Medical image processing method and program product

Abstract

This invention discloses a medical image processing method and program product. The method includes: acquiring a target medical image of a target site; determining target image features of the target medical image, wherein the target medical image includes a lesion region, and the target image features include quantitative and semantic features of the lesion region; determining a target data table corresponding to the target image features, wherein the target data table stores multiple image association data corresponding to multiple tissue regions in the target site, and the multiple image association data are stored correspondingly, wherein the image association data includes at least a reference disease type and a reference image feature; determining disease description information corresponding to the target medical image based on the target image features and the target data table; generating clinical suggestion information corresponding to the target medical image based on the disease description information, wherein the clinical suggestion information includes at least examination suggestion information for the target site to improve the accuracy of medical image detection.

Description

Technical Field

[0001] This invention relates to the field of medical image processing and computer-aided diagnosis technology, and in particular to a medical image processing method and program product. Background Technology

[0002] Medical imaging is an indispensable core support tool in clinical disease diagnosis, providing objective and accurate imaging evidence for early screening, type determination, disease assessment, and monitoring of treatment effectiveness.

[0003] In current medical imaging techniques, most imaging examinations rely on manual inspection and judgment by operators. Manual inspection is affected by various factors, including the operator's professional level, clinical experience, and subjective judgment, resulting in low efficiency, high labor intensity, and a high risk of missed or misdiagnosed lesions. This is particularly true for identifying small or occult lesions, where the accuracy of manual inspection is difficult to guarantee consistently, failing to meet the demands for efficient, accurate, and standardized imaging in clinical diagnosis and treatment. Therefore, a medical image processing method is urgently needed to improve the efficiency and accuracy of medical imaging examinations. Summary of the Invention

[0004] This invention provides a medical image processing method and program product to solve the problems of low detection efficiency and difficulty in ensuring stable accuracy in related technologies that rely on operators to manually inspect medical images.

[0005] According to one aspect of the present invention, a medical image processing method is provided, the method comprising: Acquire a target medical image of a target site, determine the target image features of the target medical image, wherein the target medical image includes a lesion region, and the image features include the quantitative features and semantic features of the lesion region; A target data table corresponding to the target image features is determined. The target data table stores multiple image association data corresponding to multiple tissue regions in the target site, and the multiple image association data are stored correspondingly. The image association data includes at least a reference disease type and a reference image feature. Based on the target image features and the target data table, disease description information corresponding to the target medical image is determined. Clinical recommendation information corresponding to the target medical image is generated based on the disease description information. The clinical recommendation information includes at least examination recommendations for the target site. According to another aspect of the present invention, a medical image processing apparatus is provided, the apparatus comprising: The target image feature acquisition module is used to acquire target medical images of target sites and determine the target image features of the target medical images. The target medical images include lesion areas, and the image features include quantitative features and semantic features of the lesion areas. The target data table determination module is used to determine the target data table corresponding to the target image features. The target data table stores multiple image association data corresponding to multiple tissue regions in the target site, and the multiple image association data are stored correspondingly. The image association data includes at least a reference disease type and a reference image feature. The image analysis module is used to determine disease description information corresponding to the target medical image based on the target image features and the target data table, and to generate clinical suggestion information corresponding to the target medical image based on the disease description information. The clinical suggestion information includes at least examination suggestion information for the target site.

[0006] According to another aspect of the present invention, an electronic device is provided, the electronic device comprising: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program that can be executed by the at least one processor, the computer program being executed by the at least one processor to enable the at least one processor to perform the medical image processing method according to any embodiment of the present invention.

[0007] According to another aspect of the present invention, a computer-readable storage medium is provided, the computer-readable storage medium storing computer instructions for causing a processor to execute and implement the medical image processing method according to any embodiment of the present invention.

[0008] According to another aspect of the present invention, embodiments of this disclosure also provide a computer program product, including a computer program that, when executed by a processor, implements the medical image processing method as described in any of the embodiments of this disclosure.

[0009] The technical solution of this invention first involves acquiring a target medical image of a target site and determining the target image features of that image. The target medical image includes a lesion region, and the target image features include quantitative and semantic features of the lesion region. The target image features enable a multi-dimensional characterization of the lesion region, providing structured input for subsequent image analysis. Next, a target data table corresponding to the target image features is determined. This target data table stores multiple image-related data corresponding to multiple tissue regions in the target site, and these multiple image-related data are stored correspondingly. The image-related data includes at least a reference disease type and reference image features. The target data is then determined. The table enables rapid retrieval and accurate matching of target image features with reference data, improving diagnostic reasoning efficiency and enhancing the reliability of diagnostic reasoning results. Finally, by determining the disease description information corresponding to the target medical image based on the target image features and the target data table, and generating clinical suggestion information corresponding to the target medical image based on the disease description information, the clinical suggestion information includes at least examination suggestions for the target site. Transforming the matching results into specific disease descriptions and generating personalized clinical suggestion information can assist operators in developing more scientific and standardized treatment plans, reducing the risk of missed or misdiagnosed diagnoses, enhancing the objectivity and consistency of disease diagnosis, and improving overall treatment quality and patient experience.

[0010] It should be understood that the description in this section is not intended to identify key or essential features of the embodiments of the present invention, nor is it intended to limit the scope of the invention. Other features of the invention will become readily apparent from the following description. Attached Figure Description

[0011] To more clearly illustrate the technical solutions in the embodiments of the present invention, the accompanying drawings used in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0012] Figure 1 This is a flowchart of a medical image processing method provided according to Embodiment 1 of the present invention; Figure 2 This is a flowchart of a medical image processing method provided in Embodiment 2 of the present invention; Figure 3 This is a schematic diagram of the structure of a medical image processing device according to Embodiment 3 of the present invention; Figure 4 This is a schematic diagram of the structure of an electronic device that implements the medical image processing method of the present invention. Detailed Implementation

[0013] To enable those skilled in the art to better understand the present invention, the technical solutions of the present invention will be clearly and completely described below with reference to the accompanying drawings of the embodiments of the present invention. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort should fall within the scope of protection of the present invention.

