Examination report generation method and equipment based on medical image, and medium

Abstract

The invention relates to an examination report generation method based on a medical image. The examination report generation method comprises the following steps: S1, identifying the medical image; s2, receiving a disease type input by a user and a path marked on the medical image; s3, judging objects penetrated by the path according to the coordinates of the path and the distribution areas of the objects of the first hierarchy; s4, according to a disease type input by a user, taking the objects, the classification of which is the same as the disease type, in the superposed objects of the first level as one or more target objects penetrated by the path, and forming an integral target object based on the independent objects of the first level and the target objects; and S5, sequentially identifying the lesion conditions of the objects of the first level on the path in the whole target object, and generating an examination report of a corresponding sequence, and S6, sequentially executing the steps S1 to S5 on the object of the second hierarchy and the object of the third hierarchy. The report generation efficiency can be improved, and computing resources can be saved.

Description

Technical Field

[0001] The present invention relates to the field of intelligent medical technology, and in particular to a method, device and medium for generating an examination report based on medical images in the field of intelligent medical technology. Background Art

[0002] In the prior art, with the development of artificial intelligence technology, it has been possible to automatically identify each object in human medical images and generate an overall image report. However, this method of generating an overall image report requires and consumes a lot of computing resources, especially when the overall image involves more parts of the human body and the image data is three-dimensional image data. In addition, this indiscriminate overall recognition is also prone to output a large amount of meaningless data that is irrelevant to the diagnostic target, which not only wastes resources but also interferes with target judgment. Summary of the invention

[0003] In view of the above problems, the first aspect of the present application proposes a method for generating an examination report based on a medical image, the method comprising the following steps:

[0004] A method for generating an examination report based on a medical image, the method comprising:

[0005] S1. Identify the medical image, determine the name and distribution area of ​​the first-level objects in the medical image, and medically classify each first-level object, wherein the first-level objects include organs, and the classification includes: classifying medically related objects with lesions at the same time into the same category according to the disease type;

[0006] S2. receiving the disease type input by the user and the path marked on the medical image, and recording the coordinates of the path and the generation time of each coordinate, wherein the path runs through a plurality of first-level objects and is used to indicate the first-level object that the user is concerned about;

[0007] S3. According to the coordinates of the path and the distribution area of ​​the plurality of first-level objects, determining the independent first-level objects and the plurality of superimposed first-level objects that the path passes through;

[0008] S4. According to the disease type input by the user, the objects in the stacked first-level objects that are classified in the same way as the disease type are used as one or more target objects traversed by the path, and the overall target object is formed based on the independent first-level objects traversed by the path and the determined target objects in the stacked first-level objects; and

[0009] S5. According to the generation time of the coordinates on the path running through the overall target object, the pathological conditions of the first-level objects on the path in the overall target object are identified in sequence and an inspection report of a corresponding order is generated.

[0010] S6. Execute the steps S1-S5 on the objects of the second level and the objects of the third level in sequence, wherein the objects of the second level include lymph nodes and the objects of the third level include bones.

[0011] According to some embodiments of the present invention, the path is marked by the user's predicted direction of disease expansion based on the disease type.

[0012] According to some embodiments of the present invention, the method further includes pre-setting disease extension routes for each disease type and automatically generating a path based on the disease extension routes, wherein the disease extension routes include various objects involved in the disease type and the order in which they are involved, and the receiving of the disease type input by the user and the path marked on the medical image includes: receiving a confirmation operation of the user on the automatically generated path or receiving an adjustment operation of the user on the automatically generated path.

[0013] According to some embodiments of the present invention, the method further includes receiving symbols that the user continues to mark on the path, wherein the symbols are used to indicate the order of description of the objects in the report; sequentially identifying the lesion conditions of the corresponding objects on the path in the overall target object and generating inspection reports of a corresponding order includes sequentially identifying the lesion conditions of the corresponding objects on the path in the overall target object and generating inspection reports of a corresponding order according to the order indicated by the continued marked symbols.

[0014] According to some embodiments of the present invention, the method further comprises adding a visual enhanced medical image into the detection report, which comprises a distribution diagram of the path and the overall target object, and a highlighted diagram of the lesion area.

[0015] According to some embodiments of the present invention, the method further comprises marking the lesion condition of the object directly on the corresponding object in the visualization enhanced medical image.

[0016] According to some embodiments of the present invention, the medical image includes a two-dimensional or three-dimensional image; and the distribution area includes a two-dimensional and three-dimensional distribution area.

