CN118276298A

CN118276298A - Slide scanning method, slide reader and storage medium

Info

Publication number: CN118276298A
Application number: CN202211726709.0A
Authority: CN
Inventors: 严欧飞; 闫红力; 林冲
Original assignee: Shenzhen Reetoo Biotechnology Co Ltd
Current assignee: Shenzhen Reetoo Biotechnology Co Ltd
Filing date: 2022-12-30
Publication date: 2024-07-02

Abstract

The embodiment of the invention provides a slide scanning method, a slide reader and a storage medium, belonging to the field of image scanning. The method comprises the following steps: controlling a microscope device to scan a sample area on a slide based on a first magnification to obtain N first images; determining the quality evaluation scores of the first images, and selecting a target image from N first images according to the quality evaluation score of each first image; and controlling the microscope device to scan a sample area corresponding to the target image on the slide based on the second magnification to obtain a plurality of second images, and stitching the plurality of second images to obtain a target stitching image. The technical scheme of the embodiment of the invention greatly improves the scanning accuracy of the slide.

Description

Slide scanning method, slide reader and storage medium

Technical Field

The present invention relates to the field of image scanning, and in particular, to a slide scanning method, a reader, and a storage medium.

Background

Currently, in order to assist a doctor in diagnosing a patient, an inspector is required to manufacture a slide from a biological sample such as body fluid, semen, blood, secretion, excreta, organ tissue, and the like of the patient, scan the slide by a reader, and analyze the scanned image by analysis software. However, there is a certain reject ratio in the preparation of the slide, and in the case of a bad slide, for example, the sample concentration of some areas in the slide is higher, and the sample concentration of some areas is lower, so when the slide is scanned by the reader, the bad areas with higher sample concentration or lower sample concentration may be scanned, and the scanned images have abnormal images which cannot accurately describe the isolated biological sample, and the abnormal images may affect the analysis result of the isolated biological sample. Therefore, how to improve the accuracy of slide scanning is a problem to be solved at present.

Disclosure of Invention

The embodiment of the invention provides a slide scanning method, a slide reader and a storage medium, aiming at improving the accuracy of slide scanning.

In a first aspect, an embodiment of the present invention provides a slide scanning method, including:

Controlling a microscope device to scan a sample area on a slide based on a first magnification to obtain N first images;

determining the quality evaluation scores of the first images, and selecting a target image from N first images according to the quality evaluation score of each first image;

And controlling the microscope device to scan a sample area corresponding to the target image on the slide based on a second magnification to obtain a plurality of second images, and splicing the second images to obtain a target spliced image, wherein the first magnification is smaller than the second magnification.

In a second aspect, embodiments of the present invention also provide a film reader comprising a microscope device, a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for enabling a connection communication between the microscope device, the processor and the memory, wherein the computer program, when executed by the processor, implements the slide scanning method according to the first aspect.

In a third aspect, embodiments of the present invention also provide a storage medium for computer-readable storage, the storage medium storing one or more programs executable by one or more processors to implement the slide scanning method as described in the first aspect.

The embodiment of the invention provides a slide scanning method, a slide reader and a storage medium, wherein the embodiment of the invention scans a sample area on a slide by controlling a microscope device to use a lower magnification ratio to obtain N first images, then determines the quality evaluation scores of the first images, selects target images from the N first images according to the quality evaluation scores of each first image, finally controls the microscope device to scan the sample area corresponding to the target images on the slide by using the higher magnification ratio, and splices a plurality of second images to obtain a target spliced image, thereby realizing image acquisition of the sample area with higher preparation quality of an isolated biological sample, greatly improving the accuracy of slide scanning, ensuring the preparation quality of the isolated biological sample in the acquired images, avoiding the problem of poor preparation quality of the isolated biological sample in the acquired images due to poor slide preparation, and avoiding larger deviation of analysis results due to poor slide preparation in the subsequent analysis of the images.

Drawings

In order to more clearly illustrate the technical solutions of the embodiments of the present application, the drawings required for the description of the embodiments will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present application, and other drawings may be obtained according to these drawings without inventive effort for a person skilled in the art.