[0014] It should be noted that the terms "first," "second," "target," etc., used in the specification, claims, and accompanying drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that embodiments of the invention described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms "comprising" and "having," and any variations thereof, are intended to cover a non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0015] It should be noted that the terms "a" and "a plurality of" used in this disclosure are illustrative rather than restrictive, and those skilled in the art should understand that, unless otherwise expressly indicated in the context, they should be understood as "one or more".

[0016] The names of messages or information exchanged between multiple devices in the embodiments of this disclosure are for illustrative purposes only and are not intended to limit the scope of such messages or information.

[0017] It is understood that before using the technical solutions disclosed in the various embodiments of this disclosure, users should be informed of the types, scope of use, and usage scenarios of the personal information involved in this disclosure in an appropriate manner in accordance with relevant laws and regulations, and user authorization should be obtained.

[0018] For example, upon receiving a user's active request, a prompt message is sent to the user to explicitly inform them that the requested operation will require the acquisition and use of the user's personal information. This allows the user to independently choose whether to provide personal information to the software or hardware, such as the electronic device, application, server, or storage medium performing the operations of this disclosed technical solution, based on the prompt message.

[0019] As an optional but non-limiting implementation, in response to a user's active request, sending a prompt message to the user can be done via a pop-up window, where the prompt message can be presented in text format. Furthermore, the pop-up window can also include a selection control allowing the user to choose "agree" or "disagree" to provide personal information to the electronic device.

[0020] It is understood that the above notification and user authorization process are merely illustrative and do not constitute a limitation on the implementation of this disclosure. Other methods that comply with relevant laws and regulations may also be applied to the implementation of this disclosure.

[0021] It is understood that the data involved in this technical solution (including but not limited to the data itself, the acquisition or use of the data) shall comply with the requirements of relevant laws, regulations and related provisions.

[0022] Example 1 Figure 1 This is a flowchart of a medical image processing method provided in Embodiment 1 of the present invention. This embodiment is applicable to medical images. The method can be executed by a medical image processing device, which can be implemented in hardware and / or software, optionally through an electronic device, such as a mobile terminal, a PC, or a server. Figure 1 As shown, the method may specifically include: S110. Acquire a target medical image of the target site, determine the target image features of the target medical image, wherein the target medical image includes a lesion area, and the target image features include the quantitative features and semantic features of the lesion area.

[0023] In this embodiment of the invention, the target site can be understood as the site where disease detection and analysis are required. The target medical image can be a medical image acquired for disease analysis targeting the target site. The target medical image may include lesion areas requiring focused detection. A lesion area can be an area in the target medical image that differs from normal tissue areas and is suspected of having a lesion. Target image features can be features extracted from the target medical image that reflect image information and the state of the lesion. Target image features may include, but are not limited to, quantitative features and semantic features of the lesion area.

[0024] Optionally, images can be acquired for the lesion area of ​​the target site to accurately obtain the target medical image of the target site, and feature extraction can be performed on the target medical image to determine the target image features of the target medical image, ensuring that the extracted features can accurately correspond to the actual situation of the lesion.

[0025] Based on the above scheme, optionally, acquiring the target medical image includes: acquiring an initial medical image and determining the sharpness index of the initial medical image; in response to the sharpness index meeting preset conditions, preprocessing the initial medical image to obtain the target medical image, wherein the preprocessing includes at least one of format conversion processing, noise removal processing, artifact correction processing, and data standardization processing. Preprocessing the initial medical image effectively improves image quality, eliminates interfering factors, and ensures the accuracy of subsequent feature extraction and matching degree calculation.

[0026] The initial medical image can be the raw medical image directly exported from the imaging device without any processing. The sharpness index can be understood as a quantitative indicator used to measure the sharpness of the initial medical image.

[0027] Specifically, initial medical images can be acquired, their format analyzed, and their corresponding image format determined, such as Digital Imaging and Communications in Medicine (DICOM) or Neuroimaging Informatics Technology Initiative (NIFTI) formats. Simultaneously, key imaging parameters such as tube voltage and slice thickness of the imaging device are extracted to obtain basic image information. Next, the sharpness index of the initial medical images is calculated, for example, using the entropy method to measure image sharpness. If the sharpness index meets preset conditions, preprocessing operations can be performed on the initial medical images. If the sharpness index does not meet the standards, a message such as "Image quality is poor, re-image recommended" is displayed to the operator, or targeted enhancement processing is performed on the images. This is achieved by re-acquiring or optimizing image data to ensure the input quality of the initial medical images and prevent poor-quality images from interfering with diagnostic results. The preset conditions can be pre-defined standards used to determine whether the sharpness of the initial medical images meets the standards.

[0028] Optionally, the initial medical images can be preprocessed to optimize image quality and standardize image data format, providing high-quality, standardized target medical images for subsequent feature extraction and disease diagnosis. For example, the original format of the parsed initial medical images can be converted to a standard, universal format, effectively solving the data compatibility problem between different imaging devices and image formats, facilitating subsequent data reading and analysis. Furthermore, suitable noise removal algorithms can be applied to the initial medical images of different modalities. For instance, Computed Tomography (CT) images can use Adaptive Statistical Iterative Reconstruction (ASIR), Magnetic Resonance Imaging (MRI) images can use Non-Local Means (NLM), and X-ray images can use median filtering and wavelet denoising algorithms. This eliminates irrelevant interference signals in the images, reduces the negative impact of noise on feature extraction and disease discrimination, and significantly improves image clarity. Additionally, artifact correction can be performed on the initial medical images, such as using an Iterative Metal Artifact Suppression algorithm. Motion artifacts in CT medical images are corrected using Reduction (IMAR), and motion compensation algorithms based on phase correction are used to correct motion artifacts in MRI medical images. These methods correct false images in initial medical images caused by external factors such as imaging equipment failure and operational errors during the imaging process, preventing artifacts from being misidentified as lesions and affecting the accurate extraction of lesion features. Furthermore, initial medical images can be standardized, unifying the spatial resolution of images. For example, CT and MRI medical images are standardized to a spatial resolution of 1mm×1mm×1mm, and X-ray medical images are standardized to a spatial resolution of 0.1mm×0.1mm. Simultaneously, grayscale values ​​are normalized, such as mapping the grayscale values ​​of CT medical images to [-1024, 400] Hounsfield Units (HU), and MRI medical images to [0, 255] grayscale levels, making image data from different sources and of different specifications comparable and facilitating subsequent feature extraction and matching analysis.

