Cell segmentation method and device based on spatial omics sequencing, storage medium and program product

Abstract

The invention discloses a cell segmentation method and device based on spatial omics sequencing, a storage medium and a program product. The method comprises the following steps: acquiring an acquired signal distribution image; performing initial smoothing operation based on the signal distribution image to obtain an initial smooth distribution image, and performing image segmentation operation based on the initial smooth distribution image to obtain a current cell segmentation region set; a smoothing parameter corresponding to the smoothing operation is adjusted, based on the adjusted smoothing parameter, the smoothing operation and the image segmentation operation are performed on the cell region image in the current first region set, the current cell segmentation region set is updated, the previous screening step is returned until a termination condition is satisfied, and a target second region set is obtained; and obtaining each cell region based on the target second region set.

Description

Technical Field

[0001] The present invention relates to the field of gene technology, and in particular to a cell segmentation method and system based on spatial omics sequencing, a computer device, a computer-readable storage medium and a computer program product. Background Art

[0002] The spatial transcriptome sequencing method is a sequencing method that can read the base sequence information of RNA fragments and record the spatial position of the fragments at the same time. The spatial information that can be recorded by current spatial omics sequencing is generally limited to two-dimensional space, which is achieved by covering tissue sections on sequencing chips. Probes that can capture RNA fragments are distributed on the surface of the sequencing chip. The sequencer can read the base sequence information of the RNA fragments bound to the probes, and combined with the known probe positions, the spatial information of the base sequence can be obtained.

[0003] At present, the bright spots in the signal distribution map in spatial omics sequencing cannot always remain isolated and complete. Depending on the tissue section and experimental conditions, the bright spots may appear blurred, crowded, and have unclear boundaries. Therefore, the methods in the prior art cannot accurately segment cells. For example, one limitation of spatial transcriptome sequencing is that it cannot determine which probes capture RNA fragments from the same cell, which limits the ability to analyze cell-to-cell specificity. In the cell-dense area, the RNA signals of different cells are mixed and it is difficult to form a clear boundary. Therefore, the bright spots in the RNA signal distribution map cannot always remain isolated and complete. Depending on the tissue section and experimental conditions, the bright spots may appear blurred, crowded, and have unclear boundaries. Therefore, the methods in the prior art cannot accurately segment cells. Summary of the invention

[0004] In order to solve the existing technical problems, the present invention provides a cell segmentation method and system based on spatial omics sequencing, a computer device, a computer-readable storage medium and a computer program product, which can improve the accuracy of cell segmentation.

[0005] In a first aspect, a cell segmentation method based on spatial omics sequencing is provided, comprising: acquiring a collected signal distribution image, wherein the signal distribution image indicates the distribution characteristics of the spatial omics signal of the tissue section; performing an initial smoothing operation based on the signal distribution image to obtain an initial smoothed distribution image, and performing an image segmentation operation based on the initial smoothed distribution image to obtain a current cell segmentation region set; based on the current cell segmentation region set, screening and obtaining cell region images to be further segmented to obtain a current first region set, and screening cell region images not to be further segmented to obtain a current second region set; adjusting a smoothing parameter corresponding to the smoothing operation, and based on the adjusted smoothing parameter, performing a smoothing operation and an image segmentation operation on the cell region images in the current first region set, and updating the current cell segmentation region set, returning to the previous screening step until a termination condition is met to obtain a target second region set; and obtaining each cell region based on the target second region set.

[0006] In a second aspect, a computer device is provided, comprising a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the cell segmentation method based on spatial omics sequencing provided in an embodiment of the present application.

[0007] In a third aspect, a computer-readable storage medium is provided, storing a computer program, and when the computer program is executed by a processor, the processor executes the steps of the cell segmentation method based on spatial omics sequencing provided in an embodiment of the present application.

[0008] In a fourth aspect, a computer program product is provided, comprising a computer program, which, when executed by a processor, implements the steps of the cell segmentation method based on spatial omics sequencing provided in an embodiment of the present application.

[0009] The present application obtains a collected signal distribution image, performs an initial smoothing operation based on the initial signal distribution image to obtain an initial smoothed distribution image, performs an image segmentation operation based on the initial smoothed distribution image to obtain a current cell segmentation region set, screens the cell region images to be further segmented based on the current cell segmentation region set to obtain a current first region set, screens the cell region images that are not further segmented to obtain a current second region set, performs smoothing operations and image segmentation operations again on the cell region images to be further segmented until a termination condition is met to obtain a target second region set, thereby obtaining individual cell regions, and adjusting the smoothing parameters during multiple smoothing operations so that the adjusted smoothing parameters are more suitable for the current smoothing operation, and further subdivides the cell region images in dense areas to obtain single cell region images, thereby achieving better segmentation and improving the accuracy of cell segmentation. BRIEF DESCRIPTION OF THE DRAWINGS

[0010] Figure 1 A schematic diagram of a bright spot presented by an RNA signal distribution image in one embodiment; Figure 2 A schematic diagram of RNA signal distribution at different positions on the same tissue section in one embodiment; Figure 3 This is a diagram of the application environment of a cell segmentation method based on spatial omics sequencing in one embodiment; Figure 4 This is a flow chart of a cell segmentation method based on spatial omics sequencing in one embodiment; Figure 5 is a schematic diagram of performing multiple smoothing operations and image segmentation operations in one embodiment; Figure 6 A schematic diagram of segmenting cells using a cell segmentation method based on spatial transcriptome sequencing in one embodiment; Figure 7 is a flow chart of a cell segmentation method based on spatial omics sequencing in another embodiment; Figure 8 A schematic diagram of a cell segmentation device based on spatial omics sequencing in one embodiment; Fig. 9 Schematic diagram of the structure of a computing device in one embodiment. DETAILED DESCRIPTION

[0011] The technical solution of the present invention is further described in detail below in conjunction with the accompanying drawings and specific embodiments.

