CN115018831A

CN115018831A - Overlapping chromosome separation method, system, electronic terminal and readable storage medium

Info

Publication number: CN115018831A
Application number: CN202210932697.0A
Authority: CN
Inventors: 彭伟雄; 穆阳; 卢沁阳; 蔡昱峰
Original assignee: Hunan Zixing Wisdom Medical Technology Co ltd
Current assignee: Hunan Zixing Wisdom Medical Technology Co ltd
Priority date: 2022-08-04
Filing date: 2022-08-04
Publication date: 2022-09-06

Abstract

The invention discloses a method, a system, an electronic terminal and a readable storage medium for separating overlapped chromosomes, wherein the method comprises the following steps: acquiring an overlapping region mask and a non-overlapping region mask corresponding to the overlapping chromosome cluster images to be separated; dividing the non-overlapping area into a plurality of connected domains based on the non-overlapping area mask; separating a single chromosome based on morphological rules of the connected domain and the overlapping region; the form rule indicates a grouping relationship between the overlapping regions and the connected domains set according to a position relationship and a form relationship between each overlapping region after the boundary of each overlapping region expands outwards and the connected domains intersected with the overlapping region after the boundary expands outwards, wherein the regions in the same group are combined to obtain a single separated chromosome. The invention establishes a set of simple and effective morphological rules to identify each part of the single chromosome, further divides each part of the single chromosome into the same group, and finally combines to obtain the separated single chromosome, thereby having good interpretability and high separation accuracy.

Description

Overlapping chromosome separation method, system, electronic terminal and readable storage medium

Technical Field

The invention belongs to the technical field of chromosome segmentation, and particularly relates to a method, a system, an electronic terminal and a readable storage medium for separating overlapped chromosomes.

Background

The analysis and identification of human chromosomes are important contents of cytogenetics, the automatic segmentation technology of the metaphase images of the cells mainly comprises two steps of denoising and separating single chromosomes, the work of image denoising is already complete at present, but in the aspect of separating all single chromosomes from chromosome clusters, particularly overlapping chromosome clusters, a small promotion space exists.

Due to chromosome flexibility and other reasons, chromosomes are often overlapped, especially crossed; in the process of identification and segmentation, because of cross overlapping, a plurality of overlapped chromosomes are easily segmented into one chromosome, so that the chromosome type is judged wrongly, and great influence is brought to research or patient diagnosis.

With the development of the neural network, experiments prove that the separation effect of applying the convolutional neural network to the conglutinated chromosome cluster is good, but the separation accuracy of the overlapped chromosome cluster is not high because the positions of chromosome examples in the overlapped chromosome cluster are too close. Compared with a deep learning method, the traditional segmentation method has stronger interpretability, but depends on targeted manual features, has insufficient robustness and can only be well performed on the overlapped chromosome clusters in a specific form.

Disclosure of Invention

The invention aims to overcome the technical problem of low accuracy of overlapped chromosome separation in the prior art, and further provides an overlapped chromosome separation method, a system, an electronic terminal and a readable storage medium. The method for separating the overlapped chromosomes is used for identifying each part of the single chromosome by establishing a set of simple and effective morphological rules, further dividing each part of the single chromosome into the same group, and finally combining the parts to obtain the separated single chromosome, so that the method has good interpretability and high separation accuracy.

In one aspect, the present invention provides a method for separating overlapping chromosomes, comprising the steps of:

step 1: acquiring an overlapping region mask and a non-overlapping region mask corresponding to the overlapping chromosome cluster images to be separated;

step 2: partitioning the non-overlapping region into a number of connected domains based on the non-overlapping region mask;

and 3, step 3: separating out a single chromosome based on morphological rules of the connected domain and the overlapping region;

the form rule represents a grouping relation between the overlapping regions and the connected domains set according to the position relation and the form relation between each overlapping region after being expanded and the connected domains intersected with the overlapping region after the boundary of each overlapping region is expanded outwards, wherein the regions in the same group are combined to obtain a single separated chromosome.