[0029] Optionally, the target image features may include the quantitative features of the lesion region. Optionally, quantitative features can be understood as lesion region features that can be quantitatively described, providing accurate quantitative basis for disease diagnosis. The quantitative features may include, but are not limited to, at least one of first morphological features, signal features, and location features. The first morphological features may include the geometric parameters of the lesion region, used to quantitatively describe the state, size, structure, and other parameters of the lesion. Specifically, the geometric parameters of the lesion region may include the three-dimensional diameter (length × width × height), volume, surface area, sphericity, etc., of the lesion. The signal features can be used to quantitatively describe the signals generated by the lesion region during imaging. The signal features may include imaging signal features and tissue signal features. Imaging signal features may refer to the quantitative features corresponding to the signals generated by the lesion region in the imaging device, such as the average computed tomography value, the standard deviation of the computed tomography value, the magnetic resonance imaging signal intensity, the T1 / T2 signal intensity ratio of magnetic resonance imaging, etc. Tissue signal features may refer to the quantitative features of the signal characteristics of the tissue to which the lesion region belongs, used to distinguish the differences between lesion tissue and normal tissue, such as the apparent diffusion coefficient. Coefficient (ADC) value, etc.; the location features can be used to accurately locate the specific spatial location of the lesion area in the target site. The location features include the location data of at least one feature point in the lesion area. The feature point can be a representative and locatable point in the lesion area, such as the center point or edge feature point in the lesion. The location data can be quantitative data used to describe the specific location of the feature point. The location features can include the coordinates of the lesion center, the relative position of the lesion and adjacent organs, etc.

[0030] Optionally, the target image features may further include semantic features of the lesion region. Optionally, semantic features may be non-quantitative features that can reflect the essential attributes and functional state of the lesion, and can provide a qualitative description of the lesion. The semantic features include at least one of second morphological features and functional features. The second morphological features can be understood as a qualitative description of the lesion morphology. The second morphological features may include the type information of the visually visible attributes of the lesion area. The type information of the visually visible attributes of the lesion area can be understood as the type of visual features of the lesion that can be determined by visual observation or image interpretation. The type information of the visually visible attributes may include, but is not limited to, the edge type of the lesion area (lobed, spiculated, smooth and regular, etc.), the calcification distribution of the lesion area (eccentric calcification, diffuse calcification, no calcification, etc.), and the proportion of solid components (Consolidation Tumor Ratio, CTR) of the lesion area. The functional features may include features that reflect the physiological functional state of the lesion. The physiological functional state of the lesion can be understood as the physiological activity state of the lesion area. The functional features may include, but are not limited to, the type of computed tomography enhancement curve of the lesion area (rapid rise and fall, plateau, slow rise, etc.), and the degree of magnetic resonance imaging enhancement of the lesion area (mild enhancement, moderate enhancement, severe enhancement, etc.), which can be used to assist in judging the nature and development stage of the lesion.

[0031] Based on the acquisition of target image features, the extreme value normalization (min-max) algorithm can be used to map the extracted target image features to the quantization threshold range of the target data table, eliminate the interference caused by the difference in dimensionality and numerical value between different features to subsequent analysis, and generate a standardized target image feature vector with dimension N×1, where N is the total number of features included in the target image features.

[0032] Optionally, to further ensure feature quality and avoid invalid or abnormal features interfering with diagnostic results, the extracted target image features can be validated. If a target image feature exceeds the medically reasonable range, such as a CT value greater than 1000 HU after excluding metal artifacts, the feature is deemed invalid, and the operation of re-acquiring and re-extracting features from the target medical image is triggered, providing reliable support for subsequent matching degree calculation and disease screening.

[0033] S120. Determine a target data table corresponding to the target image features. The target data table stores multiple image association data corresponding to multiple tissue regions in the target site, and the multiple image association data are stored correspondingly. The image association data includes at least a reference disease type and a reference image feature.

[0034] The target data table can be understood as a pre-established set of standardized image-related data corresponding to the target site. The target data table can store various image-related data corresponding to multiple tissue regions of the target site, with each type of image-related data corresponding to multiple tissue regions, providing a reference basis for disease diagnosis. A tissue region can be understood as an image region corresponding to tissues with different physiological functions and anatomical structures within the target site. Image-related data can be various types of data associated with the target site's tissue regions, disease types, and image features. The image-related data must include at least reference disease types and reference image features. Reference disease types can be understood as various disease types corresponding to the target site's tissue regions. Reference image features can be typical image features corresponding to multiple reference disease types, used to accurately determine the disease type to which the target image features belong.

[0035] Optionally, a hierarchical and scalable structured target data table can be pre-established, which can be expanded and updated according to clinical needs and operator feedback to adapt to the diagnostic needs of different clinical scenarios and different disease types. When performing image detection, the corresponding target data table can be accurately matched and called according to the type of the target site to ensure the relevance and accuracy of image detection and improve the user experience of operators.

[0036] S130. Based on the target image features and the target data table, determine the disease description information corresponding to the target medical image, and generate clinical suggestion information corresponding to the target medical image based on the disease description information. The clinical suggestion information includes at least examination suggestion information for the target site.

[0037] The disease description information can be a detailed description of the disease corresponding to the target medical image, generated based on the matching results between the target image features and the target data table. Clinical recommendation information can be guiding suggestions for clinical diagnosis and treatment based on the disease description information. Clinical recommendation information includes at least examination recommendations for the target site. Examination recommendations can refer to further examination-related suggestions for the target site and its corresponding disease description information, such as, but not limited to, examination items, examination frequency, and examination methods, providing guidance for subsequent disease diagnosis and treatment.