[0012] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art of the present invention. The terms used in the specification of the present invention herein are only for the purpose of describing specific embodiments and are not intended to limit the scope of protection of the present invention. The term "and / or" used herein includes any and all combinations of one or more related listed items.

[0013] In the following description, reference is made to “some embodiments”, which describes a subset of all possible embodiments, but it should be understood that “some embodiments” may be the same subset or different subsets of all possible embodiments and may be combined with each other without conflict.

[0014] The spatial omics sequencing method is a sequencing method that can read the base sequence information of ribonucleic acid (RNA) fragments and record the spatial position of the fragments. The spatial information that can be recorded by current spatial omics sequencing is generally limited to two-dimensional space, which is achieved by covering tissue sections on sequencing chips. For example, based on the spatial transcriptome sequencing method, probes that can capture RNA fragments are distributed on the surface of the sequencing chip. The gene sequencer can read the base sequence information of the RNA fragments bound to the probes, and combined with the known probe positions, the spatial information of the base sequence can be obtained.

[0015] One of the current limitations of spatial transcriptome sequencing is that it cannot determine which probes capture RNA fragments from the same cell, which limits the ability to analyze cell-to-cell specificity. In order to overcome this limitation, the data obtained from spatial transcriptome sequencing often needs to undergo subsequent cell segmentation processing, that is, through data analysis methods, to identify which base sequences come from different cells. The mainstream cell segmentation method is based on images, and there are two main sources of images: 1) RNA signal distribution map composed of the distribution of signal intensity (probe density that captures RNA fragments) captured by the sequencing chip; 2) Staining signal distribution map obtained by additional staining of tissue sections used for sequencing. Both images are characterized by the presence of a strong signal peak at the corresponding position of the cell nucleus of the tissue section, which is reflected in the image as an isolated bright spot (or a spot that is significantly different from the background), such as Figure 1 As shown, cell segmentation is to identify the range of complete spots on the image, and regard the RNA base sequences captured by the probes corresponding to the range as originating from the same cell, so that the base sequences obtained by sequencing are integrated by cell unit for subsequent analysis.

[0016] The difficulty in identifying bright spots (or other spots) from images is that bright spots cannot always remain isolated and complete. Depending on the tissue section and experimental conditions, bright spots may appear blurred, crowded, or have unclear boundaries. They may also appear in the same image in a variety of different situations, such as Figure 2 As shown, the RNA signal distribution status at different positions in the same tissue section is different.

[0017] The methods for identifying bright spots in images to segment cells in the prior art mainly include: 1) watershed-based algorithms; 2) clustering-based methods; 3) deep learning-based methods. The watershed algorithm is a classic algorithm used in the field of image segmentation, which can accurately and quickly identify the range of bright spots, but it requires smooth signal transitions and clear boundaries, and these two conditions are often not met in the signal distribution images of sample slices, especially for RNA signal distribution maps. The methods based on watershed improvements in the prior art, such as image preprocessing, have not been explored in terms of adaptive parameters and have failed to adapt to variable sample conditions. The difficulty of the requirement for signal continuity is that the position of the RNA signal comes from the position of the probe, and the position of the probe is not continuous, resulting in the formation of isolated signal points instead of complete bright spots. The difficulty of the requirement for clear boundaries is that in the cell-dense area, the RNA signals of different cells are mixed, and it is difficult to form a clear boundary. In order to make the signal continuous, the signal is often smoothed in the prior art to suppress random fluctuations and isolated signals, but the smoothing process itself will cause the boundary to be further blurred, making it impossible to identify individual cells. The spatial transcriptome sequencing method is a sequencing method that can read the base sequence information of RNA fragments and record the spatial position of the fragments at the same time. The spatial information that can be recorded by current spatial omics sequencing is generally limited to two-dimensional space, which is achieved by covering tissue sections on sequencing chips. Probes that can capture RNA fragments are distributed on the surface of the sequencing chip. The sequencer can read the base sequence information of the RNA fragments bound to the probes, and combined with the known probe positions, the spatial information of the base sequence can be obtained.

[0018] One limitation of spatial omics sequencing is that it cannot determine which probes capture RNA fragments from the same cell, which limits the ability to analyze cell-to-cell specificity. In densely populated areas, RNA signals from different cells are mixed and it is difficult to form clear boundaries. Therefore, the bright spots in the RNA signal distribution map cannot always remain isolated and complete. Depending on the tissue section and experimental conditions, the bright spots may appear blurred, crowded, or have unclear boundaries. Therefore, the methods in the prior art cannot accurately segment cells.

[0019] The embodiment of the present application provides a cell segmentation method based on spatial omics sequencing, which can adaptively adjust local parameters according to local conditions of the image to improve the recognition accuracy. The embodiment of the present application is based on the improvement of the watershed algorithm to make it more suitable for cell segmentation; automatically adjust parameters to increase the degree of smoothing in sparse cell areas to suppress isolated random noise; in dense cell areas, reduce the degree of smoothing to preserve the boundary morphology.

