Focus auxiliary analysis method, device and equipment and computer readable storage medium

Abstract

The invention discloses a focus auxiliary analysis method, device and equipment and a computer readable storage medium, and the method comprises the steps: obtaining a plurality of stages of medical images collected in a target examination period; focus detection is carried out on the multi-stage medical images, and focus information of a target focus in a target examination period is determined; determining analysis information of the target focus according to the focus information of the target focus; determining a target medical image according to the analysis information and the multiple medical images in the target examination period; acquiring a reference medical image corresponding to the target medical image in a reference examination period; and outputting lesion analysis information of the target lesion according to the analysis information corresponding to the multiple stages of target medical images and the analysis information corresponding to the corresponding reference medical images. The method can effectively improve the lesion auxiliary analysis efficiency.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a lesion-assisted analysis method, device, equipment and computer-readable storage medium. Background Art

[0002] With the development of AI imaging technology, image scanning has become a common auxiliary diagnosis and treatment method in modern medical diagnosis and treatment. Medical imaging can provide doctors with more and more intuitive information about the human body. It speeds up the doctor's diagnosis of the patient's condition. At present, for postoperative recovery of some diseases, treatment of chronic diseases, or observation period of malignant diseases, long-term follow-up of patients is required to ensure that doctors can understand the development of the patient's condition and make new treatment plans in time. However, auxiliary solutions for lesion analysis can only call historical medical images for doctors to view, and the efficiency of auxiliary analysis of lesions is low. Summary of the invention

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

[0004] In a first aspect, an embodiment of the present invention provides a lesion-assisted analysis method, the lesion-assisted analysis method comprising:

[0005] Acquire multiple medical images during the target examination cycle;

[0006] Perform lesion detection on multiple medical images to determine the lesion information of the target lesion in the target inspection period;

[0007] Determining analysis information of the target lesion according to the lesion information of the target lesion;

[0008] Determine a target medical image based on the analysis information and multiple medical images within the target examination period;

[0009] Acquire a reference medical image corresponding to the target medical image within a reference examination period;

[0010] According to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images, the pathological change analysis information of the target lesion is output.

[0011] Optionally, determining the analysis information of the target lesion according to the lesion information of the target lesion includes:

[0012] Querying a preset correspondence relationship according to the lesion information to determine preset lesion information matching the lesion information, wherein the preset correspondence relationship includes different preset lesion information and its corresponding preset lesion information;

[0013] The analysis information is determined according to preset analysis information corresponding to preset lesion information matching the lesion information.

[0014] Optionally, determining the target medical image according to the analysis information and multiple medical images within the target examination period includes:

[0015] Determining an initial medical image that includes all or part of the target lesion from multiple medical images in a target examination cycle;

[0016] The target medical image is determined from the initial medical image according to the analysis information.

[0017] Optionally, outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images includes:

[0018] For each target medical image, determining change information of the analysis information according to the analysis information corresponding to the target medical image and the analysis information corresponding to the reference medical image corresponding to the target medical image;

[0019] The lesion analysis information is determined according to the change information of the corresponding analysis information of the multi-phase target medical images.

[0020] Optionally, outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images includes:

[0021] Calculating first difference information of target lesions in the target medical images of the plurality of periods according to analysis information corresponding to the target medical images of the plurality of periods, and calculating second difference information of target lesions in the reference medical images of the plurality of periods according to analysis information corresponding to the reference medical images of the plurality of periods;

[0022] The lesion analysis information is determined according to the first difference information and the second difference information.

[0023] Optionally, outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images includes:

[0024] Determining a first lesion index of the target lesion within the target examination period according to the corresponding analysis information of the target medical images of multiple periods;

[0025] Determining a second lesion index of the target lesion within the reference examination period according to corresponding analysis information of reference medical images corresponding to the target medical images of multiple periods;

[0026] The lesion analysis information is determined according to the first lesion index and the second lesion index.

[0027] Optionally, the acquiring a reference medical image corresponding to the target medical image within a reference examination period includes:

[0028] Obtain multiple selected reference medical images collected during a reference examination period;

[0029] If the attribute information of the reference medical image to be selected is the same as the attribute information of the target medical image, the reference medical image to be selected is used as the reference medical image corresponding to the target medical image.

[0030] Optionally, the performing lesion detection on multiple medical images to determine lesion information of a target lesion in a target inspection period includes:

[0031] Acquire medical record information of a target object corresponding to the medical image, and determine lesion indication information according to the medical record information;

[0032] Lesion detection is performed on the medical images of multiple phases based on the lesion indication information to obtain lesion information of the target lesion.

[0033] Optionally, the performing lesion detection on multiple medical images to determine lesion information of a target lesion in a target inspection period includes:

[0034] Performing lesion detection on the medical images of the plurality of phases to determine lesion information of at least two lesions;

[0035] Outputting lesion information of at least two lesions, and receiving a lesion analysis instruction corresponding to the lesion information of at least one lesion;

[0036] According to the lesion analysis instruction, the lesion information corresponding to the target lesion is determined from the lesion information of the at least two lesions.

[0037] In a second aspect, an embodiment of the present invention provides a lesion auxiliary analysis device, the lesion auxiliary analysis device comprising:

[0038] The first acquisition module is used to acquire multiple medical images collected during a target examination cycle;

[0039] A detection module is used to perform lesion detection on multiple medical images and determine the lesion information of the target lesion in the target inspection period;

[0040] A first determination module, configured to determine analysis information of a target lesion according to the lesion information of the target lesion;

[0041] A second determination module is used to determine a target medical image based on the analysis information and multiple medical images within the target examination period;

[0042] A second acquisition module is used to acquire a reference medical image corresponding to the target medical image within a reference examination period;

[0043] The analysis module is used to output the pathological analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images.

[0044] In a third aspect, an embodiment of the present invention further provides a lesion-assisted analysis device, comprising a processor and a memory, wherein the memory stores a computer program. When the computer program is executed by the processor, the processor executes the steps of any lesion-assisted analysis method provided by the embodiment of the present invention.

[0045] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium, the computer-readable storage medium comprising a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of any one of the lesion-assisted analysis methods provided in the embodiments of the present invention.

[0046] The present invention acquires multiple medical images collected within a target inspection cycle; performs lesion detection on the multiple medical images to determine the lesion information of the target lesion in the target inspection cycle; determines the analysis information of the target lesion according to the lesion information of the target lesion; determines the target medical image according to the analysis information and the multiple medical images within the target inspection cycle; acquires the reference medical image corresponding to the target medical image within the reference inspection cycle; outputs the lesion analysis information of the target lesion according to the analysis information corresponding to the multiple target medical images and the analysis information corresponding to the corresponding reference medical images. In this way, lesion detection is performed on multiple medical images collected within the target inspection cycle to determine the lesion information of the target lesion, the target medical image is determined from the multiple medical images of the target inspection cycle according to the analysis information, the reference medical image corresponding to the target medical image is acquired from the reference inspection cycle, the target lesion is analyzed using the target medical image and the analysis information in the reference medical image, and the lesion analysis information of the target lesion is output, thereby providing the doctor with reference information of the lesion trend, so as to assist the doctor in analyzing the lesion, thereby improving the efficiency of assisting in analyzing the lesion. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative work.

