Pathological digital section manufacturing method, electronic equipment, storage medium and program product
By using a digital slice scanner to obtain the coordinates of key areas and establish local three-dimensional images, the problems of blurry and time-consuming two-dimensional digital slices in existing technologies are solved, and clearer and faster three-dimensional pathology digital slice production is achieved to meet the needs of pathology reading.
Patent Information
- Application Number
- CN202510960529.6
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2025-07-11
- Publication Date
- 2025-10-17
AI Technical Summary
The existing two-dimensional digital slice scanning technology is prone to forming local blurred areas, and the multi-layer focus fusion scanning technology is time-consuming and the final image is still a two-dimensional image, which is difficult to meet the pathology teacher's needs for careful observation of key areas.
A digital slice scanner is used for rough scanning to obtain the coordinates of key areas, and a local three-dimensional image is established through fine scanning. The three-dimensional image is generated using three-dimensional reconstruction technology, and the local three-dimensional digital slice image is formed by combining image fusion technology.
The generated images are clearer, take less time, can better meet the pathology teacher's needs for observing key areas, and provide a three-dimensional effect.
Smart Images

Figure CN120809104A_ABST
Abstract
Description
TECHNICAL FIELD
[0001] The present application relates to the technical field of medical pathology, and in particular to a pathological digital slice making method, an electronic device, a storage medium and a program product. BACKGROUND
[0002] A pathological section is a thin slice with uniform thickness obtained by cutting a tissue after dehydration and embedding treatment, and is encapsulated on a slide surface after staining, and is commonly used for microscopic observation of tissue structure and cell morphology to determine the type of disease. The pathological section is a physical slide, and the digitization of the section can be achieved by scanning under a high-power microscope. Pathological digital slices are convenient for storage and data exchange, and have been widely used in pathological remote consultation, pathological digital slice archiving and other scenarios.
[0003] The commonly used technologies for pathological section digitization currently include two-dimensional digital slice scanning technology and multi-layer focus fusion scanning technology. The two-dimensional digital slice scanning technology is to splice images of different areas of a section collected by a CCD into a two-dimensional digital slice, and the main disadvantage is that local fuzzy areas are easily formed, which are often areas that need to be observed in detail. The multi-layer focus fusion scanning technology is to collect images of the same area and different focal lengths by a CCD, and fuse them into a relatively clear image by image fusion technology. The same method is used for different areas, and finally a large digital slice image is spliced.
[0004] When a pathology teacher reviews a two-dimensional digital slice and wants to observe the key areas in detail, the problem of fuzzy areas and lack of stereoscopic effect often occurs, making it difficult for the pathology teacher to accurately diagnose. SUMMARY
[0005] Embodiments of the present application provide a pathological digital slice making method, an electronic device and a readable storage medium, to solve the problem that current digital slice technology cannot fully meet the needs of pathology teachers in reviewing slices.
[0006] Therefore, according to one aspect of the present application, a pathological digital slice making method is provided, comprising the following steps:
[0007] S1. Using a digital slice scanner to perform coarse scanning on the slice, analyzing and processing the collected images, finding key areas and recording the coordinates of the key areas, the key areas being cell cluster areas in cytological sections or suspected positive areas in histological sections;
[0008] S2. Using a digital slice scanner to perform fine scanning on the slice, collecting multiple images of different focal lengths for the key areas, and collecting a single image for non-key areas;
[0009] S3. The multiple images of different focal lengths of the key areas are generated into a three-dimensional image through three-dimensional reconstruction technology, and the three-dimensional image is combined with the single image of the non-key area to form a local three-dimensional digital slice image.
[0010] Optionally, in step S1, the collected image is analyzed and processed to find the key area and record the coordinates of the key area, specifically comprising:
[0011] During the scanning process, the key area is detected by the trained detection model, the identified key area is screened through image processing, and the specific coordinates of the key area are recorded and then subjected to coordinate conversion.
