RU2824324C1 - Method for determination of presence of slide on microscope object table having multi-slide configuration - Google Patents

Abstract

FIELD: medical computer equipment.

SUBSTANCE: method consists of steps of moving a microscope object table into a pure light region; obtaining a first digital image, which is received as a correcting image. Each color channel of each pixel is assigned a numerical value in the interval from the minimum value corresponding to the black color, to a maximum value corresponding to the maximum saturated color, each color channel of each pixel is encoded with one byte; subsequent digital image is obtained, which is converted using a correcting image by correcting the background, the converted image is stored in memory and taken as a reference image. Object table is then moved to the area of the intended location of the information part of the slide and a digital image is obtained, which is stored in memory; calculating the root-mean-square deviation between the byte arrays of the reference image and the image obtained in the area of the intended location of the information part of the slide; obtained value of root-mean-square deviation is compared with a predetermined threshold value, based on the results of comparison, a conclusion is made on the presence or absence of a slide on the object table.

EFFECT: method provides automatic determination of the presence of a slide on a microscope object table having a multi-slide configuration when operating in transmitted light.

1 cl, 1 dwg

Description

Field of technology to which the invention relates

The invention relates to medical computer technology used for digitalization of biological preparations, in particular using digital microscopy systems, for automatic determination of the presence of a slide on the object table of a microscope having a multi-slide configuration.

State of the art

Currently, automated analysis systems are used to analyze human biological preparations. One of the necessary stages of such analysis is the creation of a digital image of the biological preparation (digitization). In its simplest form, an automated system for digitizing a biological preparation is a microscope with a digital camera and a motorized stage connected to it, controlled by a computer. Due to the large number of analyses performed, in order to speed up the work, modern automated systems for digitizing biological preparations have stage tables designed to accommodate several slides with biological preparations at once. To ensure the smooth operation of such systems in automatic mode, among other things, solutions are needed that would allow determining the presence of a slide on the microscope stage.

The prior art discloses a method disclosed in patent US 10345218 B2 "Automated slide assessments and tracking in digital microscopy" (IPC G01N 15/02, G01N 15/14, G06K 9/46, G06T 7/00, G06T 7/11, G06K 9/00, G01N 15/00, G01N 15/10, published 09.07.2019), according to which an additional digital camera is used to determine the presence of a slide on the object table, with the help of which an image of that part of the slide that carries information about the patient is obtained.

The disadvantage of this solution is the need for additional equipment in the form of a second digital camera, which is used to obtain an image of the part of the slide that contains information about the patient.

A method and device for determining the slide loading are known, disclosed in patent CN 112945956 B "Glass slide loading detection method and device, terminal equipment and storage medium" (IPC G01N 21/01, G01N 21/84, published on 27.06.2023), according to which the terminal equipment (device for determining the slide loading) is equipped with a removable device for a convex lens and, in turn, this device is equipped with a slide holder, and the method includes the following steps:

obtaining the first image using the camera module upon detection of a slide loading operation, monitoring the change in lighting conditions based on the obtained image, and if the change meets a certain condition, it is considered that the slide loading operation has been detected;

determining the slide loading status based on the first image;

output of information corresponding to the loading state.

The disadvantage of this solution is its limited suitability for use in automated digital microscopy devices due to the need to track the brightness parameter when installing the slide, since slides with biological preparations can have fairly transparent biological samples that will slightly change the brightness parameter of the images, which can lead to an erroneous interpretation of the change in brightness parameters by the automated system. In particular, for the same reasons, this method has limited suitability for working with slides containing biological samples of human fluid.

The closest analogue to the claimed invention is the stuck slide determination system according to patent US 10654655 B2 “Stuck slide determination system” (IPC B65G 43/00, G01N 35/00, G01V 8/12, G01N 21/64, G02B 21/00, published 05/19/2020), which consists of:

using a device for digitizing slides, including a slide stage for placing and securing a slide on it, a drive for moving the slide stage during the digitizing process, a paired sensor, which consists of a transmitting element and a receiving element, wherein the transmitting and receiving elements are arranged in such a way as to detect the presence or absence of a slide in one or more positions during the digitizing process, wherein the transmitting element and the receiving element of the paired sensor are arranged on different sides of the slide stage, wherein one of the pair of elements is arranged above the slide stage, and the second of the pair of elements is arranged below the slide stage, wherein the transmitting element is configured to transmit a signal, and the receiving element is located in the field of view of the transmitting element and is configured to receive a signal that the transmitting element transmits when the signal passes through one or more positions of the slide;

using at least one processor during the digitization of the slide to control the drive of the slide stage, receive a signal from a paired sensor, analyze the signal to determine the absence or presence of the slide, determine the position of the slide, stop the movement of the slide stage when an incorrect position of the slide on the slide stage is determined.