[0048] Figure 1 It is a flow chart of an embodiment of the lesion auxiliary analysis method provided in an embodiment of the present invention;

[0049] Figure 2 is a flow chart of another embodiment of the lesion auxiliary analysis method provided in an embodiment of the present invention;

[0050] Figure 3 is a schematic diagram of providing a target medical image and a reference medical image in an embodiment of the present invention;

[0051] Figure 4 is a schematic structural diagram of a lesion auxiliary analysis device provided in an embodiment of the present invention;

[0052] Figure 5 It is a schematic diagram of the structure of the lesion auxiliary analysis device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0053] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments in the present invention, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of the present invention. At the same time, in the description of the embodiments of the present invention, the terms "first", "second", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance. Therefore, the features defined as "first" and "second" may explicitly or implicitly include one or more features. In the description of the embodiments of the present invention, the meaning of "multiple" is two or more, unless otherwise clearly and specifically defined.

[0054] Embodiments of the present invention provide a lesion-assisted analysis method, apparatus, device, and computer-readable storage medium.

[0055] Specifically, this embodiment will be described from the perspective of a lesion-assisted analysis device, which can be specifically integrated in a lesion-assisted analysis device, that is, the lesion-assisted analysis method of the embodiment of the present invention can be executed by a lesion-assisted analysis device, and the lesion-assisted analysis device can be a medical device (such as a magnetic resonance imaging device, etc.), a terminal device (such as a computer, a mobile phone, etc.), etc.

[0056] The following is a detailed description in conjunction with the accompanying drawings. In this embodiment, the execution subject is an auxiliary analysis device for lesions. It should be noted that the description order of the following embodiments is not intended to limit the preferred order of the embodiments. Although the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in an order different from that shown in the accompanying drawings.

[0057] According to the background technology of the present invention, at present, for some diseases, such as postoperative recovery, chronic disease treatment or malignant disease observation period, long-term follow-up of patients is required to ensure that doctors can understand the progress of patients' conditions and make new treatment plans in time. However, auxiliary solutions for lesion analysis can only call historical medical images for doctors to view, and the efficiency of auxiliary analysis of lesions is low.

[0058] In order to solve the above problems, the present invention discloses a lesion auxiliary analysis method, please refer to Figure 1 The specific process of the lesion auxiliary analysis method can be as follows: Step S10 to Step S60, wherein:

[0059] Step S10, acquiring multiple medical images collected during a target examination period;

[0060] In this embodiment, the inspection cycle is the cycle for each detection of the target object. For example, in the postoperative recovery of some diseases, the treatment of chronic diseases or the observation period of malignant diseases, it is necessary to follow up the patient for a long time to ensure that the doctor can understand the development of the patient's condition. Each follow-up must be detected on the target object, so the follow-up cycle can be used as the inspection cycle. For some diseases, the target area on the target object will be scanned in some cycles to obtain multiple multi-phase medical images for the target tissue area. In this embodiment, the target tissue area of ​​the target object will be scanned in the target inspection cycle to obtain multiple (at least two) medical images of the target tissue area in the target inspection cycle. The target object can be an organism with biological characteristics, such as a human body, a pet, etc. Medical images of different periods are medical images collected in different ways at different times in the inspection cycle. For example, within a 10-minute inspection cycle in January, medical image A is collected in the first minute, and medical image B is collected at the end of the second minute.

[0061] The acquisition methods corresponding to multiple medical images acquired within the same examination cycle are different. Since medical images of different periods are images acquired based on different acquisition methods, the information contained in the target tissue area of ​​medical images of different periods is different, and may include information such as liver tissue, blood vessels, and lesions. For example, a medical image of a certain period mainly shows blood vessels, while a medical image of another period mainly shows lesion information, etc.

[0062] Step S20, performing lesion detection on multiple medical images to determine lesion information of a target lesion in a target inspection period;

[0063] In this embodiment, it is necessary to combine multiple medical images for lesion analysis to determine the target lesions on the target object that need to be assisted in the current detection cycle. Lesions refer to areas where pathological changes occur in local tissue structures caused by diseases inside a living organism. It can be the result of infection, inflammation, tumors, injuries or other pathological processes. Lesions can be single or multiple, and their size, shape and properties vary depending on the cause. In medical images, lesions are the focus of attention, and the content contained in medical images of different periods is different. Therefore, combined with multiple medical images, it is possible to detect the lesions of the target object contained in the detection area corresponding to the medical image, and select at least one lesion as the target lesion. There are many ways to detect lesions, such as target detection based on deep learning network models, atlas analysis, image thresholds, etc., which are not limited in this embodiment. After the target lesion is detected, the lesion information of the target lesion can be obtained accordingly. The lesion information is data related to the target lesion, including at least one of the lesion type, location, morphology, signs, etc.

[0064] Step S30: Determine analysis information of the target lesion according to the lesion information of the target lesion.

[0065] In this embodiment, after the lesion information of the target lesion is determined, the analysis information of the target lesion that needs to be paid attention to can be determined based on the lesion information of the target lesion, and the analysis information points to the information that needs to be analyzed and paid attention to of the target lesion, including at least one of the lesion type, location, morphology, size, signs, etc. According to the lesion information corresponding to the target lesion, the analysis information of the target lesion can be determined accordingly. For example, after the lesion type of the target lesion is determined, it can be determined that the size of the target lesion that needs to be checked and paid attention to can be determined accordingly. For another example, after the size of the target lesion is determined, the morphology of the target lesion that needs to be paid attention to can be determined accordingly.

[0066] Optionally, determining the analysis information of the target lesion according to the lesion information of the target lesion includes:

[0067] Querying a preset correspondence relationship according to the lesion information to determine preset lesion information matching the lesion information, wherein the preset correspondence relationship includes different preset lesion information and its corresponding preset lesion information;

[0068] The analysis information is determined according to preset analysis information corresponding to preset lesion information matching the lesion information.

[0069] In this embodiment, it can be pre-configured analysis information related to lesion information, so that the lesion information of the target lesion can find the analysis information of its corresponding target lesion that needs to be paid attention to based on the preset corresponding relationship. A plurality of preset lesion information are set in advance for different lesions. For each preset lesion information, the preset analysis information of its corresponding lesion that needs to be paid attention to is set according to the doctor's setting, user information, etc., to obtain a preset correspondence relationship including different preset lesion information and its corresponding preset lesion information. The preset correspondence relationship is queried based on the lesion information of the target lesion, and the preset lesion information that matches the lesion information of the target lesion is determined, and then the preset analysis information corresponding to the preset lesion information that matches the lesion information in the preset correspondence relationship is used as the analysis information.

