Method and device for synchronizing multiple digital pathological sections and readable storage medium
By acquiring and stitching images at different focus levels of pathological slices, panoramic and animation images are formed, which solves the limitations of the field of vision and cumbersome operation of traditional pathological diagnosis methods and the limitations of single focus layer pictures of digital pathological technology, improving the accuracy of diagnosis and Efficiency reduces the risk of missed diagnosis and misdiagnosis.
Patent Information
- Application Number
- CN202411505530.1
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-10-28
- Publication Date
- 2024-11-26
- Estimated Expiration
- Not applicable · inactive patent
AI Technical Summary
Traditional pathological diagnosis methods have limited vision and cumbersome operations. Digital pathology technology. Single focus layer pictures cannot show the full picture of pathological sections, increasing the risk of missed diagnosis and misdiagnosis.
By obtaining the focus images of each sub-region of the pathological section at different focus levels, stitching and synchronous display, forming a panoramic image and animated image, providing more comprehensive pathological information.
It improves the accuracy and efficiency of pathological diagnosis, reduces the risks of missed diagnosis and misdiagnosis, simplifies the observation process, and facilitates teaching and scientific research.
Smart Images

Figure CN119028535A_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the technical field of digital pathology slice processing, and in particular to a method, a device and a readable storage medium for synchronizing multiple digital pathology slices. Background Art
[0002] Pathology plays a vital role in medical diagnosis. Traditional pathology diagnosis mainly relies on the observation of pathology sections under a microscope. With the development of information technology and digital technology, digital pathology technology has gradually emerged, aiming to convert traditional pathology sections into digital form for better storage, transmission and analysis. However, the existing technology has the following problems: 1. Limitations of traditional pathological diagnosis 1. Limited field of vision When observing pathological sections with traditional microscopes, their field of view is relatively small. Doctors need to constantly move the sections and adjust the focus and position of the microscope to observe different areas of the pathological sections, which makes the observation process cumbersome and time-consuming.
[0003] 2. Complicated operation When using a microscope, doctors need to manually adjust multiple parameters such as focal length and stage position. The operation process is complicated and prone to errors. Long-term operation will make doctors feel tired, affecting diagnostic efficiency and accuracy.
[0004] 2. Existing defects of digital pathology technology 1. Limitations of single focus layer images Although digital pathology technology has made some progress, most digital pathology slides currently present images of a single focus layer. This means that these images can only show the information of the pathology slide at a specific focus layer, and the pathology slide has a certain thickness, and different focus layers may contain different pathological feature information.
[0005] 2. Increased risk of missed diagnosis and misdiagnosis Since a single focus layer image does not display complete information, doctors may miss some important pathological features during the diagnosis process, thereby increasing the risk of missed diagnosis and misdiagnosis, which may have serious adverse effects on the patient's treatment and prognosis.
[0006] In view of the limitations of traditional pathological diagnosis methods and the problems caused by the existing defects of digital pathology technology, the present invention aims to develop a technology that can synchronously display multiple images of different focus levels of pathological sections. Through this technology, it is expected to improve the accuracy and efficiency of pathological diagnosis, provide doctors with more comprehensive pathological information, and thus better serve clinical diagnosis and treatment. Summary of the invention
[0007] The embodiments of the present invention provide a method, device and readable storage medium for synchronizing multiple digital pathology slices, which are aimed at the problems of limited field of view, complicated operation and easy fatigue existing in the current technology.
[0008] The core technology of the present invention is mainly a method and system for synchronously displaying multiple digital pathology sections. By acquiring regional focus images of each sub-area of the pathology section at different focus levels, and splicing and synchronously displaying them, panoramic images and animated images are formed, so that doctors can quickly and comprehensively observe the pathology sections and improve the accuracy and efficiency of diagnosis.