Specifically, the execution process of step 3 is as follows:

step 3-1: sequentially expanding the boundary of each overlapping area outwards by N pixels based on the overlapping area mask, wherein N is a positive integer;

step 3-2: counting the number n of the intersected connected domains of the expanded overlapped region and the connected domains for each overlapped region;

step 3-3: determining the grouping relation between the connected domains and the overlapping regions according to the following rules according to the number of the intersected connected domains corresponding to each overlapping region:

when n =1, the region where the connected domain exists and the corresponding overlapping region are divided into a group;

when n =2, the areas where the two connected domains with the intersection relationship are located are respectively divided into a group with the corresponding overlapping area;

when n is greater than 2, connecting the centroids of the connected domains with the intersecting relation with the centroid of the overlapping region;

when n =3 or 4, dividing the region where a pair of connected domains forming the maximum included angle and the corresponding overlapping region into one group, and dividing the region where the remaining connected domains and the corresponding overlapping region into another group;

when n is greater than 4, the areas where the pair of connected domains forming the largest included angle are grouped with the corresponding overlapping areas, the areas where the pair of connected domains forming the second large included angle are grouped with the corresponding overlapping areas, and the rest connected domains are not grouped;

step 3-4: judging whether two or more groups with the same non-overlapping area exist, if so, merging the groups with the same non-overlapping area, and then executing the step 3-5; otherwise, executing the step 3-5;

step 3-5: the regions of the same group are combined to obtain a single chromosome which is separated.

According to the invention, after the overlapping area is expanded, the overlapping area is intersected with the surrounding connected domain, so that the connected domain around the overlapping area can be effectively and accurately obtained. And then, summarizing a set of morphological rules by utilizing the intersection condition and morphological relation of the connected domain and the overlapped region, identifying each region belonging to the same chromosome, dividing the regions into a group, and finally merging the regions of the same group to obtain the separated single chromosome. The method provided by the technical scheme of the invention can process a single chromosome in a high-precision way, and effectively improve the separation precision in the prior art.

According to the separation technology based on the form rule provided by the technical scheme of the invention, in the specific implementation process, the connected domain (non-overlapping part) centroid around the overlapping region is taken, the influence of chromosome bending can be effectively reduced, and the provided rule based on the centroid connecting line angle is simple and is suitable for chromosomes in various cross forms.

Further optionally, the value range of N is: 1-6.

Further optionally, the obtaining process of the overlapping area mask and the non-overlapping area mask in step 1 is as follows:

step 1-1: acquiring an overlapped chromosome cluster image to be separated and an original image mask thereof;

step 1-2: inputting the overlapping chromosome cluster picture to be separated into an overlapping region mask extraction model based on neural network pre-training to obtain an overlapping region mask;

step 1-3: and subtracting the overlapping area mask from the original image mask to obtain a non-overlapping area mask.

According to the technical scheme, a deep learning method is introduced, and accurate overlapping area masks are obtained by utilizing the strong characteristic learning capability of deep learning in the segmentation of the overlapping areas.

Further optionally, the overlap region mask extraction model is constructed based on a pnet + + network, and the pre-trained corresponding sample of the overlap region mask extraction model is an overlap chromosome cluster picture labeled as an overlap region mask.

Further optionally, in step 2, based on the non-overlapping region mask, the non-overlapping region is segmented into a plurality of connected domains by using a watershed algorithm.

In a second aspect, the present invention provides a system based on the overlapping chromosome separation method, comprising:

the mask acquisition module is used for acquiring an overlapping region mask and a non-overlapping region mask corresponding to the overlapping chromosome cluster image to be separated;

a connected domain generating module, configured to divide the non-overlapping region into a plurality of connected domains based on the non-overlapping region mask;

the separation module is used for separating a single chromosome based on the morphological rule of the connected domain and the overlapping region;

Wherein the separation module comprises:

the expanding unit is used for sequentially expanding the boundary of each overlapping area outwards by N pixels based on the overlapping area mask, wherein N is a positive integer;

the statistical unit is used for counting the number n of the connected domains intersected by the expanded overlapped region and the connected domains for each overlapped region;

and the grouping unit is used for determining the grouping relation between the connected domains and the overlapping regions according to the number of the intersected connected domains corresponding to each overlapping region and the following rules:

the merging unit is used for judging whether two or more groups with the same non-overlapping area exist or not, and if so, merging the groups with the same non-overlapping area;

and the merging unit is also used for merging the regions in the same group to obtain separated single chromosomes.