[0070] Optionally, lesion indication information related to the lesion information of the target lesion to be inspected can also be pre-configured to characterize the target lesion and its lesion information that need to be focused on in the current detection cycle. The lesion indication information can be lesion-related information of the lesion to be inspected determined according to the doctor's setting and user information, such as at least one of the lesion type, location, morphology, size, and signs, etc. Lesion detection is performed on multiple medical images according to the lesion indication information, so that the target lesion in the target inspection cycle can be accurately and quickly determined, and the lesion information of the target lesion that meets the lesion indication information can be obtained. Therefore, before step S20, it also includes obtaining the lesion indication information configured by the user, so as to detect multiple medical images in a targeted manner and determine the lesion information of the target lesion contained in each medical image.

[0071] Optionally, the performing lesion detection on multiple medical images to determine a target lesion in a target inspection period includes:

[0072] Performing lesion detection on the medical images of the plurality of phases to determine lesion information of at least two lesions;

[0073] Outputting lesion information of at least two lesions, and receiving a lesion analysis instruction corresponding to the lesion information of at least one lesion;

[0074] According to the lesion analysis instruction, the lesion information corresponding to the target lesion is determined from the lesion information of the at least two lesions.

[0075] In this embodiment, the target lesion can be based on the lesion detection of multiple medical images, and the user selects one or more lesions from the lesion detection results for auxiliary analysis according to the needs. First, the lesion detection is performed on the multiple medical images respectively to determine the lesion information of at least two lesions that can be detected by the multiple medical images, and then the lesion information of these lesions is summarized, and the lesion information of at least two lesions is output. The lesion information may include at least one of the name, type, location, size, and signs of the lesion. The lesion information of the lesion can be output in the form of text, image, voice, etc. The user clicks, selects, etc. according to the lesion information of the output lesion, and selects the lesion information of at least one lesion to trigger the lesion analysis instruction to indicate that the lesion needs to be auxiliary analyzed. If the lesion analysis instruction corresponding to the lesion information of at least one lesion is received, the lesion information of the target lesion can be determined from the lesion information of at least two lesions according to the lesion analysis instruction. The lesion analysis instruction can correspond to one or more lesions to be examined. Subsequently, several lesions corresponding to the lesion analysis instruction can be used as target lesions one by one, and the lesion information of the target lesions can be obtained, and then auxiliary analysis can be performed on the target lesions selected by the user in the target tissue area. In other words, not all lesions in the target medical image will be used as target lesions. This is related to actual needs and user settings, and this implementation does not limit this.

[0076] In this way, by detecting multiple medical images, the lesions contained in the target tissue area are comprehensively detected, and the target lesions and their lesion information are selected from these lesions, so that the lesions of interest can be selected for auxiliary analysis as needed, thereby improving the accuracy and customization of the auxiliary analysis of lesions and facilitating medical diagnosis.

[0077] Step S40, determining a target medical image from multiple medical images of a target examination cycle according to the analysis information.

[0078] In this embodiment, the target lesion is a lesion in the multi-phase medical image that needs to be analyzed auxiliary, and is a lesion that needs to be focused on in the target inspection cycle. According to the analysis information of the target lesion, a target medical image that is valuable for analyzing the target lesion is determined from the multi-phase medical image, so that the analysis information of the target lesion can be obtained from the target medical image.

[0079] Optionally, determining the target medical image according to the analysis information and multiple medical images within the target examination period includes:

[0080] Determining an initial medical image that includes all or part of the target lesion from multiple medical images in a target examination cycle;

[0081] The target medical image is determined from the initial medical image according to the analysis information.

[0082] In this embodiment, based on the target lesion, each period of medical images can be detected to determine the medical images that contain all or part of the target lesions in these multiple medical images, and these medical images are set as initial medical images. The initial medical image contains part or all of the target lesions, which means that at least one image area in the initial medical image belongs to the target lesion. The initial medical image contains part or all of the target lesions, and then the initial medical image containing the analysis information is identified from the initial medical image based on the analysis information of the target lesion. These initial medical images are medical images with analysis value for the target lesions and can be used as target medical images. It can be understood that the analysis information contained in the target medical image can assist in analyzing the target lesion, and the target medical image belongs to the medical image within the target inspection cycle.

[0083] Step S50, outputting the pathological analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images;

[0084] In this embodiment, after determining the multiple target medical images that are valuable for analyzing the target lesions within the target inspection cycle, considering the possibility that medical images of the target tissue area may have been acquired in other inspection cycles, it is necessary to obtain reference medical images corresponding to the target medical images within the reference inspection cycle for comprehensive auxiliary analysis.

[0085] The reference inspection cycle is other inspection cycles for detecting the target tissue area in addition to the target inspection cycle. The reference inspection cycle can be selected from all or part of these other inspection cycles according to needs.

[0086] In some embodiments, the target inspection cycle may be the current inspection cycle, and the reference inspection cycle may be the historical inspection cycle corresponding to the current inspection cycle. Through analysis, the lesion analysis information of the target lesion in the past may be obtained, which is suitable for judging the benign or malignant nature of the target lesion. The target inspection cycle may be the historical inspection cycle, and the reference inspection cycle may be the subsequent inspection cycle corresponding to the historical inspection cycle. Through analysis, the lesion analysis information of the target lesion after the historical inspection cycle may be obtained, which is suitable for the lesion analysis information of the target lesion after treatment and observing the recovery of the target lesion.

[0087] A reference medical image corresponding to the target medical image within a historical examination period is obtained. The reference medical image corresponding to the target medical image needs to meet the following conditions: the image is collected within the reference examination period, the collection method is the same as that of the target medical image, and the image is also collected for the target tissue area.

[0088] Step S60: outputting the pathological analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images.

[0089] In this embodiment, since the target medical image contains analysis information that has analysis value for the target lesion, the reference medical image corresponding to the target medical image will also contain analysis information that has analysis value for the target lesion. Based on the analysis information in the target medical image and the analysis information in the corresponding reference medical image, the lesion analysis information of the target lesion in the target medical image between the reference inspection cycle and the target inspection cycle can be analyzed. The lesion analysis information can characterize the changes in the target lesion between the reference inspection cycle and the target inspection cycle. The output lesion analysis information can be sent to the target terminal via reports, voice, etc. The doctor can view the lesion analysis information on the target terminal, which can assist the doctor in analyzing the target lesion and improve the diagnosis efficiency.

[0090] It should be noted that there can be one or more reference inspection cycles, which are not limited here. This embodiment does not need to obtain the analysis information of all medical images collected within the reference inspection cycle for processing. This embodiment first detects the medical images of each period to determine the multi-period target medical images that contain the analysis information of the target lesion among the multi-period medical images within the target inspection cycle, and then directly uses the reference medical images corresponding to the target medical images within the reference inspection cycle for the analysis of the target lesions, which is more targeted and has higher analysis efficiency.