[0012] Optionally, before using the digital slice scanner to perform rough scanning on the slice, the method further comprises constructing and training the detection model: first, a data set labeled with the key area is established, then a detection model is constructed, and the data set is trained to enable the detection model to detect the key area.
[0013] Optionally, when screening through image processing, the screening conditions are as follows:
[0014] α·A+β·C+γ·D>T
[0015] Wherein: A is the area, C is the color ratio, D is the definition ratio, α, β, γ are different coefficients, T is the threshold value, all variables are real numbers, α≠β≠γ≠0, the ratio parameters (C, D) need to be standardized to the same dimension.
[0016] Optionally, the formula of the coordinate conversion is as follows:
[0017] (xn, yn) = n / m*(xm, ym)
[0018] Scanning area: two-dimensional plane [0, Lx] x [0, Ly], starting coordinate (0, 0), and ending coordinate (Lx, Ly);
[0019] Original magnification: m;
[0020] Target magnification: n;
[0021] Image coordinates: (xm, ym) is the coordinate in the m-times lens spliced image, and (xn, yn) is the coordinate in the n-times lens spliced image.
[0022] Optionally, step S3 specifically comprises the following steps:
[0023] S31. The multiple images of different focal lengths of the key areas are generated into a three-dimensional image through three-dimensional reconstruction technology, and the three-dimensional image is combined with the single image of the non-key area to form a local three-dimensional digital slice image;
[0024] S32. In constructing the three-dimensional image, the multiple images of different focal lengths collected in each of the focus areas are converted into height z according to a conversion formula of pixel value height by comparing the pixel gray value of the same two-dimensional coordinate between different focal lengths, so as to obtain the height of all layer pixel points;
[0025] S33. After the z value is calculated, the z value is added to each pixel of the clear image generated in step S31 under the condition that (x, y) remains unchanged, that is, (x, y, z), a three-dimensional image format is generated according to the given three-dimensional coordinates, saved down, and named according to the coordinates of the focus area;
[0026] S34. The coordinates of the focus area recorded by scanning are added to the two-dimensional digital slice image generated in step S31, a mouse-over event is set in the program, a three-dimensional image prompt is given when the mouse is over the focus area, and local three-dimensional image viewing is performed through the mouse event.
[0027] Optionally, in step S32, the conversion formula is as follows:
[0028] z = round(f(min(x, y)) + c x k)
[0029] In the formula, z represents height, f represents a height comparison function, min(x, y) represents the minimum value of (x, y) coordinates, c represents clarity, k represents a coefficient, and round() represents a rounding function.
[0030] According to another aspect of the present application, an electronic device is provided, which comprises a memory and a processor, the memory stores a computer program executable on the processor, and the processor implements the steps of the method according to any one of the above when executing the computer program.
[0031] According to another aspect of the present application, a computer readable storage medium is provided, which stores a computer program, and the computer program is executed by a processor to implement the steps of the method according to any one of the above.
[0032] According to another aspect of the present application, a computer program product is provided, which comprises computer instructions, and the computer instructions are executed by a processor to implement the steps of the method according to any one of the above.
[0033] The pathological digital slice production method, electronic device and readable storage medium provided by the present application have the following beneficial effects:
[0034] The key area coordinates are obtained by rough scanning the section by using a digital section scanner, and then a local three-dimensional image is established by fine scanning, and the needs of the pathological teacher to carefully observe the key area are met by establishing a local three-dimensional image of the key area. Compared with two-dimensional digital sections, the image obtained by the pathological digital section manufacturing method of the application is clearer, compared with the multi-layer fusion scanning technology, the time is shorter, more attention is paid to the key area, and a three-dimensional image is formed, which can better meet the needs of pathological reading. BRIEF DESCRIPTION OF DRAWINGS
[0035] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor.