[0009] In a first aspect, the present invention provides a method for synchronizing multiple digital pathology sections, the method comprising the following steps: S00, obtaining a set of regional focus images, each set containing multiple images of a corresponding region at different focus levels; S10, selecting the image with the highest definition in each area as the optimal image for stitching; S20, after multiple stitching, multiple panoramic images of pathological slices are obtained and stored, and can be displayed to medical staff through a display device; S30: Combine the multiple panoramic images into an animated image in chronological order and display the animated image to medical staff.
[0010] Furthermore, in step S10, the clarity score of the image in each region is calculated according to the gradient method, and the image with the highest clarity score is taken as the optimal image.
[0011] Furthermore, in step S10, an image stitching algorithm is used to stitch the images of the area to be stitched into a panoramic image of the pathological slice.
[0012] Furthermore, in step S10, the steps of the image stitching algorithm are: Use the FAST algorithm to detect feature points in the images to be stitched; Determine the direction of the feature point by calculating the centroid of the feature point; Calculate the binary descriptor of the feature point; Rotate the coordinate system according to the direction of the feature point. The rotated coordinate system takes the feature point as the origin, and the line connecting the feature point and the centroid as the new X-axis of the coordinate system. Matching is done by calculating the descriptor Hamming distance between two feature points. When the Hamming distance is less than the threshold, the two feature points are matched. The above steps are repeated to complete the splicing steps; Among them, the descriptor is a feature vector used to describe the feature points in the image.
[0013] Furthermore, in step S10, the angle between the line connecting the feature point and the centroid and the horizontal axis of the coordinate system is calculated to obtain the direction of the feature point.
[0014] Furthermore, in step S10, a circle is made with the feature point as the center and a set radius; within the circle, N points are selected according to the rotated coordinate system, and the grayscale value of each point is compared to generate a binary descriptor.
[0015] Furthermore, in step S30, the specific steps of combining the multiple panoramic images into an animated image in chronological order are as follows: The image quality of each panoramic image was scored based on image clarity, color reproduction, contrast, noise and artifacts, slice integrity, and staining uniformity, which was calculated by weighted calculation; The display time of each panoramic image is determined according to the scoring results, and the lower the score, the longer the display time; Using the animation generation algorithm, multiple panoramic images are combined into an animated image in chronological order.
[0016] In a second aspect, the present invention provides a multi-frame synchronization device for digital pathology slices, comprising: An acquisition module, for acquiring a set of regional focus images, each set comprising a plurality of images of a corresponding region at different focus levels; The stitching module selects the image with the highest definition in each area as the optimal image for stitching; The display module obtains multiple panoramic images of pathological slices after multiple splicing and stores them, which can be displayed to medical staff through a display device; multiple panoramic images are combined into animated images in chronological order and displayed to medical staff.
[0017] In a third aspect, the present invention provides an electronic device, including a memory and a processor, wherein a computer program is stored in the memory, and the processor is configured to run the computer program to execute the above-mentioned method for synchronizing multiple digital pathology slices.
[0018] In a fourth aspect, the present invention provides a readable storage medium storing a computer program, wherein the computer program includes a program code for controlling a process to execute the process, wherein the process includes the method for synchronizing multiple digital pathology slices according to the above-mentioned method.
[0019] The main contributions and innovations of the present invention are as follows: 1. Improve observation efficiency The multi-frame synchronization technology can significantly shorten the observation time of pathological sections. Traditional pathological diagnosis relies on microscopic observation, which has a limited field of view and cumbersome operation, and requires constant adjustment of focus and position; existing digital pathological sections are mostly single-focus layer images with incomplete information, and the focus layer needs to be switched multiple times during observation. The present invention can synchronously display images of different focus layers without frequent operation, thus improving observation efficiency.
[0020] 2. Enhance diagnostic accuracy Panoramic images provide more comprehensive pathological information. In the prior art, a single focus layer image cannot show all the features of different layers of the pathological slice, which can easily lead to missed diagnosis and misdiagnosis. The technology of the present invention can obtain and display images of different focus layers, so that doctors can observe the pathological slice more comprehensively, which helps to diagnose the disease more accurately.