[0091] In the technical solution disclosed in this embodiment, multiple medical images collected within the target inspection cycle are acquired; lesion detection is performed on the multiple medical images to determine the lesion information of the target lesion in the target inspection cycle; analysis information of the target lesion is determined based on the lesion information of the target lesion; the target medical image is determined based on the analysis information and the multiple medical images within the target inspection cycle; the reference medical image corresponding to the target medical image within the reference inspection cycle is acquired; and the lesion analysis information of the target lesion is output based on the analysis information corresponding to the multiple target medical images and the analysis information corresponding to the corresponding reference medical images. In this way, lesion detection is performed on multiple medical images collected within the target inspection cycle to determine the lesion information of the target lesion, the target medical image is determined from the multiple medical images of the target inspection cycle according to the analysis information, the reference medical image corresponding to the target medical image is acquired from the reference inspection cycle, the target lesion is analyzed using the target medical image and the analysis information in the reference medical image, and the lesion analysis information of the target lesion is output, so as to provide doctors with reference information of lesion trends, so as to assist doctors in analyzing lesions, thereby improving the efficiency of assisting in analyzing lesions.

[0092] Optionally, step S50 of “outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images” may include:

[0093] Determining a first lesion index of the target lesion within the target examination period according to the corresponding analysis information of the target medical images of multiple periods;

[0094] Determining a second lesion index of the target lesion within the reference examination period according to corresponding analysis information of reference medical images corresponding to the target medical images of multiple periods;

[0095] The lesion analysis information is determined according to the first lesion index and the second lesion index.

[0096] In this embodiment, the analysis of the target lesion in the target medical image that has analytical value is different in different target medical images due to different acquisition methods. Therefore, the target lesions in different target medical images have different analysis information. The analysis information may be the lesion signs of the target lesion, etc., which have different analytical values.

[0097] In this embodiment, the target inspection cycle and the reference inspection cycle may be analyzed separately. For the target inspection cycle, a comprehensive analysis may be performed based on the analysis information of the target lesion in each period of the target medical image. For example, the signs of the target lesion contained in the analysis information in the target medical image may be analyzed to determine the first lesion index about the target lesion. The analysis information is associated with a preset lesion index type. The preset lesion index type is a number of indicators required to integrate the analysis information of the target lesion. The first lesion index is an index data that meets the preset lesion index type and can be obtained based on the corresponding analysis information of the target medical image in each period of the target inspection cycle.

[0098] For the reference inspection period, a comprehensive analysis can be first performed based on the analysis information of the target lesion in the reference medical images of each period, for example, the signs of the target lesion contained in the analysis information in the reference medical images can be analyzed to determine the second lesion index for the target lesion. The second lesion index is the index data that can be obtained based on the analysis information of the reference medical images of each period in the reference inspection period and meets the preset lesion index type.

[0099] By comparing and analyzing the first lesion indicator and the second lesion indicator corresponding to the same preset lesion indicator type, the lesion analysis information corresponding to the preset lesion indicator type can be obtained, thereby obtaining the lesion analysis information corresponding to one or more preset lesion indicator types for output.

[0100] For example, reference Figure 3 , for the target inspection period, the target medical image A, target medical image B, and target medical image C are obtained, and for the reference inspection period, the reference medical image a (corresponding to A) and the reference medical image b (corresponding to B) are obtained, and no reference medical image corresponding to C is found. The red box is part or all of the target lesions in the corresponding image. In this case, the analysis information corresponding to each target medical image and each reference medical image can be the sign of the target lesion. Based on the signs in the target medical image A, the signs in the target medical image B, and the signs in the target medical image C, the first lesion index including R index 1 and F index 1 can be obtained. Based on the signs in the reference medical image a and the signs in the reference medical image b, the second lesion index including R index 2 and F index 2 can be obtained. By comparing R index 1 and R index 2 belonging to the same preset lesion index type R, the lesion change information corresponding to the preset lesion index type R can be obtained. By comparing F index 1 and F index 2 belonging to the same preset lesion index type F, the lesion change information corresponding to the preset lesion index type F can be obtained.

[0101] In this way, the first lesion index of the target lesion within the target inspection period is determined according to the corresponding analysis information of multiple target medical images, the second lesion index of the target lesion within the reference inspection period is determined according to the corresponding analysis information of the reference medical images corresponding to the multiple target medical images, and the lesion analysis information is determined according to the first lesion index and the second lesion index. The lesion change information corresponding to various preset lesion index types of the target lesion can be obtained quickly and accurately, and even if the reference medical image corresponding to the target medical image is not found, the corresponding analysis information of this period of target medical images will not be wasted, and it can be used for lesion analysis, thereby improving the efficiency and accuracy of lesion auxiliary analysis.

[0102] Optionally, step S50 of “outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images” may also include:

[0103] For each target medical image, determining change information of the analysis information according to the analysis information corresponding to the target medical image and the analysis information corresponding to the reference medical image corresponding to the target medical image;

[0104] The lesion analysis information is determined according to the change information of the corresponding analysis information of the multi-phase target medical images.

[0105] In this embodiment, the analysis information corresponding to the target medical image and the analysis information corresponding to the reference medical image may be compared and analyzed to determine the change information of the analysis information in the target medical image and in the reference medical image corresponding to the target medical image.

[0106] Optionally, the target medical image may include part or all of the target lesions, and the reference medical image corresponding to the target medical image may also include part or all of the target lesions. Then the analysis information corresponding to the target medical image includes the signs of the target lesions in the target medical image, and the analysis information corresponding to the reference medical image includes the signs of the target lesions in the reference medical image. The signs of the target lesions corresponding to the target medical image and the signs of the target lesions corresponding to the corresponding reference medical image may be analyzed first, and the sign change information is determined as the change information of the analysis information. Signs refer to the features presented by the target lesions in the corresponding images, such as geometric information, texture information, color information, etc. Due to the differences in acquisition methods and acquisition times, the signs are different in different medical images, so different target medical images correspond to different lesion signs, and the target lesions in the reference medical images corresponding to different target medical images also correspond to different lesion signs. For each target medical image, the sign of the target lesion corresponding to the target medical image is compared with the sign of the target lesion corresponding to the reference medical image corresponding to the target medical image to obtain sign change information, which can characterize the difference in sign change of the target lesion, and the sign change information corresponding to the target medical images of multiple periods is used as the change information of the analysis information, and is output as the lesion analysis information, so that the doctor can more accurately determine the change between the signs of the target lesions in the medical images of different periods. In some embodiments, the sign change information of the target lesions corresponding to the target medical images of multiple periods can also be analyzed to obtain higher-dimensional diagnostic information as the lesion analysis information output.

[0107] It should be noted that if the target medical image does not find a corresponding reference medical image, the target medical image can be ignored. If the analysis information of the target lesion is not detected in the reference medical image, the reference medical image can also be ignored, or the blank analysis can be compared with the corresponding analysis information of the target medical image to obtain the corresponding change information.

