Method for pathological section row discrete speed planning and scanning and application thereof
By comparing the execution requirements of pathological slides with the equipment capabilities, the upper limit of the executable speed was deduced and a row-level discrete speed table was planned. This solved the problem of drastic changes in local focal height during pathological slide scanning, achieving efficient and stable segmented variable speed scanning, and reducing the risk of defocusing and time loss.
Patent Information
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- SHENZHEN SHENGQIANG TECH
- Filing Date
- 2026-04-28
- Publication Date
- 2026-05-29
Smart Images
Figure CN122120384A_ABST
Abstract
Description
Technical Field
[0001] This invention relates to the field of pathological slide scanning imaging technology, and in particular to a method for row-level discrete velocity planning and scanning of pathological slides and its application. Background Technology
[0002] In digital pathology slide scanning, to ensure the clarity of the full-field image, scanning equipment typically needs to achieve precise Z-axis autofocus. Current technologies usually involve first acquiring a low-magnification preview image of the pathology slide and identifying candidate scanning areas. Discrete focal height data is then obtained through the focus point, and a fitted focal plane is generated using spline surfaces, planes, or triangular meshes. During the actual scanning phase, the scanning equipment performs continuous tracking scans based on the target focal height provided by this fitted focal plane. Regarding scanning speed settings, existing solutions often use a fixed scanning speed for the entire slide, or set only a few uniform speed levels for the entire slide. However, the fitted focal plane of a real pathology sample often has areas with sharp bends or rapid changes in focal height. If the default scanning speed is used along the entire row in these areas, the focusing axis needs to complete a larger Z-axis change and a faster response within a limited pass time. If the entire slide is uniformly set to a lower speed to accommodate a few high-risk areas, smooth areas will also be forced to be scanned at a low speed.
[0003] Therefore, there is an urgent need for a pathological slide row-level discrete velocity planning and scanning method and its application to solve the problems existing in the current technology. Summary of the Invention
[0004] This invention provides a method for planning and scanning discrete velocity at the row level for pathological slides and its application. It addresses the problems of existing technologies, such as the inability to determine the risk of defocusing at the default speed based on the device's dynamic focusing capability when there are drastic changes in local focal height on the fitted focal plane, and the lack of a mechanism to convert the velocity planning results into a directly executable discrete segmented velocity strategy.
[0005] The core technology of this invention is to calculate the dynamic focus execution requirements of each scanning position at the default speed, compare it with the maximum focus capability parameter of the hardware to deduce the upper limit of the executable speed, and then compress the continuous speed matrix into a row-level discrete speed table with inter-segment transition buffers according to the threshold rule, so as to guide the stage and the focusing mechanism to perform segmented variable speed scanning row by row.
[0006] In a first aspect, the present invention provides a method for planning and scanning the row-level discrete velocity of pathological sections, the method comprising the following steps:
[0007] Obtain the fitted focal plane array and row-level effective scan interval of the pathological sections; Based on the fitted focal plane array and the default scan speed, the default speed execution requirement matrix is calculated. The execution requirement matrix represents the dynamic focus execution requirements that the device needs to undertake under the default scan speed. The execution requirement matrix is compared with the device's dynamic focus capability parameter set to identify execution violation areas. Based on the comparison results, the upper limit of the allowed scanning speed for each scanning position is deduced to generate an executable speed matrix. The executable velocity matrix is compressed into a row-level discrete velocity table according to the preset discretization rules; Segmented execution control instructions are generated based on row-level discrete speed tables. The segmented execution control instructions include an inter-segment transition buffer strategy determined according to the differences between adjacent speed segments, and discrete segmented variable speed scanning is performed according to the segmented execution control instructions.
[0008] Furthermore, the requirements for dynamic focus tracking include at least one of the following: Z-axis rate of change requirement, Z-axis tracking acceleration requirement, and response time requirement. The steps for calculating the default speed execution demand matrix include: The required Z-axis rate of change is calculated based on the changes in focal height at adjacent positions in the fitted focal plane array and the default scan speed; and / or, Calculate the required Z-axis following acceleration based on the local second-order changes in the fitted focal plane array and the default scan rate; and / or, The effective response margin is calculated based on the spatial distance between adjacent locations, the default scan speed, and the control response delay to characterize the response time requirement.
[0009] Furthermore, the set of parameters for the device's dynamic focusing capability includes at least one of the following: the device's maximum permissible Z-axis change rate, the device's maximum permissible Z-axis following acceleration, and the preset safety response time. The steps for generating an executable speed matrix by inversely calculating the upper limit of the allowable scanning speed for each scanning position based on the comparison results include: When the required Z-axis rate of change exceeds the equipment's maximum permissible Z-axis rate of change, the first speed upper limit is calculated by reverse calculation based on the ratio of the equipment's maximum permissible Z-axis rate of change to the required Z-axis rate of change; and / or, When the Z-axis following acceleration demand exceeds the equipment's maximum permissible Z-axis following acceleration, the second speed upper limit is calculated by reverse calculation based on the ratio of the equipment's maximum permissible Z-axis following acceleration to the Z-axis following acceleration demand; and / or, When the effective response margin does not meet the preset safe response time, the upper limit of the third speed is calculated by back-calculating the control response delay and the preset safe response time. The upper limit of the scan speed at each position in the executable speed matrix is determined by combining at least one of the default scan speed, the first speed limit, the second speed limit, and the third speed limit.
[0010] Furthermore, the preset discrete rules include at least one of the following: minimum stable speed threshold, minimum segment length threshold, adjacent segment merging threshold, and maximum number of segments per line threshold; The steps for compressing the executable velocity matrix into a row-level discrete velocity table according to a preset discretization rule include: Mark locations below the minimum stable velocity threshold as execution violation areas; and / or, Candidate segments with a length less than the minimum segment length threshold will be merged or transferred to violation processing; and / or, Merge adjacent segments whose target velocity difference is less than the adjacent segment merging threshold into a single segment; and / or, When the number of segments in a compressed line exceeds the maximum number of segments in a single line, secondary speed segments are merged according to priority or the process is switched to violation handling.
[0011] Furthermore, the steps for generating segmented execution control commands based on row-level discrete speed tables include: For cases where the target velocity in the first segment is greater than that in the second segment, an advance deceleration buffer is set before the boundary of the second segment. The length of the advance deceleration buffer is determined based on the difference in target velocities between adjacent segments and the available deceleration of the platform; and / or, If the target speed of the first segment is less than that of the second segment in two adjacent segments, a recovery acceleration buffer is set at the segment boundary.
[0012] Furthermore, it also includes a step to repair execution violation areas, which include areas where the executable speed is lower than the minimum stable scan speed, areas where the number of segments after compression exceeds the maximum number of segments per line threshold, or areas where the buffer length is greater than the allowed length of the effective tissue interval; The repair steps include at least one of the following: For the areas where violations occurred, local point supplementation was performed and the local focal plane was refitted; Perform local smooth reconstruction on the areas where violations occurred; Expand the front and rear buffer zones and regenerate the row-level discrete velocity table; The areas with violations will be transferred to a low-speed re-sweeping task for separate processing.
[0013] Furthermore, the steps for executing discrete segmented variable speed scanning according to segmented execution control commands include: Speed switching begins in the pre-deceleration buffer zone before entering the current segment; Within the current segment, control the platform to move at the target speed, and perform continuous following by obtaining the target focal height based on the fitted focal plane array; When leaving the current segment, press Restore Acceleration Buffer to smoothly switch to the next speed segment; When using a serpentine scanning method for reverse scanning, the mirror references the row-level discrete velocity table of the current row.
[0014] Secondly, the present invention provides a pathological slide row-level discrete velocity planning and scanning device, comprising: Imaging unit, used to acquire preview images and focused images of pathological sections; The processing unit is used to generate a fitted focal plane array and row-level effective scanning intervals, calculate the default speed execution demand matrix based on the fitted focal plane array and default scanning speed, compare the execution demand matrix with the device's dynamic focusing capability parameter set to identify execution violation areas and back-generate an executable speed matrix, compress the executable speed matrix into a row-level discrete speed table, and generate segmented execution control instructions based on the row-level discrete speed table. The instructions include an inter-segment transition buffer strategy. The motion control unit is used to drive the stage and focusing mechanism to perform discrete segmented variable speed scanning according to segmented control commands; The data management unit is used to save speed plans and execution status.
[0015] Thirdly, the present invention provides an electronic device including a memory and a processor, wherein the memory stores a computer program and the processor is configured to run the computer program to execute the above-described pathological slide row-level discrete speed planning and scanning method.
[0016] Fourthly, the present invention provides a readable storage medium storing a computer program, the computer program including program code for controlling a process to execute the process, the process including the pathological slide row-level discrete velocity planning and scanning method described above.
[0017] The main contributions and innovations of this invention are as follows: 1. Significantly reduces the risk of local defocusing and image trailing: This invention calculates the execution requirements at the default speed (such as the Z-axis change rate and following acceleration) in advance, and compares them with the upper limit of the dynamic focusing capability of the hardware device to infer the upper limit of the speed. It can accurately identify and intervene in the local focal plane drastic change area that exceeds the device's execution limit. By accurately reducing the speed as needed, it ensures the image focusing quality from the physical control level.
[0018] 2. Effectively balances high scanning throughput efficiency: Unlike the strategy in existing technologies that forces the entire flat slice to run at a uniform low speed in order to accommodate a few high-risk and drastic regions, the row-by-row segmentation planning mechanism constructed in this invention allows the device to maintain the highest safe speed in flat tissue regions with redundant capacity, completely avoiding the large-area time loss caused by the deceleration of the entire slice.
[0019] 3. Significantly improves the engineering execution stability of multi-segment variable speed scanning: This invention does not simply output a continuously fluctuating speed function, but uses the minimum stable speed, minimum segment length and inter-segment merging rules to compress and merge the fragmented original two-dimensional speed matrix into a row-level discrete speed table; at the same time, by introducing the platform-available deceleration calculation to pre-decelerate and restore acceleration buffer length, it effectively solves the platform jitter problem caused by the excessive fragmentation of speed cutting commands, and ensures a smooth transition of hardware handover.
[0020] 4. Possesses extremely high system compatibility and self-healing evolution capability: The speed planning results of this invention can be directly and seamlessly integrated with existing focal plane array representation and row-level scanning architecture without the need to reconstruct the underlying fitting algorithm; and through the precise marking of violation areas, the system can independently trigger local supplementary scanning, parameter updates, or focal plane smoothing reconstruction, accumulating a data closed-loop optimization foundation for scanning equipment to process complex similar pathological sections.
[0021] Details of one or more embodiments of the present invention are set forth in the following drawings and description, so that other features, objects and advantages of the invention will be more readily understood. Attached Figure Description
[0022] The accompanying drawings, which are included to provide a further understanding of the invention and form part of this invention, illustrate exemplary embodiments of the invention and are used to explain the invention, but do not constitute an undue limitation of the invention. In the drawings: Figure 1 This is a flowchart of a pathological slide row-level discrete velocity planning and scanning method according to an embodiment of the present invention; Figure 2 This is a schematic diagram of the hardware structure of an electronic device according to an embodiment of the present invention. Detailed Implementation
[0023] Exemplary embodiments will now be described in detail, examples of which are illustrated in the accompanying drawings. When the following description relates to the drawings, unless otherwise indicated, the same numerals in different drawings denote the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with one or more embodiments of this specification. Rather, they are merely examples of apparatuses and methods consistent with some aspects of one or more embodiments of this specification as detailed in the appended claims.
[0024] It should be noted that the steps of the corresponding methods are not necessarily performed in the order shown and described in this specification in other embodiments. In some other embodiments, the methods may include more or fewer steps than described in this specification. Furthermore, a single step described in this specification may be broken down into multiple steps in other embodiments; and multiple steps described in this specification may be combined into a single step in other embodiments.
[0025] Example 1 This embodiment provides a method and system for row-level discrete velocity planning and scanning of pathological slides based on the device's dynamic focusing capability to deduce the executable velocity matrix. The method and system are applied to an automated pathological slide scanning device, which includes at least an imaging unit, a processing unit, a motion control unit, and a data management unit. The imaging unit acquires low-magnification preview images and focused images; the processing unit generates a fitted focal plane array and executes velocity planning; the motion control unit drives the stage and focusing mechanism to perform scanning actions; and the data management unit saves the velocity plan and execution status. For ease of understanding, several core terms involved in this invention are first defined: (1) Candidate scanning region: refers to one or more effective scanning regions obtained from the tissue identification results in the preview image, which can be expressed by tissue mask, closed contour or row-level effective scanning interval.
[0026] (2) Fitted focal plane array: refers to the two-dimensional focal height array generated based on the successful focus point, local fitting parameters or focal plane reconstruction algorithm, denoted as Z(r,c).
[0027] (3) Row-level effective scan interval: refers to the starting column index and ending column index that actually fall within the effective organizational range when scanning the r-th row, denoted as ... and .
[0028] (4) Default speed execution requirement matrix: refers to the local Z-axis execution requirement matrix calculated from the fitted focal plane array under the reference scan speed or the default scan speed. It represents the dynamic focus execution requirements that the device needs to undertake under the current default scan speed, including at least one of the following: required Z-axis change rate requirement, required Z-axis following acceleration requirement, and response time requirement.
[0029] (5) Set of parameters for dynamic focusing capability of the device: refers to the set of parameters related to the continuous focusing capability during the scanning process, including at least one of the following: the maximum allowable Z-axis change rate of the device, the maximum allowable Z-axis following acceleration of the device, the default scanning speed, the minimum stable scanning speed, the control response delay, the available deceleration of the platform, and the trigger cycle.
[0030] (6) Executable speed matrix: refers to the two-dimensional speed upper limit matrix derived from the default speed execution requirement matrix and the device dynamic focus capability parameter set, denoted as V. allow (r,c).
[0031] (7) Execution violation area: refers to the local area where the execution demand exceeds the upper limit of the device’s dynamic focus capability at the default scan speed, or where the execution speed is lower than the minimum stable scan speed.
[0032] (8) Row-level discrete speed table: refers to the set of segmented speed plans obtained by compressing the executable speed matrix of each row. Each segment includes at least the start column, end column, target scan speed and segment number.
[0033] (9) Inter-segment transition buffer: refers to the buffer zone allocated before and after the segment boundary to ensure smooth deceleration or recovery when the target scanning speeds of two adjacent segments are different.
[0034] (10) Segmented execution control instructions: refers to scan execution instructions generated based on row-level discrete speed tables and inter-segment transition buffers, which include at least the segment start and end range, target speed, transition mode, and referenced focal plane array range.
[0035] like Figure 1 As shown, the method in this embodiment includes steps S1 to S7.
[0036] Step S1: Obtain the fitted focal plane array and the row-level effective scan interval.
[0037] The device first acquires a low-magnification preview of the current pathological slide and identifies one or more candidate scanning regions. The processing unit generates a fitted focal plane array based on the focus point, regional fitting results, or focal plane reconstruction results. This fitted focal plane array is a two-dimensional array, denoted as Z(r,c), where r represents the row index, c represents the column index, and each element represents the target focal height at the corresponding position.
[0038] Simultaneously, the processing unit obtains the effective scan interval for each row based on the tissue mask or scan region boundary, that is, the starting column index where each row actually falls within the effective tissue area. and End Column Index For invalid blank lines, the previous valid line range can be inherited or the line can be marked as skipped.
[0039] Step S2: Calculate the default speed execution requirement matrix.
[0040] The processing unit is based on the default scan speed V. def The default speed execution requirement matrix for each scan position is calculated based on the fitted focal plane array. This matrix represents the Z-axis execution requirement that the device needs to undertake at the default scan speed.
[0041] Specifically, for the focal plane sample value Z(r,c) in the r-th row and c-th column (which can also be called the effective sampling point (c from...)... arrive The processing unit first calculates the change in focal height between adjacent sampling positions: ΔZ(r,c) = |Z(r,c+1) - Z(r,c)| Then calculate its local second-order change. For non-boundary sampling points within the effective scan interval (i.e., c satisfies...) <c< ),have: Δ2Z(r,c) = |Z(r,c+1) - 2Z(r,c) + Z(r,c-1)| For non-boundary sampling points within the valid scanning interval, the calculation is performed according to the above formula; for boundary sampling points (c= Or c = Its acceleration requirement is taken from the value of the adjacent interior point or directly set to zero.
[0042] Let Δx be the spatial distance between adjacent column sampling positions in the scanning direction. Then, at the default scanning speed V... def Below, the required rate of change of the Z-axis at this position is: R req (r,c)=V def ×ΔZ(r,c) / Δx The required Z-axis following acceleration for this position is: A req (r,c)=V def 2 ×Δ2Z(r,c) / Δx 2 In addition, to account for control link response latency, the processing unit also calculates the effective response margin at this location under the default speed: T mar (r,c)=Δx / V def -t delay -t cycle Where t delay To control response latency, t cycle For the trigger period, Δx is the spatial distance between adjacent sampling positions in the scanning direction, and its value is equal to the physical pixel spacing of the scanned image in the row direction. Specifically, t delay t is the control link delay constant from the issuance of the speed command to the start of the mechanical response. cycle Both are period constants for position-triggered sampling and are determined by the device hardware characteristics.
[0043] The above calculation yields the default speed execution requirement matrix, which includes the Z-axis change rate requirement, Z-axis following acceleration requirement, and response time margin for each location.
[0044] Step S3: Identify the execution violation area and deduce the executable speed matrix based on the device's dynamic focus capability.
[0045] The processing unit reads the dynamic focusing capability parameter set corresponding to the current objective lens and the current device. This parameter set includes at least the device's maximum permissible Z-axis change rate R. z,max The maximum permissible Z-axis following acceleration A of the equipment z,max (Take a positive value), default scan speed V def Minimum stable scan rate V min Control response delay t delay The platform can use deceleration a x,max and trigger period t cycle .
[0046] The processing unit first identifies the execution violation region at the default scan speed. A minimum safety response margin T is pre-set. safe Its value ranges from 0.1ms to 5ms, and is preferably 1ms in this embodiment. For any position (r,c), if at least one of the following conditions is met, the position is determined to be an execution violation position under the default speed: (1) R req (r,c)>R z,max ; (2) A req (r,c)>A z,max ; (3) T mar (r,c)≤T safe When multiple adjacent violation locations are connected or clustered within the same window, the processing unit merges them into an execution violation region.
[0047] Furthermore, the processing unit inversely calculates the upper limit of the locally executable speed based on the comparison between execution requirements and device capabilities. Safety factors η1, η2, and η3 are pre-set, each with an independent value range of 0.7 to 0.95; in this embodiment, 0.85 is preferred. Simultaneously, a very small positive number ε is set. R ε A ε T Its value is less than one-thousandth of the measurement accuracy of the equipment, and in this embodiment, it is preferably taken as 0.001.
[0048] Based on the comparison between the Z-axis rate of change demand and capacity, the rate demand ratio Q is calculated. rate (r,c)=R req (r,c) / R z,max When Qrate When (r,c)>1, the corresponding upper limit of the reverse velocity is: V rate (r,c)=η1×V def ×R z,max / max(R req (r,c),ε R ) Based on the comparison of Z-axis following acceleration demand and capability, the acceleration demand ratio Q is calculated. acc (r,c)=A req (r,c) / A z,max When Q acc When (r,c)>1, the corresponding upper limit of the reverse velocity is: V acc (r,c)=η2×V def ×sqrt(A z,max / max(A req (r,c),ε A )) Calculate the response-demand ratio Q based on the response time constraint. delay (r,c)=(t delay +t cycle +T safe ) / max(Δx / V def ,ε T When Q delay When (r,c)>1, the corresponding upper limit of the reverse velocity is: V delay (r,c)=η3×Δx / (t delay +t cycle +T safe ) The processing unit, by combining the above constraints, obtains the executable speed matrix, denoted as V. allow (r,c): V allow (r,c)=min(V def V rate (r,c),V acc (r,c),V delay (r,c),V hw ) Among them, V hw The maximum scanning speed allowed by the equipment structure is determined by the objective lens magnification, stage motor performance, and safety specifications.
[0049] It should be noted that when the execution demand at the default speed is close to but does not exceed the device's capacity limit (e.g., R...), req Slightly smaller than R z,max The safety factor will make V rate(r,c) is slightly lower than V def This introduces a safety margin into the executable speed matrix, which is the preferred design of this invention.
[0050] Step S4: Compress the executable velocity matrix into a row-level discrete velocity table.
[0051] The processing unit compresses the executable velocity matrix for each row, generating a row-level discrete velocity table. Specific compression rules include: (1) Set the minimum stable speed threshold V min If V at a certain position allow (r,c) <V min If so, then mark that position as an execution violation position.
[0052] (2) Set the minimum segment length L seg,min If the length of a certain low-speed candidate segment is less than L seg,min Then, based on the speed difference between the two sides, the violation density, and the transition cost, the process will be either absorption merging, extended merging, or violation transfer to rescanning.
[0053] (3) Set the threshold H for merging adjacent segments merge If the velocity difference between two adjacent target segments is less than H merge If so, they will continue to be merged into the same segment.
[0054] (4) Set the threshold N for the maximum number of segments in a single line. seg,max If the number of segments in a line still exceeds N after compression. seg,max If a violation occurs, the secondary speed ranges will be merged according to priority, or the high-risk areas in a particular region will be transferred to the violation area for separate processing.
[0055] After the above processing, the r-th row yields several discrete velocity segments: Seg(r,k)={c start (r,k),c end (r,k),V seg (r,k)}, where k is the segment number within that row, c start and c end These are the starting and ending columns of this segment, respectively, and the target velocity V. seg (r,k) takes the V within this segment. allow The minimum or safe quantile of (r,c).
[0056] Step S5: Calculate the inter-segment transition buffer and generate segmented execution control instructions.
[0057] The processing unit calculates the inter-segment transition buffer based on the speed difference between adjacent speed segments in the row-level discrete speed table. A minimum reserved buffer length L0 is preset, with a value ranging from 0.1 mm to 1 mm, and preferably 0.5 mm in this embodiment.
[0058] For two adjacent segments Seg(r,k) and Seg(r,k+1): If V seg (r,k)>V seg If (r, k+1), then set an advance deceleration buffer length before the latter boundary segment: L pre (r,k)=max(L0,(V seg (r,k) 2 -V seg (r,k+1) 2 ) / (2×a x,max )) If V seg (r,k) <V seg If (r, k+1), then set the recovery acceleration buffer length L at the end of the previous segment or the beginning of the next segment. post (r,k). Its calculation method is the same as L. pre Similarly, using the platform's available acceleration (typically related to a) x,max equal).
[0059] Combining segment boundaries and buffer lengths, the processing unit generates segmented execution control instructions. Each instruction includes the line number, the segment start column and the segment end column, the target execution speed, the length of the early deceleration buffer, the length of the recovery acceleration buffer, the range of the focal plane array referenced by the segment, and whether it belongs to an adjacent segment of the violation region.
[0060] Step S6: Perform discrete segmented variable speed scanning row by row.
[0061] The motion control unit executes discrete segmented variable speed scanning for each scan line according to the segmented execution control commands. For any segment Seg(r,k), the motion control unit performs the following actions: initiating speed switching in the pre-deceleration buffer zone before entering the segment; and maintaining the target speed V within the segment. Seg (r,k) controls the platform movement; within this segment, the target focal height corresponding to the current position is obtained by looking up a table or interpolating based on the fitted focal plane array, and continuous following is performed; when leaving this segment, the speed is smoothly switched to the next segment according to the length of the recovery buffer.
[0062] For implementations using a serpentine scanning method, the discrete velocity values of the same row are directly reused during reverse scanning, with mirrored references only made in the column index order.
[0063] Step S7: Perform partial repair or write-back update on the violation area.
[0064] The processing unit will mark the corresponding region as an execution violation region that needs to be repaired in the following cases: V at a certain location. allow (r,c) <V minThe compression of a certain line produces too many speed segments, exceeding the maximum number of segments per line threshold; the length of the advance deceleration buffer required for adjacent segments is greater than the allowable length of the current effective organization interval; the review after scanning reveals that the clarity of local images has significantly decreased or the execution trajectory residual exceeds the limit.
[0065] For regions with execution violations, the processing unit performs at least one of the following repair actions: performs point patching and refits the local focal plane for the local region; performs local smoothing reconstruction for the local region to reduce execution demand spikes caused by extreme local focal height changes; expands the front and rear buffers and regenerates the row-level discrete velocity table while keeping the current focal plane unchanged; transfers the local region to a low-speed scan task for separate processing; and updates the safety factors η1, η2, η3 or the local calibration lookup table based on the feedback from this execution for reuse in subsequent similar samples.
[0066] Example 2 This embodiment also provides a pathological slide row-level discrete velocity planning and scanning system based on the device's dynamic focusing capability to deduce the executable velocity matrix. The system includes: The imaging unit is used to acquire preview images and focused images of pathological sections.
[0067] The processing unit is used to generate a fitted focal plane array and row-level effective scanning intervals, calculate a default speed execution requirement matrix based on the fitted focal plane array and default scanning speed, compare the execution requirement matrix with the device's dynamic focus capability parameter set to identify execution violation areas and reverse-engineer an executable speed matrix, compress the executable speed matrix into a row-level discrete speed table, and generate segmented execution control instructions based on the row-level discrete speed table. The instructions include an inter-segment transition buffer strategy.
[0068] The motion control unit is used to drive the stage and focusing mechanism to perform discrete segmented variable speed scanning by executing control commands in segments.
[0069] The data management unit is used to save speed plans and execution status.
[0070] Example 3 This embodiment also provides an electronic device, see reference. Figure 2 It includes 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 perform the steps in any of the above method embodiments.
[0071] Specifically, the processor 402 may include a central processing unit (CPU), or an application-specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement embodiments of the present invention.
[0072] Memory 404 may include a mass storage device for data or instructions. For example, and not limitingly, memory 404 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, memory 404 may include removable or non-removable (or fixed) media. Where appropriate, memory 404 may be internal or external to a data processing device. In a particular embodiment, memory 404 is non-volatile memory. In a particular embodiment, memory 404 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable read-only memory (EPROM), an electrically erasable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.
[0073] The memory 404 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 402.
[0074] The processor 402 reads and executes computer program instructions stored in the memory 404 to implement any of the pathological slide row-level discrete velocity planning and scanning methods in the above embodiments.
[0075] 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.
[0076] The transmission device 406 can be used to receive or send data via a network. Specific examples of the network described above may include wired or wireless networks provided by the communication provider of the electronic device. In one example, the transmission device includes a Network Interface Controller (NIC), which can connect to other network devices via a base station to communicate with the Internet. In another example, the transmission device 406 may be a Radio Frequency (RF) module used for wireless communication with the Internet.
[0077] Input / output device 408 is used to input or output information.
[0078] Example 4 This embodiment also provides a readable storage medium storing a computer program, the computer program including program code for controlling a process to execute the process, the process including the pathological slide row-level discrete velocity planning and scanning method according to Embodiment 1.
[0079] It should be noted that the specific examples in this embodiment can refer to the examples described in the above embodiments and optional implementations, and will not be repeated here.
[0080] Generally, various embodiments can be implemented in hardware or dedicated circuitry, software, logic, or any combination thereof. Some aspects of the invention can be implemented in hardware, while others can be implemented by 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, flowcharts, or using some other graphical representation, it should be understood that, by way of non-limiting example, these blocks, apparatuses, systems, techniques, or methods described herein can be implemented in hardware, software, firmware, dedicated circuitry or logic, general-purpose hardware or controllers or other computing devices, or some combination thereof.
[0081] Embodiments of the present invention can be implemented by computer software, which may be executable by a data processor of a mobile device, such as 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 can be stored in any device-readable data storage medium, and they include program instructions for performing specific tasks. The computer program product may include one or more computer-executable components configured to perform the embodiments when the program is run. The one or more computer-executable components may be at least one piece of software code or a portion thereof. Additionally, it should be noted in this respect that, as Figure 1 Any box in the logical flow can represent a program step, or interconnected logic circuits, boxes and functions, or a combination of program steps and logic circuits, boxes and functions. Software can be stored on physical media such as memory chips or blocks of storage implemented within a processor, magnetic media such as hard disks or floppy disks, and optical media such as DVDs and their data variants, CDs, etc. The physical medium is a non-transient medium.
[0082] Those skilled in the art should understand that the technical features of the above embodiments can be combined in any way. For the sake of brevity, not all possible combinations of the technical features in the above embodiments have been 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.
[0083] The above embodiments are merely illustrative of several implementations of the present invention, and their descriptions are relatively specific and detailed, but they should not be construed as limiting the scope of the present invention. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of the present invention, and these all fall within the protection scope of the present invention. Therefore, the protection scope of the present invention should be determined by the appended claims.
Claims
1. A method for row-level discrete velocity planning and scanning of pathological sections, characterized in that, Includes the following steps: Obtain the fitted focal plane array and row-level effective scan interval of the pathological sections; Based on the fitted focal plane array and the default scanning speed, a default speed execution requirement matrix is calculated. The execution requirement matrix represents the dynamic focus execution requirements that the device needs to undertake under the default scanning speed. The execution requirement matrix is compared with the device's dynamic focus capability parameter set to identify execution violation areas. Based on the comparison results, the upper limit of the allowed scanning speed for each scanning position is deduced to generate an executable speed matrix. The executable velocity matrix is compressed into a row-level discrete velocity table according to a preset discretization rule; Based on the row-level discrete speed table, segmented execution control instructions are generated. The segmented execution control instructions include an inter-segment transition buffer strategy determined according to the difference between adjacent speed segments, and discrete segmented variable speed scanning is performed according to the segmented execution control instructions.
2. The method for planning and scanning row-level discrete velocity of pathological sections as described in claim 1, characterized in that, The dynamic focus execution requirements include at least one of the following: Z-axis change rate requirement, Z-axis following acceleration requirement, and response time requirement. The steps for calculating the default speed execution demand matrix include: The required Z-axis change rate is calculated based on the change in focal height at adjacent positions in the fitted focal plane array and the default scanning speed. And / or, The required Z-axis following acceleration is calculated based on the local second-order changes in the fitted focal plane array and the default scan speed; and / or... The effective response margin is calculated based on the spatial distance between adjacent locations, the default scan speed, and the control response delay to characterize the response time requirement.
3. The method for planning and scanning row-level discrete velocity of pathological sections as described in claim 2, characterized in that, The set of parameters for the device's dynamic focus tracking capability includes at least one of the following: the device's maximum permissible Z-axis change rate, the device's maximum permissible Z-axis following acceleration, and a preset safety response time. The step of inferring the upper limit of the allowed scanning speed for each scanning position based on the comparison results and generating an executable speed matrix includes: When the required Z-axis rate of change exceeds the maximum permissible Z-axis rate of change of the device, the first speed upper limit is calculated by reverse calculation based on the ratio of the maximum permissible Z-axis rate of change of the device to the required Z-axis rate of change; and / or, When the required Z-axis following acceleration exceeds the maximum permissible Z-axis following acceleration of the device, a second speed upper limit is calculated based on the ratio of the maximum permissible Z-axis following acceleration to the required Z-axis following acceleration; and / or, When the effective response margin does not meet the preset safety response time, the upper limit of the third speed is calculated by back-calculating based on the control response delay and the preset safety response time; The upper limit of the scan speed at each position in the executable speed matrix is determined by combining at least one of the default scan speed, the first speed limit, the second speed limit, and the third speed limit.
4. The method for row-level discrete velocity planning and scanning of pathological sections as described in claim 1, characterized in that, The preset discrete rules include at least one of the following: minimum stable speed threshold, minimum segment length threshold, adjacent segment merging threshold, and maximum number of segments in a single line threshold; The step of compressing the executable velocity matrix into a row-level discrete velocity table according to a preset discretization rule includes: Locations below the minimum stable velocity threshold are marked as violation regions; and / or, Candidate segments with a length less than the minimum segment length threshold will be merged or transferred to violation processing; and / or, Merge adjacent segments whose target velocity difference is less than the adjacent segment merging threshold into a single segment; and / or, When the number of segments in a compressed single line exceeds the maximum number of segments in a single line threshold, secondary speed segments are merged according to priority or the process is switched to violation handling.
5. The method for planning and scanning row-level discrete velocity of pathological sections as described in claim 1, characterized in that, The steps for generating segmented execution control commands based on the row-level discrete velocity table include: For cases where the target velocity of the preceding segment is greater than that of the following segment, an advance deceleration buffer is set before the boundary of the following segment. The length of the advance deceleration buffer is determined based on the difference in target velocities between adjacent segments and the available deceleration of the platform; and / or, If the target speed of the first segment is less than that of the second segment in two adjacent segments, a recovery acceleration buffer is set at the segment boundary.
6. The method for row-level discrete velocity planning and scanning of pathological sections as described in claim 1, characterized in that, It also includes a step of repairing execution violation areas, which include areas where the executable speed is lower than the minimum stable scan speed, areas where the number of segments after compression exceeds the threshold of the maximum number of segments per line, or areas where the buffer length is greater than the allowed length of the effective tissue interval. The repair steps include at least one of the following: Local point patching and refitting of the local focal plane are performed on the region of execution violation. Perform local smooth reconstruction on the region of execution violation; Expand the front and rear buffer zones and regenerate the row-level discrete velocity table; The area with the execution violation will be transferred to a low-speed rescanning task for separate processing.
7. The method for row-level discrete velocity planning and scanning of pathological sections as described in claim 1, characterized in that, The steps for executing discrete segmented variable speed scanning according to the segmented execution control command include: Speed switching begins in the pre-deceleration buffer zone before entering the current segment; Within the current segment, the platform is controlled to move at the target speed, and continuous following is performed based on the target focal height obtained from the fitted focal plane array. When leaving the current segment, press Restore Acceleration Buffer to smoothly switch to the next speed segment; When using a serpentine scanning method for reverse scanning, the mirror references the row-level discrete velocity table of the current row.
8. A pathological slide row-level discrete velocity planning and scanning system, characterized in that, include: Imaging unit, used to acquire preview images and focused images of pathological sections; The processing unit is used to generate a fitted focal plane array and a row-level effective scanning interval, calculate a default speed execution requirement matrix based on the fitted focal plane array and the default scanning speed, compare the execution requirement matrix with the device dynamic focus capability parameter set to identify execution violation areas and back-generate an executable speed matrix, compress the executable speed matrix into a row-level discrete speed table, and generate segmented execution control instructions based on the row-level discrete speed table, wherein the instructions include an inter-segment transition buffer strategy. A motion control unit is used to drive the stage and focusing mechanism to perform discrete segmented variable speed scanning according to the segmented execution control commands; The data management unit is used to save speed plans and execution status.
9. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the pathological slide row-level discrete velocity planning and scanning method according to any one of claims 1 to 7.
10. A readable storage medium, characterized in that, The readable storage medium stores a computer program, the computer program including program code for controlling a process to execute the process, the process including the pathological slide row-level discrete velocity planning and scanning method according to any one of claims 1 to 7.