[0020] like Figure 3 As shown, Figure 3This is an application environment diagram of a cell segmentation method based on spatial omics sequencing in an embodiment; the gene sequencer 10 communicates with the computer device 20, and is implemented by covering the tissue slices on the sequencing chip of the gene sequencer 10. The surface of the sequencing chip of the gene sequencer 10 is distributed with probes that can capture RNA fragments. The gene sequencer 10 can read the base sequence information of the RNA fragment bound to the probe. Combined with the known probe position, the spatial information of the base sequence can be obtained. The signal intensity (probe density that captures the RNA fragment) captured by the sequencing chip in the gene sequencer 10 is distributed to form an RNA signal distribution map. The computer device 20 obtains the RNA signal distribution image for processing and segments the cells. In an optional implementation, the cell segmentation method based on spatial omics sequencing can also be implemented in the gene sequencer 10.

[0021] See also Figure 4 , is a flow chart of a cell segmentation method based on spatial omics sequencing provided in an embodiment of the present application. The cell segmentation method based on spatial omics sequencing is applied to a computer device, and the cell segmentation method based on spatial omics sequencing includes the following steps: S11. Acquire a collected signal distribution image, where the signal distribution image indicates distribution characteristics of spatial omics signals of a tissue section.

[0022] In this embodiment, the signal distribution image refers to an image that can reflect the distribution characteristics of the spatial omics signal of the tissue slice in the physical space, which can be an RNA signal distribution image captured by a sequencing chip, or an image obtained by staining the genetic material of the slice and taking a photo. Figure 1 and Figure 2 As shown, there is a strong signal peak at the position corresponding to the cell nucleus of the tissue section, which is reflected as an isolated bright spot (or a spot with a large difference from the background) in the picture. Subsequently, the range of the complete spot on the image is identified, and the RNA base sequence captured by the probe corresponding to the range of the complete spot is regarded as originating from the same cell, so that the base sequence obtained by sequencing is integrated by cell. Among them, spatial omics can be understood as spatial multi-omics, and spatial omics includes but is not limited to one or more of the following combinations: transcriptomics, genomics, proteomics, metabolomics, lipidomics, glycomics, epigenetic omics, immunomics, microbiome, metagenomics, pharmacomics, etc. Spatial omics signals include but are not limited to one or more of the following combinations: transcriptomics signals, genomics signals, proteomics signals, metabolomics signals, lipidomics signals, glycomics signals, epigenetic omics signals, immunomics signals, microbiome signals, metagenomics signals, pharmacomics signals, etc.

[0023] S12. Based on the signal distribution image, perform an initial smoothing operation to obtain an initial smoothed distribution image; based on the initial smoothed distribution image, perform an image segmentation operation to obtain a current cell segmentation region set.

[0024] In this embodiment, a smoothing function is used to perform an initial smoothing operation based on the signal distribution image to obtain an initial smoothed distribution image, wherein the initial smoothed distribution image is an image obtained after performing the first smoothing operation based on the signal distribution image. The smoothing function includes but is not limited to a Gaussian function, wherein the formula of the Gaussian function is as follows: The Gaussian function curve is a dotted line similar to an inverted V shape, with a convex middle and smooth transition, and relatively gentle on both sides. Parameter a is the magnification, which changes the height of the curve. For example, it can be set to 1; parameter b is the horizontal position offset, which changes the horizontal position of the curve. It is set to 0 here; the smoothing parameter c affects the shape of the curve. The larger the value of the smoothing parameter, the gentler the curve, and the smaller the value, the sharper it is; e is the natural base. When using the Gaussian function for smoothing, the degree to which the pixel value at a position is affected by the surrounding pixel values ​​is related to the shape of the Gaussian curve. When the smoothing parameter c is large, the curve is gentle and the two sides decline slowly, which means that the influence of the surrounding pixels on the pixel slowly decreases with increasing distance; conversely, the curve is sharp and the two sides decline rapidly, which means that as the distance increases, the influence of the farther pixels on the pixel decreases sharply.

[0025] Through the smoothing operation, each pixel on the image is subjected to a certain operation based on the values ​​of the neighboring pixels around it, and the original value of the pixel is changed. A typical smoothing operation is Gaussian blur. The calculation formula for the value of a point with coordinates (x, y) in two-dimensional space after Gaussian blur is as follows: Among them, width is the image length, height is the image width, is the signal intensity of the pixel at coordinate (i, j), a is a constant, e is the constant natural base, c is the smoothing parameter, is a smooth distribution image.

[0026] In an optional implementation, the image segmentation operation may use a watershed algorithm, and the watershed algorithm is used to identify the signal peak on the smooth distribution image after the smoothing operation, such as Figure 1 and Figure 2 The bright spots and their distribution ranges are shown, and the signal distribution within the range of each bright spot is extracted.

[0027] In an optional implementation, for a signal distribution image containing a variety of distribution conditions, the current cell segmentation region set after the first segmentation can also be obtained by dividing the regions with different conditions in advance, that is, pre-segmenting.

[0028] S13. Based on the current cell segmentation region set, filter out the cell region images to be further segmented to obtain the current first region set, and filter out the cell region images not to be further segmented to obtain the current second region set.

[0029] In this embodiment, the current first region set stores cell region images that need to be further segmented, and the cell region images that need to be further segmented indicate that there are multiple bright spots in the cell region image and that further segmentation is required. The current second region set stores cell region images that do not need to be further segmented, that is, a cell region image in the current second region set is the distribution range of the region where a bright spot is located.