[0036] Among them:
[0037] Figure 1 is a flow chart of the pathological digital section manufacturing method shown in an embodiment of the present application;
[0038] Figure 2 is a flow chart of step S3 in the pathological digital section manufacturing method shown in an embodiment of the present application;
[0039] Figure 3 is an image schematic diagram obtained after rough scanning in the pathological digital section manufacturing method shown in an embodiment of the present application;
[0040] Figure 4 is an image schematic diagram obtained after fine scanning in the pathological digital section manufacturing method shown in an embodiment of the present application;
[0041] Figure 5 is a structural schematic diagram of an electronic device shown in an embodiment of the present application. DETAILED DESCRIPTION
[0042] In order to facilitate understanding of the present application, the present application will be described more fully with reference to the related drawings. The preferred embodiments of the present application are shown in the drawings. However, the present application can be realized in many other different forms, and is not limited to the embodiments described herein. On the contrary, the purpose of providing these embodiments is to make the disclosure of the present application more thorough and comprehensive.
[0043] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs; the terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of this application; the use of the terms "including," "comprising," "having" and "with" in this specification and the appended claims are used synonymously to mean "including, but not limited to."
[0044] In addition, the terms "first", "second", etc. are used herein only to describe various embodiments and are not intended to, nor should they be construed to, connote relative importance or imply the number of indicated technical features. Thus, features defined with "first", "second", etc. can include one or more of the features. In the description of the application, the meaning of "a plurality" is two or more, unless otherwise expressly specified.
[0045] Reference herein to "an embodiment" means that a particular feature, structure, or characteristic described in connection with the embodiment can be included in at least one embodiment of the application. The appearances of the phrase "in an embodiment" in various places in the specification are not necessarily all referring to the same embodiment, nor are they necessarily mutually exclusive of one another. It is expressly understood that any of the embodiments described herein can be combined with any of the other embodiments.
[0046] As described in the background, in the related art, the two-dimensional digital slice scanning technology is prone to form a locally blurred area, and the blurred area is often an area that needs to be observed carefully; the multi-layer focus fusion scanning technology collects a large number of layers and takes a long time, and finally forms a two-dimensional digital slice image. When the pathology teacher reviews the two-dimensional digital slice and wants to carefully observe the key area, the pathology teacher often encounters the problems of blurred area and insufficient stereoscopic effect, which makes it difficult for the pathology teacher to accurately diagnose.
[0047] To solve the above problems, according to one aspect of the application, the embodiment of the application provides a pathological digital slice manufacturing method, as shown in the figure, the method comprises the following steps: Figure 1
[0048] S1. Use a digital slice scanner to perform a rough scan on the slice, analyze and process the collected image, find a key area and record the coordinates of the key area, the key area being a cell cluster area in a cytological slice or a suspected positive area in a histological slice.
[0049] S2. Use a digital slice scanner to scan the slice, and collect a single image for non-key areas; collect multiple images with different focal lengths for key areas. Specifically, the objective lens can remain stationary on the x and y axes, and collect images with different focal lengths by adjusting the z axis. It should be understood that the focal length is adjusted by adjusting the height of the z axis of the objective lens. The adjustment interval is usually between 20-50mm. Within a certain range of focal length adjustment, the smaller the interval, the more images that need to be collected, the richer the image information obtained, and the longer the time consumed. Conversely, the larger the interval, the fewer images that need to be collected, the less image information obtained, and the faster the time. However, it is easy to miss the clearest layer. This interval value can be set in advance according to the task requirements.
[0050] S3. Generate a three-dimensional image by three-dimensional reconstruction technology from the multiple images with different focal lengths collected for the key areas, and combine the three-dimensional image with the single image collected for the non-key areas to form a local three-dimensional digital slice image.
[0051] In a specific embodiment, before using the digital slice scanner to scan the slice, the method further comprises detecting the construction and training of a model: first, a data set with key areas labeled is established, then a detection model (i.e. a target detection model, generally a yolo series) is constructed, and the data set is trained so that the detection model can detect the key areas.
[0052] In step S1, the collected images are analyzed and processed to find the key areas and record the coordinates of the key areas. Specifically, the key areas are detected by the trained detection model during scanning, the identified key areas are filtered by image processing, and the specific coordinates of the key areas are recorded and then converted.