In a third aspect, the present invention further provides an electronic terminal, which includes:

one or more processors;

a memory storing one or more computer programs;

the processor invokes the computer program to implement:

a step of a method for separating overlapping chromosomes.

In a fourth aspect, the present invention provides a readable storage medium storing a computer program for invocation by a processor to implement:

a step of a method for separating overlapping chromosomes.

Advantageous effects

According to the method for separating the overlapped chromosomes, provided by the technical scheme of the invention, a set of efficient and simple separation process is designed, the method is still effective for chromosome clusters with multiple crossed chromosomes, the probability of manual intervention is reduced, and the workload of chromosome karyotype analyzers is reduced. After the overlapping area is expanded, the overlapping area is intersected with the surrounding connected domain, so that the connected domain around the overlapping area can be effectively and accurately acquired. And summarizing a set of morphological rules by utilizing the intersection relation and the morphological relation of the connected domain and the overlapping region, identifying each region belonging to the same chromosome, dividing the regions into a group, and finally combining the regions in the same group to obtain the separated single chromosome. The method provided by the technical scheme of the invention can process a single chromosome in a high-precision way, and effectively improve the separation precision in the prior art.

The invention further preferably introduces a deep learning method, and obtains an accurate overlapping area mask by utilizing the powerful characteristic learning capability of deep learning in the segmentation of the overlapping area. And then after the overlapping region is obtained, the complete chromosome is obtained by splicing all parts of the chromosome by using a set of established simple and effective rules, and the method has good interpretability.

Drawings

FIG. 1 is a schematic flow chart of the method for separating overlapping chromosomes according to the embodiment of the invention.

Fig. 2 is a flow chart illustrating a configuration rule set according to an embodiment of the present invention.

Fig. 3 is a schematic diagram of a centroid connecting line between an overlapping region and a surrounding connected domain provided by the embodiment of the present invention.

Detailed Description

The invention provides a method for separating overlapped chromosomes, which is used for separating the overlapped chromosomes to obtain a single chromosome and is suitable for separating chromosome clusters crossed by a plurality of chromosomes. The core of the technical scheme of the invention is to provide a set of simple and practical morphological rules between the connected domain of the non-overlapping region and the overlapping region, and apply the morphological rules to the overlapping chromosome cluster picture to separate a single chromosome. The present invention will be further described with reference to the following examples.

Example 1:

this example provides a method of separating overlapping chromosomes, comprising the steps of:

s1: and acquiring the overlapped chromosome cluster picture and an original picture mask thereof.

The overlapping chromosome cluster picture refers to a chromosome picture containing overlapping chromosomes.

S2: and inputting the overlapping chromosome cluster picture into an overlapping region mask extraction model constructed based on a Unet + + network to obtain an overlapping region mask.

In this embodiment, the overlap area mask extraction model is constructed using a pnet + + network. Samples for model training are obtained in advance, and the corresponding samples are overlapped chromosome cluster pictures marked as overlapped region masks. The input of the overlap region mask extraction model obtained after model training is as follows: overlapping chromosome cluster pictures; the output is the corresponding overlap area mask. It should be understood that, since the present invention does not optimize the Unet + + network and its training process, no specific statements and constraints are made on its network architecture and training details. It should also be understood that in other possible embodiments, other types of neural networks may be selected to implement the overlap region mask extraction based on the determination of the model input, the model output, and the training samples.

S3: and subtracting the overlapping area mask from the original image mask to obtain a non-overlapping area mask.

S4: based on the non-overlapping region masks, a watershed algorithm is applied to divide the non-overlapping regions into a plurality of connected domains.

In the embodiment, the existing watershed algorithm is selected to realize the segmentation of the connected domain. The connected component obtained by the division is substantially a partial region of the chromosome. The aim of the next step is therefore to find other regions of the chromosome, so as to group regions belonging to the same chromosome.

S5: and separating the single chromosome based on the morphological rule of the connected domain and the overlapping region.

It should be noted that the morphological rule set by the present invention indicates the grouping relationship between the overlapping regions and the connected domains set according to the positional relationship and morphological relationship between each overlapping region and the connected domains intersected with the overlapping region after the boundary of each overlapping region is expanded outwards, wherein the regions in the same group are merged to obtain a single separated chromosome.

