components. Those skilled in the art will understand the specific meanings of these terms in this application based on the specific circumstances.

[0036] In some embodiments, the terms "comprises," "comprising," or any other variations thereof are intended to encompass non-exclusive inclusion, such that a process, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, article, or apparatus. In the absence of further limitations, an element defined by the phrase "comprising a ..." does not preclude the presence of additional identical elements in the process, article, or apparatus that includes the element.

[0037] In some embodiments, words such as "exemplary" or "for example" are used to indicate an example, illustration, or description. Any embodiment or design described as "exemplary" or "for example" in the embodiments of this application should not be construed as being preferred or advantageous over other embodiments or designs. Rather, the use of words such as "exemplary" or "for example" is intended to present the relevant concepts in a concrete manner.

[0038] In the description of this specification, specific features, structures, materials or characteristics may be combined in an appropriate manner in any one or more embodiments or examples.

[0039] Currently, there are two common defects in image detection technology: First, regarding image acquisition, insufficient professionalism or misunderstanding of the subject matter by data collectors leads to a low relevance of medical content to promotional topics. For example, images promoting medical policy often lack core policy symbols, and images with medical themes suffer from illogical composition. Existing detection methods rely on manual annotation, which can lead to misjudgment and result in image data that does not meet requirements.

[0040] 2. In terms of compliance testing, since each promotion and marketing platform has its own standards, such as image size, resolution, file format, etc., manual screening may lead to negligence, resulting in the determined images not complying with the platform's regulations, seriously affecting the promotion effect.

[0041] Therefore, the accuracy of existing image detection methods using manual detection is low.

[0042] In this context, in order to solve the problem of low accuracy of image detection using manual detection in related technologies, the present application provides a medical image screening method, device, equipment and storage medium. The implementation method of the embodiment of the present application is described in detail below in conjunction with the drawings in the specification.

[0043] Figure 1 This is a schematic diagram of the framework of the medical image screening platform provided in an embodiment of the present application. The medical image screening platform 100 includes a knowledge rules module 110, a unit system module 120, a detection and determination module 130, an image review module 140, and a data output module 150. The detection and determination module 130 includes a quality detection submodule 131, a topic detection submodule 132, and a regulation determination submodule 133.

[0044] In some embodiments, the knowledge rule module 110 is used to store various knowledge rules for photographic images used for promotion and to extract the first requirement feature corresponding to each knowledge rule. The knowledge rules cover the subject requirements of medical topics, promotion standards of different platforms, and specific specifications in medical work.

[0045] For example, the first requirement feature can clarify the key elements and color style preferences that need to be displayed in the picture for different medical topics; based on the characteristics of common promotion and marketing platforms, it can specify requirements such as picture size, resolution, file format, etc.

[0046] In some embodiments, the unit system module 120 is used to store the unit's internal system specifications regarding the collection, use, and dissemination of photographic data, and to extract the second requirement feature corresponding to each system specification.

[0047] For example, the second requirement includes process specifications for data collection, such as photography permission regulations in specific scenarios; division of data usage permissions, clarifying the operation permissions of different levels of personnel on photographic data; and institutional requirements for the publicity and promotion process, such as the specific steps and responsible persons in the review process.

[0048] In some embodiments, the quality detection submodule 131 is used to evaluate the quality of photographic images. Specifically, image analysis techniques can be used to detect image clarity to determine whether there are issues such as blur or excessive noise. The image's color reproduction can be analyzed to ensure that the colors match the actual scene. The image's contrast can be checked to avoid areas that are too bright or too dark, which could affect the visual experience. Furthermore, the image's integrity can be checked to check for missing parts or damage.

[0049] In some embodiments, the topic detection submodule 132 is configured to perform matching analysis between the photographic image and the corresponding medical topic based on the first required feature.

[0050] For example, image recognition and text analysis technologies can be used to identify key elements and scenes in a picture and determine whether they meet the required characteristics, for example, whether the picture can reflect the theme of medical promotion and whether the included medical theme elements are sufficient.

[0051] In some embodiments, the regulation determination submodule 133 is configured to perform a compliance check on the photographic image based on the second required feature. Specifically, the regulatory determination submodule 133 may check whether the content of the photographic image involves sensitive information, violates laws and regulations, or the confidentiality provisions of the unit, confirm whether the data collection process complies with the unit's established process specifications, or whether the position / action of elements such as people and equipment in the photographic image complies with the unit's specifications.