[0053] It should be noted that the coarse scanning is used to obtain the coordinates of the key areas, and the fine scanning is used to establish a local three-dimensional image. In a specific implementation, in step S1, when the digital slice scanner is used to coarsely scan the slice, an objective lens with a magnification of less than 20 times (in this embodiment, a 5x lens) is used, the resolution is set to 1K, the scanning speed is set to 10 fields per second, and the trained detection model is used to detect the key areas during scanning. Figure 3 As shown in the figure, the gray part represents the overlapping or suspected area in this field of view.
[0054] Coarse scanning: Coarse scanning uses a low-power lens to collect images of the target area, and only one image is collected for each field of view. The key areas are detected by the trained detection model during scanning, the identified key areas are filtered by image processing algorithm, and the specific coordinates are recorded and then converted.
[0055] When filtering by image processing, the filtering conditions are as follows:
[0056] α·A+β·C+γ·D>T
[0057] Where: A is the detected area, C is the color ratio, D is the clarity ratio, α, β, and γ are different coefficients, T is the threshold, all variables are real numbers, α≠β≠γ≠0, and ratio parameters (C, D) need to be normalized to the same dimension (such as the interval [0,1]).
[0058] Optionally, the coordinate transformation formula is as follows:
[0059] (xn,yn)=n / m*(xm,ym)
[0060] Scanning area: two-dimensional plane [0, Lx] × [0, Ly], starting point coordinates are (0, 0), and end point coordinates are (Lx, Ly);
[0061] Original magnification: m;
[0062] Target magnification: n;
[0063] Image coordinates: (xm, ym) are the coordinates in the m-fold stitched image, and (xn, yn) are the coordinates in the n-fold stitched image.
[0064] In step S2, when using a digital slide scanner to perform a precise scan of the slice, a 20x objective lens or higher is used (a 20x objective lens is used in this embodiment), the resolution is set to 4K, the scanning speed is set to 15 fields per second, the number of scanning layers is 20, and the z-axis spacing is 20 microns. Figure 4 As shown in the figure, the gray part indicates that the field of view is the key area and requires multi-layer scanning.
[0065] Precision Scan Instructions: After detecting key areas through rough scanning, record the coordinates and convert them using the formula (e.g. Figure 4 The gray part shown is the key area after the coordinate conversion. By replacing the high-power lens for scanning, only one image is collected for the non-key area, and multiple images (such as 20) are collected for the key area. While the x and y axes remain unchanged, the z axis is adjusted to collect images with different focal length values.
[0066] like Figure 2 As shown, the image processing process after fine scanning, that is, step S3, specifically includes the following steps:
[0067] S31. Multiple images of different focal lengths collected from each key area are fused to generate a clear image, which is then stitched together with the single image collected from the non-key area to form a two-dimensional digital slice image;
[0068] S32. When constructing the three-dimensional image, the multiple images of different focal lengths collected in each focus area are compared in terms of the pixel gray value of the same two-dimensional coordinate, and the pixel points are converted into height z according to the conversion formula of pixel value height, so as to obtain the height of all layer pixel points. Taking the image with the smallest focal length as the reference height 0, the pixel gray value of the same two-dimensional coordinate between different focal lengths is compared first, and the focal length when the minimum value of each pixel under the same two-dimensional coordinate is recorded, which is the preliminary height at this time. Then, the difference between the pixel value and the surrounding pixel value at the minimum focal length is calculated to correct the height error, that is, the value of z in the coordinate;
[0069] S33. After calculating the z value, the z value is added to each pixel of the clear image generated in step S31 under the condition that (x, y) remains unchanged, that is, (x, y, z), according to the given three-dimensional coordinates, a three-dimensional image format is generated and saved, and is named according to the coordinates of the focus area for easy calling;
[0070] S34. The coordinates of the focus area recorded by scanning are added to the two-dimensional digital slice image generated in step S31. A mouse-over event is set in the program. When the mouse is over the focus area, a three-dimensional image prompt is given, and the local three-dimensional image is viewed through the mouse event.