[0038] Optionally, the target image features can be matched with image association data in the target data table to determine the disease description information corresponding to the target medical image, and then clinical suggestion information corresponding to the target medical image can be generated based on the disease description information.

[0039] To enhance the compatibility and scalability of the target data table and adapt to the expansion needs of different image modalities, the target data table supports storage and parsing in Extensible Markup Language (XML) format. The table structure can adopt a design of core fixed fields and extended fields, and flexible field expansion can be achieved through tag-based design. According to the needs of adding new image modalities, adding new disease types, etc., the corresponding fields can be quickly added without reconstructing the entire table structure, reducing the maintenance cost of the data table and improving the adaptability of the data table.

[0040] Specifically, to ensure the accuracy and timeliness of the target data table, closed-loop iterative optimization of the target data table can be performed. Sample medical images and their corresponding disease description information and clinical suggestion information are collected. The disease description information can be generated by matching the target image features with the existing target data table and is reviewed and confirmed by multiple operators to ensure accurate matching with the sample medical images. The target data table update process is triggered when any of the following diagnostic conditions are met: the similarity between the target image features of the newly added sample medical image and the reference disease type in the existing target data table is less than a preset similarity threshold, that is, the existing data table does not contain the disease information corresponding to this type of image feature and needs to be supplemented, and is confirmed by consensus diagnosis of multiple operators; the classification accuracy of a certain disease type is less than a preset classification accuracy threshold for a continuous preset time, that is, the reference data corresponding to this disease type has deviation and needs to be optimized; new reference image features for disease judgment are added, or the feature thresholds corresponding to existing reference image features are adjusted to adapt to changes in clinical diagnostic needs, etc., to achieve automatic updating of the target data table.

[0041] Optionally, based on newly added sample medical images and their corresponding disease description information and clinical recommendation information, a multivariate logistic regression analysis method can be used to optimize and adjust the feature quantification threshold and feature weight of the reference image features, and add or revise preset screening rules to ensure the scientific nature and pertinence of the preset screening rules. To verify the accuracy of the updated preset screening rules, data testing can be conducted using at least 50 validation sample medical images. The preset screening rules can only be updated when the test accuracy rate is greater than the preset test accuracy rate threshold, ensuring that the updated rules can effectively improve the accuracy of disease diagnosis.

[0042] To ensure the security and traceability of target data table updates, a new version number is generated and historical version data is retained with each update. Version rollback is supported, allowing for rapid rollback to a stable historical version if issues arise after the update, thus preventing impact on clinical diagnosis. Simultaneously, update logs are pushed to operators, clearly indicating the added or modified fields, rules, and basis for the modifications, providing a clear understanding of the update content. After the update, the updated target data table can be validated through multi-center clinical trials. For example, multiple hospitals of different levels can be selected, with each hospital providing more clinical data than a preset number of trials. The classification accuracy of the updated data table is verified, requiring a pre-set threshold improvement in classification accuracy compared to the previous version. If this threshold is not met, a version rollback is performed, providing more reliable support for disease diagnosis.

[0043] The technical solution of this invention first involves acquiring a target medical image of a target site and determining the target image features of that image. The target medical image includes a lesion region, and the target image features include quantitative and semantic features of the lesion region. The target image features enable a multi-dimensional characterization of the lesion region, providing structured input for subsequent image analysis. Next, a target data table corresponding to the target image features is determined. This target data table stores multiple image-related data corresponding to multiple tissue regions in the target site, and these multiple image-related data are stored correspondingly. The image-related data includes at least a reference disease type and reference image features. The target data is then determined. The table enables rapid retrieval and accurate matching of target image features with reference data, improving diagnostic reasoning efficiency and enhancing the reliability of diagnostic reasoning results. Finally, by determining the disease description information corresponding to the target medical image based on the target image features and the target data table, and generating clinical suggestion information corresponding to the target medical image based on the disease description information, the clinical suggestion information includes at least examination suggestions for the target site. Transforming the matching results into specific disease descriptions and generating personalized clinical suggestion information can assist operators in developing more scientific and standardized treatment plans, reducing the risk of missed or misdiagnosed diagnoses, enhancing the objectivity and consistency of disease diagnosis, and improving overall treatment quality and patient experience.

[0044] Example 2 Figure 2 This is a flowchart illustrating a medical image processing method according to Embodiment 2 of the present invention, further describing a specific implementation method for determining disease description information corresponding to a target medical image based on target image features and a target data table. Specific implementation methods can be found in the description of this embodiment. Technical features that are the same as or similar to those in the foregoing embodiments will not be repeated here. Figure 2 As shown, the method may specifically include: S210. Acquire a target medical image of the target site, determine the target image features of the target medical image, wherein the target medical image includes a lesion area, and the target image features include the quantitative features and semantic features of the lesion area.

[0045] S220. Determine a target data table corresponding to the target image features. The target data table stores multiple image association data corresponding to multiple tissue regions in the target site, and the multiple image association data are stored correspondingly. The image association data includes at least a reference disease type and a reference image feature.

[0046] S230. Based on the tissue region where the lesion area is located in the target site, determine a first disease type from multiple reference disease types in the target data table.

[0047] The first disease type can be selected based on the specific tissue region where the lesion is located in the target site, and can be one of several disease types related to that tissue region.

[0048] Optionally, the lesion area can be matched with multiple tissue regions in the target site in the target data table based on the tissue region it occupies within the target site. This determines the image association data corresponding to the tissue region, and then at least one primary disease type corresponding to that tissue region can be selected from multiple reference disease types in the target data table. Using tissue regions allows for preliminary screening of disease types, narrowing the scope of disease identification and improving the efficiency and specificity of subsequent disease type matching.

[0049] S240. Determine the target disease type from the first disease type based on the target image features and the reference image features corresponding to the first disease type.

[0050] The target disease type can be determined based on the characteristics of the target image and the characteristics of the reference image, and is the disease type corresponding to the target medical image.

[0051] Optionally, the target disease type can be determined from multiple first disease types by matching the target image features with the reference image features corresponding to each first disease type one by one, thereby achieving a preliminary determination of the disease type.