[0052] In some embodiments, the image review module 140 is used to provide a manual review channel for photographic images that are in doubt (i.e., it is impossible to determine whether there is a problem) and have passed the inspection after the detection and judgment module 130 completes the preliminary inspection; the reviewer can log in to the audit end to view the detailed information, detection results and related analysis data of the photographic image, and make manual judgments and confirmations.

[0053] In some embodiments, the data output module 150 is used to output and store photographic images that comply with publicity regulations.

[0054] In this way, on the one hand, through the image recognition and text analysis technology of the topic detection sub-module, photographic images and key elements of medical topics (such as clinical scenes, core figures, iconic symbols, etc.) are automatically matched, solving the "off-topic" problem caused by deviation in subject understanding or insufficient shooting skills in traditional manual collection; on the other hand, through the regulations judgment sub-module, risks such as sensitive information and process violations are checked to effectively ensure the seriousness and authority of medical work; further, combined with the image review module, a "machine initial screening plus manual refinement" collaborative model is formed to improve the accuracy of image detection.

[0055] Refer to the following Figure 2 The medical image screening method provided in the embodiments of the present application is described.

[0056] Figure 2 This is a method flow chart of the medical image screening method provided in an embodiment of the present application. The subject executing the method can be an electronic device or various devices / modules in the electronic device, such as an integrated circuit or chip, and the embodiment of the present application does not make specific limitations on this.

[0057] For example, Figure 2 As shown, the medical image screening method provided in the embodiment of the present application may include the following steps S201 to S203: S201. Determine a first image that meets the requirements of the medical publicity theme from a medical image database.

[0058] In an embodiment of the present application, a plurality of images are stored in a medical image database, and the image quality of each image meets a preset quality control condition.

[0059] For example, the medical imaging database may include 1,000-5,000 images, and the specific data may be determined according to the actual promotion scenario.

[0060] Optionally, the original medical images may be pre-processed to obtain qualified images that meet quality control conditions, and a medical image database may be generated based on the qualified images.

[0061] In some embodiments, the pre-processing includes: performing noise suppression and resolution standardization on the original image; and verifying the validity of the hospital identifier and acquisition time in the original image.

[0062] For example, the screening of images for liver cancer interventional treatment education was conducted. 1,000 computed tomography (CT) abdominal images were selected from the original medical image collection. After noise suppression (such as 3D non-local means (NLM) filtering), the peak signal-to-noise ratio (PSNR) was increased from 28 dB to 43 dB. The images were then resampled to standard resolution (1 mm slice thickness) with an interpolation error of less than 0.5%. Verification revealed that 15 imaging devices had unregistered serial numbers and were automatically removed. Twenty images containing patient names were then hashed and desensitized. Finally, 850 qualified images were generated and stored for subsequent screening of promotional materials for liver cancer vascular invasion characteristics.

[0063] In the embodiment of the present application, images in the original medical image set can support accessing original images from various data sources. For example, images can be scanned and queried from data sources such as a local file system, a distributed storage system, and a database table.

[0064] In some embodiments, the above-mentioned quality control conditions may include at least one of the following: the clarity of the original image is greater than or equal to the preset clarity, the color reproduction of the original image is less than or equal to the preset color reproduction, the contrast of the original image is greater than or equal to the preset contrast, and the integrity of the original image is greater than or equal to the preset integrity.

[0065] For example, taking the preset definition as 100, the variance value V of each image can be calculated by formula (1), and when the variance value V is greater than or equal to 100, the image is determined to be a clear image.

[0066] V=∑(I(x,y)-μ)^2 / (M×N) Formula (1) Where (I(x,y) is the pixel grayscale value, μ is the image mean, and M×N is the image size.

[0067] For example, taking the preset color reproduction degree as 3 as an example, the color difference formula can be used to calculate the difference between the image color and the standard color card. When the difference is less than or equal to 3, it is determined that the color reproduction degree of the image is qualified.

[0068] For example, taking the preset contrast as 0.35 as an example, the contrast C of each image can be calculated using the contrast formula (Formula (II)). When the contrast C is greater than or equal to 0.35, the contrast of the image is determined to be qualified.