[0030] S14. Adjust the smoothing parameters corresponding to the smoothing operation, and based on the adjusted smoothing parameters, perform smoothing operations and image segmentation operations on the cell area images in the current first area set, and update the current cell segmentation area set, and return to the previous screening step until the termination condition is met to obtain the target second area set.

[0031] The smoothing operation and the image segmentation operation are performed again on the cell region image to be further segmented, and the current cell segmentation region set is updated, that is, returning to the previous screening step, that is, returning to execute S13, and then executing S14, and the cycle is repeated until the termination condition is met, wherein the termination condition includes but is not limited to that the current cell segmentation region set is empty, the number of smoothing operations and image segmentation operations is greater than the preset number, and the current second region set after the termination condition is met is used as the target second region set.

[0032] like Figure 5 As shown, Figure 5 FIG. 1 is a schematic diagram of performing multiple smoothing operations and image segmentation operations in one embodiment. The dots represent signal points whose signal strength values ​​exceed the preset signal strength values. The solid circles represent the bright spots identified by the initial segmentation, i.e., the signal-intensive areas. The dotted circles represent the bright spot areas identified by the second segmentation. After performing the second smoothing operation and image segmentation operation, the larger cell area image can be segmented again. Figure 5 The solid line area where the two dotted line areas are located.

[0033] In this embodiment, the smoothing parameter corresponding to the initial smoothing operation is more suitable for sparse cell areas, but not for dense cell areas. If the smoothing parameter corresponding to the initial smoothing operation is used, the latter cannot be effectively segmented, and multiple cells are identified as a whole. Figure 5In order to further separate the cells in the large solid circle in the lower right corner, it is necessary to adjust the smoothing parameters to smooth again and segment the area where the dotted box is located. By adjusting the smoothing parameters during multiple smoothing operations, the cell area image in the dense area can be subdivided again.

[0034] S15. Based on the target second region set, obtain each cell region.

[0035] In this embodiment, a cell region image in the target second region set is a distribution range of a bright spot. Figure 6 As shown, Figure 6 is a schematic diagram of segmenting cells using a cell segmentation method based on spatial transcriptome sequencing in one embodiment, Figure 6 The area enclosed by the white curve is considered to be covered by a single cell.

[0036] In the above embodiment, the collected signal distribution image is obtained, and based on the initial signal distribution image, an initial smoothing operation is performed to obtain an initial smoothed distribution image. Based on the initial smoothed distribution image, an image segmentation operation is performed to obtain a current cell segmentation region set. Based on the current cell segmentation region set, the cell region images to be further segmented are screened to obtain the current first region set. The cell region images not to be further segmented are screened to obtain the current second region set. The smoothing operation and image segmentation operation are performed again on the cell region images to be further segmented until the termination condition is met to obtain the target second region set, thereby obtaining each cell region. By adjusting the smoothing parameters during multiple smoothing operations so that the adjusted smoothing parameters are more suitable for the current smoothing operation, the cell region images in the dense area are subdivided again to obtain single cell region images, thereby achieving better segmentation and improving the accuracy of cell segmentation.

[0037] In some embodiments, performing a smoothing operation based on the signal distribution image to obtain an initial smoothed distribution image includes: Acquire a filtering threshold, and filter the signal distribution image based on the filtering threshold to obtain a filtered distribution image; Based on the filtered distribution image, an initial smoothing operation is performed to obtain an initial smoothed distribution image.

[0038] Optionally, the obtaining of the filtering threshold and filtering the signal distribution image based on the filtering threshold to obtain the filtered distribution image includes at least one of the following: Obtaining a preset filtering threshold, setting the signal intensity of the pixel points in the signal distribution image that are less than the filtering threshold to a preset intensity value, and obtaining the filtered distribution image; Calculating the filtering threshold based on the signal strength corresponding to the pixel points in the signal distribution image, setting the signal strength of the pixel points in the signal distribution image that are less than the filtering threshold to a preset strength value, and obtaining the filtered distribution image; Obtain the signal strength value of each neighboring pixel point in the neighborhood of each pixel point in the signal distribution image, calculate the average signal strength value corresponding to each pixel point based on the signal strength value of each neighboring pixel point corresponding to each pixel point, determine the filtering threshold corresponding to each pixel point based on the average signal strength value corresponding to each pixel point, set the signal strength of the pixel point that is less than the filtering threshold corresponding to the pixel point to a preset strength value, and obtain the filtered distribution image.

[0039] In this embodiment, based on a given preset filtering threshold, if the signal strength at a certain position in the signal distribution image is lower than the preset filtering threshold, its strength is set to 0. If the signal strength at a certain position in the signal distribution image is greater than or equal to the preset filtering threshold, the signal strength at the position remains unchanged. For pixels at different positions, their thresholds may be the same or different. When setting a filtering threshold for a pixel at a position, the average signal strength of the signal strengths corresponding to the pixels in a circular area around the pixel may be calculated, and a preset ratio of the average signal strength may be used as the filtering threshold for the pixel. In an optional implementation, the radius of the circular area is preferably 10 times the preset radius, and the preset ratio is preferably 100%. For the preset filtering threshold, 100% of the average signal strength in the signal distribution image is preferred. If necessary, the preset filtering threshold may be set to 0, i.e., no filtering is performed.