[0052] Based on the above scheme, optionally, to improve the accuracy and clinical applicability of the target disease type determination, the image association data further includes the clinical priority corresponding to the reference disease type; the step of determining the target disease type from the first disease types based on the target image features and the reference image features corresponding to the first disease type includes: determining the matching degree between the target image features and the first disease type based on the target image features and the reference image features corresponding to the first disease type; determining a second disease type from multiple first disease types based on the matching degree corresponding to multiple first disease types; and determining the target disease type from the second disease type based on the matching degree corresponding to the second disease type and the clinical priority.

[0053] Clinical priority can be a pre-defined clinical importance level corresponding to each reference disease type. Clinical priority can be used to prioritize and treat target disease types that require more attention when multiple disease types have similar matching degrees. Matching degree can be the degree of similarity between the target image features and the reference image features corresponding to the first disease type; a higher matching degree indicates a stronger correlation between the target image features and the first disease type. The second disease type can be a disease type with a relatively high matching degree selected from the first disease types based on the matching degrees corresponding to multiple first disease types.

[0054] Specifically, the target image features can be matched one by one with the reference image features corresponding to the first disease type. The feature similarity of each reference image feature is integrated to quantify the matching degree between the target image features and the first disease type. Then, the matching degrees corresponding to multiple first disease types are sorted or thresholded to determine the second disease type from the multiple first disease types. Finally, the matching degrees corresponding to multiple second disease types are weighted according to their clinical priority, and the target disease type is determined from the second disease types according to the weighted matching degree. For example, a disease matching degree threshold can be preset for screening, and the disease types with a weighted matching degree higher than the threshold can be selected as the target disease type. Alternatively, the top-ranked disease types can be determined as the target disease type based on the ranking results of the weighted matching degree.

[0055] Based on the above scheme, optionally, to further improve the accuracy of the matching degree calculation, the image association data also includes the feature weights corresponding to the reference image features under the first disease type; the step of determining the matching degree between the target image features and the reference image features corresponding to the first disease type includes: for each first disease type, determining the similarity between the target image features and each reference image feature of the first disease type, and determining the matching degree between the target image features and the first disease type based on the feature weights corresponding to the reference image features under the first disease type and the similarity.

[0056] The feature weights can be pre-defined importance coefficients for each reference image feature in the image association data under the first disease type. Different first disease types may include the same reference image features. The feature weights of the same reference image feature may be the same or different under different first disease types. The feature weights are determined according to their importance to the first disease type; the higher the feature weight, the greater the influence of the reference image feature on determining the disease type. Similarity can be the degree of similarity between the target image feature and each reference image feature corresponding to the first disease type.

[0057] Specifically, for each first disease type, the similarity between the target image features and each reference image feature of the first disease type can be calculated to obtain the similarity value corresponding to each reference image feature; then, the similarity of each reference image feature under the first disease type can be weighted and calculated to obtain the weighted similarity value; finally, the weighted similarity of each reference image feature corresponding to the first disease type can be integrated to obtain the matching degree between the target image features and the first disease type.

[0058] Based on the above scheme, optionally, considering that differences between different imaging devices may lead to deviations in image features, thereby affecting the accuracy of matching degree calculation, the image association data also includes imaging device adaptation parameters. The step of determining the second disease type from the multiple first disease types based on the matching degrees corresponding to the multiple first disease types includes: obtaining the target imaging device adaptation parameters corresponding to the target medical image from the imaging device adaptation parameters in the target data table based on the imaging device information of the target medical image; correcting the matching degrees corresponding to the multiple first disease types based on the target imaging device adaptation parameters; and determining the second disease type from the first disease types based on the preset matching degree threshold and the corrected matching degree.

[0059] The imaging device adaptation parameters can be parameter information stored in the image association data corresponding to different imaging devices. These parameters can be used to correct image feature deviations caused by differences in imaging devices, ensuring the accuracy of the matching degree calculation. The imaging device information can be relevant information about the imaging device used to acquire the target medical image, such as, but not limited to, device model, imaging parameters (e.g., tube voltage, slice thickness), and imaging method (e.g., computed tomography, magnetic resonance imaging lamp). The target imaging device adaptation parameters can be determined based on the imaging device information of the target medical image, specifying the adaptation parameters corresponding to that imaging device.

[0060] Specifically, based on the imaging equipment information of the target medical image, the target imaging equipment adaptation parameters corresponding to the target medical image can be obtained from the imaging equipment adaptation parameters in the target data table; then, the matching degree corresponding to multiple first disease types can be specifically corrected according to the target imaging equipment adaptation parameters to eliminate the influence of imaging equipment differences on the matching degree; and the corrected matching degree of multiple first disease types can be screened according to the preset matching degree threshold to determine the second disease type.

[0061] Based on the above scheme, optionally, in order to further improve the accuracy of the target disease type, the image association data also includes a preset filtering rule, which is used to indicate the conflict information between the reference disease type and the reference image features; the step of determining the target disease type from the first disease type according to the target image features and the reference image features corresponding to the first disease type includes: removing the first disease type that conflicts with the target image features from the first disease type according to the preset filtering rule to obtain the target disease type.

[0062] The preset screening rules can be pre-defined rules used to indicate the conflict relationship between reference disease types and reference image features. Conflict information can be understood as a contradictory relationship between the target image features and the reference image features corresponding to a certain first disease type. That is, the existence of the target image feature does not match the typical reference image features of the first disease type, or the feature value of the target image feature exceeds the feature quantization threshold range of the reference image features corresponding to the first disease type. Based on this, the disease type can be excluded to avoid logically contradictory detection results.

[0063] Specifically, for each first disease type, a preset screening rule can be used to check for conflicts between the target image features and the reference image features corresponding to the first disease type. If a conflict is found between the target image features and the first disease type, for example, if the first disease type is a malignant nodule and the target image feature is diffuse calcification, and the preset screening rule clearly states that "diffuse calcification can exclude malignant nodules", then the malignant nodule is removed from the first disease type. The first disease type that does not conflict with the target image features after screening is determined, and the target disease type is obtained.