[0021] 3. Convenient for teaching and scientific research Digital pathology slides can be permanently stored and accessed at any time. In teaching and scientific research, collective slide reading and discussion are common activities, and the limitations of existing technologies are not conducive to the efficient development of these activities. The technology of the present invention facilitates teaching and scientific research personnel to obtain comprehensive pathology slide information at any time, which is conducive to the conduct of collective slide reading and discussion and other activities.
[0022] The details of one or more embodiments of the invention are set forth in the following drawings and description so that other features, objects, and advantages of the invention are more readily apparent. BRIEF DESCRIPTION OF THE DRAWINGS
[0023] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of the present invention. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings: Figure 1 The present invention provides a flow chart of a method for synchronizing multiple digital pathology sections according to an embodiment of the present invention; Figure 2 is another implementation flow chart according to an embodiment of the present invention; Figure 3 4 is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. DETAILED DESCRIPTION
[0024] Exemplary embodiments will be described in detail herein, examples of which are shown in the accompanying drawings. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementations described in the following exemplary embodiments do not represent all implementations consistent with one or more embodiments of this specification. Instead, they are merely examples of devices and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.
[0025] It should be noted that: in other embodiments, the steps of the corresponding method are not necessarily performed in the order shown and described in this specification. In some other embodiments, the steps included in the method may be more or less than those described in this specification. In addition, a single step described in this specification may be decomposed into multiple steps for description in other embodiments; and multiple steps described in this specification may be combined into a single step for description in other embodiments.
[0026] In the prior art, digital pathology sections are mostly images of a single focus layer, which do not display complete information and increase the risk of missed diagnosis and misdiagnosis.
[0027] Based on this, the present invention solves the problems existing in the prior art based on the technology of synchronously displaying multiple images of different focus levels of pathological sections.
[0028] Embodiment 1 The present invention aims to propose a method for synchronizing multiple digital pathology slices. Specifically, referring to Figure 1 , the method comprises the following steps: S00, obtain regional focus image set First, the pathological sections are scanned using a high-resolution digital microscope or scanning system to obtain regional focus images of each sub-region at different focus levels to form a set of regional focus images, each of which contains multiple images of the sub-region at different focus levels.
[0029] S10, from each set of regional focus images, select an optimal regional focus image for stitching according to the image clarity. The specific steps include: (1) Obtain the clarity score of the focused image in each area.
[0030] According to the image clarity score calculation formula (Brenner gradient method):
[0031] Among them, FBrenner represents the clarity score result of the image; M and N are index variables used to represent the image pixel coordinate range, corresponding to the pixel range in the row and column directions of the image, respectively, and are used to traverse all pixels in the image or pixels in a specific area; f(x,y) is a function about the image pixel coordinate (x,y), representing the pixel value or degree value of the image at the coordinate (x,y); x and y represent the horizontal and vertical coordinate positions of the pixels in the image, respectively. In the formula, (x+2,y) and (x,y) are the relevant pixel coordinate positions used to compare the pixel value difference to calculate the clarity score.
[0032] (2) Sort the clarity scores and select the image with the highest clarity for stitching.
[0033] (3) Use the image stitching algorithm ORB (Oriented FAST and Rotated BRIEF) to stitch the selected area focus images into a panoramic image of the pathological section. The steps are as follows: 1) oFAST (OrientedFAST) Feature point detection: The ORB algorithm uses the improved FAST algorithm (Features from Accelerated Segment Test) to detect feature points. The basic idea of the FAST algorithm is to compare the grayscale difference between the candidate point and its surrounding pixels. If the difference is large enough, the point is considered a feature point.