[0040] In the above embodiment, before performing the smoothing operation, the signal distribution image is first filtered, so that noise can be effectively filtered, the image quality before segmentation is improved, and the accuracy of cell segmentation is improved.

[0041] In some embodiments, the smoothing parameter corresponding to the adjustment smoothing operation includes: The smoothing parameter value of each smoothing operation is calculated, wherein the smoothing parameter value corresponding to the current smoothing operation currently being executed is smaller than the smoothing parameter value corresponding to the previous smoothing operation of the current smoothing operation.

[0042] Optionally, the smoothing parameter value corresponding to the current smoothing operation is between 1 / 10 and 9 / 10 of the smoothing parameter value corresponding to the previous smoothing operation.

[0043] In this embodiment, a hierarchical parameter adjustment strategy is adopted. Specifically, in the initial smoothing operation, a higher smoothing parameter is used, which will make the area of ​​the tissue section where the cells are sparse obtain a more ideal bright spot, and the area of ​​the single cell is identified; while in the area where the cells are dense, due to the use of a higher smoothing parameter, the bright spot boundary will be more difficult to identify, resulting in multiple cells being identified as a whole area. Therefore, before the secondary segmentation, the cell-dense area will be re-smoothed and a reduced smoothing parameter will be used. That is, the automatic adjustment parameters are used to increase the smoothing degree in the cell-sparse area to suppress isolated random noise; in the cell-dense area, the smoothing degree is reduced to retain the boundary morphology. In an optional implementation, the smoothing parameter value corresponding to the current smoothing operation is between 1 / 4 of the smoothing parameter value corresponding to the previous smoothing operation and 3 / 4 of the smoothing parameter value corresponding to the previous smoothing operation. Generally, when the smoothing parameter is reduced, the value of the smoothing parameter is reduced to a certain proportion of the smoothing parameter value corresponding to the previous smoothing operation. The area obtained by the second segmentation will continue to be screened according to the preset upper and lower limits, and the cell area image to be further segmented will be screened for three or more times until the final index meets the expectations or the number of segmentation times reaches the preset value.

[0044] In the above embodiment, a hierarchical parameter adjustment strategy is adopted. In the process of performing multiple smoothing operations, the smoothing parameters are gradually reduced so that the cell-dense areas are re-smoothed, so that the smoothing parameters are more suitable for the segmentation of single cell areas in the cell-dense areas, and the smoothing degree is increased in the cell-sparse areas to suppress isolated random noise; in the cell-dense areas, the smoothing degree is reduced to retain the boundary morphology, thereby retaining more details of the cell-dense areas, so that the image segmentation operation can identify the cell boundaries therein, thereby improving the accuracy of cell segmentation.

[0045] In some embodiments, based on the current cell segmentation region set, screening the cell region images to be further segmented to obtain the current first region set, and screening the cell region images not to be further segmented to obtain the current second region set comprises: Putting cell region images above a preset screening upper limit in the current cell segmentation region set into the current first region set; The cell region images in the current cell segmentation region set that are lower than a preset screening upper limit and higher than a preset screening lower limit are placed into the current second region set.

[0046] In the present embodiment, the preset upper screening limit includes but is not limited to the preset upper cell area limit and the preset upper limit of the total RNA quantity of the cell. The preset lower screening limit includes but is not limited to the preset lower cell area limit and the preset lower limit of the total RNA quantity of the cell. Different preset upper screening limits and preset lower screening limits correspond to different cell types. A parameter setting control can be provided through a user interface, and the options of the preset upper screening limits and preset lower screening limits corresponding to different cell types can be set through the parameter setting control, or the preset upper screening limit and the preset lower screening limit can be input by the user. A trigger operation for the parameter setting control is obtained based on the user interface, and the target upper limit and the target lower limit corresponding to the trigger operation are obtained, and the target upper limit is used as the preset upper screening limit, and the target lower limit is used as the preset lower screening limit. Therefore, the preset upper screening limit and the preset lower screening limit can be adjusted according to the cell category, so as to improve the accuracy of cell segmentation.

[0047] The cell region images that are lower than or equal to the preset upper screening limit and higher than or equal to the preset lower screening limit are the images that meet the requirements of single cell region, and this part is the area that will no longer be segmented. The cell region images that are higher than the preset upper screening limit are the cell-dense areas, and the cell region images that need to be segmented further. The cell region images that are lower than the preset lower screening limit are the noise region images, and this part of the images is discarded and no longer processed.

[0048] In the above embodiment, single cell regions and dense cell regions that need to be further segmented in the current cell segmentation region set are screened by a preset upper screening limit and a preset lower screening limit, thereby achieving continuous segmentation of dense cell regions until single cell regions are obtained, thereby improving the accuracy of cell segmentation.

[0049] In some embodiments, performing an initial smoothing operation based on the signal distribution image to obtain an initial smoothed distribution image includes: Based on the signal distribution image and the initial smoothing parameter value, an initial smoothing operation is performed to obtain an initial smoothed distribution image, wherein the initial smoothing parameter value is a minimum value that satisfies the inequality, wherein the inequality is: in represents the average cell radius, represents the smoothing parameter.

[0050] In this embodiment, the inequality is derived based on the Gaussian function, and the average cell radius can be configured on the user interface. Since different cell types correspond to different average cell radii, different average cell radii corresponding to different cell types can be configured on the user interface to obtain smoothing parameters suitable for the cell type. In this way, during the smoothing operation, appropriate smoothing processing is applied to the conditions of different areas on the signal distribution image to ensure that image segmentation can identify the bright spots on the image as accurately as possible.