[0064] Furthermore, for each second disease type, second disease types that conflict with the target image features can be removed from the second disease types according to preset screening rules to obtain the target disease type, thereby further improving the accuracy and reliability of the target disease type determination.

[0065] S250. Obtain matching basis information between the target image features and the target disease type, generate disease description information based on the target disease type and the matching basis information, and generate clinical suggestion information corresponding to the target medical image based on the disease description information. The clinical suggestion information includes at least examination suggestion information for the target site.

[0066] The matching basis information can be understood as the basis for explaining the relationship between the target image features and the target disease type. For example, the matching basis information may include, but is not limited to, the similarity between the target image features and the reference image features of the disease, the feature matching content, the feature weight, etc., which are used to reflect the rationality of the disease type judgment.

[0067] Based on the obtained target disease type, matching information between target image features and target disease type can be acquired. Disease description information is then generated based on the target disease type and matching information. This description information may specifically include target image features with high matching degrees during the matching process and their corresponding feature weight percentages, such as a 90% weight for lobulated lesion edges and a 92% similarity to the reference image features of the target disease type. It also includes detailed conflict elimination processes, such as excluding benign nodules: because the solid component proportion CTR=0.6>0.5, which does not meet the feature threshold requirements for benign nodules, this disease type is excluded. Furthermore, based on the disease description information and actual needs, clinical recommendation information corresponding to the target medical image is generated. This clinical recommendation information includes at least examination recommendations for the target site; for example, for level 1 diseases, further pathological examination within 48 hours can be recommended, providing diagnostic and treatment assistance to operators and improving disease diagnosis and treatment efficiency.

[0068] The technical solution of this invention firstly determines a first disease type from multiple reference disease types in a target data table based on the tissue region where the lesion area is located in the target site. This preliminary and accurate screening of disease types is achieved based on the specificity of the tissue region, narrowing the screening range, avoiding interference from irrelevant disease types, reducing the complexity of subsequent disease type matching, laying the foundation for accurate localization of the target disease type, and improving the overall efficiency and specificity of disease diagnosis. Next, the target disease type is determined from the first disease type based on the target image features and the reference image features corresponding to the first disease type. Further screening is then performed from the first disease type based on the image features. The target disease type is identified to ensure the scientific rigor and accuracy of the disease type determination. This effectively addresses the potential for disease type confusion when screening solely based on tissue region, enabling precise focus on the disease type and improving the reliability and standardization of the diagnosis results. Finally, by acquiring the matching criteria information between the target image features and the target disease type, disease description information is generated based on the target disease type and the matching criteria information. This clarifies the core basis for disease judgment, making the disease description information traceable and facilitating operators to verify the rationality of the judgment logic. The disease description generated based on the matching criteria and the target disease type accurately reflects the correlation between lesions and the disease, enhancing the objectivity, completeness, and clinical interpretation value of the disease description.

[0069] Example 3 Figure 3 This is a schematic diagram of a medical image processing apparatus provided in Embodiment 3 of the present invention. This apparatus is used to execute the medical image processing method provided in any of the above embodiments. This apparatus and the medical image processing methods of the above embodiments belong to the same inventive concept. Details not described in detail in the embodiments of the medical image processing apparatus can be found in the embodiments of the above medical image processing methods. Figure 3 As shown, the device includes: a target image feature acquisition module 310, a target data table determination module 320, and an image analysis module 330.

[0070] The system includes a target image feature acquisition module 310, which acquires a target medical image of a target site and determines the target image features of the target medical image. The target medical image includes a lesion area, and the target image features include quantitative and semantic features of the lesion area. A target data table determination module 320 determines a target data table corresponding to the target image features. The target data table stores multiple image-related data corresponding to multiple tissue regions in the target site, and these multiple image-related data are stored correspondingly. The image-related data includes at least a reference disease type and reference image features. An image analysis module 330 determines disease description information corresponding to the target medical image based on the target image features and the target data table, and generates clinical suggestion information corresponding to the target medical image based on the disease description information. The clinical suggestion information includes at least examination suggestions for the target site. The technical solution of this invention firstly involves acquiring a target medical image of a target site through a target image feature acquisition module 310, and determining the target image features of the target medical image. The target medical image includes a lesion region, and the target image features include quantitative and semantic features of the lesion region. The target image features enable multi-dimensional characterization of the lesion region, providing structured input for subsequent image analysis. Next, a target data table determination module 320 determines a target data table corresponding to the target image features. The target data table stores multiple image-related data corresponding to multiple tissue regions in the target site, and these multiple image-related data are stored correspondingly. The image-related data at least includes a reference disease type and a reference image feature. The system identifies target image features and a target data table, enabling rapid retrieval and accurate matching between these features and reference data. This improves diagnostic reasoning efficiency and enhances the reliability of the results. Finally, the image analysis module 330 determines the disease description information corresponding to the target medical image based on the target image features and the target data table. Based on this disease description information, it generates clinical recommendation information corresponding to the target medical image, including at least examination recommendations for the target site. Transforming the matching results into specific disease descriptions and generating personalized clinical recommendation information assists operators in developing more scientific and standardized treatment plans, reducing the risk of missed or misdiagnosed diagnoses, enhancing the objectivity and consistency of disease diagnosis, and improving overall treatment quality and patient experience.

[0071] Based on the above scheme, optionally, the image analysis module 330 includes a first disease type determination submodule, a target disease type determination submodule, and a disease description information generation submodule. The first disease type determination submodule is used to determine a first disease type from multiple reference disease types in the target data table based on the tissue region where the lesion area is located in the target site. The target disease type determination submodule is used to determine a target disease type from the first disease type based on the target image features and the reference image features corresponding to the first disease type. The disease description information generation submodule is used to obtain matching information between the target image features and the target disease type, and generate disease description information based on the target disease type and the matching information.