[0017] A second aspect of the present application provides an electronic device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the method when executing the computer program.

[0018] A third aspect of the present application provides a non-transitory computer-readable storage medium having a computer program stored thereon, wherein the computer program implements the method described when executed by a processor.

[0019] A fourth aspect of the present application provides a computer program product, including a computer program, which implements the method when executed by a processor.

[0020] Through the present invention, an examination report of the lesion area can be generated with minimal computing resources, thus saving computing resources and improving the efficiency of generating medical examination reports. Moreover, the present invention avoids possible omissions and deviations when a single doctor makes disease judgments and writes reports by classifying target objects into various disease types, thereby improving the quality of report generation. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings herein are incorporated into and constitute a part of the specification, and the accompanying drawings illustrate embodiments consistent with the present invention and are used together with the specification to explain the present invention. Elements with the same reference numerals in the accompanying drawings represent similar elements, and unless otherwise stated, the drawings in the accompanying drawings do not constitute a scale limitation.

[0022] Figure 1 A schematic flow chart showing a method for generating an examination report based on a medical image according to some embodiments of the present invention;

[0023] Figure 2a A schematic diagram showing a marked path on an organ according to some embodiments of the present invention;

[0024] Figure 2b Schematic diagram showing a marked path on an organ according to still other embodiments of the present invention;

[0025] Figure 3a A schematic diagram showing a labeled path on a lymph node according to some embodiments of the present invention;

[0026] Figure 3b A schematic diagram showing a marked path on a lymph node according to still further embodiments of the present invention;

[0027] Figure 4 A schematic structural block diagram of a medical image-based examination report generating device according to some embodiments of the present invention is shown;

[0028] Figure 5 A schematic structural diagram of a medical image-based examination report generating device according to some embodiments of the present invention is shown. DETAILED DESCRIPTION

[0029] The present invention will be exemplarily described below with reference to the accompanying drawings and in combination with embodiments. It should be noted that the embodiments and features in the embodiments in this application can be combined with each other without conflict. In addition, the described embodiments are only some embodiments of the present invention, not all embodiments.

[0030] According to some embodiments of the present invention, Figure 1 As shown, the medical image-based examination report generation method includes steps S1-S6:

[0031] S1. Identify the medical image, determine the name and distribution area of ​​the first-level objects in the medical image, and medically classify each first-level object. The classification includes: classifying medically related objects with simultaneous lesions into the same category according to the disease type.

[0032] Deep learning technology can be used for medical image recognition, for example, using convolutional neural network (CNN), U-Net and other medical image recognition models to recognize the names of different organs in medical images and their corresponding spatial distribution areas. The medical image can include a two-dimensional or three-dimensional image. The distribution area can include a two-dimensional and three-dimensional distribution area.

[0033] The classification includes: dividing medically related objects with simultaneous lesions into the same category according to the disease type. For example, organs associated with lung cancer include lungs, liver, brain, etc., lymph nodes associated with lung cancer include cervical lymph nodes, mediastinal lymph nodes, retroperitoneal lymph nodes and pelvic lymph nodes, etc., and bones associated with lung cancer include spine, pelvis, ribs, long bones of limbs, etc. For some organs, they may appear in other disease types at the same time, for example, lungs also appear in pneumonia. In this step and the following description, the organs are set to the first level, and the second and third levels mentioned later are lymph nodes and bones, respectively.

[0034] S2. Receive the disease type input by the user and the path marked on the medical image, and record the coordinates of the path and the generation time of each coordinate, wherein the path runs through multiple first-level objects and is used to indicate the first-level objects that the user is concerned about.

[0035] In the path marking operation, users can freely mark one or more paths in the medical image through a stylus, mouse or other input device. These paths are used to describe the area of ​​interest of the user (such as a doctor) or the possible path of disease progression. For three-dimensional images, three-dimensional marking can be achieved by rotating the image and introducing a depth parameter corresponding to the touch pressure on the touchpad.

[0036] like Figure 2aAs shown in FIG. 1 , the blue line shows the lung cancer path that the user is concerned about: from top to bottom, it involves the brain, lungs, and liver. In addition, according to some embodiments of the present invention, the user can select the lung cancer path according to the order of their concern (such as Figure 2b As shown in the figure, draw a path from ① to ②, and then draw a path from ① to ③. After the user completes the path marking, the geometric information of the path is recorded, which includes the spatial coordinates of each path point (expressed in two-dimensional or three-dimensional form) and its generation time.