[0069] C=(I max -I min ) / I max +I min )Formula (2) Among them, I max is the maximum grayscale value, I min is the minimum grayscale value.

[0070] For example, taking the preset completeness as 70%, the detection model can be used to identify the integrity of the image body, and the image is determined to be complete when the subject area accounts for greater than or equal to 70% and no key parts are missing.

[0071] Optionally, after quality control screening, the original medical image set can be normalized. For example, all images can be uniformly converted to a uniform color space and the resolution of each image can be normalized.

[0072] For example, consider testing product images on an e-commerce platform, with preset values ​​for clarity (100), color reproduction (3), contrast (0.35), and completeness (70%). The original medical image set may include 5,000 images of clothing products. During preprocessing, 15 images with non-specific formats were excluded. Quality testing was then performed, revealing that 4,820 images had clarity greater than 100, 4,790 had color reproduction less than 3, 4,750 had contrast greater than 0.35, and 4,720 had completeness greater than 0.7.

[0073] In this way, before double screening the image, the present application first detects the quality of the image to determine multiple original images that meet the quality control conditions, providing effective image data for subsequent image detection steps, and indirectly improving the accuracy of image detection.

[0074] Optionally, the above-mentioned determination of the first image that meets the medical publicity theme requirement may be achieved in the following manner: wherein the matching degree between the first image and the medical publicity theme requirement is greater than or equal to a first matching degree.

[0075] It should be noted that the first matching degree is a preset value, which can be flexibly adjusted according to actual scenarios. For example, the first matching degree can be 90%.

[0076] In some embodiments, the number of medical features and clinical scenarios of each image in the medical imaging database are identified, and the medical feature number threshold and clinical scenario type corresponding to the medical promotion theme requirements are analyzed. Finally, the image whose number of medical features is greater than or equal to the medical feature number threshold and whose clinical scenario belongs to the clinical scenario type is determined as the first image.

[0077] In an embodiment of the present application, the medical feature includes at least one of a pathological marker, an anatomical structure marker, and a diagnostic and treatment equipment feature.

[0078] For example, taking the theme of medical publicity as an example, a pre-trained model can be used for image recognition to identify medical-related elements in the image (such as pathological signs, anatomical structure markers, diagnostic and treatment equipment features, etc.), and then count the number of elements that meet medical characteristics in a single image. Furthermore, a deep learning model can be used to classify image scenes and output scene type medical labels (such as lesion location coordinates, image acquisition equipment model, patient anonymization code, and compliance review timestamp, etc.).

[0079] Furthermore, the medical feature quantity threshold and clinical scenario type whitelist in the promotional document can be parsed. For example, the medical feature quantity threshold is 3, and the clinical scenario types are radiology diagnosis and orthopedics.

[0080] In some embodiments, the degree of matching may be related to the number of medical features and the clinical scenario.

[0081] For example, when the number of medical features is less than the medical feature number threshold and the clinical scenario does not belong to the clinical scenario type, the matching degree can be 10%; when the number of medical features is greater than the medical feature number threshold and the clinical scenario does not belong to the clinical scenario type, the matching degree can be 40%; when the number of medical features is less than the medical feature number threshold and the clinical scenario belongs to the clinical scenario type, the matching degree can be 70%; when the number of medical features is greater than the medical feature number threshold and the clinical scenario belongs to the clinical scenario type, the matching degree can be 95%.

[0082] Specifically, taking the example of a medical image database with a first matching degree of 90% and 850 images, if 520 images are identified with more than three elements related to the medical promotion theme, and the clinical scene of the images is a radiological diagnosis scene, then the matching degree of these 520 images with the medical promotion theme requirement exceeds 90%, and these 520 images can be determined as the first images.

[0083] In this way, this application ensures that the degree of match between the determined first image and the medical promotion theme requirements is greater than the first degree of match by comparing the number of theme elements in each image that meet the medical promotion theme requirements and judging whether the clinical scene of the image belongs to the clinical scene type.

[0084] S202: Determine a second image that meets medical compliance rules from the first image.

[0085] The matching degree between the second image and the medical compliance rule is greater than or equal to the second matching degree.

[0086] It should be noted that the second matching degree is a manually set value, which can be flexibly adjusted according to actual scenarios. For example, the second matching degree can be 95%.