FIG. 1 is a schematic flow chart of a slide scanning method according to an embodiment of the present invention;

FIG. 2 is a schematic diagram showing a distribution of N scanning position points in a sample area according to an embodiment of the present invention;

FIG. 3 is another distribution diagram of N scan position points within a sample area in an embodiment of the present invention;

FIG. 4 is a further schematic distribution of N scanning position points within a sample region in an embodiment of the present invention;

FIG. 5 is a block diagram schematically illustrating a structure of a film reader according to an embodiment of the present invention.

Detailed Description

The following description of the embodiments of the present invention will be made clearly and fully with reference to the accompanying drawings, in which it is evident that the embodiments described are some, but not all embodiments of the invention. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.

The flow diagrams depicted in the figures are merely illustrative and not necessarily all of the elements and operations/steps are included or performed in the order described. For example, some operations/steps may be further divided, combined, or partially combined, so that the order of actual execution may be changed according to actual situations.

It is to be understood that the terminology used in the description of the invention herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the invention. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise.

The embodiment of the invention provides a slide scanning method, a slide reader and a storage medium. The slide scanning method realizes image acquisition of a sample area with higher preparation quality of the in-vitro biological sample, greatly improves the accuracy of slide scanning, can ensure the preparation quality of the in-vitro biological sample in the acquired image, and avoids the problem of poor preparation quality of the in-vitro biological sample in the acquired image caused by poor slide preparation, so that larger deviation of analysis results caused by poor slide preparation can be avoided when the images are analyzed subsequently.

Some embodiments of the invention are described in detail below with reference to the accompanying drawings. The following embodiments and features of the embodiments may be combined with each other without conflict.

Referring to fig. 1, fig. 1 is a flow chart of a slide scanning method according to an embodiment of the invention. The slide scanning method is applied to a slide reader to improve the scanning accuracy of slides.

As shown in fig. 1, the slide scanning method includes steps S101 to S103.

Step S101, controlling a microscope device to scan a sample area on a slide based on a first magnification to obtain N first images.

In the embodiment of the invention, the microscope device and the slide can relatively move, so that the microscope device can scan the whole sample area on the slide. For example, a slide reader includes a microscope device, a stage for placing a slide specimen, and a motion mechanism for driving the stage or the microscope device in motion to enable relative movement of the microscope device and the slide.

In one embodiment, N scanning position points of a microscope device within a sample region on a slide are acquired; the control microscope device shoots the sample area at each of the N scanning position points based on the first magnification to obtain N first images. Wherein N is a natural number greater than 1, and N scanning position points are uniformly dispersed in the sample area at intervals, or N scanning position points are continuously distributed in a partial area or the whole sample area of the sample area.

In one embodiment, N scan position points are uniformly spaced apart within a sample region on a slide, for example, as shown in fig. 2, the sample region 10 includes 81 sample sub-regions 11, and the scan position points of the microscope device within the sample region 10 include 41 scan position points 12, the scan position points 12 being the center points of the sample sub-regions 11, that is, 41 scan position points 12 are uniformly spaced apart within the sample region 10, and any adjacent two scan position points 12 of the same row or column are spaced apart by one sample sub-region 11.

In an embodiment, the N scanning position points are continuously distributed in a partial area or in the entire sample area. For example, as shown in fig. 3, the sample region 10 includes 81 sample sub-regions 11, and the scanning position points of the microscope device within the sample region 10 include 81 scanning position points 12, the scanning position points 12 being the center points of the sample sub-regions 11, that is, the 81 scanning position points 12 are continuously distributed throughout the sample region 10. As another example, as shown in fig. 4, the sample region 10 includes 81 sample sub-regions 11, and the scanning position points of the microscope device within the sample region 10 include 25 scanning position points 12 of the middle region.

In one embodiment, the manner of acquiring N scan position points of the microscope device within a sample area on a slide may be: acquiring position information of a sample area on a slide; according to the position information of the sample area, N scanning position points of the microscope device in the sample area on the slide are acquired. The N scanning position points of the microscope device within the sample region on the slide can be accurately determined from the positional information of the sample region on the slide.

In an embodiment, according to the position information of the sample area, the manner of acquiring N scanning position points of the microscope device in the sample area on the slide may be: determining a total area of a sample area on the slide; under the condition that the total area is larger than a preset area threshold value, N scanning position points are uniformly and alternately determined in a sample area on a slide according to the position information of the sample area; in the case where the total area is less than or equal to the preset area threshold, N scan position points are continuously determined throughout the sample area on the slide. By determining N scanning position points at even intervals in the sample area in case the sample area is large, it is ensured that the microscope device can scan different areas of the sample area uniformly while reducing scanning time consumption, while N scanning position points are determined continuously in the whole sample area in case the sample area is small, it is ensured that the microscope device can scan the whole sample area.