[0072] Based on the above scheme, optionally, the image association data further includes the clinical priority corresponding to the reference disease type; the target disease type determination submodule includes a matching degree determination unit, a second disease type determination unit, and a target disease type determination unit. The matching degree determination unit is used to determine the matching degree between the target image features and the first disease type based on the target image features and the reference image features corresponding to the first disease type; the second disease type determination unit is used to determine a second disease type from multiple first disease types based on the matching degrees corresponding to multiple first disease types; and the target disease type determination unit is used to determine the target disease type from the second disease type based on the matching degree corresponding to the second disease type and the clinical priority.

[0073] Optionally, based on the above scheme, the image association data further includes the feature weights corresponding to the reference image features under the first disease type; the matching degree determination unit includes a matching degree determination subunit. The matching degree determination subunit is used to determine, for each of the first disease types, the similarity between the target image feature and each of the reference image features of the first disease type, and to determine the matching degree between the target image feature and the first disease type based on the feature weights corresponding to the reference image features under the first disease type and the similarity.

[0074] Optionally, based on the above scheme, the image association data further includes imaging device adaptation parameters, and the second disease type determination unit includes a device adaptation parameter determination subunit and a second disease type determination subunit. The device adaptation parameter determination subunit is used to obtain target imaging device adaptation parameters corresponding to the target medical image from the imaging device adaptation parameters in the target data table based on the imaging device information of the target medical image; the second disease type determination subunit is used to correct the matching degree corresponding to multiple first disease types based on the target imaging device adaptation parameters, and determine the second disease type from the first disease types based on a preset matching degree threshold and the corrected matching degree.

[0075] Optionally, based on the above scheme, the image association data further includes preset filtering rules, which are used to indicate conflict information between the reference disease type and the reference image features; the target disease type determination submodule includes a target disease type determination unit. The target disease type determination unit is used to remove first disease types that conflict with the target image features from the first disease types according to the preset filtering rules, thereby obtaining the target disease type.

[0076] Based on the above scheme, optionally, the target image feature acquisition module 310 includes a sharpness index determination submodule and a target medical image determination submodule. The sharpness index determination submodule is used to acquire an initial medical image and determine the sharpness index of the initial medical image; the target medical image determination submodule is used to preprocess the initial medical image in response to the sharpness index meeting preset conditions to obtain a target medical image. The preprocessing includes at least one of format conversion processing, noise removal processing, artifact correction processing, and data standardization processing.

[0077] Based on the above scheme, optionally, the quantification features include at least one of a first morphological feature, a signal feature, and a location feature, wherein the first morphological feature includes the geometric parameters of the lesion region; the signal feature includes imaging signal features and tissue signal features; and the location feature includes the location data of at least one feature point in the lesion region.

[0078] Based on the above scheme, optionally, the semantic features include at least one of a second morphological feature and a functional feature, wherein the second morphological feature includes type information of the visually visible attributes of the lesion region, and the functional feature includes features for reflecting the physiological functional state of the lesion.

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

[0080] Example 4 Figure 4 A schematic diagram of an electronic device 10, which can be used to implement embodiments of the present invention, is shown. The electronic device is intended to represent various forms of digital computers, such as laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The electronic device can also represent various forms of mobile devices, such as personal digital processors, cellular phones, smartphones, wearable devices (e.g., helmets, glasses, watches, etc.), and other similar computing devices. The components shown herein, their connections and relationships, and their functions are merely illustrative and are not intended to limit the implementation of the invention described and / or claimed herein.

[0081] like Figure 4 As shown, the electronic device 10 includes at least one processor 11 and a memory, such as a read-only memory (ROM) 12 or a random access memory (RAM) 13, communicatively connected to the at least one processor 11. The memory stores computer programs executable by the at least one processor. The processor 11 can perform various appropriate actions and processes based on the computer program stored in the ROM 12 or loaded from storage unit 18 into the RAM 13. The RAM 13 can also store various programs and data required for the operation of the electronic device 10. The processor 11, ROM 12, and RAM 13 are interconnected via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0082] Multiple components in electronic device 10 are connected to I / O interface 15, including: input unit 16, such as keyboard, mouse, etc.; output unit 17, such as various types of displays, speakers, etc.; storage unit 18, such as disk, optical disk, etc.; and communication unit 19, such as network card, modem, wireless transceiver, etc. Communication unit 19 allows electronic device 10 to exchange information / data with other devices through computer networks such as the Internet and / or various telecommunications networks.

[0083] Processor 11 can be a variety of general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of processor 11 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various special-purpose artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any suitable processor, controller, microcontroller, etc. Processor 11 performs the various methods and processes described above, such as medical image processing methods.

[0084] In some embodiments, the medical image processing method may be implemented as a computer program tangibly contained in a computer-readable storage medium, such as storage unit 18. In some embodiments, part or all of the computer program may be loaded and / or mounted on electronic device 10 via ROM 12 and / or communication unit 19. When the computer program is loaded into RAM 13 and executed by processor 11, one or more steps of the medical image processing method described above may be performed. Alternatively, in other embodiments, processor 11 may be configured to perform the medical image processing method by any other suitable means (e.g., by means of firmware).

[0085] Various embodiments of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field-programmable gate arrays (FPGAs), application-specific integrated circuits (ASICs), application-specific standard products (ASSPs), systems-on-a-chip (SoCs), payload-programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments may include implementations in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which may be a dedicated or general-purpose programmable processor, capable of receiving data and instructions from a storage system, at least one input device, and at least one output device, and transmitting data and instructions to the storage system, the at least one input device, and the at least one output device.

[0086] Computer programs used to implement the methods of the present invention may be written in any combination of one or more programming languages. These computer programs may be provided to a processor of a general-purpose computer, a special-purpose computer, or other programmable data processing device, such that when executed by the processor, the computer programs cause the functions / operations specified in the flowcharts and / or block diagrams to be performed. The computer programs may be executed entirely on a machine, partially on a machine, or as a standalone software package, partially on a machine and partially on a remote machine, or entirely on a remote machine or server.

[0087] In the context of this invention, a computer-readable storage medium can be a tangible medium that may contain or store a computer program for use by or in conjunction with an instruction execution system, apparatus, or device. A computer-readable storage medium may include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination thereof. Alternatively, a computer-readable storage medium may be a machine-readable signal medium. More specific examples of machine-readable storage media include electrical connections based on one or more wires, portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), optical fibers, portable compact disk read-only memory (CD-ROM), optical storage devices, magnetic storage devices, or any suitable combination thereof.