[0051] In the above embodiment, the average cell radius suitable for the cell type is obtained in combination with the cell type, thereby obtaining a more accurate initial smoothing parameter. In this way, during the smoothing operation, appropriate smoothing processing is applied to the conditions of different areas on the signal distribution image to ensure that the image segmentation can identify the bright spots on the image as accurately as possible.

[0052] In some embodiments, obtaining each cell region based on the target second region set comprises: Acquire multiple target area images in the target second area set; for any of the target area images, acquire each probe corresponding to each pixel point in the target area image, and mark each probe corresponding to each pixel point in the target area image as the same cell.

[0053] In this embodiment, the probe is a short single-stranded DNA or RNA fragment (about 20 to 500 bp) used to detect a complementary nucleic acid sequence. The probe is used in a cell or tissue sample to visualize the location and distribution of RNA by complementing the target RNA sequence. These probes are usually labeled with multiple fluorescent dyes so that the spatial distribution of RNA can be captured by an image acquisition device. In image analysis, each pixel represents a specific position in the image, and the signal intensity corresponding to each pixel can reflect the RNA distribution at that position. In spatial omics sequencing, these probes are designed to specifically identify and capture target mRNA. In the signal distribution image, each position corresponds to a pixel, and each pixel in the same bright spot area corresponds to at least one probe position, and the corresponding at least one probe position is the same cell. The distribution area of ​​the same bright spot can represent the same cell area. When the tissue slice is covered on the sequencing chip, the probe position corresponding to the position where the cell exists on the slice corresponds to the position where the bright spot is located in the signal distribution image. The probe position corresponding to the position where there is no cell on the slice does not exist in the signal distribution image. Since the target second region set is a single cell region image, each probe position corresponding to each pixel point in the single cell region image is the same cell region.

[0054] In the above embodiment, after segmenting to obtain a single cell region, the probe position is obtained according to the position of the pixel points in the single cell region, so that the probe positions corresponding to the pixels in the same cell region image are marked as the same cell, thereby improving the accuracy of cell segmentation.

[0055] like Figure 7 As shown, Figure 7 The flowchart of a cell segmentation method based on spatial omics sequencing in another embodiment includes: S71. Acquire the collected signal distribution image.

[0056] S72. Perform signal filtering on the signal distribution image to obtain a filtered distribution image.

[0057] S73. Perform a smoothing operation on the filtered distribution image to obtain an initial smoothed distribution image, and perform an image segmentation operation based on the initial smoothed distribution image to obtain a current cell segmentation region set.

[0058] S74. Based on the current cell segmentation region set, filter out the cell region images to be further segmented to obtain the current first region set, and filter out the cell region images not to be further segmented to obtain the current second region set.

[0059] In this embodiment, according to the preset upper and lower limits of screening, S 0 Discard any area with an index below the preset lower limit, and transfer any area with an index above the preset upper limit to another set S 1 , which is the current first region set. At this time, S 0 Only the area between the preset upper and lower limits of all indicators will be retained. S 0 Move the elements to another set S , that is, the current second region set, and clear S 0 .

[0060] S75. Adjust the smoothing parameters corresponding to the smoothing operation, and based on the adjusted smoothing parameters, perform smoothing and image segmentation operations on the cell region images in the current first region set to obtain a current segmentation result, and based on the current segmentation result, update the current cell segmentation region set.

[0061] For S74 S 1 For each element (region) in , the signal distribution of each region is re-smoothed. At this time, the smoothing parameter cIt is set to a certain ratio of the smoothing parameter corresponding to the previous smoothing operation, the ratio is preferably in the range of 1 / 10 to 9 / 10, more preferably in the range of 1 / 4 to 3 / 4, and the most preferably is 1 / 2. After the smoothing process is completed, the image segmentation operation is performed on each area separately, and the identified area is stored in S 0 . Clear S 1 .

[0062] S76: Determine whether the current condition satisfies the termination condition.

[0063] If the current condition does not meet the termination condition, return to execute S74. If the current condition meets the termination condition, that is, until S 1 If it does not contain any elements or the number of repetitions reaches the specified upper limit, execute S77.

[0064] S77. Based on the target second region set, obtain each cell region.

[0065] On the other hand, the present application provides a computer program product, including a computer program, which, when executed by a processor, implements the cell segmentation method based on spatial omics sequencing described in any embodiment of the present application.

[0066] Among them, in the computer program product, an optional implementation form of the program module architecture of the computer program that implements each step of the cell segmentation method based on spatial omics sequencing can be a cell segmentation device based on spatial omics sequencing.

[0067] See also Figure 8 An embodiment of the present application provides a cell segmentation device based on spatial omics sequencing, including: an acquisition module 81, used to acquire a collected signal distribution image, wherein the signal distribution image indicates the distribution characteristics of the spatial omics signal of the tissue section; a smoothing and segmentation module 82, used to perform an initial smoothing operation based on the signal distribution image to obtain an initial smoothed distribution image, and perform an image segmentation operation based on the initial smoothed distribution image to obtain a current cell segmentation region set; a screening module 83, used to screen and obtain cell region images to be further segmented based on the current cell segmentation region set to obtain a current first region set, and screen cell region images that are not further segmented to obtain a current second region set; the smoothing and segmentation module 82 is also used to adjust the smoothing parameters corresponding to the smoothing operation, and based on the adjusted smoothing parameters, perform smoothing operations and image segmentation operations on the cell region images in the current first region set, and update the current cell segmentation region set, and return to the previous screening step until the termination condition is met to obtain a target second region set; a determination module 84, used to obtain each cell region based on the target second region set.