The disadvantage of the above system is the need to use additional sensors, which reduces the fault tolerance of the device for digitizing slides, and also makes it impossible to use commercially available slide tables that do not have the technical capability to accommodate additional sensors.

The technical task is to create a method for automatically determining the presence of a slide on the stage of a microscope with a multi-slide configuration, when an automated system for digitizing biological preparations in transmitted light is operating.

Disclosure of the essence of the invention

The technical problem is solved by a computer-implemented method for determining the presence of a slide with a dedicated information part on the microscope stage of a multi-slide configuration, carried out using an automated system for digitizing biological preparations in transmitted light. The claimed method consists of the following stages:

a) move the microscope stage to the area of pure light;

b) in the region of pure light, a first digital image is obtained, accepted as a correction image, which is placed in the computer memory in the form of a set of pixels of a color space, wherein each color channel of each pixel is assigned a numerical value in the range from the minimum value corresponding to the color black to the maximum value corresponding to the most saturated color, each color channel of each pixel is encoded by one byte;

c) then a subsequent digital image is obtained, which is transformed using the correction image by means of background correction, namely, a value corresponding to the most saturated color is added to each value of the color channel of each pixel of the corrected image, and the value of the corresponding color channel of the pixel of the correction image is subtracted from the obtained value, the digital image transformed in this way is saved in the computer memory and accepted as a reference image;

d) then the microscope stage is moved to the area where the information part of the slide is supposed to be located and a digital image is obtained, which is saved in the computer’s memory;

d) then the standard deviation is calculated between the byte arrays of the reference image and the image obtained in the area of the supposed location of the information part of the slide;

e) the obtained value of the standard deviation is compared with a pre-set threshold value; if the value of the standard deviation exceeds the specified threshold value, then it is considered that the slide is present on the microscope stage; if the value of the standard deviation does not exceed the specified threshold value, then it is considered that the slide is absent from the microscope stage.

Description of the figure

The figure illustrates a schematic representation of a glass slide, where: 1 - glass slide; 2 - biological preparation; 3 - information part of the glass slide.

Implementation of the invention

Any commercially available device that includes a microscope for studying biological samples in transmitted light, a motorized stage, a digital camera connected to the microscope, and at least one processor for controlling the movement of the stage and a digital camera for obtaining digital images can be used to implement the proposed solution. The slide used must have a section dedicated to the application of information about the type of sample and/or other information that allows identifying the slide and patient information - the information section. As a rule, the information section of the slide contains a sticker (label) with patient information or a bar code. In this case, the information section of the slide is opaque in visible light, provided that transmitted light is used in microscopes.

Under the control of the processor, the microscope stage is moved relative to the microscope objective along the X and Y axes so that a continuous optical path (clear light area) is formed between the microscope objective and the light source. This optical path can be formed by an unoccupied mounting place for the slide in the case of microscope stage stages with a multi-slide configuration, or by a technological opening in the stage itself. The coordinates of the clear light area can be determined by the user. For example, the user can manually move the stage to the clear light area, save the coordinates of the stage position in the computer memory and use them to implement the invention. Or the coordinates of the clear light area can be determined automatically, depending on the type of stage used. The dimensions and geometric features of various stage stages and the coordinates corresponding to them can be stored in the computer memory and used to move the stage to the clear light area.

Then, the first digital image is obtained in the pure light area. In computer representation, a color digital image is represented by a set of pixels. Each pixel has its own value depending on the color space used. For example, in the RGB color space, where three channels are used for color encoding - red, green, blue, each pixel is represented by three values in the range from 0 to 255 for each of the channels, where 0 represents absolute black, and 255 is the most saturated color. The resulting color image, accepted as a correction image, is placed in the computer memory as a set of pixels of the color space, with each color channel of each pixel assigned a numerical value in the range from the minimum value corresponding to black to the maximum value corresponding to the most saturated color, each color channel of each pixel is coded by one byte.

Then, a subsequent digital image is obtained, which is transformed using the correcting image by correcting the background, namely, a value corresponding to the most saturated color is added to each value of the color channel of each pixel of the corrected image, and the value of the corresponding color channel of the pixel of the correcting image is subtracted from the obtained value, the digital image transformed in this way is saved in the computer memory and accepted as a reference image.