[0037] According to some embodiments of the present invention, the core information of the path can be stored as structured data, which includes the point set, time series and basic attributes of the path. Taking JSON as an example, the data structure of the path can be expressed in the following form:

[0038]

[0039]

[0040] During the path marking process, path information may be collected and saved at certain time intervals, wherein the path information includes the coordinates of the path points and the generation time thereof.

[0041] S3. According to the coordinates of the path and the distribution areas of the plurality of first-level objects, determine the independent first-level objects and the plurality of overlapping first-level objects that the path passes through.

[0042] According to some embodiments of the present invention, a region intersection judgment algorithm based on coordinate mapping can be used to judge the penetration situation. Specifically, if the coordinates of the path point are (x, y, z), if (x, y, z) meets the conditions of the organ boundary, that is, the path point is located within the distribution area of ​​the organ, then the path is marked as intersecting with the organ. If the path point meets the boundary conditions of multiple organs at the same time, the path point is marked as an "overlapping point", and the organs that the path passes through are recorded as "overlapping organs". The independent organ penetrated by the path refers to a single organ whose distribution does not overlap with its area. For example, if a section of the path is only located in the liver area, the path point of this section is marked as independently penetrating the liver; when the path passes through the overlapping area of ​​the liver and gallbladder, the liver and gallbladder are simultaneously marked as overlapping organs.

[0043] S4. According to the disease type input by the user, objects in the superimposed first-level objects with the same classification as the disease type are taken as one or more target objects traversed by the path, and an overall target object is formed based on the independent first-level objects traversed by the path and the determined target objects in the superimposed first-level objects.

[0044] As mentioned above, all organs can be classified according to disease type. If the disease type input by the user is lung cancer, the organ whose classification among the overlapping organs on the path (i.e., classified into the category of lung cancer) is consistent with lung cancer can be used as the target organ. If both organs at the overlapping position are consistent with lung cancer, both organs are used as target organs.

[0045] S5. According to the generation time of the coordinates on the path running through the overall target object, the pathological conditions of the first-level objects on the path in the overall target object are identified in sequence and an inspection report of a corresponding order is generated.

[0046] For the overall target organ that the path passes through, the deep learning model is used to automatically detect the characteristics of the lesions. For example, a convolutional neural network (CNN) is used to detect the tumor area in lung cancer and extract features such as the tumor boundary, volume, and density distribution, such as a "low-density mass."

[0047] Afterwards, according to the generation time of the standardized template and the coordinates of the path running through the overall target organ, a corresponding examination report is generated for the lesions of the corresponding organs on the path in the overall target organ. The report content may include, for example: patient information, examination items, examination purpose, examination findings, diagnosis opinion, etc. The final generated examination report is output in PDF or electronic medical record format for further diagnosis by the user.

[0048] S6. Execute the steps S1-S5 on the objects of the second level and the objects of the third level in sequence, wherein the objects of the first level include organs (as described above), the objects of the second level include lymph nodes, and the objects of the third level include bones.

[0049] The steps before S6 are descriptions of organs as objects. In addition, since human diseases usually involve lymph nodes and bones, for example, lung cancer usually involves cervical lymph nodes, mediastinal lymph nodes, retroperitoneal lymph nodes and pelvic lymph nodes, as well as the spine, pelvis, ribs, etc. Therefore, in the present invention, steps S1-S5 are continued to generate further inspection reports for the second-level objects (bones) and the third-level objects (lymph nodes), so as to truly comprehensively and hierarchically reflect the condition. Figure 3a The path on the lymph node that the user is interested in is given. Figure 3b The digitally marked paths that users are interested in are given, including ① mediastinal lymph nodes, ② cervical lymph nodes, ③ retroperitoneal lymph nodes, and ④ pelvic lymph nodes. Figure 2a and Figure 2b The description also applies to Figure 3a and Figure 3b , for the sake of simplicity, it will not be described here.

[0050] According to some embodiments of the present invention, the method may further include adding a visual enhanced medical image to the detection report, which includes a distribution map of the path and the overall target organ, and a highlighted display map of the lesion area, to facilitate user understanding. According to some embodiments of the present invention, the lesion condition of the organ may be directly marked on the corresponding organ of the visual enhanced medical image.