The specific implementation process for separating the single chromosome based on the morphological rule is as follows:

s5-1: sequentially expanding the boundary of each overlapping area outward by 6 pixels based on the overlapping area mask. In the embodiment, 6 pixels are obtained through a plurality of experimental verifications and are used as an optimal example, and in other feasible embodiments, the extended range can be adaptively adjusted according to application requirements and algorithm precision.

It should be understood that this step belongs to morphological operations, and since the non-overlapping region is obtained by subtraction, after the boundary of the overlapping region is expanded outwards, the expanded overlapping region and the non-overlapping region will necessarily intersect. Therefore, the purpose of this step is to obtain a connected domain around the overlap region; meanwhile, in the subsequent centroid calculation process, if a more complete and wider non-overlapping region is used, the influence of chromosome bending is larger.

S5-2: and counting the number n of the connected domains intersected by the expanded overlapped region and the connected domains for each overlapped region.

S5-3: determining the grouping relation between the connected domains and the overlapping regions according to the following rules according to the number of the intersected connected domains corresponding to each overlapping region:

and when n =1, the areas where the connected domains with the intersection relationship exist are grouped with the corresponding overlapping areas. In the normal case, after the overlapping region is removed from the crossed chromosome, only a part of the crossed chromosome is not left, that is, only one crossed connected domain does not exist, so if n =1 appears, the overlapped region is considered to be a wrong prediction, and is itself a part of the non-overlapped region, therefore, the region (corresponding to the non-overlapped region) where the connected domain is located and the corresponding overlapped region are in the same group, that is, the region part of the same chromosome.

And when n =2, the areas where the two connected domains with the intersection relationship exist are respectively grouped with the corresponding overlapping areas. Wherein, the overlapping region is composed of at least two chromosomes, when n =2, two connected domains which have an intersecting relationship with the overlapping region necessarily belong to different groups, i.e. respectively form a group with the overlapping region.

when n =3 or 4, the area where a pair of connected domains forming the largest included angle is located and the corresponding overlapping area are divided into one group, and the area where the remaining connected domains are located and the corresponding overlapping area are divided into another group.

When n is greater than 4, the areas where the pair of connected domains forming the largest included angle is located and the corresponding overlapping areas are grouped together, the areas where the pair of connected domains forming the second largest included angle is located and the corresponding overlapping areas are grouped together, and the remaining connected domains are not grouped together.

According to the topology structure of the chromosome, the connecting line of the three centroids of the overlapped region and two non-overlapped regions of the same chromosome nearby should approximate a straight line. n >4, one case is that the redundant parts will get grouped when discussing other overlapping regions, and the other extreme case is that the overlapping regions are made up of more than two chromosomes, which the present invention has never considered.

S5-4: judging whether two or more groups with the same non-overlapping area exist, if so, merging the groups with the same non-overlapping area, and then executing S5-5; otherwise, S5-5 is performed.

The present invention contemplates that there may be multiple overlapping regions of some chromosomes, and thus combinations where the same non-overlapping regions exist. For more clear description of the above features, the present embodiment is exemplified as follows:

for the overlapping area A, the grouping is divided into (overlapping area A, non-overlapping area b, c),

(an overlapping area A, a non-overlapping area d, e);

grouping for the overlapping region F { overlapping region F, non-overlapping region e, g },

(iv) an overlapping area F, a non-overlapping area h, i);

then the two are combined into a group of { overlapping areas A and F, non-overlapping areas d, e and g }, and finally a group of (r), (r) and (g) are obtained.

S5-5: the individual regions of the same set are combined to give a single chromosome which is isolated.

The regions of the same group grouped according to the invention correspond to different parts of the chromosome and are therefore finally merged.

In summary, the method for separating overlapping chromosomes provided by this embodiment generally combines the advantages of the deep learning method and the conventional method, utilizes the strong feature learning capability of deep learning in the segmentation of the overlapping region, and utilizes a set of simple and effective rules established after the overlapping region is obtained to splice each part of the chromosome to obtain a complete chromosome, which has good interpretability. The method has the advantages that the non-overlapping part of the centroids near the overlapping region is taken, so that the influence of chromosome bending is reduced, the rule based on the connecting line angle of the centroids is simple and is suitable for chromosomes in various cross forms, and under the data set of the task, the segmentation accuracy rate of the method reaches 98.8%.