[0087] In some embodiments, the medical content and acquisition process of each image in the first image are identified, and the promotion content rules and acquisition process specifications corresponding to the medical compliance rules are analyzed. Finally, the image whose medical content complies with the promotion content rules and whose acquisition process complies with the acquisition process specifications is determined as the second image.

[0088] For example, let's take the example of a promotional content rule that prohibits the appearance of competitor content. A pre-trained model can be used for multi-medical label classification to identify whether the medical content in each image is similar to the competitor's content. For example, a confidence threshold (0.85) can be set. When competitor content is identified in an image and the confidence is greater than 0.85, it indicates that the image does not comply with the promotional content rules; further, the image's shooting device model, shooting time, shooting coordinates and other data can be extracted from the image's attribute information to verify whether it is the authorized shooting device model, shooting time, and shooting coordinates. If not, it indicates that the image does not comply with the acquisition process specifications.

[0089] In some embodiments, the degree of matching may be related to the medical content and the acquisition process.

[0090] For example, when the medical content does not comply with the promotion content rules and the collection process does not comply with the collection process specifications, the matching degree can be 5%; when the medical content complies with the promotion content rules and the collection process does not comply with the collection process specifications, the matching degree can be 35%; when the medical content does not comply with the promotion content rules and the collection process complies with the collection process specifications, the matching degree can be 65%; when the medical content complies with the promotion content rules and the collection process complies with the collection process specifications, the matching degree can be 95%.

[0091] Specifically, taking the example of a first image set with a second matching degree of 95% and 520 images, if the medical content of 350 images is identified as meeting the promotional content rules and the collection process meets the collection process specifications, then the matching degree of these 350 images with the medical compliance rules reaches 95%, and these 350 images can be determined as the first images.

[0092] In this way, this application ensures that the matching degree between the determined second image and the promotion content rules is greater than the second matching degree by judging whether the medical content of each first image complies with the medical content of the promotion content rules, and judging whether the acquisition process of each first image complies with the acquisition process specifications.

[0093] S203: Upon receiving a confirmation instruction for the second image input by the clinical reviewer, output the second image to the medical publicity and distribution system.

[0094] In some embodiments, after the second image is determined, the number of medical features, clinical scenarios, medical content and acquisition process of each image in the second image can also be displayed, and the second image can be output to the medical publicity and distribution system in response to the confirmation instructions entered by the clinical reviewer.

[0095] For example, the second image is an image related to the theme of medical publicity. A grid layout can be used to display multiple second images (such as 4-6 thumbnails per row), and the corresponding large image preview can be displayed when the mouse hovers over each thumbnail, and the original resolution image of the corresponding image can be viewed by clicking the mouse. Furthermore, an information panel can be set for each thumbnail to display the number of medical features, clinical scenarios, medical content and acquisition process of the current image; clinical reviewers can screen out the second images that need to be output in the end by viewing the original resolution images and the information panel of each second image.

[0096] Optionally, the determined second images also support flexible selection by clinical reviewers to batch select / deselect images that meet the release standards.

[0097] In some embodiments, in order to ensure the quality of the output second image, the degree of matching of each determined second image with the medical promotion theme requirements and the medical compliance rules can be judged. When the degree of matching with the medical promotion theme requirements is equal to the first matching degree, it indicates that the second image is a fuzzy rule image (i.e., there is a risk of unqualified); when the degree of matching with the medical compliance rules is equal to the second matching degree, it also indicates that the second image is a fuzzy rule image (i.e., there is a risk of unqualified), and the corresponding image needs to be deleted.

[0098] For example, if among the 350 second images determined, 100 second images have the same degree of matching as the first, and 150 second images have the same degree of matching as the second, indicating that there are second images among the 250 second images, the clinical reviewer can delete the 200 second images through batch selection and retain the final 100 second images.

[0099] In the medical image screening method provided in the embodiment of the present application, manual detection may result in errors in detection, resulting in low detection accuracy. Therefore, the present application first sets medical publicity theme requirements to screen the images in the medical image database for theme matching, and then sets medical compliance rules to screen the images that meet the medical publicity theme requirements for rule matching, so as to perform double screening on each image, avoid possible errors in manual detection, and improve detection accuracy; and the second image obtained by the double screening is manually reviewed to eliminate images that may have publicity risks in the second image, further improving the detection accuracy of the image.