[0034] Feature point direction determination: The ORB algorithm determines the direction of a feature point by calculating its center of mass (IntensityCentroid). The center of mass calculation is based on the distribution of pixel values in the neighborhood of the feature point. The specific steps are as follows: The moment mpq in the neighborhood of the feature point is defined as:
[0035] Where I(x,y) is the grayscale value of the pixel (x,y); the range of x and y is within the neighborhood of the feature point, and x and y represent the horizontal and vertical coordinate positions of the pixels in the neighborhood of the feature point, respectively; p and q are integer exponents used to determine the order of the moment. Different p and q values correspond to different moments. These moments can describe the distribution of pixel values in the neighborhood of the feature point from different angles.
[0036] Calculate the position of the center of mass C:
[0037] Among them, C represents the centroid position of the feature point, which is a result in the form of two-dimensional coordinates (x, y) and is used to determine the direction of the feature point; m 00 is the zero-order moment, through the formula It is calculated and represents the sum of the gray values of all pixels in the neighborhood of the feature point, which is used to normalize other moments; m 10 is the first-order moment, through the formula It is calculated to represent the sum of the products of the horizontal coordinate x and the gray value I(x,y) of the pixels in the neighborhood of the feature point, reflecting the distribution characteristics of the pixels in the neighborhood in the horizontal direction; m 01 is the first-order moment, through the formula It is calculated and represents the sum of the products of the vertical coordinate y of the pixels in the neighborhood of the feature point and the gray value I(x,y), reflecting the distribution characteristics of the pixels in the neighborhood in the vertical direction.
[0038] Calculate the angle θ between the line connecting the feature point O and the centroid C and the horizontal axis, which is the direction of the feature point.
[0039] 2) rBRIEF (RotatedBRIEF) Descriptor calculation: The ORB algorithm uses the rotated BRIEF algorithm to calculate the descriptor of the feature points. The BRIEF algorithm originally generates binary descriptors by randomly selecting point pairs and comparing their grayscale values, but the ORB algorithm rotates the coordinate system to make the descriptor rotationally invariant. The specific steps are as follows: With feature point P as the center, make a circle O with a certain radius d.
[0040] In the circle O, select N point pairs (usually N=256) according to the rotated coordinate system.
[0041] For each point pair, the grayscale values are compared and a binary descriptor is generated.
[0042] Among them, the rotated coordinate system: In order to achieve rotation invariance, the ORB algorithm rotates the coordinate system according to the direction θ of the feature point. The rotated coordinate system takes the feature point P as the origin and the line connecting the feature point P and the center of mass C as the new X-axis.
[0043] A descriptor is a feature vector used to describe a feature point in an image. It extracts and encodes the pixel information around the feature point in a certain way, so that it can represent the unique properties of the feature point in subsequent operations such as image matching.
[0044] In the BRIEF algorithm, multiple point pairs are selected in a circle with the feature point as the center (usually 256 in this scheme). Then the grayscale values of each point pair are compared. If the grayscale value of the first point in a point pair is greater than the grayscale value of the second point, the corresponding bit in the binary descriptor is set to 1, otherwise it is set to 0. By performing such grayscale value comparison operations on all selected point pairs, a binary string consisting of 0 and 1 can be generated. This string is the binary descriptor of the feature point. It can reflect the feature information such as the grayscale relationship of the pixels around the feature point to a certain extent, and is used for subsequent matching with other feature point descriptors and other operations.
[0045] 3) Matching and Hamming distance The descriptors generated by the ORB algorithm are binary strings, so feature points can be quickly matched by calculating the Hamming distance. The Hamming distance refers to the number of different characters at corresponding positions of two strings of equal length. In the ORB algorithm, when the Hamming distance of the descriptors of two feature points is less than a certain threshold, the two feature points are considered to be matched.
[0046] For example, there are two binary descriptors: descriptor A = "101011" and descriptor B = "111001".
[0047] Compare the characters in corresponding positions from left to right: The first digit is 1, the same.
[0048] In the second digit, A is 0 and B is 1, which are different, so the count is increased by 1.
[0049] The third digit, A is 1, B is 1, the same.
[0050] The fourth digit, A is 0, B is 0, the same.
[0051] The fifth digit, A is 1, B is 0, different, the count is increased by 1.