[0108] For example, reference Figure 3, for the target examination period, the target medical image A, target medical image B, and target medical image C are obtained, and for the reference examination period, the reference medical image a (corresponding to A) and reference medical image b (corresponding to B) are obtained, and no reference medical image corresponding to C is found. The red box contains part or all of the target lesions in the corresponding image. In this case, the analysis information corresponding to each target medical image and each reference medical image can be the sign of the target lesion. The sign change information corresponding to the target medical image A can be determined based on the sign in the target medical image A and the sign in the reference medical image a, and the sign change information corresponding to the target medical image B can be determined based on the sign in the target medical image B and the sign in the reference medical image b. Then, the sign change information corresponding to the target medical image A and the sign change information corresponding to the target medical image B can be integrated to output the lesion change information.

[0109] In this way, for each target medical image, the sign change information can be determined based on the corresponding analysis information of the target medical image and the analysis information of the reference medical image corresponding to the target medical image. The lesion analysis information can be output based on the sign change information corresponding to multiple target medical images. By directly analyzing the corresponding analysis information of the target medical image and the analysis information of its corresponding reference medical image, the efficiency and accuracy of lesion auxiliary analysis can be further improved.

[0110] Optionally, the method may further include: if there are more than a preset number of target medical images and the corresponding reference medical images are queried, executing the step of determining the change information of the analysis information for each target medical image according to the analysis information corresponding to the target medical image and the analysis information corresponding to the reference medical image corresponding to the target medical image.

[0111] In this embodiment, since it is necessary to process based on the corresponding analysis information of the target medical image and the corresponding analysis information of the reference medical image, it is necessary to ensure that there are more than a preset number of target medical images and the corresponding reference medical images can be queried before executing the step of "for each target medical image, determining the change information of the analysis information according to the analysis information corresponding to the target medical image and the analysis information corresponding to the reference medical image corresponding to the target medical image". The lesion analysis information obtained by this comparison method is more diverse.

[0112] In some embodiments, if there are no target medical images greater than a preset number, so that a large number of corresponding reference medical images can be queried, the first lesion index of the target lesion in the target inspection period can be determined based on the corresponding analysis information of the multi-phase target medical images, and the second lesion index of the target lesion in the reference inspection period can be determined based on the corresponding analysis information of the reference medical images corresponding to the multi-phase target medical images. The lesion analysis information is determined based on the first lesion index and the second lesion index to improve the efficiency of auxiliary analysis of lesions. It should be noted that if there are target medical images greater than a preset number and the corresponding reference medical images are queried, the above steps can also be performed to improve the efficiency of auxiliary analysis of lesions.

[0113] Optionally, step S50 of “outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images” may include:

[0114] Calculating first difference information of target lesions in the target medical images of the plurality of periods according to analysis information corresponding to the target medical images of the plurality of periods, and calculating second difference information of target lesions in the reference medical images of the plurality of periods according to analysis information corresponding to the reference medical images of the plurality of periods;

[0115] The lesion analysis information is determined according to the first difference information and the second difference information.

[0116] In this embodiment, since the information contained in medical images of different periods in the same inspection cycle is different, the analysis information corresponding to different medical images will also be different, and this difference can also reflect the characteristics of the target lesion. For example, the size of the target lesion observed from the target medical image A is 10, the size of the target lesion observed from the target medical image B is 100, the size of the target lesion observed from the reference medical image a is 20, and the size of the target lesion observed from the reference medical image b is 200. This may be because medical images A and medical image a collect the inner diameter of the lesion, and medical images B and medical image b collect the outer diameter of the lesion. The difference of 90 in the corresponding size between the target medical image A and the target medical image B can be the first difference information in the target inspection cycle, and the difference of 180 in the corresponding size between the target medical image a and the target medical image b can be the second difference information in the reference inspection cycle.

[0117] Based on this, in this embodiment, the corresponding analysis information of the target medical images of each period can be compared with each other to calculate the first difference information within the target inspection period, and the corresponding analysis information of the target medical images of each period can be compared with each other to calculate the second difference information within the reference inspection period. Then, the first difference information and the second difference information can be compared, and the lesion analysis information of the difference corresponding features between the target medical image corresponding analysis information and the reference medical image corresponding analysis information can be output.

[0118] Exemplarily, for a target medical image A, a target medical image B, and a target medical image C are obtained during the target inspection period, and for a reference medical image a (corresponding to A) and a reference medical image b (corresponding to B) are obtained during the reference inspection period, but no reference medical image corresponding to C is found. In this case, first difference information corresponding to the target lesion can be obtained based on a comparison of the corresponding analysis information of the target medical image A and the corresponding analysis information of the target medical image B, and second difference information corresponding to the target lesion can be obtained based on the corresponding analysis information of the reference medical image a and the corresponding analysis information of the reference medical image b, and lesion change information corresponding to the lesion feature can be output according to the first difference information and the second difference information.

[0119] In this way, based on the first difference information between the corresponding analysis information of multiple target medical images and the second difference information between the corresponding analysis information of multiple reference medical images, more dimensional lesion analysis information can be determined, thereby further improving the efficiency of auxiliary analysis of lesions.

[0120] Optionally, refer to Figure 2 Based on any of the above embodiments, in another embodiment of the lesion auxiliary analysis method of the present invention, step S40, "obtaining a reference medical image corresponding to the target medical image within a reference examination period", may include:

[0121] S31, obtaining a plurality of expected selected reference medical images collected within a reference examination period;

[0122] S32: If the attribute information of the reference medical image to be selected is the same as the attribute information of the target medical image, use the reference medical image to be selected as the target medical image.

[0123] In this embodiment, after determining the reference inspection cycle that needs to be comprehensively analyzed with the target inspection cycle, multiple medical images collected for the same target tissue area of ​​the same target object during the reference inspection cycle can be obtained as reference medical images to be selected, thereby obtaining multiple reference medical images to be selected collected during the reference inspection cycle.

[0124] In this embodiment, since the content contained in each medical image is different, this is specifically manifested in the different analysis information contained in each medical image. This is because the acquisition methods of the medical images are different. In order to distinguish the medical images of each period, attribute information can be added to the medical images of the same acquisition method. According to the attribute information, the tissue contained in the medical image can be determined.

[0125] Optionally, the attribute information may be the name, number, etc. of the medical image. In the medical field, the medical image may be identified and zoned by the name of the medical image, thereby directly determining the type of the medical image, the tissue type it contains, or the tissue it can mainly display.

[0126] Optionally, the attribute information may also be the type of medical image contained in the medical image, the type of tissue contained in the medical image, or the tissue that the medical image can mainly display.

[0127] In this embodiment, the attribute information of each reference medical image to be selected and the attribute information of the target medical image of each period are obtained, and the attribute information of each reference medical image to be selected and the attribute information of the target medical image of each period are matched. If the attribute information of the reference medical image to be selected is the same as the attribute information of the target medical image, the reference medical image to be selected and the target medical image corresponding to the same attribute information are matched to obtain the reference medical image corresponding to the target medical image.