[0051] In some cases, the order of the organs or paths that the user is concerned about may be different from the order of the coordinates on the path line. Therefore, according to some embodiments of the present invention, the user can continue to mark the path, such as marking numeric symbols, to indicate the order of description of the organs in the report, such as Figure 2b and Figure 3b As shown, the order of the paths that the user is concerned about is given by numbers, that is, at this time, the path (which contains the initial path annotation and the annotations that continue to be added, both of which together constitute the path) is used to indicate the order of the organs that the user is concerned about. Therefore, the method also includes receiving symbols that the user continues to annotate on the path, and the symbols are used to indicate the order of description of the organs in the report; the sequential identification of the pathological conditions of the corresponding organs on the path in the overall target organ and the generation of the inspection report in the corresponding order includes sequentially identifying the pathological conditions of the corresponding organs on the path in the overall target organ according to the order indicated by the symbols that continue to be annotated and generating the inspection report in the corresponding order.

[0052] According to some embodiments of the present invention, the method may further include pre-setting disease extension routes for various disease types and automatically generating a path based on the disease extension routes, wherein the disease extension routes include various organs involved in the disease type and the order in which they are involved, and the receiving of the disease type input by the user and the path marked on the medical image includes: receiving a user confirmation operation on the automatically generated path; or, receiving a user adjustment operation on the automatically generated path, for example, by slightly dragging the path line to make the path line meet the user's expectations.

[0053] According to some embodiments of the present invention, the path may be marked by the user according to the disease type and the predicted disease extension direction, such as Figure 2b and Figure 3b As shown, it can be assumed that the multiple digital symbols represent the user's sequential marking of the expansion direction of a certain disease condition.

[0054] Through the present invention, an examination report of the lesion area can be generated with minimal computing resources, thus saving computing resources and improving the efficiency of generating medical examination reports. Moreover, the present invention avoids possible omissions and deviations when a single doctor makes disease judgments and writes reports by classifying target objects into various disease types, thereby improving the quality of report generation.

[0055] Figure 4 FIG. 5 is a schematic structural block diagram of a medical image-based examination report generating device 5000 according to some embodiments of the present invention. Figure 4 As shown, the medical image-based examination report generating device 5000 may include: an organ classification unit 5001, an input acquisition unit 5002, a judgment unit 5003 and a report generating unit 5004.

[0056] The organ classification unit 5001 is used to identify the medical image, determine the name and distribution area of ​​each organ in the medical image, and perform medical classification on each organ.

[0057] The input acquisition unit 5002 is used to receive the disease type input by the user and the path marked on the medical image, and record the coordinates of the path and the generation time of each coordinate. The path runs through multiple organs and is used to indicate the organ that the user is concerned about.

[0058] The judgment unit 5003 is used to judge the independent organs and the multiple superimposed organs penetrated by the path according to the coordinates of the path and the distribution areas of the multiple organs; according to the disease type input by the user, the organ in the superimposed organs classified with the same disease type as one of the target organs penetrated by the path; and the overall target organ is formed based on the independent organs penetrated by the path and the target organs in the determined superimposed organs.

[0059] The report generating unit 5004 is used to sequentially identify the pathological conditions of corresponding organs on the path in the overall target organ according to the generation time of the coordinates on the path passing through the overall target organ and generate a corresponding examination report.

[0060] The corresponding detailed descriptions made with reference to the various figures above are included here by reference, and more corresponding detailed functions can be realized by adding corresponding functional units or modules, or by further limiting the above units, which will not be repeated here.

[0061] Figure 5 FIG. 6 is a schematic structural diagram of a medical image-based examination report generating device 6000 according to some embodiments of the present invention. Figure 5 As shown, the device includes a processor 6051, a memory 6052 and a bus 6053.

[0062] In some examples, the device may also include an input device 6001, an input port 6002, an output port 6003, and an output device 6004. The input port 6002, the processor 6051, the memory 6052, and the output port 6003 are connected via a bus 6053, and the input device 6001 and the output device 6004 are connected to the bus 6053 via the input port 6002 and the output port 6003, respectively, and then connected to other components of the device. It should be noted that the output interface and the input interface here can also be represented by an I / O interface. Specifically, the input device 6001 receives input information from the outside, and transmits the input information to the processor 6051 via the input port 6002; the processor 6051 processes the input information based on the computer executable instructions stored in the memory 6052 to generate output information, temporarily or permanently stores the output information in the memory 6052, and then transmits the output information to the output device 6004 via the output port 6003.