[0071] In step S32, the conversion formula is as follows:
[0072] z = round(f(min(x, y)) + c x k)
[0073] In the formula, z represents the height, f represents the height comparison function, min(x, y) represents the minimum value of the (x, y) coordinate, c represents the definition, k represents the coefficient, and round() represents the rounding function.
[0074] As can be seen from the above, the three-dimensional reconstruction technology in the present patent application is similar to the radar scanning mode, and the gradual change of the image gray value in the focusing process is taken as the reflection signal to construct a three-dimensional image, which is simple and has high resolution. Although the collected image is two-dimensional, the slice is not completely two-dimensional, but has a slight depth. The process of adjusting the focal length is the process of adjusting the depth of shooting. The principle is similar to that of a satellite scanning a three-dimensional map from the sky. The target height is determined by the radar reflection signal to construct a three-dimensional map. The two-dimensional image obtained by adjusting the focal length during the scanning of the slice will produce a gradual change process, and the pixel value and definition will change. This pixel value and definition can be used to determine the depth of the target, so as to construct a three-dimensional image.
[0075] The existing three-dimensional reconstruction technology is generally divided into two kinds, one is to build a three-dimensional image by multi-view two-dimensional images, which is relatively complex to realize, needs to shoot the target from multiple angles, and the reconstruction process is more dependent on the shooting angle and algorithm, and is easy to form distortion. The other is a radar scanning mode, which uses reflected signals to construct a three-dimensional image, which is relatively simple to realize, but has low resolution.
[0076] In summary, the pathological digital slice production method provided by the embodiment of the application uses a digital slice scanner to perform rough scanning on the slice to obtain key area coordinates, and then performs fine scanning to establish a local three-dimensional image. The key area is established to meet the demand of the pathological teacher to carefully observe the key area. Compared with a two-dimensional digital slice, the image obtained by the pathological digital slice production method is clearer, and compared with a multi-layer fusion scanning technology, the time consumption is shorter, the key area is paid more attention to, and a three-dimensional image is formed, which can better meet the pathological reading demand.
[0077] In addition, the embodiment of the application further provides an electronic device, such as Figure 5 As shown in the figure, the electronic device 6 includes a memory 602 and a processor 601, the memory 602 stores a computer program 603 executable on the processor, and the processor 601 implements the steps of the pathological digital slice production method according to any one of the above when executing the computer program 603.
[0078] The electronic device 6 can be a desktop computer, a notebook computer, a palm computer, a cloud server and the like. The electronic device 6 can include but is not limited to a processor 601 and a memory 602. Those skilled in the art can understand that Figure 5 The electronic device 6 is only an example and does not constitute a limitation on the electronic device 6, and can include more or fewer components than the figure, or combine certain components, or different components, for example, can also include input / output devices, network access devices and the like.
[0079] The processor 601 can be a central processing unit (CPU), and the processor 601 can also be other general-purpose processors 601, digital signal processors 601 (DSP), application specific integrated circuits (ASIC), field programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor 601 can be a microprocessor or can also be any conventional processor 601 or the like.
[0080] The memory 602 may, in some embodiments, be an internal storage unit of the electronic device 6, such as a hard disk or a memory of the electronic device 6. The memory 602 may, in other embodiments, also be an external storage device of the electronic device 6, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) card, a Flash Card, and the like equipped on the electronic device 6. Further, the memory 602 may also include both an internal storage unit and an external storage device of the electronic device 6. The memory 602 is used to store an operating system, application programs, a Boot Loader, data, and other programs, such as program codes of the computer program 603 and the like. The memory 602 may also be used to temporarily store data that has been output or is to be output.
[0081] The present application also provides a computer readable storage medium for storing a computer program. The computer readable storage medium can be applied to a computer device, and the computer program causes the computer device to perform the corresponding procedures in the detection method in the embodiments of the present application. For brevity, details are not repeated here.
[0082] The present application also provides a computer program product, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device performs the corresponding procedures in the detection method in the embodiments of the present application. For brevity, details are not repeated here.