Example 2

The present embodiment provides a system based on the method for separating overlapping chromosomes, which includes: the system comprises a mask obtaining module, a connected domain generating module and a separating module.

The mask acquiring module is used for acquiring an overlapping region mask and a non-overlapping region mask corresponding to the overlapping chromosome cluster images to be separated. The connected domain generating module is used for dividing the non-overlapping area into a plurality of connected domains based on the non-overlapping area mask. And the separation module is used for separating out a single chromosome based on the morphological rule of the connected domain and the overlapping region.

In this embodiment, the mask acquiring module includes an overlapping chromosome cluster image acquiring unit, an overlapping region mask extracting unit, and a non-overlapping region mask extracting unit. The overlapping chromosome cluster image acquisition unit is used for acquiring overlapping chromosome cluster images to be separated and original image masks thereof. And the overlapping region mask extracting unit is used for inputting the overlapping chromosome cluster pictures to be separated into an overlapping region mask extracting model based on neural network pre-training to obtain an overlapping region mask. And a non-overlapping area mask extracting unit, configured to subtract the overlapping area mask from the original image mask to obtain a non-overlapping area mask.

In this embodiment, the separation module includes: an expansion unit, a statistic unit and a grouping unit. The expanding unit is used for sequentially expanding the boundary of each overlapping area outwards by N pixels based on the overlapping area mask, wherein N is a positive integer; the statistical unit is used for counting the number n of the connected domains intersected by the expanded overlapped region and the connected domains for each overlapped region; the grouping unit is configured to determine a grouping relationship between the connected component and the overlapping area according to the number of the intersecting connected components corresponding to each overlapping area and according to the following rule, where:

and the merging unit is used for merging the regions in the same group to obtain separated single chromosomes.

For the implementation process of each module, please refer to the content of the above method, which is not described herein again. It should be understood that the above described division of functional blocks is merely a division of logical functions and that in actual implementation there may be additional divisions, for example, where multiple elements or components may be combined or integrated into another system or where some features may be omitted, or not implemented. Meanwhile, the integrated unit can be realized in a hardware form, and can also be realized in a software functional unit form.

Example 3

The present embodiment provides an electronic terminal, which includes: one or more processors, and memory storing one or more computer programs. Wherein the processor invokes the computer program to implement: a step of a method for separating overlapping chromosomes.

In some implementations, the processor invokes the computer program to specifically implement:

and step 3: separating out a single chromosome based on morphological rules of the connected domain and the overlapping region;

In other possible implementations, the processor invokes the computer program to implement:

S2: and inputting the overlapped chromosome cluster picture into an overlapped region mask extraction model constructed based on a Unet + + network to obtain an overlapped region mask.

S4: based on the non-overlapping region mask, a watershed algorithm is applied to divide the non-overlapping region into a plurality of connected domains.

In a specific implementation process, a computer program corresponding to the method of the present invention is loaded into a memory, so that a processor of the electronic terminal invokes the computer program to implement the above process.

The electronic terminal further comprises: and the communication interface is used for communicating with external equipment and carrying out data interactive transmission. Such as the collection equipment of the operation information collection subsystem and the communication modules of other trains, so as to obtain the real-time operation information of the train and the adjacent trains.

The memory may include high speed RAM memory, and may also include a non-volatile defibrillator, such as at least one disk memory.

If the memory, the processor and the communication interface are implemented independently, the memory, the processor and the communication interface may be connected to each other through a bus and perform communication with each other. The bus may be an industry standard architecture bus, a peripheral device interconnect bus, an extended industry standard architecture bus, or the like. The bus may be divided into an address bus, a data bus, a control bus, etc.

Optionally, in a specific implementation, if the memory, the processor, and the communication interface are integrated on a chip, the memory, the processor, that is, the communication interface may complete communication with each other through the internal interface.

The specific implementation process of each step refers to the explanation of the foregoing method.

It should be understood that in the embodiments of the present invention, the Processor may be a Central Processing Unit (CPU), and the Processor may also be other general purpose processors, Digital Signal Processors (DSPs), Application Specific Integrated Circuits (ASICs), Field Programmable Gate Arrays (FPGAs) or other Programmable logic devices, discrete Gate or transistor logic devices, discrete hardware components, and the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like. The memory may include both read-only memory and random access memory, and provides instructions and data to the processor. The portion of memory may also include non-volatile random access memory. For example, the memory may also store device type information.