[0128] In this way, by determining the reference medical image corresponding to the target medical image through attribute information, the matching efficiency can be improved, and the efficiency of auxiliary analysis of lesions can be further improved.

[0129] Optionally, step S20 of “performing lesion detection on multiple medical images to determine lesion information of a target lesion in a target inspection period” may include:

[0130] Acquire medical record information of a target object corresponding to the medical image, and determine lesion indication information according to the medical record information;

[0131] Lesion detection is performed on the medical images of multiple phases based on the lesion indication information to obtain lesion information of the target lesion.

[0132] In this embodiment, the medical record information of the target object corresponding to the medical image is obtained, and the medical record information includes relevant information of the lesions that the target object needs to focus on, so that the lesion information of these lesions can be followed up for a long time, that is, in these scenarios, each time the medical image of the target tissue area of ​​the target object is collected, it is mainly for the review of the lesions, and these lesions are also the target lesions that need to be focused on during the target inspection cycle. Therefore, the target lesions and the relevant information of the lesion information that need to be reviewed in the target tissue area corresponding to the medical image of the target object can be determined according to the medical record information as lesion indication information. Then, based on the lesion indication information, multi-phase medical images can be detected in a targeted manner, so as to accurately determine the lesion information of the target lesion from the multi-phase medical images. And the analysis information of the target lesion is determined according to the lesion information, and the target medical image corresponding to the analysis information can be obtained from the multi-phase medical images, and the corresponding reference medical image is obtained for lesion analysis.

[0133] In the scenario of this embodiment, the target inspection cycle can be the current inspection cycle, and the reference inspection cycle can be the historical inspection cycle for the target lesion, so that the historical inspection information can be combined to comprehensively diagnose the target lesion in the current detection cycle, and the lesion analysis information of the target lesion can be obtained to characterize the change trend of the target lesion in the follow-up period, thereby facilitating doctors to adjust the treatment plan and improve the diagnosis and treatment effect.

[0134] In this way, the lesion information of the target lesion can be detected in a targeted manner according to the medical image corresponding to the medical record information of the target object, and based on the analysis information corresponding to the lesion information of the target lesion, the target medical image can be obtained from multiple medical images to be quickly used for lesion analysis of the target lesion, which can further improve the efficiency of auxiliary analysis of lesions.

[0135] This embodiment also provides a lesion auxiliary analysis device, which can be integrated into a lesion auxiliary analysis device. Figure 4 As shown, the lesion auxiliary analysis device may include:

[0136] The first acquisition module 1001 is used to acquire multiple medical images collected within a target examination period;

[0137] The detection module 1002 is used to perform lesion detection on multiple medical images to determine the lesion information of the target lesion in the target inspection period;

[0138] A first determination module 1003 is used to determine analysis information of a target lesion according to the lesion information of the target lesion;

[0139] A second determination module 1004 is used to determine a target medical image according to the analysis information and multiple medical images within the target examination period;

[0140] The second acquisition module 1005 is used to acquire a reference medical image corresponding to the target medical image within a reference examination period;

[0141] The analysis module 1006 is used to output the pathological analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images.

[0142] Optionally, the first determining module 1003 is further configured to:

[0143] Querying a preset correspondence relationship according to the lesion information to determine preset lesion information matching the lesion information, wherein the preset correspondence relationship includes different preset lesion information and its corresponding preset lesion information;

[0144] The analysis information is determined according to preset analysis information corresponding to preset lesion information matching the lesion information.

[0145] Optionally, the second determining module 1004 is further configured to:

[0146] Determining an initial medical image that includes all or part of the target lesion from multiple medical images in a target examination cycle;

[0147] The target medical image is determined from the initial medical image according to the analysis information.

[0148] Optionally, the analysis module 1006 is further configured to:

[0149] For each target medical image, determining change information of the analysis information according to the analysis information corresponding to the target medical image and the analysis information corresponding to the reference medical image corresponding to the target medical image;

[0150] The lesion analysis information is determined according to the change information of the corresponding analysis information of the multi-phase target medical images.

[0151] Optionally, the analysis module 1006 is further configured to:

[0152] Calculating first difference information of target lesions in the target medical images of the plurality of periods according to analysis information corresponding to the target medical images of the plurality of periods, and calculating second difference information of target lesions in the reference medical images of the plurality of periods according to analysis information corresponding to the reference medical images of the plurality of periods;

[0153] The lesion analysis information is determined according to the first difference information and the second difference information.

[0154] Optionally, the analysis module 1006 is also used to

[0155] Determining a first lesion index of the target lesion within the target examination period according to the corresponding analysis information of the target medical images of multiple periods;

[0156] Determining a second lesion index of the target lesion within the reference examination period according to corresponding analysis information of reference medical images corresponding to the target medical images of multiple periods;

[0157] The lesion analysis information is determined according to the first lesion index and the second lesion index.

[0158] Optionally, the second acquisition module 1005 is further configured to:

[0159] Obtain multiple selected reference medical images collected during a reference examination period;

[0160] If the attribute information of the reference medical image to be selected is the same as the attribute information of the target medical image, the reference medical image to be selected is used as the reference medical image corresponding to the target medical image.

[0161] Optionally, the detection module 1002 is further configured to:

[0162] Acquire medical record information of a target object corresponding to the medical image, and determine lesion indication information according to the medical record information;

[0163] Lesion detection is performed on the medical images of multiple phases based on the lesion indication information to obtain lesion information of the target lesion.

[0164] Optionally, the detection module 1002 is further configured to:

[0165] Performing lesion detection on the medical images of the plurality of phases to determine lesion information of at least two lesions;

[0166] Outputting lesion information of at least two lesions, and receiving a lesion analysis instruction corresponding to the lesion information of at least one lesion;

[0167] According to the lesion analysis instruction, the lesion information corresponding to the target lesion is determined from the lesion information of the at least two lesions.

[0168] This embodiment acquires multiple medical images collected within the target inspection cycle; performs lesion detection on the multiple medical images to determine the lesion information of the target lesion in the target inspection cycle; determines the analysis information of the target lesion based on the lesion information of the target lesion; determines the target medical image based on the analysis information and the multiple medical images within the target inspection cycle; acquires the reference medical image corresponding to the target medical image within the reference inspection cycle; outputs the lesion analysis information of the target lesion based on the analysis information corresponding to the multiple target medical images and the analysis information corresponding to the corresponding reference medical images. In this way, lesion detection is performed on multiple medical images collected within the target inspection cycle to determine the lesion information of the target lesion, the target medical image is determined from the multiple medical images of the target inspection cycle based on the analysis information, the reference medical image corresponding to the target medical image is acquired from the reference inspection cycle, the target lesion is analyzed using the target medical image and the analysis information in the reference medical image, and the lesion analysis information of the target lesion is output, thereby providing the doctor with reference information of the lesion trend to assist the doctor in analyzing the lesion, thereby improving the efficiency of assisting in analyzing the lesion.