It will be appreciated that the preset area threshold may be set based on practical situations, which is not particularly limited in the embodiments of the present invention. For example, the preset area threshold value is 9mm×9 mm=81 mm ², and if the total area of the sample areas is 19mm×19 mm=361 mm ², the preset area threshold value is larger than 81mm ², so that 81 scanning position points are uniformly spaced in the sample area of 19mm×19mm, and if the total area of the sample areas is 5mm×5 mm=25 mm ², the preset area threshold value is smaller than 81mm ², so that 81 scanning position points are continuously determined in the sample area of 5mm×5 mm.

In one embodiment, the manner of determining the total area of the sample area on the slide may be: the total area of the sample area is determined based on the positional information of the sample area on the slide. The position information of the sample area comprises slide coordinates of a plurality of boundary corner points of the sample area in a slide coordinate system, wherein the slide coordinate system is a rectangular coordinate system established by taking a reference point on a slide as an origin, and the reference point can be a central point of the slide or any boundary corner point. For example, the slide coordinates of boundary corner a, boundary corner B, boundary corner C, and boundary corner D of the sample region are a (x ₁,y₁)、B(x₂,y₁)、C(x₁,y₂) and D (x ₂,y₂), respectively, and the total area of the sample region can be calculated from a (x ₁,y₁)、B(x₂,y₁)、C(x₁,y₂) and D (x ₂,y₂).

In one embodiment, the total area of the sample area on the slide may also be determined by: scanning the two-dimensional code on the slide to obtain the sample type of the in-vitro biological sample on the slide; and inquiring a pre-stored mapping relation table between the sample types and the areas to obtain the total area of the sample area on the slide. The mapping relation table between the sample type and the area is set based on an empirical value, which is not particularly limited in the embodiment of the present invention.

In one embodiment, the manner of acquiring the positional information of the sample area on the slide may be: scanning the two-dimensional code on the slide to obtain the sample type of the in-vitro biological sample on the slide; and inquiring a mapping relation table between the pre-stored sample type and the position information of the sample area to obtain the position information of the sample area on the slide. The mapping relation table between the sample type and the position information of the sample area is set based on an empirical value, which is not particularly limited in the embodiment of the present invention. By setting the mapping relation table between the sample type and the position information of the sample area in advance, the position information of the sample area can be obtained without complex calculation, and the scanning efficiency of the slide can be improved.

Step S102, determining the quality evaluation scores of the first images, and selecting a target image from N first images according to the quality evaluation score of each first image.

In the embodiment of the invention, the quality evaluation score is used for describing the preparation quality of the in-vitro biological sample in the sample area corresponding to the first image. The higher the quality evaluation score of the first image, the better the preparation quality of the isolated biological sample in the sample area corresponding to the first image, and the lower the quality evaluation score of the first image, the worse the preparation quality of the isolated biological sample in the sample area corresponding to the first image.

In an embodiment, the manner of determining the quality evaluation score of the first image may include: and inputting the first image into a preset quality scoring model for processing to obtain the quality evaluation score of the first image. The quality scoring model is obtained by training a neural network model according to a plurality of training sample images marked with quality evaluation scores and test sample images, and the neural network model comprises, but is not limited to, a convolutional neural network (Convolutional Neural Networks, CNN) model, a deep neural network (Deep Neural Networks, DNN) model, a cyclic neural network (Recurrent Neural Network, RNN) model, a neural network (Factorisation Machine supported Neural Network, FNN) model supporting a decomposer and a neural factor decomposer (Neural Factorization Machine, NFM) model. The quality evaluation score of the first image can be quickly and accurately determined by pre-training a quality scoring model and then using the quality scoring model.