Then the microscope stage is moved to the area of the supposed location of the information part of the slide. The coordinates of the information part can be set by the user manually. For example, the user can manually move the stage so that the information part of the slide falls into the field of view of the camera and save the coordinates of this position of the stage in the computer memory. This will allow this stage to be performed automatically when working with identical slides. Or the coordinates can be found mathematically based on the physical dimensions of the slide and the known coordinates of the landing site for the slide. For example, the coordinates of the point at which the image will be obtained in the area of the information part can be 85% of the length of the slide along the X axis and 25% of the width of the slide along the Y axis, provided that the origin of the coordinates is in the lower right corner of the slide.

After moving the object stage to a position in which the information part of the object glass should fall into the camera’s field of view, a digital image is obtained, which is saved in the computer’s memory.

Next, the standard deviation is calculated between the byte arrays of the reference image and the image obtained in the area of the supposed location of the information part of the slide. In the computer representation, each channel of each pixel is encoded by one byte, i.e., there are three bytes per pixel, where each byte has a value corresponding to the value of the pixel's color channel. In this way, the byte arrays of the reference image and the image obtained in the area of the supposed location of the information part of the slide are compared. The standard deviation between the byte arrays of the images is calculated using the following formula:

Where:

N - length of the image byte array;

Xi - i-th byte of the reference image;

Yi is the i-th byte of the image obtained in the area of the supposed location of the information part of the slide.

The obtained value of the standard deviation is then compared with a preset threshold value. If the value of the standard deviation exceeds the specified threshold value, then it is considered that the object glass is present on the microscope stage; if it does not exceed the threshold value, then it is considered that the object glass is absent from the microscope stage. The threshold value of the standard deviation can be set manually by the user depending on the type of object glass and light source used, or it can be set automatically by the system depending on the equipment used.

Example of implementation of the invention

An example of the invention is the automatic system for scanning biological samples Vision Pro 8 Cell Imaging Analyzer (https://wm-vision.ru/ru/product/hema). The system includes a scanning microscope with a motorized stage, a monitor, a 10x lens, a digital camera and a personal computer with installed software from the Vision family from West Medica.

A glass slide is placed on the object table, on which is placed a sample containing a biological preparation and there is an information part (sticker).

The object stage, under the control of the processor, moves in such a way that an area of pure light falls into the field of view of the lens, and therefore the digital camera.

In the pure light region, a correction image is obtained. The image in the form of an array of bytes encoding digital channels of pixels in the RGB color model is stored in the computer's memory. This image is then used to correct the background of the subsequent image, in which the value of 255 is added to each channel of the corrected image and the value of the correction image is subtracted. After the correction, the corrected (reference) image is stored in the computer's memory.

Then, the object stage, under the control of the processor, moves in such a way that the area where the information part (sticker) of the object glass is located comes into the field of view of the lens, and, consequently, the digital camera.

In the area of the information part of the slide, the system receives a digital image. After that, the standard deviation between the byte arrays of the previously received reference image and the image received in the area of the information part (sticker) of the slide is calculated. Then, the obtained value of the standard deviation is compared with the previously set threshold value equal to 100. The threshold value is expressed in dimensionless quantities.

If the value of the standard deviation exceeds 100, the system considers that the slide is present on the microscope stage; if it does not exceed 100, the slide is not present on the microscope stage.

Claims (7)

A computer-implemented method for determining the presence on the object stage of a microscope with a multi-slide configuration of a slide with a dedicated information part, carried out using an automated system for digitizing biological preparations in transmitted light, consisting of the following stages: a) move the microscope stage to the area of pure light; b) in the region of pure light, a first digital image is obtained, accepted as a correction image, which is placed in the computer memory in the form of a set of pixels of a color space, wherein each color channel of each pixel is assigned a numerical value in the range from the minimum value corresponding to the color black to the maximum value corresponding to the most saturated color, each color channel of each pixel is encoded by one byte; c) then a subsequent digital image is obtained, which is transformed using the correction image by means of background correction, namely, a value corresponding to the most saturated color is added to each value of the color channel of each pixel of the corrected image, and the value of the corresponding color channel of the pixel of the correction image is subtracted from the obtained value, the digital image transformed in this way is saved in the computer memory and accepted as a reference image; d) then the microscope stage is moved to the area where the information part of the slide is supposed to be located and a digital image is obtained, which is saved in the computer’s memory; d) then the standard deviation is calculated between the byte arrays of the reference image and the image obtained in the area of the supposed location of the information part of the slide; e) the obtained value of the standard deviation is compared with a pre-set threshold value; if the value of the standard deviation exceeds the specified threshold value, then it is considered that the slide is present on the microscope stage; if the value of the standard deviation does not exceed the specified threshold value, then it is considered that the slide is absent from the microscope stage.