[0169] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0170] like Figure 5 As shown, Figure 5 A schematic diagram of the structure of a lesion-assisted analysis device provided in an embodiment of the present invention. The lesion-assisted analysis device 1100 includes a processor 1101 having one or more processing cores, a memory 1102 having one or more computer-readable storage media, and a computer program stored in the memory 1102 and executable on the processor. The processor 1101 is electrically connected to the memory 1102. It will be understood by those skilled in the art that the structure of the lesion-assisted analysis device shown in the figure does not constitute a limitation on the lesion-assisted analysis device, and may include more or fewer components than shown in the figure, or combine certain components, or arrange components differently.

[0171] The processor 1101 is the control center of the lesion auxiliary analysis device 1100, and uses various interfaces and lines to connect various parts of the entire lesion auxiliary analysis device 1100. By running or loading software programs and / or units stored in the memory 1102, and calling data stored in the memory 1102, the processor 1101 executes various functions of the lesion auxiliary analysis device 1100 and processes data, thereby monitoring the lesion auxiliary analysis device 1100 as a whole. The processor 1101 can be a processor CPU, a graphics processor GPU, a network processor (Network Processor, NP), etc., and can implement or execute the various methods, steps and logic block diagrams disclosed in the embodiments of the present invention.

[0172] In the embodiment of the present invention, the processor 1101 in the lesion auxiliary analysis device 1100 will load instructions corresponding to the processes of one or more application programs into the memory 1102 according to the following steps, and the processor 1101 will run the application programs stored in the memory 1102 to implement various functions, such as:

[0173] Acquire multiple medical images during the target examination cycle;

[0174] Perform lesion detection on multiple medical images to determine the lesion information of the target lesion in the target inspection period;

[0175] Determining analysis information of the target lesion according to the lesion information of the target lesion;

[0176] Determine a target medical image based on the analysis information and multiple medical images within the target examination period;

[0177] Acquire a reference medical image corresponding to the target medical image within a reference examination period;

[0178] According to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images, the pathological change analysis information of the target lesion is output.

[0179] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0180] Optional, such as Figure 5 As shown, the lesion auxiliary analysis device 1100 also includes: a touch screen 1103, a radio frequency circuit 1104, an audio circuit 1105, an input unit 1106 and a power supply 1107. Among them, the processor 1101 is electrically connected to the touch screen 1103, the radio frequency circuit 1104, the audio circuit 1105, the input unit 1106 and the power supply 1107 respectively. Those skilled in the art can understand that Figure 5 The structure of the lesion-assisted analysis device shown in the figure does not constitute a limitation of the lesion-assisted analysis device, and may include more or fewer components than shown in the figure, or a combination of certain components, or a different arrangement of components.

[0181] The touch display screen 1103 can be used to display a graphical user interface and receive the operation instructions generated by the user acting on the graphical user interface. The touch display screen 1103 may include a display panel and a touch panel. Wherein, the display panel may be used to display the information input by the user or the information provided to the user and various graphical user interfaces of the lesion auxiliary analysis device, and these graphical user interfaces may be composed of graphics, text, icons, videos and any combination thereof. Optionally, the display panel may be configured in the form of a liquid crystal display (LCD, Liquid Crystal Display), an organic light emitting diode (OLED, Organic Light-Emitting Diode) and the like. The touch panel may be used to collect the user's touch operation on or near it (such as the user uses any suitable object or attachment such as a finger, a stylus, etc. on the touch panel or near the touch panel), and generate corresponding operation instructions, and the operation instructions execute corresponding programs. Optionally, the touch panel may include two parts, a touch detection device and a touch controller. Among them, the touch detection device detects the user's touch orientation, detects the signal brought by the touch operation, and transmits the signal to the touch controller; the touch controller receives the touch information from the touch detection device, converts it into the touch point coordinates, and then sends it to the processor 1101, and can receive the command sent by the processor 1101 and execute it. The touch panel can cover the display panel. When the touch panel detects a touch operation on or near it, it is transmitted to the processor 1101 to determine the type of touch event, and then the processor 1101 provides corresponding visual output on the display panel according to the type of touch event. In an embodiment of the present invention, the touch panel and the display panel can be integrated into the touch display screen 1103 to realize the input and output functions. However, in some embodiments, the touch panel and the touch panel can be used as two independent components to realize the input and output functions. That is, the touch display screen 1103 can also be used as a part of the input unit 1106 to realize the input function.

[0182] The radio frequency circuit 1104 may be used to send and receive radio frequency signals, so as to establish wireless communication with a network device or other lesion auxiliary analysis device through wireless communication, and to send and receive signals between the network device or other lesion auxiliary analysis device.

[0183] The audio circuit 1105 can be used to provide an audio interface between the user and the lesion auxiliary analysis device through a speaker and a microphone. The audio circuit 1105 can transmit the electrical signal converted from the received audio data to the speaker, which is converted into a sound signal for output; on the other hand, the microphone converts the collected sound signal into an electrical signal, which is received by the audio circuit 1105 and converted into audio data, and then the audio data is output to the processor 1101 for processing, and then sent to another lesion auxiliary analysis device through the radio frequency circuit 1104, or the audio data is output to the memory 1102 for further processing. The audio circuit 1105 may also include an earplug jack to provide communication between an external headset and the lesion auxiliary analysis device.

[0184] The input unit 1106 may be used to receive input numbers, character information or user feature information (such as fingerprint, iris, facial information, etc.), and generate keyboard, mouse, joystick, optical or trackball signal input related to user settings and function control.

[0185] The power supply 1107 is used to supply power to various components of the lesion auxiliary analysis device 1100. Optionally, the power supply 1107 can be logically connected to the processor 1101 through a power management system, so as to manage charging, discharging, and power consumption management through the power management system. The power supply 1107 can also include one or more DC or AC power supplies, recharging systems, power failure detection circuits, power converters or inverters, power status indicators, and other arbitrary components.

[0186] although Figure 5 Not shown in the figure, the lesion auxiliary analysis device 1100 may also include a camera, a sensor, a wireless fidelity module, a Bluetooth module, etc., which will not be repeated here.

[0187] In the above embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0188] A person of ordinary skill in the art will appreciate that all or part of the steps in the various methods of the above embodiments may be completed by instructions, or by controlling related hardware through instructions. The instructions may be stored in a computer-readable storage medium and loaded and executed by a processor.

[0189] To this end, an embodiment of the present invention provides a computer-readable storage medium, in which a plurality of computer programs are stored, and the computer program can be loaded by a processor to execute any one of the lesion-assisted analysis methods provided in the embodiments of the present invention. The computer program can execute the following steps of the lesion-assisted analysis method:

[0190] Acquire multiple medical images during the target examination cycle;

[0191] Perform lesion detection on multiple medical images to determine the lesion information of the target lesion in the target inspection period;

[0192] Determining analysis information of the target lesion according to the lesion information of the target lesion;

[0193] Determine a target medical image based on the analysis information and multiple medical images within the target examination period;

[0194] Acquire a reference medical image corresponding to the target medical image within a reference examination period;

[0195] According to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images, the pathological change analysis information of the target lesion is output.