In an embodiment, the training of the neural network model according to the plurality of training sample images marked with the quality evaluation scores and the test sample image may be: selecting one training sample image from a plurality of training sample images each time, inputting the training sample images into a neural network model for processing, and obtaining predicted quality evaluation scores; calculating a loss value of the neural network model according to the labeled quality evaluation score and the predicted quality evaluation score corresponding to the training sample image, updating parameters of the neural network model under the condition that the loss value is larger than a preset loss value, and returning to execute the step of selecting one training sample image from a plurality of training sample images each time to input the training sample image into the neural network model for processing to obtain the predicted quality evaluation score; stopping performing iterative training under the condition that the loss value is smaller than or equal to a preset loss value to obtain an initial quality scoring model; sequentially inputting each test sample image into an initial quality scoring model for processing to obtain a predicted quality evaluation score corresponding to each test sample image; for each test sample image, calculating a difference value between the predicted quality evaluation score and the annotated quality evaluation score of the test sample image, determining that the test sample image passes the test if the difference value is less than or equal to a preset difference value, and determining that the test sample image fails the test if the difference value is greater than the preset difference value; determining a ratio of the number of test sample images passing the test to the total number of test sample images, and determining an initial quality scoring model as a final quality scoring model if the ratio is greater than or equal to a preset ratio; and under the condition that the ratio is smaller than a preset ratio, a plurality of training sample images marked with quality evaluation scores are selected again to train the neural network model, and the process is repeated. The preset loss value, the preset difference value and the preset ratio may be set based on practical situations, which is not particularly limited in the embodiment of the present invention.

In an embodiment, the quality evaluation score of the training sample image is determined based on the recognition result of the target substance of the training sample image and/or the distribution uniformity of the substance in the training sample image. The quality evaluation score of the test sample image is determined based on the identification of the target substance of the test sample image and/or the uniformity of the distribution of the substance in the test sample image. The recognition result of the target substance of the training sample image is obtained by recognizing the target substance of the training sample image, wherein the recognition result of the target substance comprises the presence of the target substance in the training sample image or the absence of the target substance in the training sample image, and the target substance comprises at least one of trichomonas, hypha and bacillus. The quality evaluation score of the first image can be accurately described through the identification result of the target substance and/or the distribution uniformity of the substance in the training sample image, so that the preparation quality of the isolated biological sample in the sample area corresponding to the first image can be accurately described.

It can be understood that, if the recognition result of the target substance is that the target substance exists in the training sample image, the quality evaluation score of the label of the corresponding training sample image is higher, and if the recognition result of the target substance is that the target substance does not exist in the training sample image, the quality evaluation score of the label of the training sample image is lower. The quality evaluation score and the distribution uniformity of the substances in the training sample image are in positive correlation, namely, the higher the distribution uniformity of the substances in the training sample image is, the higher the quality evaluation score of the labels of the training sample image is, and the lower the distribution uniformity of the substances in the training sample image is, the lower the quality evaluation score of the labels of the training sample image is.

In an embodiment, according to the quality evaluation score of each first image, the manner of selecting the target image from the N first images may be: sequencing each first image according to the size sequence of the quality evaluation score to obtain an image sequencing queue; the first M first images in the image sorting queue are acquired as target images. The number of target images, that is, the specific value of M, may be set by the user as required, which is not particularly limited in the embodiment of the present invention. By selecting M first images with the front quality evaluation scores as target images, the microscope device can scan a sample area with better slide quality, and the accuracy of slide scanning can be improved.

In one embodiment, the quality assessment score of the training sample image is determined based on the uniformity of distribution of the substance in the training sample image and the sharpness of the training sample image. Or the quality evaluation score of the training sample image is determined according to the recognition result of the target substance of the training sample image and the definition of the training sample image. Or the quality evaluation score of the training sample image is determined according to the distribution uniformity of substances in the training sample image, the identification result and the definition of target substances of the training sample image.

In an embodiment, the method for determining the quality evaluation score of the first images and selecting the target image from the N first images according to the quality evaluation score of each first image may include: determining whether a target substance exists in the first image, and setting a quality evaluation score of the first image to a preset value when the target substance exists in the first image; when the first image does not contain the target substance, inputting the first image into a preset quality scoring model for processing to obtain a quality evaluation score of the first image; and selecting a first image with the quality evaluation score larger than or equal to a preset value from N first images as a target image. Wherein the glass slide is coated with a microecological sample, and the target substance comprises at least one of trichomonas, hypha and bacillus. Because the target substances such as trichomonas, hypha and bacillus are objects of great concern in cell analysis, when the target substances exist in the first image, the quality evaluation score of the first image is set to be a preset value, and when the target substances do not exist in the first image, the first image is scored by using a quality scoring model, and the first image with the quality evaluation score larger than or equal to the preset value is selected from N first images as the target image, so that a sample area containing the target substances and a sample area with high quality evaluation score can be accurately positioned and shot, and the accuracy of slide scanning is improved.