[0052] In the sixth position, A is 1 and B is 1, the same.
[0053] So the Hamming distance between these two descriptors is 2.
[0054] 4) The splicing is completed through the above steps.
[0055] S20, generating and displaying a panoramic image of pathological sections The multiple pathological slice panoramic images obtained by multiple stitching are stored and displayed to the doctor as needed. The doctor can observe the overall structure and detailed information of the pathological slice on the display.
[0056] S30, generating and displaying pathological slice animation images Furthermore, a pathological slice animation image is generated based on the multiple pathological slice panoramic images obtained by multiple stitching. The specific steps include: (1) Score the image quality of each panoramic image and obtain the score of each slice. The steps are as follows: When evaluating the image quality of pathological sections, the following factors are usually considered: 1. Image clarity: including the clarity of the cell structure, nucleus and cytoplasm boundaries, and the discernibility of image details.
[0057] 2. Color reproduction: The colors in pathological images should accurately reflect the true colors of the tissue, such as the blue of the cell nucleus and the red of the cytoplasm.
[0058] 3. Contrast: The contrast between different tissues or cell structures in the image should be moderate to facilitate observation and diagnosis.
[0059] 4. Noise and artifacts: The interference of noise and artifacts in the image should be minimized, such as scanning lens noise, uneven image stitching, etc.
[0060] 5. Slice integrity: The slices should be complete and without wrinkles, folds, knife marks, cracks and other quality problems.
[0061] 6. Staining uniformity: The sections should be stained evenly without local over- or under-staining.
[0062] Set scoring criteria and weightings: 1. Image clarity: full score 20 points, weight 0.3; 2. Color reproduction: full score 15 points, weight 0.2; 3. Contrast: full score 10 points, weight 0.15; 4. Noise and artifacts: full score 10 points, weight 0.15; 5. Slice integrity: full score 20 points, weight 0.2; 6. Dyeing uniformity: full score 15 points, weight 0.1; Total score = (imaging clarity score × 0.3) + (color reproduction score × 0.2) + (contrast score × 0.15) + (noise and artifact score × 0.15) + (slice integrity score × 0.2) + (staining uniformity score × 0.1).
[0063] (2) Determine the display time of each panoramic image based on the scoring results; the lower the score, the longer the display time.
[0064] (3) Using an animation generation algorithm, multiple panoramic images are combined into an animated image in chronological order and displayed to the doctor. The doctor can observe the changes of the pathological slice at different focus levels through the animated image.
[0065] Among them, animation generation based on traditional algorithms, such as keyframe interpolation: by defining keyframes (i.e. key actions or postures) in the animation sequence, and then using interpolation algorithms (such as linear interpolation, spline interpolation, etc.) to generate transition frames between keyframes, thereby generating a complete animation.
[0066] Embodiment 2 Based on the same concept, the present invention also proposes a multi-frame synchronization device for digital pathology slices, comprising: An acquisition module, for acquiring a set of regional focus images, each set comprising a plurality of images of a corresponding region at different focus levels; The stitching module selects the image with the highest definition in each area as the optimal image for stitching; The display module obtains multiple panoramic images of pathological slices after multiple splicing and stores them, which can be displayed to medical staff through a display device; multiple panoramic images are combined into animated images in chronological order and displayed to medical staff.
[0067] Embodiment 3 This embodiment also provides an electronic device, referring to Figure 3 , comprises a memory 404 and a processor 402, wherein the memory 404 stores a computer program, and the processor 402 is configured to run the computer program to execute the steps in any of the above method embodiments.
[0068] Specifically, the processor 402 may include a central processing unit (CPU), or an application specific integrated circuit (ASIC), or may be configured to implement one or more integrated circuits of the embodiment of the present invention.