[0083] The present application also provides a computer program, which includes computer instructions stored in a computer readable storage medium. A processor of a computer device reads the computer instructions from the computer readable storage medium, and the processor executes the computer instructions, so that the computer device performs the corresponding procedures in the detection method in the embodiments of the present application. For brevity, details are not repeated here.
[0084] It should be understood that the processor of the embodiments of the present application can be an integrated circuit chip with a signal processing capability.
[0085] In the implementation process, each step of the above method embodiments can be completed by integrated logic circuits of hardware in the processor or instructions in the form of software. The above processor can be a general-purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), a field programmable gate array (FPGA) or other programmable logic devices, discrete gates or transistor logic devices, discrete hardware components. The disclosed methods, steps and logic block diagrams in the embodiments of the present application can be implemented or executed. The general-purpose processor can be a microprocessor or the processor can also be any conventional processor. The steps of the method disclosed in combination with the embodiments of the present application can be directly embodied as hardware decoding processor for execution, or executed by hardware and software modules in the decoding processor. The software module can be located in the random access memory, flash memory, read-only memory, programmable read-only memory or electrically erasable programmable memory, register and other mature storage media in the art. The storage medium is located in the memory, and the processor reads the information in the memory, and combines the hardware to complete the steps of the above pathological digital section making method.
[0086] It is to be understood that the memory in the embodiments of the present application can be a volatile memory or a nonvolatile memory, or can include both volatile and nonvolatile memory. Among them, the nonvolatile memory can be a read-only memory (Read-Only Memory, ROM), a programmable read-only memory (Programmable ROM, PROM), an erasable programmable read-only memory (Erasable PROM, EPROM), an electrically erasable programmable read-only memory (Electrically EPROM, EEPROM) or a flash memory. The volatile memory can be a random access memory (Random Access Memory, RAM) used as an external cache. By way of example, but not limitation, many forms of RAM are available, such as static random access memory (Static RAM, SRAM), dynamic random access memory (Dynamic RAM, DRAM), synchronous dynamic random access memory (Synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (Double Data Rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (Enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (Synchlink DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM). It should be noted that the memory of the system and method described herein is intended to include, but not limited to, these and any other suitable types of memory.
[0087] It should be understood that the above-mentioned memory is exemplary but not limiting, for example, the memory in the embodiments of the present application can also be static random access memory (static RAM, SRAM), dynamic random access memory (dynamic RAM, DRAM), synchronous dynamic random access memory (synchronous DRAM, SDRAM), double data rate synchronous dynamic random access memory (double data rate SDRAM, DDR SDRAM), enhanced synchronous dynamic random access memory (enhanced SDRAM, ESDRAM), synchronous link dynamic random access memory (synch link DRAM, SLDRAM) and direct memory bus random access memory (Direct Rambus RAM, DR RAM) and the like. That is, the memory in the embodiments of the present application is intended to include, but not limited to, these and any other suitable types of memory.
[0088] Those skilled in the art will appreciate that the modules and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered beyond the scope of this application.
[0089] Those skilled in the art will clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and modules described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.
[0090] In the several embodiments provided in this application, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are merely schematic. For example, the division of the modules is merely a logical function division. In actual implementation, there may be other division methods, such as multiple modules or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or modules, which can be electrical, mechanical or other forms.
[0091] The modules described as separate components may or may not be physically separate, and the components shown as modules may or may not be physical modules, that is, they may be located in one place or distributed across multiple network elements. Some or all of the modules may be selected to achieve the purpose of the solution of this embodiment according to actual needs.
[0092] In addition, each functional module in the embodiment of the present application may be integrated into one processing module, or each module may exist physically separately, or two or more modules may be integrated into one module.
[0093] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a cloud server) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes various media that can store program codes, such as a USB flash drive, a mobile hard drive, a ROM, a RAM, a magnetic disk, or an optical disk.