[0100] Optionally, after receiving the confirmation instruction input by the clinical reviewer for the second image, the embodiment of the present application may also generate a medical label corresponding to each image in the second image.

[0101] Among them, medical labels are used to indicate the number of medical features, clinical scenarios, medical content and acquisition process of the image.

[0102] In some embodiments, different medical labels can be configured for different specifications of medical feature quantity, clinical scenarios, medical content, and acquisition processes. After determining the second image to be output, the matching medical label is determined based on the medical feature quantity, clinical scenario, medical content, and acquisition process of each second image, and the medical label is saved.

[0103] In this way, the present application generates a medical label for the finally determined image so that when the image is used again in the future, it can be determined directly based on the medical label without the need for re-detection, thereby improving the reuse efficiency of the image.

[0104] The above mainly introduces the solution provided by the embodiment of the present application from the perspective of method. In order to realize the above functions, the medical image screening device or electronic device includes hardware structures and / or software modules corresponding to the execution of each function. It should be easily appreciated by those skilled in the art that, in combination with the units and algorithm steps of each example described in the embodiments disclosed herein, the present application can be implemented in the form of hardware or a combination of hardware and computer software. Whether a function is executed in the form of hardware or computer software driving hardware depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0105] The embodiment of the present application can, according to the above method, exemplarily divide the functional modules of the medical image screening device or electronic device. For example, the medical image screening device or electronic device can include various functional modules corresponding to the various functional divisions, or two or more functions can be integrated into one processing module. The above-mentioned integrated modules can be implemented in the form of hardware or in the form of software functional modules. It should be noted that the division of modules in the embodiment of the present application is schematic and is only a logical functional division. There may be other division methods in actual implementation.

[0106] Figure 3 This is a structural diagram of a medical image screening device provided in an embodiment of the present application. The medical image screening device 300 includes: a determination unit 301 and an output unit 302.

[0107] Wherein: the above-mentioned determination unit 301 is used to determine a first image that meets the requirements of the medical publicity and promotion theme from the medical image database, and the matching degree of the first image with the requirements of the medical publicity and promotion theme is greater than or equal to the first matching degree; the above-mentioned determination unit 301 is also used to determine a second image that meets the medical compliance rules from the first image, and the matching degree of the second image with the medical compliance rules is greater than or equal to the second matching degree; the above-mentioned output unit 302 is used to output the second image to the medical publicity and promotion system when receiving a confirmation instruction for the second image input by the clinical reviewer.

[0108] In some embodiments, the above-mentioned determination unit 301 is specifically used to: identify the number of medical features and clinical scenarios of each image in the medical imaging database, where the medical features include at least one of pathological markers, anatomical structure markers, and diagnostic and treatment equipment features; analyze the medical feature number threshold and clinical scenario type corresponding to the medical promotion theme requirements; and determine an image whose number of medical features is greater than or equal to the medical feature number threshold and whose clinical scenario belongs to the clinical scenario type as the first image.

[0109] In some embodiments, the above-mentioned determination unit 301 is specifically used to: identify the medical content and acquisition process of each image in the first image; analyze the promotion content rules and acquisition process specifications corresponding to the medical compliance rules; and determine the image whose medical content complies with the promotion content rules and whose acquisition process complies with the acquisition process specifications as the second image.

[0110] In some embodiments, the output unit 302 is specifically used to: display the number of medical features, clinical scenarios, medical content and acquisition process of each image in the second image; and output the second image to the medical publicity and distribution system in response to the confirmation instruction input by the clinical reviewer.

[0111] In some embodiments, the medical image screening device provided in the embodiments of the present application also includes: a generation unit, which is used to generate a medical label corresponding to each image in the second image after receiving a confirmation instruction for the second image input by the clinical reviewer, and the medical label is used to indicate the number of medical features, clinical scenes, medical content and acquisition process of the image.

[0112] In some embodiments, the above-mentioned determination unit 301 is further used to: pre-process the original medical image set to obtain qualified images that meet quality control conditions, and generate a medical image database based on the qualified images; the pre-processing includes: noise suppression and resolution standardization of the original images; and verification of the validity of the hospital identifier and acquisition time in the original images.