For example, n=81, and the number of first images of 81 is denoted by [ a ₁,A₂,...,A₈₀,A₈₁ ], and the recognition result of the target substance in each first image can be obtained by recognizing the target substance in each first image, and the first images a ₃, a ₆, a, the first image a ₁₅, the first image a ₂₀, the first image a ₂₂, and the first image a ₃₀ contain a target substance, Then first image A ₃, first image A ₆, first image A ₁₅, first image A ₂₀, The quality evaluation scores of the first image A ₂₂ and the first image A ₃₀ are set to be preset values, each of the remaining first images is scored by using a quality scoring model, and the first images A ₃, A ₆ are found by comparison, First image A ₁₅, first image A ₂₀, first image A ₂₂ and first image A ₃₀, first image A ₄₃, The quality evaluation scores of the first image A ₅₁, the first image A ₆₆ and the first image A ₈₁ are larger than or equal to a preset value, the first image A ₃, First image A ₆, first image A ₁₅, first image A ₂₀, first image A ₂₂ and first image A ₃₀, first image a ₄₃, first image a ₅₁, first image a ₆₆, and first image a ₈₁ are target images.

In an embodiment, the manner of selecting, as the target image, the first image having the quality evaluation score greater than or equal to the preset value from the N first images may be: determining a first number of first images with the quality evaluation score being greater than or equal to a preset value in the N first images; when the first number is larger than or equal to the second number of target images set by a user, selecting first images with the quality evaluation score larger than or equal to a preset value from N first images as target images each time until the number of target images reaches the second number; when the first number is smaller than the second number of target images set by a user, selecting first images with the quality evaluation scores larger than or equal to a preset value from N first images as target images, and selecting corresponding first images from the rest first images as target images each time according to the high-low sequence of the quality evaluation scores until the number of the target images reaches the second number. The second number of target images may be set by the user, which is not specifically limited in the embodiment of the present invention.

And step S103, controlling the microscope device to scan a sample area corresponding to the target image on the slide based on the second magnification to obtain a plurality of second images, and stitching the plurality of second images to obtain a target stitched image.

In the embodiment of the invention, the target image can be one or more, and the first magnification is smaller than the second magnification. For example, the first magnification is 200 times (10-time eyepiece and 20-time objective lens) or 400 times (10-time eyepiece and 40-time objective lens), and the second magnification is 1000 times (10-time eyepiece and 100-time objective lens). The microscope device may include a first objective lens, which may be a 20-fold objective lens or a 40-fold objective lens, and a second objective lens, which may be a 100-fold objective lens. The sample area with good preparation quality is scanned by using higher magnification, a clearer high-power mirror image can be obtained, and a plurality of high-power mirror images are spliced to obtain an image with larger size, so that a user can conveniently observe substances such as trichomonas, hypha and bacillus in an isolated biological sample well.

In an embodiment, an image overlapping rate between any two adjacent second images in the plurality of second images is within a preset image overlapping rate range, where the image overlapping rate is a ratio of an area of a next second image scanned by the microscope device based on the second magnification to an area of a previous second image scanned by the next second image. The preset image overlapping rate range may be set based on practical situations, which is not specifically limited in the embodiment of the present invention. For example, the preset image overlapping rate ranges from 10% to 40%, from 15% to 40%, or from 10% to 45%, or the like. By ensuring that the image overlapping rate between any two adjacent second images in the plurality of second images is in a preset image overlapping rate range, the target spliced image obtained by splicing the plurality of second images can comprehensively contain cells or substances in the corresponding sample area, so that omission of the cells or the substances in the corresponding sample area can be avoided, and the accuracy of slide scanning is improved.

In an embodiment, acquiring an image overlapping rate set by a user, and determining a target movement distance of the object carrying platform after each time of acquiring the second image according to the image overlapping rate and the second magnification; and according to the movement distance, controlling the microscope device to scan the target sample subarea based on the second magnification to obtain a plurality of second images. The target movement distance of the object carrying platform after the second images are acquired each time can be calculated through the image overlapping rate and the second magnification, so that the microscope device is controlled to scan a sample area corresponding to the target image based on the second magnification based on the target movement distance, and the image overlapping rate between any two adjacent second images in the acquired second images can be ensured to be the image overlapping rate set by a user.

For example, the image overlapping rate between any two adjacent second images in the plurality of second images is 40%, the glass slide is placed on the carrying platform, the moving mechanism is used for driving the carrying platform to move so as to realize the relative movement of the microscope device and the glass slide, the corresponding width of each second image is 60um under the 100-time objective lens, the target moving distance of the carrying platform after each second image shooting can be calculated to be 40% = 60um = 24um according to the image overlapping rate of 40% and the corresponding width of the second image, after the first second image is acquired, a corresponding control instruction is issued to a motor for driving the moving mechanism to enable the motor to operate so as to drive the moving mechanism to move, then after the moving distance of the carrying platform reaches the target moving distance, the microscope device is controlled to acquire the second image based on the second magnification, the target number of the second image set by a user is set as P, and the process is repeated, so that the P second images can be obtained.

In an embodiment, the method for controlling the microscope device to scan the sample area corresponding to the target image on the slide based on the second magnification to obtain the plurality of second images may be: acquiring the target number of the second images set by the user; and controlling the microscope device to scan the sample area corresponding to the target image based on the second magnification to obtain second images of the target number. The more the number of the second images is, the longer the time required by the microscope device to scan the sample area corresponding to the target image is, and the shorter the time required by the microscope device to scan the sample area corresponding to the target image is, so that the time required by the microscope device to scan the sample area corresponding to the target image can be regulated and controlled by the user by setting the number of the second images, the time required by the microscope device to scan the sample sub-area corresponding to the target image accords with the requirements of the user, and the user experience is greatly improved.

In an embodiment, the method for controlling the microscope device to scan the sample area corresponding to the target image on the slide based on the second magnification to obtain the plurality of second images may include: determining the position information of a sample area corresponding to the target image according to the target image; and according to the position information, controlling the microscope device to scan a sample area corresponding to the target image based on the second magnification to obtain a plurality of second images. The microscope device can be accurately controlled to scan the sample area corresponding to the target image through the position information of the sample area corresponding to the target image, and the accuracy of slide scanning is improved.

In an embodiment, according to the position information of the sample area corresponding to the target image, the method for controlling the microscope device to scan the sample area corresponding to the target image based on the second magnification, to obtain a plurality of second images may include: acquiring a first slide coordinate of a starting position point and a second slide coordinate of a cut-off position point of a sample area corresponding to a target image from position information of the sample area corresponding to the target image; acquiring a conversion relation between pre-stored slide coordinates and mechanical coordinates, determining a first mechanical coordinate of the object carrying platform when the center of the visual field of the microscope device is located at the starting position point according to the conversion relation and the first slide coordinates, and determining a second mechanical coordinate of the object carrying platform when the center of the visual field of the microscope device is located at the stopping position point according to the conversion relation and the second slide coordinates; controlling the movement of the carrying platform according to the first mechanical coordinates so that the initial position point is positioned at the center of the visual field of the microscope device; and controlling the moving distance of the moving object of the carrying platform each time by taking the first mechanical coordinates as the initial position point, and controlling the microscope device to acquire images based on the second magnification after controlling the moving distance of the moving object of the carrying platform each time, so as to obtain a second image until the mechanical coordinates of the carrying platform are the second mechanical coordinates, thereby obtaining a plurality of second images. The conversion relation between the pre-stored slide coordinates and the mechanical coordinates can be calibrated in advance, and the embodiment of the invention is not particularly limited.

In one embodiment, after step S103, the method further includes: and controlling the display device to display the target spliced image. Because the target spliced image is spliced by a plurality of second images with higher magnification, the target spliced image is displayed, so that the user can conveniently observe trichomonas, hyphae, bacillus, cells and the like, and the user experience is greatly improved.

According to the slide scanning method provided by the embodiment, the microscope device is controlled to scan the sample area on the slide by using the lower magnification, N first images are obtained, then the quality evaluation scores of the first images are determined, the target image is selected from the N first images according to the quality evaluation scores of each first image, finally the microscope device is controlled to scan the sample area corresponding to the target image on the slide by using the higher magnification, the second images are controlled to splice the second images, and the target spliced image is obtained, so that the image acquisition of the sample area with higher preparation quality of the isolated biological sample is realized, the accuracy of slide scanning is greatly improved, the preparation quality of the isolated biological sample in the acquired images can be ensured, the problem that the preparation quality of the isolated biological sample in the acquired images is poor due to poor slide preparation is avoided, and the problem that the analysis result is greatly deviated due to poor slide preparation can be avoided when the images are analyzed later.

Referring to fig. 5, fig. 5 is a schematic block diagram of a film reader according to an embodiment of the present invention.

As shown in FIG. 5, the reader 200 includes a microscope device 210, a processor 220, and a memory 230, with the microscope device 210, the processor 220, and the memory 230 being connected by a bus 240, such as an I2C (Inter-INTEGRATED CIRCUIT) bus.

In particular, the processor 220 is configured to provide computing and control capabilities to support the operation of the entire reader. The Processor 220 may be a central processing unit (Central Processing Unit, CPU), the Processor 220 may also be other general purpose processors, digital signal processors (DIGITAL SIGNAL Processor, DSP), application SPECIFIC INTEGRATED Circuit (ASIC), field-Programmable gate array (Field-Programmable GATE ARRAY, FPGA) or other Programmable logic device, discrete gate or transistor logic device, discrete hardware components, or the like. Wherein the general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.

Specifically, the Memory 230 may be a Flash chip, a Read-Only Memory (ROM) disk, an optical disk, a U-disk, a removable hard disk, or the like.

It will be appreciated by those skilled in the art that the configuration shown in FIG. 5 is a block diagram of only some of the configurations associated with embodiments of the present invention and is not intended to limit the reader to which embodiments of the present invention may be applied, and that a particular reader may include more or fewer components than those shown, or may combine certain components, or may have a different arrangement of components.

The processor 220 is configured to execute a computer program stored in the memory 230, and implement any one of the slide scanning methods provided in the embodiments of the present invention when the computer program is executed.

In one embodiment, the processor 220 is configured to execute a computer program stored in the memory 230 and when executed implement the steps of:

In an embodiment, the processor 220, when implementing determining the quality assessment score for the first image, is configured to implement:

Inputting the first image into a preset quality scoring model for processing to obtain a quality evaluation score of the first image;

the quality scoring model is obtained by training the neural network model according to a plurality of training sample images marked with quality evaluation scores and a plurality of test sample images.

In an embodiment, the quality evaluation score of the training sample image is determined according to the recognition result of the target substance of the training sample image and/or the distribution uniformity of the substance in the training sample image.

In one embodiment, the processor 220 is configured to, when implementing determining the quality evaluation score of the first images, select a target image from the N first images according to the quality evaluation score of each of the first images, implement:

determining whether a target substance exists in the first image, and setting a quality evaluation score of the first image to a preset value when the target substance exists in the first image;

when the first image does not contain a target substance, inputting the first image into a preset quality scoring model for processing to obtain a quality evaluation score of the first image;

And selecting the first image with the quality evaluation score larger than or equal to the preset value from N first images as a target image.

In one embodiment, the slide has a microecological sample coated thereon, and the target substance comprises at least one of trichomonas, hypha, bacillus.

In an embodiment, the image overlapping rate between any two adjacent second images is within a preset image overlapping rate range, where the image overlapping rate is a ratio of an area of the microscope device scanned by the second image to an area of the second image scanned by the next image based on the second magnification to an area of the second image scanned by the next image.

In one embodiment, the processor 220 is configured to, when implementing controlling the microscope device to scan a sample area corresponding to the target image on the slide based on the second magnification, obtain a plurality of second images, implement:

Acquiring the target number of the second images set by the user;

And controlling the microscope device to scan a sample area corresponding to the target image based on a second magnification, so as to obtain second images of the target number.

In one embodiment, the processor 220 is configured to, when implementing controlling the microscope device to scan the sample area on the slide based on the first magnification to obtain N first images, implement:

Acquiring N scanning position points of a microscope device in the sample area;

And controlling the microscope device to shoot the sample area at each of the N scanning position points based on the first magnification, so as to obtain N first images.

In an embodiment, the N scanning position points are uniformly distributed at intervals in the sample area, or the N scanning position points are continuously distributed in a partial area or the whole sample area of the sample area.

In an embodiment, after implementing stitching the plurality of second images to obtain the target stitched image, the processor 220 is further configured to implement:

And controlling a display device to display the target spliced image.