[0068] Optionally, the smoothing and segmentation module 82 is further configured to: Acquire a filtering threshold, and filter the signal distribution image based on the filtering threshold to obtain a filtered distribution image; Based on the filtered distribution image, an initial smoothing operation is performed to obtain an initial smoothed distribution image.

[0069] Optionally, the smoothing and segmentation module 82 is further configured to: Obtaining a preset filtering threshold, setting the signal intensity of the pixel points in the signal distribution image that are less than the filtering threshold to a preset intensity value, and obtaining the filtered distribution image; Calculating the filtering threshold based on the signal strength corresponding to the pixel points in the signal distribution image, setting the signal strength of the pixel points in the signal distribution image that are less than the filtering threshold to a preset strength value, and obtaining the filtered distribution image; Obtain the signal strength value of each neighboring pixel point in the neighborhood of each pixel point in the signal distribution image, calculate the average signal strength value corresponding to each pixel point based on the signal strength value of each neighboring pixel point corresponding to each pixel point, determine the filtering threshold corresponding to each pixel point based on the average signal strength value corresponding to each pixel point, set the signal strength of the pixel point that is less than the filtering threshold corresponding to the pixel point to a preset strength value, and obtain the filtered distribution image.

[0070] Optionally, the smoothing and segmentation module 82 is further configured to: The smoothing parameter value of each smoothing operation is calculated, wherein the smoothing parameter value corresponding to the current smoothing operation currently being executed is smaller than the smoothing parameter value corresponding to the previous smoothing operation of the current smoothing operation.

[0071] Optionally, the smoothing parameter value corresponding to the current smoothing operation is between 1 / 10 and 9 / 10 of the smoothing parameter value corresponding to the previous smoothing operation.

[0072] Optionally, the smoothing and segmentation module 82 is further configured to: Putting cell region images above a preset screening upper limit in the current cell segmentation region set into the current first region set; The cell region images in the current cell segmentation region set that are lower than a preset screening upper limit and higher than a preset screening lower limit are placed into the current second region set.

[0073] Optionally, the smoothing and segmentation module 82 is further configured to: Based on the signal distribution image and the initial smoothing parameter value, an initial smoothing operation is performed to obtain an initial smoothed distribution image, wherein the initial smoothing parameter value is a minimum value that satisfies the inequality, wherein the inequality is: in represents the average cell radius, represents the smoothing parameter, is the natural base of the exponential function.

[0074] Optionally, the determination module 84 is further configured to: Acquire multiple target area images in the target second area set; for any of the target area images, acquire each probe corresponding to each pixel point in the target area image, and mark each probe corresponding to each pixel point in the target area image as the same cell.

[0075] It can be understood by those skilled in the art that Figure 8 The structure of the cell segmentation device based on spatial omics sequencing does not constitute a limitation on the cell segmentation device based on spatial omics sequencing, and the various modules can be implemented in whole or in part by software, hardware, and a combination thereof. The above modules can be embedded in or independent of the controller in the computing device in the form of hardware, or can be stored in the memory in the computing device in the form of software, so that the controller can call and execute the operations corresponding to the above modules. In other embodiments, the cell segmentation device based on spatial omics sequencing may include more or fewer modules than shown in the figure.

[0076] See also Fig. 9 In another aspect of the embodiment of the present application, a computing device 20 is provided, including a memory 3011 and a processor 3012, wherein the memory 3011 stores a computer program, and when the computer program is executed by the processor, the processor 3012 performs the steps of the cell segmentation method based on spatial omics sequencing provided in any of the above embodiments of the present application. The computing device may include a desktop computer, a laptop computer, a tablet computer, a handheld computer, a smart speaker, a server, etc., a mobile phone (e.g., a smart phone, a wireless phone, etc.), a wearable device (e.g., a pair of smart glasses or a smart watch), or a similar device.

[0077] The processor 3012 is a control center, which uses various interfaces and lines to connect various parts of the entire computing device, and executes various functions of the computing device and processes data by running or executing software programs and / or modules stored in the memory 3011, and calling data stored in the memory 3011. Optionally, the processor 3012 may include one or more processing cores; the processor 3012 includes but is not limited to a combination of one or more of the following: a central processing unit (CPU), a graphics processing unit (GPU), a field programmable gate array (FPGA), etc. Preferably, the processor 3012 can integrate an application processor and a modem processor, wherein the application processor mainly processes the operating system, user pages and application programs, etc., and the modem processor mainly processes wireless communications. It is understandable that the above-mentioned modem processor may not be integrated into the processor 3012.

[0078] The memory 3011 can be used to store software programs and modules. The processor 3012 executes various functional applications and data processing by running the software programs and modules stored in the memory 3011. The memory 3011 may mainly include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function (such as a sound playback function, an image playback function, etc.), etc.; the data storage area may store data created according to the use of the computing device, etc. In addition, the memory 3011 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other volatile solid-state storage devices. Accordingly, the memory 3011 may also include a memory controller to provide the processor 3012 with access to the memory 3011.

[0079] On the other hand, an embodiment of the present application further provides a storage medium storing a computer program. When the computer program is executed by a processor, the processor executes the steps of the cell segmentation method based on spatial omics sequencing provided in any of the above embodiments of the present application.