[0088] To provide interaction with a user, the systems and techniques described herein can be implemented on an electronic device having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user provides input to the electronic device. Other types of devices can also be used to provide interaction with the user; for example, feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including sound input, voice input, or tactile input).

[0089] The systems and technologies described herein can be implemented in computing systems that include backend components (e.g., as data servers), or middleware components (e.g., application servers), or frontend components (e.g., user computers with graphical user interfaces or web browsers through which users can interact with implementations of the systems and technologies described herein), or any combination of such backend, middleware, or frontend components. The components of the system can be interconnected via digital data communication of any form or medium (e.g., communication networks). Examples of communication networks include local area networks (LANs), wide area networks (WANs), blockchain networks, and the Internet.

[0090] A computing system can include clients and servers. Clients and servers are generally located far apart and typically interact through communication networks. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or cloud host, which is a hosting product within the cloud computing service system to address the shortcomings of traditional physical hosts and VPS services, such as high management difficulty and weak business scalability.

[0091] In particular, according to embodiments of the present invention, the processes described above with reference to the flowcharts can be implemented as computer software programs. For example, embodiments of the present invention include a computer program product comprising a computer program carried on a non-transitory computer-readable medium, the computer program containing program code for performing the methods shown in the flowcharts. In such embodiments, the computer program can be downloaded and installed from a network via communication unit 19, or installed from storage unit 18, or installed from ROM 12. When the computer program is executed by processor 11, it performs the functions defined in the methods of the embodiments of the present invention.

[0092] It should be understood that the various forms of processes shown above can be used, with steps reordered, added, or deleted. For example, the steps described in this invention can be executed in parallel, sequentially, or in different orders, as long as the desired result of the technical solution of this invention can be achieved, and this is not limited herein.

[0093] The specific embodiments described above do not constitute a limitation on the scope of protection of this invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of this invention should be included within the scope of protection of this invention.

Claims

1. A medical image processing method, characterized in that, include: Acquire a target medical image of a target site, determine the target image features of the target medical image, wherein the target medical image includes a lesion region, and the image features include the quantitative features and semantic features of the lesion region; A target data table corresponding to the target image features is determined. The target data table stores multiple image association data corresponding to multiple tissue regions in the target site, and the multiple image association data are stored correspondingly. The image association data includes at least a reference disease type and a reference image feature. Based on the target image features and the target data table, disease description information corresponding to the target medical image is determined, and clinical suggestion information corresponding to the target medical image is generated based on the disease description information. The clinical suggestion information includes at least examination suggestion information for the target site.

2. The medical image processing method according to claim 1, characterized in that, The step of determining the disease description information corresponding to the target medical image based on the target image features and the target data table includes: Based on the tissue region where the lesion area is located in the target site, a first disease type is determined from multiple reference disease types in the target data table; Based on the target image features and the reference image features corresponding to the first disease type, the target disease type is determined from the first disease type; Obtain matching information between the target image features and the target disease type, and generate disease description information based on the target disease type and the matching information.

3. The medical image processing method according to claim 2, characterized in that, The image association data also includes the clinical priority corresponding to the reference disease type; the step of determining the target disease type from the first disease type based on the target image features and the reference image features corresponding to the first disease type includes: The matching degree between the target image features and the first disease type is determined based on the target image features and the reference image features corresponding to the first disease type. Based on the matching degree corresponding to the multiple first disease types, a second disease type is determined from the multiple first disease types; The target disease type is determined from the second disease type based on the matching degree and the clinical priority corresponding to the second disease type.

4. The medical image processing method according to claim 3, characterized in that, The image association data further includes the feature weights corresponding to the reference image features under the first disease type; determining the matching degree between the target image features and the first disease type based on the target image features and the reference image features corresponding to the first disease type includes: For each of the first disease types, the similarity between the target image feature and each of the reference image features of the first disease type is determined, and the matching degree between the target image feature and the first disease type is determined based on the feature weight corresponding to the reference image feature under the first disease type and the similarity.

5. The medical image processing method according to claim 3, characterized in that, The image association data also includes imaging device adaptation parameters. The step of determining a second disease type from multiple first disease types based on the matching degree corresponding to multiple first disease types includes: Based on the imaging device information of the target medical image, obtain the target imaging device adaptation parameters corresponding to the target medical image from the imaging device adaptation parameters in the target data table; The matching degree corresponding to various first disease types is corrected according to the target imaging device adaptation parameters, and a second disease type is determined from the first disease types according to the preset matching degree threshold and the corrected matching degree.

6. The medical image processing method according to claim 2, characterized in that, The image association data further includes preset filtering rules, which are used to indicate conflict information between the reference disease type and the reference image features; determining the target disease type from the first disease type based on the target image features and the reference image features corresponding to the first disease type includes: According to preset screening rules, the first disease type that conflicts with the target image features is removed from the first disease type to obtain the target disease type.

7. The medical image processing method according to claim 1, characterized in that, The acquisition of the target medical image includes: Acquire initial medical images and determine the resolution index of the initial medical images; In response to the resolution index meeting preset conditions, the initial medical image is preprocessed to obtain the target medical image. The preprocessing includes at least one of format conversion processing, noise removal processing, artifact correction processing, and data standardization processing.

8. The medical image processing method according to claim 1, characterized in that, The quantification features include at least one of a first morphological feature, a signal feature, and a location feature, wherein the first morphological feature includes geometric parameters of the lesion region; the signal feature includes imaging signal features and tissue signal features; and the location feature includes location data of at least one feature point in the lesion region.

9. The medical image processing method according to claim 1, characterized in that, The semantic features include at least one of a second morphological feature and a functional feature, wherein the second morphological feature includes type information of the visually visible attributes of the lesion region, and the functional feature includes features that reflect the physiological functional state of the lesion.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the medical image processing method as described in any one of claims 1-9.

Images