It should be noted that, for convenience and brevity of description, the specific working process of the reader described above may refer to the corresponding process in the foregoing slide scanning method embodiment, and will not be described herein.

Embodiments of the present invention also provide a storage medium for computer readable storage, where the storage medium stores one or more programs that can be executed by one or more processors to implement any of the slide scanning methods provided in the embodiments of the present invention.

The storage medium may be an internal storage unit of the reader according to the foregoing embodiment, for example, a hard disk or a memory of the reader. The storage medium may also be an external storage device of the reader, such as a plug-in hard disk, a smart memory card (SMART MEDIA CARD, SMC), a Secure Digital (SD) card, a flash memory card (FLASH CARD), or the like, which are provided on the reader.

Those of ordinary skill in the art will appreciate that all or some of the steps, systems, functional modules/units in the apparatus, and methods disclosed above may be implemented as software, firmware, hardware, and suitable combinations thereof. In a hardware embodiment, the division between the functional modules/units mentioned in the above description does not necessarily correspond to the division of physical components; for example, one physical component may have multiple functions, or one function or step may be performed cooperatively by several physical components. Some or all of the physical components may be implemented as software executed by a processor, such as a central processing unit, digital signal processor, or microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software may be distributed on computer readable media, which may include computer storage media (or non-transitory media) and communication media (or transitory media). The term computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data, as known to those skilled in the art. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital Versatile Disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, as is well known to those of ordinary skill in the art, communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media.

It should be understood that the term "and/or" as used in the present specification and the appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes such combinations. It should be noted that, in this document, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or system that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or system. Without further limitation, an element defined by the phrase "comprising one … …" does not exclude the presence of other like elements in a process, method, article, or system that comprises the element.

The foregoing embodiment numbers of the present invention are merely for the purpose of description, and do not represent the advantages or disadvantages of the embodiments. While the invention has been described with reference to certain preferred embodiments, it will be understood by those skilled in the art that various changes and substitutions may be made therein without departing from the spirit and scope of the invention as defined by the appended claims. Therefore, the protection scope of the invention is subject to the protection scope of the claims.

Claims

1. A slide scanning method, comprising:

2. The slide scanning method of claim 1, wherein the determining a quality assessment score of the first image comprises:

3. A slide scanning method as claimed in claim 2, wherein the quality assessment score of the training sample image is determined from the recognition result of the target substance of the training sample image and/or the distribution uniformity of the substance in the training sample image.

4. The slide scanning method as claimed in claim 1, wherein the determining the quality evaluation score of the first images and selecting a target image from N first images according to the quality evaluation score of each of the first images includes:

5. The slide scanning method according to claim 4, wherein the slide is coated with a microecological sample, and the target substance includes at least one of trichomonas, hypha, and bacillus.

6. The slide scanning method according to claim 1, wherein an image overlapping ratio between any adjacent two of the second images is within a preset image overlapping ratio range, the image overlapping ratio being a ratio of an area of the microscope device to cover a next one of the second image scans based on a second magnification to an area of the second image scanned by the next one of the second image scans.

7. The slide scanning method according to claim 1, wherein the controlling the microscope device to scan the sample area corresponding to the target image on the slide based on the second magnification to obtain a plurality of second images includes:

Acquiring the target number of the second images set by the user;

8. The slide scanning method as claimed in any one of claims 1 to 7, wherein the controlling the microscope device to scan the sample region on the slide based on the first magnification to obtain N first images includes:

Acquiring N scanning position points of a microscope device in the sample area;

9. The slide scanning method as claimed in claim 8, wherein the N scanning position points are uniformly dispersed at intervals within the sample area, or the N scanning position points are continuously distributed in a partial area of the sample area or the entire sample area.

10. The slide scanning method as claimed in any one of claims 1 to 7, wherein after stitching the plurality of second images to obtain a target stitched image, the method further comprises:

And controlling a display device to display the target spliced image.

11. A reader comprising a microscope device, a processor, a memory, a computer program stored on the memory and executable by the processor, and a data bus for enabling a connection communication between the microscope device, the processor and the memory, wherein the computer program when executed by the processor implements the slide scanning method of any one of claims 1 to 10.

12. A storage medium for computer readable storage, wherein the storage medium stores one or more programs executable by one or more processors to implement the slide scanning method of any one of claims 1 to 10.