[0080] Those skilled in the art can understand that all or part of the processes in the methods provided in the above embodiments can be completed by instructing the relevant hardware through a computer program, and the program can be stored in a non-volatile computer-readable storage medium. When the program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to memory, storage, database or other media used in the embodiments provided in the present application may include non-volatile and / or volatile memory. Non-volatile memory may include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory may include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (DDRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM (RDRAM).

[0081] The above is only a specific embodiment of the present invention, but the protection scope of the present invention is not limited thereto. Any person skilled in the art can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be included in the protection scope of the present invention. The protection scope of the present invention should be based on the protection scope of the claims.

Claims

1. A cell segmentation method based on spatial omics sequencing, characterized in that: include: Acquiring a collected signal distribution image, wherein the signal distribution image indicates distribution characteristics of spatial omics signals of the tissue section; Based on the signal distribution image, an initial smoothing operation is performed to obtain an initial smoothed distribution image, and based on the initial smoothed distribution image, an image segmentation operation is performed to obtain a current cell segmentation region set; Based on the current cell segmentation region set, filter out the cell region images to be further segmented to obtain the current first region set, and filter out the cell region images not to be further segmented to obtain the current second region set; Adjusting the smoothing parameters corresponding to the smoothing operation, performing the smoothing operation and the image segmentation operation on the cell region image in the current first region set based on the adjusted smoothing parameters, updating the current cell segmentation region set, and returning to the previous screening step until the termination condition is met to obtain the target second region set; Based on the target second region set, each cell region is obtained.

2. The cell segmentation method based on spatial omics sequencing according to claim 1, characterized in that: The performing a smoothing operation based on the signal distribution image to obtain an initial smoothed distribution image comprises: Acquire a filtering threshold, and filter the signal distribution image based on the filtering threshold to obtain a filtered distribution image; Based on the filtered distribution image, an initial smoothing operation is performed to obtain an initial smoothed distribution image.

3. The cell segmentation method based on spatial omics sequencing according to claim 2, characterized in that: The obtaining of the filtering threshold, filtering the signal distribution image based on the filtering threshold to obtain the filtered distribution image comprises at least one of the following: Obtaining a preset filtering threshold, setting the signal intensity of the pixel points in the signal distribution image that are less than the filtering threshold to a preset intensity value, and obtaining the filtered distribution image; Calculating the filtering threshold based on the signal strength corresponding to the pixel points in the signal distribution image, setting the signal strength of the pixel points in the signal distribution image that are less than the filtering threshold to a preset strength value, and obtaining the filtered distribution image; Obtain the signal strength value of each neighboring pixel point in the neighborhood of each pixel point in the signal distribution image, calculate the average signal strength value corresponding to each pixel point based on the signal strength value of each neighboring pixel point corresponding to each pixel point, determine the filtering threshold corresponding to each pixel point based on the average signal strength value corresponding to each pixel point, set the signal strength of the pixel point that is less than the filtering threshold corresponding to the pixel point to a preset strength value, and obtain the filtered distribution image.

4. The cell segmentation method based on spatial omics sequencing according to claim 1, characterized in that: The smoothing parameters corresponding to the adjustment smoothing operation include: The smoothing parameter value of each smoothing operation is calculated, wherein the smoothing parameter value corresponding to the current smoothing operation currently being executed is smaller than the smoothing parameter value corresponding to the previous smoothing operation of the current smoothing operation.

5. The cell segmentation method based on spatial omics sequencing according to claim 4, characterized in that: The smoothing parameter value corresponding to the current smoothing operation is between 1 / 10 of the smoothing parameter value corresponding to the previous smoothing operation and 9 / 10 of the smoothing parameter value corresponding to the previous smoothing operation.

6. The cell segmentation method based on spatial omics sequencing according to claim 1, characterized in that: The method of screening the cell region images to be further segmented based on the current cell segmentation region set to obtain the current first region set, and screening the cell region images not to be further segmented to obtain the current second region set comprises: Putting cell region images above a preset screening upper limit in the current cell segmentation region set into the current first region set; The cell region images in the current cell segmentation region set that are lower than a preset screening upper limit and higher than a preset screening lower limit are placed into the current second region set.

7. The cell segmentation method based on spatial omics sequencing according to claim 1, characterized in that: The performing an initial smoothing operation based on the signal distribution image to obtain an initial smoothed distribution image comprises: Based on the signal distribution image and the initial smoothing parameter value, an initial smoothing operation is performed to obtain an initial smoothed distribution image, wherein the initial smoothing parameter value is a minimum value that satisfies the inequality, wherein the inequality is: in represents the average cell radius, represents the smoothing parameter, is the natural base of the exponential function.

8. The cell segmentation method based on spatial omics sequencing according to claim 1, characterized in that: The obtaining of each cell region based on the target second region set includes: Acquire multiple target area images in the target second area set; for any of the target area images, acquire each probe corresponding to each pixel point in the target area image, and mark each probe corresponding to each pixel point in the target area image as the same cell.

9. A computing device, characterized in that The method comprises a memory and a processor, wherein the memory stores a computer program, and when the computer program is executed by the processor, the processor executes the steps of the method according to any one of claims 1 to 8.

10. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the processor is caused to perform the steps of the method according to any one of claims 1 to 8.

11. A computer program product, comprising a computer program, characterized in that When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images