[0196] The specific implementation of the above operations can be found in the previous embodiments, which will not be described in detail here.

[0197] The computer-readable storage medium may include: a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, etc.

[0198] Since the computer program stored in the computer-readable storage medium can execute any one of the lesion-assisted analysis methods provided in the embodiments of the present invention, the beneficial effects that can be achieved by any one of the lesion-assisted analysis methods provided in the embodiments of the present invention can be achieved. Please refer to the previous embodiments for details and will not be repeated here.

[0199] In the above-mentioned lesion-assisted analysis device, computer-readable storage medium, lesion-assisted analysis equipment, and computer program product embodiments, the description of each embodiment has its own emphasis. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments. Those skilled in the art can clearly understand that for the convenience and simplicity of description, the specific working process and beneficial effects of the above-described lesion-assisted analysis device, computer-readable storage medium, computer program product, lesion-assisted analysis equipment, and corresponding units can refer to the description of the lesion-assisted analysis method in the above embodiment, and will not be repeated here.

[0200] The above is a detailed introduction to a lesion-assisted analysis method, a lesion-assisted analysis device, a lesion-assisted analysis equipment, a computer-readable storage medium and a computer program product provided in an embodiment of the present invention. Specific examples are used herein to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core idea; at the same time, for those skilled in the art, according to the idea of ​​the present invention, there will be changes in the specific implementation methods and application scopes. In summary, the content of this specification should not be understood as a limitation on the present invention.

Claims

1. A lesion-assisted analysis method, characterized in that: The lesion auxiliary analysis method comprises: Acquire multiple medical images during the target examination cycle; Perform lesion detection on multiple medical images to determine the lesion information of the target lesion in the target inspection period; Determining analysis information of the target lesion according to the lesion information of the target lesion; Determine a target medical image based on the analysis information and multiple medical images within the target examination period; Acquire a reference medical image corresponding to the target medical image within a reference examination period; According to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images, the pathological change analysis information of the target lesion is output.

2. The lesion-assisted analysis method according to claim 1, characterized in that: The step of determining the analysis information of the target lesion according to the lesion information of the target lesion includes: Querying a preset correspondence relationship according to the lesion information to determine preset lesion information matching the lesion information, wherein the preset correspondence relationship includes different preset lesion information and its corresponding preset lesion information; The analysis information is determined according to preset analysis information corresponding to preset lesion information matching the lesion information.

3. The lesion-assisted analysis method according to claim 1, characterized in that: Determining the target medical image according to the analysis information and the multiple medical images within the target examination period includes: Determining an initial medical image that includes all or part of the target lesion from multiple medical images in a target examination cycle; The target medical image is determined from the initial medical image according to the analysis information.

4. The lesion-assisted analysis method according to claim 2, characterized in that: The step of outputting the pathological analysis information of the target lesion according to the analysis information corresponding to the target medical images of the plurality of periods and the analysis information corresponding to the corresponding reference medical images comprises: For each target medical image, determining change information of the analysis information according to the analysis information corresponding to the target medical image and the analysis information corresponding to the reference medical image corresponding to the target medical image; The lesion analysis information is determined according to the change information of the corresponding analysis information of the multi-phase target medical images.

5. The lesion-assisted analysis method according to claim 1, characterized in that: Outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of the plurality of periods and the analysis information corresponding to the corresponding reference medical images includes: Calculating first difference information of target lesions in the target medical images of the plurality of periods according to analysis information corresponding to the target medical images of the plurality of periods, and calculating second difference information of target lesions in the reference medical images of the plurality of periods according to analysis information corresponding to the reference medical images of the plurality of periods; The lesion analysis information is determined according to the first difference information and the second difference information.

6. The lesion-assisted analysis method according to claim 1, characterized in that: Outputting the lesion analysis information of the target lesion according to the analysis information corresponding to the target medical images of the plurality of periods and the analysis information corresponding to the corresponding reference medical images includes: Determining a first lesion index of the target lesion within the target examination period according to the corresponding analysis information of the target medical images of multiple periods; Determining a second lesion index of the target lesion within the reference examination period according to corresponding analysis information of reference medical images corresponding to the target medical images of multiple periods; The lesion analysis information is determined according to the first lesion index and the second lesion index.

7. The lesion-assisted analysis method according to claim 1, characterized in that: The obtaining of a reference medical image corresponding to the target medical image within a reference examination period includes: Obtain multiple selected reference medical images collected during a reference examination period; If the attribute information of the reference medical image to be selected is the same as the attribute information of the target medical image, the reference medical image to be selected is used as the reference medical image corresponding to the target medical image.

8. The lesion-assisted analysis method according to any one of claims 1 to 7, characterized in that: The step of performing lesion detection on multiple medical images to determine lesion information of a target lesion in a target inspection period includes: Acquire medical record information of a target object corresponding to the medical image, and determine lesion indication information according to the medical record information; Lesion detection is performed on the medical images of multiple phases based on the lesion indication information to obtain lesion information of the target lesion.

9. The lesion-assisted analysis method according to any one of claims 1 to 7, characterized in that: The step of performing lesion detection on multiple medical images to determine lesion information of a target lesion in a target inspection period includes: Performing lesion detection on the medical images of the plurality of phases to determine lesion information of at least two lesions; Outputting lesion information of at least two lesions, and receiving a lesion analysis instruction corresponding to the lesion information of at least one lesion; According to the lesion analysis instruction, the lesion information corresponding to the target lesion is determined from the lesion information of the at least two lesions.

10. A lesion auxiliary analysis device, characterized in that: The lesion auxiliary analysis device comprises: The first acquisition module is used to acquire multiple medical images collected during a target examination cycle; A detection module is used to perform lesion detection on multiple medical images and determine the lesion information of the target lesion in the target inspection period; A first determination module, configured to determine analysis information of a target lesion according to the lesion information of the target lesion; A second determination module is used to determine a target medical image based on the analysis information and multiple medical images within the target examination period; A second acquisition module is used to acquire a reference medical image corresponding to the target medical image within a reference examination period; The analysis module is used to output the pathological analysis information of the target lesion according to the analysis information corresponding to the target medical images of multiple periods and the analysis information corresponding to the corresponding reference medical images.

11. A lesion auxiliary analysis device, characterized in that: It comprises a processor and a memory, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the lesion-assisted analysis method according to any one of claims 1 to 9.

12. A computer-readable storage medium, characterized in that: The computer-readable storage medium comprises a computer program. When the computer program is run on an electronic device, the computer program is used to enable the electronic device to execute the steps of the lesion-assisted analysis method according to any one of claims 1 to 9.

Images