[0069] Among them, the memory 404 may include a large capacity memory 404 for data or instructions. For example, but not limitation, the memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid state drive (SSD), 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 404 may include a removable or non-removable (or fixed) medium. In appropriate cases, the memory 404 may be inside or outside the data processing device. In a specific embodiment, the memory 404 is a non-volatile memory. In a specific embodiment, the memory 404 includes a read-only memory (ROM) and a random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable ROM (Programmable Read-Only Memory, PROM for short), an erasable PROM (Erasable Programmable Read-Only Memory, EPROM for short), an electrically erasable PROM (Electrically Erasable Programmable Read-Only Memory, EEPROM for short), an electrically alterable ROM (Electrically Alterable Read-Only Memory, EAROM for short) or a flash memory (FLASH) or a combination of two or more of these. In appropriate circumstances, the RAM may be a static random access memory (SRAM) or a dynamic random access memory (DRAM), wherein the DRAM may be a fast page mode dynamic random access memory 404 (FPMDRAM), an extended data output dynamic random access memory (EDODRAM), a synchronous dynamic random access memory (SDRAM), etc.
[0070] The memory 404 may be used to store or cache various data files required for processing and / or communication, as well as possible computer program instructions executed by the processor 402 .
[0071] The processor 402 reads and executes the computer program instructions stored in the memory 404 to implement the multiple synchronization method of any digital pathology slices in the above embodiment.
[0072] Optionally, the electronic device may further include a transmission device 406 and an input / output device 408 , wherein the transmission device 406 is connected to the processor 402 , and the input / output device 408 is connected to the processor 402 .
[0073] The transmission device 406 can be used to receive or send data via a network. The specific examples of the above-mentioned network may include a wired or wireless network provided by a communication provider of the electronic device. In one example, the transmission device includes a network adapter (Network Interface Controller, referred to as NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 406 can be a radio frequency (Radio Frequency, referred to as RF) module, which is used to communicate with the Internet wirelessly.
[0074] Input / output devices 408 are used to input or output information.
[0075] Embodiment 4 This embodiment further provides a readable storage medium, in which a computer program is stored. The computer program includes a program code for controlling a process to execute the process. The process includes the method for synchronizing multiple digital pathology slices according to the first embodiment.
[0076] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementation modes, and this embodiment will not be described in detail here.
[0077] In general, various embodiments may be implemented in hardware or dedicated circuits, software, logic, or any combination thereof. Some aspects of the invention may be implemented in hardware, while other aspects may be implemented in firmware or software executed by a controller, microprocessor, or other computing device, but the invention is not limited thereto. Although various aspects of the invention may be shown and described as block diagrams, flow charts, or using some other graphical representation, it should be understood that, as non-limiting examples, the boxes, devices, systems, techniques, or methods described herein may be implemented in hardware, software, firmware, dedicated circuits or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.
[0078] Embodiments of the present invention may be implemented by computer software that is executable by a data processor of a mobile device, such as in a processor entity, or by hardware, or by a combination of software and hardware. Computer software or programs (also referred to as program products) including software routines, applets and / or macros may be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. A computer program product may include one or more computer executable components configured to perform an embodiment when the program is run. One or more computer executable components may be at least one software code or a portion thereof. In addition, at this point, it should be noted that, for example, Figure 1 Any block of the logic flow in the program may represent program steps, or interconnected logic circuits, blocks and functions, or a combination of program steps and logic circuits, blocks and functions. The software may be stored on physical media such as memory chips or storage blocks implemented within the processor, magnetic media such as hard disks or floppy disks, and optical media such as, for example, DVDs and their data variants, CDs, etc. Physical media are non-transitory media.
[0079] Those skilled in the art should understand that the technical features of the above embodiments may be arbitrarily combined. To make the description concise, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.
[0080] The above embodiments only express several implementation methods of the present invention, and the descriptions thereof are relatively specific and detailed, but they cannot be understood as limiting the scope of the present invention. It should be pointed out that, for those of ordinary skill in the art, several modifications and improvements can be made without departing from the concept of the present invention, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the present invention shall be subject to the attached claims.
Claims
1. Multiple synchronization methods for digital pathology sections, It is characterized in that The following steps are involved: S00, obtaining a set of regional focus images, each set containing multiple images of a corresponding region at different focus levels; S10, selecting the image with the highest definition in each area as the optimal image for stitching; S20, after multiple stitching, multiple panoramic images of pathological slices are obtained and stored, and can be displayed to medical staff through a display device; S30: Combine the multiple panoramic images into an animated image in chronological order and display the animated image to medical staff.
2. The method for synchronizing multiple digital pathological sections as claimed in claim 1, It is characterized in that In step S10, the clarity score of the image in each region is calculated according to the gradient method, and the image with the highest clarity score is taken as the optimal image.
3. The method for synchronizing multiple digital pathological sections as claimed in claim 1, It is characterized in that In step S10, an image stitching algorithm is used to stitch the images of the area to be stitched into a panoramic image of the pathological slice.
4. The method for synchronizing multiple digital pathological sections as claimed in claim 3, It is characterized in that In step S10, the steps of the image stitching algorithm are: Use the FAST algorithm to detect feature points in the images to be stitched; Determine the direction of the feature point by calculating the centroid of the feature point; Calculate the binary descriptor of the feature point; Rotate the coordinate system according to the direction of the feature point. The rotated coordinate system takes the feature point as the origin, and the line connecting the feature point and the centroid as the new X-axis of the coordinate system. Matching is done by calculating the descriptor Hamming distance between two feature points. When the Hamming distance is less than the threshold, the two feature points are matched. The above steps are repeated to complete the splicing steps; Among them, the descriptor is a feature vector used to describe the feature points in the image.
5. The method for synchronizing multiple digital pathological sections as claimed in claim 4, It is characterized in that In step S10, the angle between the line connecting the feature point and the centroid and the horizontal axis of the coordinate system is calculated to obtain the direction of the feature point.
6. The method for synchronizing multiple digital pathological sections as claimed in claim 4, It is characterized in that In step S10, a circle is drawn with the feature point as the center and the set radius; within the circle, N points are selected according to the rotated coordinate system, and the grayscale value of each point is compared to generate a binary descriptor.
7. The method for synchronizing multiple digital pathological sections according to any one of claims 1 to 6, It is characterized in that In step S30, the specific steps of combining the multiple panoramic images into an animated image in chronological order are as follows: The image quality of each panoramic image was scored based on image clarity, color reproduction, contrast, noise and artifacts, slice integrity, and staining uniformity, which was calculated by weighted calculation; The display time of each panoramic image is determined according to the scoring results, and the lower the score, the longer the display time; Using the animation generation algorithm, multiple panoramic images are combined into an animated image in chronological order.
8. A multi-frame synchronization device for digital pathology sections, It is characterized in that include: An acquisition module, for acquiring a set of regional focus images, each set comprising a plurality of images of a corresponding region at different focus levels; The stitching module selects the image with the highest definition in each area as the optimal image for stitching; The display module obtains and stores multiple panoramic images of pathological slices after multiple splicing, and can be displayed to medical staff through a display device; Multiple panoramic images are combined into an animated image in chronological order and displayed to medical staff.
9. An electronic device comprising a memory and a processor, It is characterized in that The memory stores a computer program, and the processor is configured to run the computer program to execute the method for synchronizing multiple digital pathology slices according to any one of claims 1 to 7.
10. A readable storage medium, It is characterized in that The readable storage medium stores a computer program, wherein the computer program includes a program code for controlling a process to execute a process, wherein the process includes the method for synchronizing multiple digital pathological sections according to any one of claims 1 to 7.
Citation Information
Patent Citations
ORB (oriented brief) image feature registration method based on LK (Lucas-Kanade) optical flow constraint
CN104751465A
Display method of digital pathological section, device and computer equipment
CN109994189A
Video quality evaluation method and device
CN110278485A
Image processing method and device and vehicle
CN115019285A
Rapid focusing method of microscopic image acquisition device and microscopic image acquisition method
CN115079372A