[0113] In some embodiments, the above-mentioned quality control conditions include at least one of the following: the clarity of the original image is greater than or equal to the preset clarity, the color reproduction of the original image is less than or equal to the preset color reproduction, the contrast of the original image is greater than or equal to the preset contrast, and the integrity of the original image is greater than or equal to the preset integrity.

[0114] In the medical image screening device provided in the embodiment of the present application, manual detection may result in errors, resulting in low detection accuracy. Therefore, the present application first sets medical publicity theme requirements to screen the images in the medical image database for theme matching, and then sets medical compliance rules to screen the images that meet the medical publicity theme requirements for rule matching, so as to perform double screening on each image, thereby avoiding possible errors in manual detection and improving detection accuracy; and the second image obtained by the double screening is manually reviewed to eliminate images that may have publicity risks in the second image, thereby further improving the detection accuracy of the image.

[0115] Regarding the apparatus in the above embodiment, the specific manner in which each module performs operations has been described in detail in the embodiment of the method, and will not be elaborated here.

[0116] Figure 4 This is a structural diagram of an electronic device provided in an embodiment of the present application. Figure 4 As shown, the electronic device 400 includes but is not limited to: a processor 401 and a memory 402 .

[0117] The memory 402 is used to store executable instructions of the processor 401. It is understandable that the processor 401 is configured to execute instructions to implement the medical image screening method in the above embodiment.

[0118] It should be noted that those skilled in the art can understand that Figure 4 The electronic device structure shown in the figure does not limit the electronic device, and the electronic device may include Figure 4 More or fewer components may be shown, or certain components may be combined, or the components may be arranged differently.

[0119] The processor 401 is the control center of the electronic device. It uses various interfaces and lines to connect the various parts of the entire electronic device. By running or executing software programs and / or modules stored in the memory 402 and calling data stored in the memory 402, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole. The processor 401 may include one or more processing units. Optionally, the processor 401 may integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, clinical reviewer interface and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 401.

[0120] Memory 402 can be used to store software programs and various data. Memory 402 may primarily include a program storage area and a data storage area. The program storage area may store an operating system and application programs required by at least one functional module (e.g., a determination unit, a processing unit, etc.). Furthermore, memory 402 may include high-speed random access memory and non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage device.

[0121] In an exemplary embodiment, a computer-readable storage medium including instructions is also provided, such as a memory 402 including instructions. The above instructions can be executed by the processor 401 of the electronic device 400 to implement the medical image screening method in the above embodiment.

[0122] In actual implementation, Figure 3 The steps performed by the determination unit 301 and the output unit 302 in Figure 4The processor 401 in the embodiment calls the computer program stored in the memory 402. The specific execution process can be referred to the description of the method part in the above embodiment, which will not be repeated here.

[0123] Optionally, the computer-readable storage medium may be a non-temporary computer-readable storage medium, for example, the non-temporary computer-readable storage medium may be a read-only memory (ROM), a random access memory (RAM), a CD-ROM, a magnetic tape, a floppy disk, an optical data storage device, etc.

[0124] In an exemplary embodiment, the present application also provides a computer program product comprising one or more instructions, which can be executed by the processor 401 of the electronic device to complete the medical image screening method in the above embodiment.

[0125] It should be noted that when the instructions in the above-mentioned computer-readable storage medium or one or more instructions in the computer program product are executed by the processor of the electronic device, the various processes of the above-mentioned method embodiment are implemented and the same technical effect as the above-mentioned method can be achieved. To avoid repetition, they will not be repeated here.

[0126] Through the description of the above implementation methods, technical personnel in the relevant field can clearly understand that for the convenience and simplicity of description, only the division of the above-mentioned functional modules is used as an example. In actual applications, the above-mentioned functions can be distributed and completed by different functional modules as needed, that is, the internal structure of the device can be divided into different functional modules to complete the full classification or partial functions described above.