[0063] The above-mentioned memory 6052 includes a large capacity memory for data or instructions. For example, but not limitation, the memory 6052 may include a HDD, a floppy disk drive, a flash memory, an optical disk, a magneto-optical disk, a tape or a universal serial bus (USB) drive or a combination of two or more of these. In appropriate cases, the memory 6052 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 6052 may be inside or outside the device. In a specific embodiment, the memory 6052 is a non-volatile solid-state memory. In a specific embodiment, the memory 6052 includes a read-only memory (ROM). In appropriate cases, the ROM may be a mask-programmed ROM, a programmable ROM (PROM), an erasable PROM (EPROM), an electrically erasable PROM (EEPROM), an electrically rewritable ROM (EAROM) or a flash memory or a combination of two or more of these.

[0064] The bus 6053 includes hardware, software or both, coupling the components to each other. For example and not limitation, the bus 6053 may include an accelerated graphics port (AGP) or other graphics bus, an enhanced industry standard architecture (EISA) bus, a front-side bus (FSB), a hypertransport (HT) interconnect, an industry standard architecture (ISA) bus, an infinite bandwidth interconnect, a low pin count (LPC) bus, a memory bus, a microchannel architecture (MCA) bus, a peripheral component interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a serial advanced technology attachment (SATA) bus, a video electronics standard association local (VLB) bus or other suitable bus or a combination of two or more of these. Although the embodiments of the present invention describe and illustrate a specific bus, the present invention contemplates any suitable bus or interconnect.

[0065] The processor 6051 performs the following actions based on the computer program stored in the memory 6052:

[0066] S1. Identify the medical image, determine the name and distribution area of ​​the first-level objects in the medical image, and medically classify each first-level object, wherein the first-level objects include organs, and the classification includes: classifying medically related objects with lesions at the same time into the same category according to the disease type;

[0067] S2. receiving the disease type input by the user and the path marked on the medical image, and recording the coordinates of the path and the generation time of each coordinate, wherein the path runs through a plurality of first-level objects and is used to indicate the first-level object that the user is concerned about;

[0068] S3. According to the coordinates of the path and the distribution area of ​​the plurality of first-level objects, determining the independent first-level objects and the plurality of superimposed first-level objects that the path passes through;

[0069] S4. According to the disease type input by the user, the objects in the stacked first-level objects that are classified in the same way as the disease type are used as one or more target objects traversed by the path, and the overall target object is formed based on the independent first-level objects traversed by the path and the determined target objects in the stacked first-level objects; and

[0070] S5. According to the generation time of the coordinates on the path running through the overall target object, sequentially identify the pathological conditions of the first-level objects on the path in the overall target object and generate an inspection report in a corresponding order;

[0071] S6. Execute the steps S1-S5 on the objects of the second level and the objects of the third level in sequence, wherein the objects of the second level include lymph nodes and the objects of the third level include bones.

[0072] According to some further embodiments of the present invention, the computer program may be divided into one or more units in various ways and stored in the memory, and executed by the processor to complete the present invention. The one or more units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the device. The computer program may be divided into one or more units in various ways and stored in the memory, and executed by the processor to complete the present invention. The one or more units may be a series of computer program instruction segments capable of completing specific functions, and the instruction segments are used to describe the execution process of the computer program in the device. Figure 5 The functions of each unit in each embodiment described are divided into multiple units, or include the aforementioned reference Figure 5 For the sake of simplicity, the various units in the various embodiments described are not repeated here.

[0073] The processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or the processor may be any conventional processor, etc. The processor is the control center of the device, and various interfaces and lines are used to connect the various parts of the entire device. The device may be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server, or a part thereof. The device may include, but is not limited to, a processor and a memory. Those skilled in the art will appreciate that the schematic diagram is merely an example of the device and does not constitute a limitation on the device.

[0074] The corresponding detailed descriptions made above with reference to the various figures are incorporated herein by reference and will not be repeated here.

[0075] The present application also proposes a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the following steps are implemented:

[0076] S1. Identify the medical image, determine the name and distribution area of ​​the first-level objects in the medical image, and medically classify each first-level object, wherein the first-level objects include organs, and the classification includes: classifying medically related objects with lesions at the same time into the same category according to the disease type;

[0077] S2. receiving the disease type input by the user and the path marked on the medical image, and recording the coordinates of the path and the generation time of each coordinate, wherein the path runs through a plurality of first-level objects and is used to indicate the first-level object that the user is concerned about;

[0078] S3. According to the coordinates of the path and the distribution area of ​​the plurality of first-level objects, determining the independent first-level objects and the plurality of superimposed first-level objects that the path passes through;

[0079] S4. According to the disease type input by the user, the objects in the stacked first-level objects that are classified in the same way as the disease type are used as one or more target objects traversed by the path, and the overall target object is formed based on the independent first-level objects traversed by the path and the determined target objects in the stacked first-level objects; and

[0080] S5. According to the generation time of the coordinates on the path running through the overall target object, sequentially identify the pathological conditions of the first-level objects on the path in the overall target object and generate an inspection report in a corresponding order;

[0081] S6. Execute the steps S1-S5 on the objects of the second level and the objects of the third level in sequence, wherein the objects of the second level include lymph nodes and the objects of the third level include bones.