[0094] The above description is only specific embodiments of the present application, but the protection scope of the present application is not limited thereto, any person skilled in the art can easily think of changes or replacements within the technical scope disclosed by the present application, which should be covered in the protection scope of the present application. Therefore, the protection scope of the present application should be subject to the protection scope of the claims.
Claims
1. A method for producing pathological digital slices, characterized in that: The following steps are involved: S1. Scan the slides using a digital slide scanner, analyze and process the acquired images, identify key areas, and record their coordinates. The key areas are cell clusters in cytological slides or suspected positive areas in histological slides. S2. Use a digital slide scanner to scan the slices, collect multiple images of different focal lengths for the key areas, and collect a single image for non-key areas; S3. Generate a three-dimensional image by using three-dimensional reconstruction technology from multiple images of different focal lengths collected from the key area, and combine the three-dimensional image with a single image collected from a non-key area to form a local three-dimensional digital slice image.
2. The method for producing pathological digital slices according to claim 1, characterized in that: In step S1, analyzing and processing the collected image, finding the key area and recording the coordinates of the key area specifically include: During the scanning process, the key areas are detected by the trained detection model, the identified key areas are screened through image processing, and the specific coordinates of the key areas are recorded and then coordinate conversion is performed.
3. The method for producing pathological digital slices according to claim 2, characterized in that: Before using a digital slide scanner to perform a rough scan of the slice, the detection model is also constructed and trained: first, a data set with the key areas marked is established, and then a detection model is constructed and the data set is trained so that the detection model can detect the key areas.
4. The method for producing pathological digital slices according to claim 2, characterized in that: When filtering by image processing, the filtering conditions are as follows: α·A+β·C+γ·D>T Where: A is the area, C is the color ratio, D is the clarity ratio, α, β, and γ are different coefficients, T is the threshold, all variables are real numbers, α≠β≠γ≠0, and ratio parameters (C, D) must be normalized to the same dimension.
5. The method for producing pathological digital slices according to claim 2, characterized in that: The coordinate transformation formula is as follows: (xn,yn)=n / m*(xm,ym) Scanning area: two-dimensional plane [0, Lx] × [0, Ly], starting point coordinates are (0, 0), and end point coordinates are (Lx, Ly); Original magnification: m; Target magnification: n; Image coordinates: (xm, ym) are the coordinates in the m-fold stitched image, and (xn, yn) are the coordinates in the n-fold stitched image.
6. The method for producing pathological digital slices according to claim 1, characterized in that: Step S3 specifically includes the following steps: S31. Multiple images of different focal lengths collected from the key areas are fused to generate a clear image, which is then stitched together with a single image collected from a non-key area to form a two-dimensional digital slice image; S32. When constructing a three-dimensional image from multiple images of different focal lengths collected at the key areas, the grayscale values of pixels at the same two-dimensional coordinates at different focal lengths are compared, and the pixel values are converted to height z according to the pixel value height conversion formula to obtain the heights of the pixels of all layers; S33. After calculating the z value, add the z value (i.e., (x, y, z)) to each pixel of the clear image generated in step S31 while keeping (x, y) unchanged. A 3D image format is generated based on the given 3D coordinates and saved. The key area is named according to the coordinates of the key area. S34. Add the coordinates of the key area recorded in the scan to the two-dimensional digital slice image generated in step S31, set a mouse hover event in the program, and give a three-dimensional image prompt when the mouse hovers over the key area, and then use the mouse event to browse the local three-dimensional image.
7. The method for producing pathological digital slices according to claim 6, characterized in that: In step S32, the conversion formula is as follows: z=round(f(min(x,y))+c×k) Where z represents the height, f represents the height comparison function, min(x,y) represents the minimum value under the (x,y) coordinates, c represents the clarity, k represents the coefficient, and round() represents the rounding function.
8. An electronic device, characterized in that: The electronic device includes a memory and a processor, wherein the memory stores a computer program that can be run on the processor, and the processor implements the steps of the method according to any one of claims 1 to 7 when executing the computer program.
9. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.
10. A computer program product comprising computer instructions, characterized in that When the computer instructions are executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.