[0127] In the several embodiments provided in this application, it should be understood that the disclosed devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of modules or units is only a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another device, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0128] The units described as separate components may or may not be physically separate, and the components shown as units may be one physical unit or multiple physical units, that is, they may be located in one place or distributed in multiple places. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0129] In addition, the functional units in the various embodiments of the present application may be integrated into a single processing unit, or each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0130] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a readable storage medium. Based on this understanding, the technical solution of the embodiment of the present application is essentially or the part that contributes to the prior art or the full classification part or part of the technical solution can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions to enable a device (which can be a single-chip microcomputer, chip, etc.) or a processor (processor) to execute the full classification part or part of the steps of the various embodiments of the present application. The aforementioned storage medium includes: various media that can store program codes, such as USB flash drives, mobile hard drives, ROM, RAM, magnetic disks or optical disks.

[0131] The above are only specific embodiments of the present application, but the scope of protection of this application is not limited thereto. Any changes or substitutions that can be easily conceived by a person skilled in the art within the technical scope disclosed in this application should be included in the scope of protection of this application. Therefore, the scope of protection of this application should be based on the scope of protection of the claims.

Claims

1. A medical image screening method, characterized in that: The method comprises: Determining a first image that meets the medical publicity theme requirements from a medical image database, where a degree of matching between the first image and the medical publicity theme requirements is greater than or equal to a first matching degree; determining a second image satisfying a medical compliance rule from the first image, wherein a degree of matching between the second image and the medical compliance rule is greater than or equal to a second matching degree; When a confirmation instruction for the second image input by the clinical reviewer is received, the second image is output to the medical publicity and distribution system.

2. The method according to claim 1, characterized in that The step of determining a first image that meets the medical publicity theme requirements from a medical image database includes: Identifying the number of medical features and clinical scenarios of each image in the medical imaging database, wherein the medical features include at least one of pathological markers, anatomical structure markers, and diagnostic and treatment equipment features; Analyze the threshold number of medical features and clinical scenario types corresponding to the requirements of the medical publicity theme; An image in which the number of medical features is greater than or equal to the medical feature number threshold and the clinical scene belongs to the clinical scene type is determined as the first image.

3. The method according to claim 1 or 2, characterized in that The determining, from the first image, a second image that satisfies a medical compliance rule includes: identifying the medical content and acquisition process of each of the first images; Analyze the promotional content rules and collection process specifications corresponding to the medical compliance rules; An image whose medical content complies with the promotion content rules and whose acquisition process complies with the acquisition process specifications is determined as the second image.

4. The method according to claim 1, wherein The step of outputting the second image to the medical publicity and distribution system upon receiving a confirmation instruction input by a clinical reviewer for the second image includes: displaying the number of medical features, clinical scenario, medical content, and acquisition process of each image in the second image; In response to a confirmation instruction input by the clinical reviewer, the second image is output to a medical publicity and distribution system.

5. The method according to claim 1 or 4, characterized in that The method further comprises: After receiving the confirmation instruction for the second image input by the clinical reviewer, a medical label corresponding to each image in the second image is generated, where the medical label is used to indicate the number of medical features, clinical scene, medical content and acquisition process of the image.

6. The method according to claim 1, characterized in that The method further comprises: Preprocessing the original medical images to obtain qualified images that meet quality control conditions, and generating the medical image database based on the qualified images; The pretreatment includes: Perform noise suppression and resolution normalization on the original image; The validity of the hospital identifier and acquisition time in the original image is verified.

7. The method according to claim 6, characterized in that The quality control conditions include at least one of the following: The clarity of the original image is greater than or equal to a preset clarity; The color restoration degree of the original image is less than or equal to the preset color restoration degree; The contrast of the original image is greater than or equal to a preset contrast; The integrity of the original image is greater than or equal to a preset integrity.

8. A medical image screening device, characterized in that: The device comprises: a determining unit, configured to determine, from a medical image database, a first image that meets the requirements of a medical publicity theme, wherein a degree of matching between the first image and the requirements of the medical publicity theme is greater than or equal to a first degree of matching; The determining unit is further configured to determine, from the first image, a second image that satisfies the medical compliance rule, wherein a degree of matching between the second image and the medical compliance rule is greater than or equal to a second matching degree; The output unit is configured to output the second image to the medical publicity and distribution system upon receiving a confirmation instruction for the second image input by a clinical reviewer.

9. An electronic device, characterized in that: include: processor; a memory for storing instructions executable by the processor; The processor is configured to execute the instructions to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium storing instructions, characterized in that: When a computer executes the instruction, the computer performs the method according to any one of claims 1 to 7.

Images