[0082] The corresponding detailed descriptions made above with reference to the various figures are incorporated herein by reference and will not be repeated here.

[0083] The computer program includes computer program code, which may be in source code form, object code form, executable file or some intermediate form, etc. The computer readable medium may include: any entity or device capable of carrying the computer program code, recording medium, USB flash drive, mobile hard disk, magnetic disk, optical disk, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal and software distribution medium, etc.

[0084] Through the present invention, an examination report of the lesion area can be generated with minimal computing resources, thus saving computing resources and improving the efficiency of generating medical examination reports. By classifying the target objects into various disease types and other actions, possible omissions and deviations that may exist when a single doctor makes disease judgments and writes reports are avoided as much as possible, thereby improving the quality of report generation.

[0085] It should be noted that although the structure of the apparatus of the present invention and the method of its operation are described in a specific order in the accompanying drawings, this does not require or imply that these operations must be performed in this specific order, or that all the operations shown must be performed to achieve the desired results. On the contrary, the steps depicted in the flow chart can be changed in the order of execution. Additionally or alternatively, some steps can be omitted, multiple steps can be combined into one step, and / or one step can be decomposed into multiple steps.

[0086] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. For those skilled in the art, the present invention may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for generating an examination report based on a medical image, the method comprising: S1. Identify the medical image, determine the name and distribution area of ​​the first-level objects in the medical image, and medically classify each first-level object, wherein the first-level objects include organs, and the classification includes: classifying medically related objects with lesions at the same time into the same category according to the disease type; S2. receiving the disease type input by the user and the path marked on the medical image, and recording the coordinates of the path and the generation time of each coordinate, wherein the path runs through a plurality of first-level objects and is used to indicate the first-level object that the user is concerned about; S3. According to the coordinates of the path and the distribution area of ​​the plurality of first-level objects, determining the independent first-level objects and the plurality of superimposed first-level objects that the path passes through; S4. According to the disease type input by the user, the objects in the stacked first-level objects that are classified in the same way as the disease type are used as one or more target objects traversed by the path, and the overall target object is formed based on the independent first-level objects traversed by the path and the determined target objects in the stacked first-level objects; and S5. According to the generation time of the coordinates on the path running through the overall target object, sequentially identify the pathological conditions of the first-level objects on the path in the overall target object and generate an inspection report in a corresponding order; S6. Execute the steps S1-S5 on the objects of the second level and the objects of the third level in sequence, wherein the objects of the second level include lymph nodes and the objects of the third level include bones.

2. The method according to claim 1, wherein: The paths are marked by the user's predicted direction of disease expansion based on disease type.

3. The method according to claim 1, further comprising presetting a disease extension route for each disease type and automatically generating a path according to the disease extension route, wherein the disease extension route includes each object involved in the disease type and the order in which it is involved, and the path for receiving the disease type input by the user and the path marked on the medical image comprises: A confirmation operation of the automatically generated path is received from the user, or an adjustment operation of the automatically generated path is received from the user.

4. The method according to claim 1 further includes receiving symbols that the user continues to mark on the path, and the symbols are used to indicate the order of description of the objects in the report; the sequentially identifying the lesion conditions of the corresponding objects on the path in the overall target object and generating an inspection report of a corresponding order includes sequentially identifying the lesion conditions of the corresponding objects on the path in the overall target object and generating an inspection report of a corresponding order according to the order indicated by the continued marked symbols.

5. The method according to claim 1 further includes adding a visual enhanced medical image to the detection report, which includes a distribution map of the path and the overall target object, and a highlighted map of the lesion area. 6 . The method according to claim 5 , further comprising directly marking the pathological condition of the object on the corresponding object in the visualization enhanced medical image.

7. The method according to claim 1, wherein the medical image comprises a two-dimensional or three-dimensional image; and the distribution area comprises a two-dimensional and three-dimensional distribution area.

8. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the computer program, the method according to any one of claims 1 to 6 is implemented.

9. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

10. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images