Example 4

The present embodiments provide a readable storage medium storing a computer program for invocation by a processor to implement: a step of a method for separating overlapping chromosomes.

In some implementations, a computer program is invoked by a processor to implement:

the form rule indicates a grouping relationship between the overlapping regions and the connected domains set according to a position relationship and a form relationship between each overlapping region after the boundary of each overlapping region expands outwards and the connected domains intersected with the overlapping region after the boundary expands outwards, wherein the regions in the same group are combined to obtain a single separated chromosome.

In other possible implementations, the computer program is invoked by a processor to implement:

It should be understood that the foregoing method contents of the processes are embodied.

The readable storage medium is a computer readable storage medium, which may be an internal storage unit of the controller according to any of the foregoing embodiments, for example, a hard disk or a memory of the controller. The readable storage medium may also be an external storage device of the controller, such as a plug-in hard disk, a Smart Media Card (SMC), a Secure Digital (SD) Card, a Flash memory Card (Flash Card), and the like provided on the controller. Further, the readable storage medium may also include both an internal storage unit of the controller and an external storage device. The readable storage medium is used for storing the computer program and other programs and data required by the controller. The readable storage medium may also be used to temporarily store data that has been output or is to be output.

Based on such understanding, the technical solution of the present invention essentially or partially contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product stored in a storage medium and including instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the method according to the embodiments of the present invention. And the aforementioned readable storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.

It should be emphasized that the examples described herein are illustrative and not restrictive, and thus the invention is not to be limited to the examples described herein, but rather to other embodiments that may be devised by those skilled in the art based on the teachings herein, and that various modifications, alterations, and substitutions are possible without departing from the spirit and scope of the invention as defined by the appended claims.

It should be emphasized that the examples described herein are illustrative and not restrictive, and thus the invention is not to be limited to the examples described herein, but rather to other embodiments that may be devised by those skilled in the art based on the teachings herein, and that various modifications, alterations, and substitutions are possible without departing from the spirit and scope of the present invention.

Claims

1. A method of separating overlapping chromosomes, comprising: the method comprises the following steps:

wherein, the execution process of the step 3 is as follows:

step 3-3: determining the grouping relationship between the connected domains and the overlapping regions according to the following rules according to the number of the intersected connected domains corresponding to each overlapping region:

when n is greater than 4, the areas where the pair of connected domains forming the maximum included angle are grouped with the corresponding overlapping areas, the areas where the pair of connected domains forming the second large included angle are grouped with the corresponding overlapping areas, and the rest connected domains are not grouped;

step 3-5: the individual regions of the same set are combined to give a single chromosome which is isolated.

2. The method for separating overlapping chromosomes according to claim 1, wherein: the value range of N is as follows: 1-6.

3. The method for separating overlapping chromosomes according to claim 1, wherein: the acquiring process of the overlapping area mask and the non-overlapping area mask in step 1 is as follows:

4. The method for separating overlapping chromosomes according to claim 3, wherein: the overlapping region mask extraction model is constructed based on a Unet + + network, and a pre-trained corresponding sample of the overlapping region mask extraction model is an overlapping chromosome cluster picture labeled as an overlapping region mask.

5. The method for separating overlapping chromosomes according to claim 1, wherein: in step 2, based on the non-overlapping region mask, the non-overlapping region is divided into a plurality of connected domains by using a watershed algorithm.

6. A system based on the method for separating overlapping chromosomes according to any one of claims 1 to 5, wherein: the method comprises the following steps:

the mask acquisition module is used for acquiring an overlapping region mask and a non-overlapping region mask corresponding to the overlapping chromosome cluster images to be separated;

wherein the separation module comprises:

when n =1, the areas where the connected domains with the intersection relation exist and the corresponding overlapping areas are divided into a group;

7. An electronic terminal, characterized by: the method comprises the following steps:

one or more processors;

a memory storing one or more computer programs;

the processor invokes the computer program to implement:

the steps of the method for separating overlapping chromosomes according to any one of claims 1 to 5.

8. A readable storage medium, characterized by: a computer program is stored, which is invoked by a processor to implement: