CN111429440A

CN111429440A - Microscopic pathological image cell sufficiency detection method, system, equipment, device and medium

Info

Publication number: CN111429440A
Application number: CN202010243365.2A
Authority: CN
Inventors: 叶德贤; 姜辰希; 房劬
Original assignee: Shanghai Xingmai Information Technology Co ltd
Current assignee: Shanghai Xingmai Information Technology Co ltd
Priority date: 2020-03-31
Filing date: 2020-03-31
Publication date: 2020-07-17
Anticipated expiration: 2040-03-31
Also published as: CN111429440B

Abstract

The invention provides a method, a system, equipment, a device and a medium for detecting the sufficiency of cells in a microscopic pathological image, wherein the method comprises the following steps: acquiring a microscopic pathological image; extracting a dyeing area in the microscopic pathological image to obtain the number of pixels of the dyeing area; obtaining the average pixel number of single cells; acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of single cells; judging whether the cell number of the staining area is lower than a preset threshold value: if yes, judging that the number of cells in the microscopic pathological image is insufficient and prompting; if not, the cell number in the microscopic pathological image is judged to be sufficient. The method obtains the cell number of the staining area by extracting the pixel number of the staining area and the average pixel number of the single cell in the microscopic pathological image, can effectively judge whether the cell number in the microscopic pathological image is sufficient according to whether the cell number of the staining area is lower than a preset threshold value, and can effectively improve the quality of the pathological microscopic pathological image used for diagnosis.

Description

Microscopic pathological image cell sufficiency detection method, system, equipment, device and medium

Technical Field

The invention belongs to the technical field of image processing, particularly relates to the technical field of medical pathological image processing, and particularly relates to a method, a system, equipment, a device and a medium for detecting the sufficiency of cells in a microscopic pathological image.

Background

The prior art pathological diagnosis method usually involves a physician directly observing the sample cells through a microscope. With the development of digital microscope technology, in order to improve the efficiency of pathological diagnosis, a digital microscope with an image scanning and shooting function can be used to complete the scanning of pathological samples and store the pathological samples on a computer, and doctors can observe microscopic pathological images through a computer screen to perform pathological diagnosis.

In pathological specimen preparation, poor specimen quality, such as insufficient cell mass on a slide, often occurs. Diagnosis based on microscopic images with insufficient cell mass may result in reduced accuracy of diagnosis. If the doctor finds that the cell amount in the microscopic pathological image is obviously insufficient, the doctor usually extracts the sample again for pathological diagnosis.

With the development of the AI image processing technology, products for intelligently diagnosing microscopic pathological images by using artificial intelligence software are already available in the market, and the intelligent diagnosis software cannot judge the problem that the sample quality is insufficient in sample cell amount, so that inaccurate diagnosis can be caused.

Disclosure of Invention

In view of the above-mentioned shortcomings of the prior art, it is an object of the present invention to provide a method, a system, a device, an apparatus and a medium for detecting the sufficiency of cells in a microscopic pathology image, which are used to solve the problem in the prior art that it is difficult to effectively analyze and judge whether the number of cells in the microscopic pathology image is sufficient.

To achieve the above and other related objects, an embodiment of the present invention provides a method for detecting cell sufficiency in a microscopic pathology image, including: acquiring a microscopic pathological image; extracting a dyeing area in the microscopic pathological image to obtain the number of pixels of the dyeing area; obtaining the average pixel number of single cells; acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell; judging whether the cell number of the staining area is lower than a preset threshold value: if yes, judging that the number of cells in the microscopic pathological image is insufficient and prompting; and if not, judging that the number of the cells in the microscopic pathological image is sufficient.

In an embodiment of the present application, the extracting the stained area in the microscopic pathology image includes: performing down-sampling processing on the microscopic pathological image to obtain a low-resolution image; a stained area in the low resolution image is extracted.

In an embodiment of the present application, one implementation manner of extracting the dyed region includes: sequentially calculating the pixel variance of each image channel at each pixel position along the image channel direction; judging the pixel variance and the dyeing threshold, if the pixel variance is larger than or equal to the dyeing threshold, marking the pixel position as a pixel point in a dyeing area, and if the pixel variance is smaller than the dyeing threshold, marking the pixel position as a pixel point in a background area; and acquiring all the pixel points of the dyeing area to form the dyeing area, and acquiring the number of the pixel points of the dyeing area.

In an embodiment of the present application, one implementation manner of obtaining the average pixel count of a single cell includes: selecting one or more local dyeing areas from the dyeing area to obtain the number of pixels of the one or more local dyeing areas; performing cell segmentation on the one or more local staining areas by using a cell segmentation model to obtain the number of cells in the one or more local staining areas; and obtaining the average pixel number of the single cell according to the pixel number of the one or more local staining areas and the cell number of the one or more local staining areas.

In an embodiment of the present application, one implementation manner of obtaining the average pixel count of a single cell includes: estimating the average pixel number of the single cell according to the cell type and the shooting parameters of the microscopic pathological image; the microscopic pathological image shooting parameters comprise microscope magnification and camera resolution.

In one embodiment of the present application, the number of cells in the staining area is:

wherein: m is the number of pixels in the staining area, N is the down-sampling multiple, and M is the average number of pixels of single cells in the microscopic pathological image.

The embodiment of the invention also provides a cell sufficiency detection system for the microscopic pathology image, which comprises: the image acquisition module is used for acquiring a microscopic pathological image; the staining region extraction module is used for extracting a staining region in the microscopic pathological image to obtain the number of pixels of the staining region; the pixel number acquisition module is used for acquiring the average pixel number of the single cell; the cell number acquisition module is used for acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell; the cell quantity judging module is used for judging whether the cell number of the staining area is lower than a preset threshold value: if yes, judging that the number of cells in the microscopic pathological image is insufficient and prompting; and if not, judging that the number of the cells in the microscopic pathological image is sufficient.

Embodiments of the present invention also provide a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, implements the microscopic pathology image cell sufficiency detection method as described above.

Embodiments of the present invention also provide an electronic device, comprising a processor and a memory, the memory storing program instructions; the processor executes program instructions to implement the microscopic pathology image cell sufficiency detection method as described above.

The embodiment of the invention also provides a pathological microscopic image scanning detection device, which comprises: the scanning unit is configured to scan the pathological sample to obtain a pathological microscopic image; a detection unit configured to detect whether or not cells are sufficient in the pathology microscope image; a display unit configured to display a prompt indicating whether the cells are sufficient.

In an embodiment of the present application, the method for detecting whether the cells in the pathological microscopic image are sufficient includes: acquiring a microscopic pathological image; extracting a dyeing area in the microscopic pathological image to obtain the number of pixels of the dyeing area; obtaining the average pixel number of single cells; acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell; judging whether the cell number of the staining area is lower than a preset threshold value: if yes, judging that the number of cells in the microscopic pathological image is insufficient; and if not, judging that the number of the cells in the microscopic pathological image is sufficient.

As described above, the method, system, device, apparatus and medium for detecting cell sufficiency in microscopic pathology images of the present invention have the following beneficial effects:

the method obtains the cell number of the staining area by extracting the pixel number of the staining area and the average pixel number of the single cell in the microscopic pathological image, can effectively judge whether the cell number in the microscopic pathological image is sufficient according to whether the cell number of the staining area is lower than a preset threshold value, can effectively improve the quality of the pathological microscopic pathological image used for diagnosis, and improves the intellectualization and the accuracy of the diagnosis.

Drawings

FIG. 1 is a schematic overall flow chart of the microscopic pathological image cell sufficiency detection method of the present invention.

FIG. 2 is a flow chart showing a method of processing a stained area in the microscopic pathology image cell sufficiency detection method of the present invention.

FIG. 3 is a flow chart showing one implementation of the method for detecting cell sufficiency in microscopic pathology images of the present invention for extracting stained areas.

FIG. 4 is a flow chart of an embodiment of the method for detecting cell sufficiency in microscopic pathology images according to the present invention.

Fig. 5 is a block diagram showing the overall schematic structure of the microscopic pathology image cell sufficiency detection system of the present invention.

Fig. 6 is a block diagram showing the schematic structure of the stained area extracting module in the microscopic pathology image cell sufficiency detecting system of the present invention.

Fig. 7 is a block diagram of the schematic structure of the pixel number acquisition module in the cell sufficiency detection system for microscopic pathology images according to the present invention.

Fig. 8 is a schematic structural diagram of an electronic device in an embodiment of the present application.

Fig. 9 is a block diagram showing the schematic structure of the pathological microscopic image scanning detection device of the present invention.

Description of the element reference numerals

Cell sufficiency detection system for 100 microscopic pathological image

110 image acquisition module

120 dyeing region extraction module

121 down-sampling unit

122 variance calculation unit

123 pixel judgment unit

124 extraction unit

130 pixel number acquisition module

131 area pixel selection unit

132 cell division unit

133 pixel number acquisition unit

140 cell number acquisition module

150 cell mass judgment module

1101 processor

1102 memory

200 pathological microscopic image scanning detection device

210 scan cell

220 detection unit

230 display unit

S100 to S700 steps

S201 to S202

S210 to S250

S310 to S330

Detailed Description

The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.

It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.

The present embodiment aims to provide a method, a system, a device, an apparatus, and a medium for detecting the sufficiency of cells in a microscopic pathology image, which are used to solve the problem in the prior art that it is difficult to effectively analyze and determine whether the number of cells in the microscopic pathology image is sufficient.

The principles and embodiments of the method, system, apparatus, device and medium for detecting cell abundance in microscopic pathology image according to the present invention will be described in detail below, so that those skilled in the art can understand the method, system, apparatus, device and medium for detecting cell abundance in microscopic pathology image without creative work.

Example 1

As shown in fig. 1, the present embodiment provides a cell sufficiency detecting method for a microscopic pathology image, which includes the steps of:

step S100, acquiring a microscopic pathological image;

step S200, extracting a dyeing area in the microscopic pathological image to obtain the number of pixels of the dyeing area;

step S300, obtaining the average pixel number of single cells;

step S400, acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell;

step S500, judging whether the cell number of the staining area is lower than a preset threshold value: if yes, go to step S600; if not, continuing to execute the step S700;

step S600, judging that the number of cells in the microscopic pathological image is insufficient and prompting;

step S700, judging that the number of cells in the microscopic pathological image is sufficient.

The following describes steps S100 to S700 of the microscopic pathology image cell sufficiency detection method of the present embodiment in detail.

And step S100, acquiring a microscopic pathological image.

After the pathological cell slide is scanned by using a digital microscope, a pathological oversized picture, namely a pathological microscopic pathological image, also called a full-field digital section (WSI) is obtained.

The pathological microscopic pathological image is formed by scanning pathological cell slides prepared from samples of cells or tissues for pathological microscopic diagnosis extracted from any human body parts such as human lungs, thyroid glands, mammary glands and the like through a digital microscope. The method for obtaining the human body cell or tissue sample can be obtained through puncture surgery, can also be obtained through an endoscope, or can be obtained through other medical means. The specimen is typically prepared as a microscopic slide and placed on a stage, in this embodiment, the microscopic pathology image is an image formed after staining the specimen slide to more clearly distinguish the cells. In the prior art, the quality of the slide cannot be controlled, and the number of cells in a microscopic pathological image cannot be judged, but the number of cells in the sample slide is too small, so that the quality of the sample slide is influenced, and the diagnosis level is influenced. In this example, whether the number of cells in the sample slide is sufficient or not is examined.

And S200, extracting a dyeing area in the microscopic pathological image to obtain the number of pixels in the dyeing area.

And removing the background in the microscopic pathological image and extracting a staining area.

In order to reduce the amount and time of computation, the microscopic pathology image is first down-sampled before the stained area is extracted in this embodiment.

As shown in fig. 2, in the present embodiment, the extracting the stained area in the microscopic pathology image includes:

step S201, performing down-sampling processing on the microscopic pathological image to obtain a low-resolution image;

step S202, extracting a dyeing area in the low-resolution image.

And carrying out down-sampling on the microscopic pathological image by N times to obtain a low-resolution image.

Specifically, as shown in fig. 3, in the present embodiment, one implementation manner of extracting the dyed region includes:

step S210, calculating the pixel variance of each image channel at each pixel position in sequence along the image channel direction;

step S220, determining the pixel variance and the staining threshold, if the pixel variance is greater than or equal to the staining threshold, executing step S230: the pixel position is marked as a pixel point in a dyeing area, and if the pixel variance is smaller than the dyeing threshold, step S240 is executed: the pixel position is marked as a background area pixel point;

step S250: and acquiring all the pixel points of the dyeing area to form the dyeing area, and acquiring the number of the pixel points of the dyeing area.

Specifically, in this embodiment, for the low resolution image (Width Height Channel) after the down-sampling, where the Channel is 3, that is, a 3-Channel RGB image, the variance of the 3 channels at each pixel position is calculated along the Channel direction, the calculated variance is larger in the cell region due to the staining, the calculated variance is white in the background region, the calculated variance is smaller, the stained region is separated by a threshold (for example, the threshold is 100 when the staining is performed by hematoxylin-eosin staining), and the number M of pixels in the stained region is calculated.

Step S300, obtaining the average pixel number of the single cell.

In this embodiment, as shown in fig. 4, one implementation of obtaining the average number of pixels of a single cell includes:

step S310, selecting one or more local dyeing areas from the dyeing areas to obtain the number of pixels of the one or more local dyeing areas;

step S320, carrying out cell segmentation on the one or more local staining areas by adopting a cell segmentation model to obtain the cell number of the one or more local staining areas;

step S330, obtaining the average pixel number of the single cell according to the pixel number of the one or more local staining areas and the cell number of the one or more local staining areas; wherein the average pixel count of a single cell is equal to the pixel count of the one or more localized stained areas divided by the cell count of the one or more localized stained areas.

That is, in this embodiment, the individual cells are obtained by dividing the stained area in the original resolution image by the cell division model (UNet), and the number of cells and the total number of pixels of the cells are counted to obtain the average number of pixels of the individual cells.

In this embodiment, a segmentation convolutional neural network algorithm is used to detect and obtain the cell region of the staining region in the microscopic pathological image.

Wherein, the microscopic pathological image can be segmented into cell areas by using but not limited to a segmentation convolutional neural network algorithm Unet (cell segmentation model). The cell segmentation model is obtained by training the following method: (1) obtaining a microscopic pathological image labeled by a pathologist as training data, wherein the labeling mode can comprise smearing on the position of cells in the microscopic pathological image or outlining the cell; (2) and inputting the training data into the Unet convolutional neural network for training to obtain a trained cell segmentation model.

In another embodiment, one implementation manner of obtaining the average pixel count of the single cell includes: estimating the average number of pixels of the single cell according to the cell type (such as lung cell, thyroid cell and mammary gland cell) and the shooting parameters of the microscopic pathological image; the microscopic pathological image shooting parameters comprise microscope magnification and camera resolution.

That is, the average number m of pixels of cells on the original resolution image (low resolution cells are blurred and difficult to estimate) can also be obtained by a priori knowledge, for example, the average number of pixels of lung cells under 40 times of magnification is 10000.

And step S400, acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell.

Specifically, in this embodiment, the number of cells in the staining area is:

Obtaining the pixel number M × N of the dyed area in the original resolution map according to the down-sampling multiple²。

and step S600, judging that the number of the cells in the microscopic pathological image is insufficient and prompting.

In this embodiment, it is determined whether the number of cells of the slide is sufficient or not according to the number of cells set by the user, and the user is not prompted sufficiently. If the cell number is less than a certain threshold value, the user is prompted that the cell number is insufficient, and the user is advised to take materials again for preparing the slide.

In this embodiment, when the number of cells in the microscopic pathology image is determined to be insufficient, the microscopic pathology image with abnormal quality is determined, and a prompt is output to the microscopic pathology image with abnormal quality.

And prompting can be output to the microscopic pathological image with abnormal quality in the form of sound, text and other alarm. For example, the user is prompted that there is a problem with the production, that the number of cells is insufficient, and that a renewed production is recommended.

Therefore, the method for detecting the sufficiency of the cells in the microscopic pathological image obtains the number of the cells in the staining area by extracting the number of the pixels in the staining area and the average number of the pixels of the single cells in the microscopic pathological image, and can effectively judge whether the number of the cells in the microscopic pathological image is sufficient according to whether the number of the cells in the staining area is lower than a preset threshold value, so that the quality of the pathological microscopic pathological image used for diagnosis can be effectively improved, and the intelligence and the accuracy of diagnosis are improved.

Example 2

As shown in fig. 5, the present embodiment provides a microscopic pathology image cell sufficiency detection system 100, and the microscopic pathology image cell sufficiency detection system 100 includes: an image acquisition module 110, a stained area extraction module 120, a pixel number acquisition module 130, a cell number acquisition module 140, and a cell amount determination module 150.

In this embodiment, the image acquiring module 110 is used for acquiring a microscopic pathology image.

In this embodiment, the stained area extracting module 120 is configured to extract a stained area in the microscopic pathology image, so as to obtain the number of stained area pixels.

Specifically, as shown in fig. 6, in the present embodiment, the dyed region extracting module 120 includes: a down-sampling unit 121, a variance calculation unit 122, a pixel judgment unit 123, and an extraction unit 124.

In this embodiment, the down-sampling unit 121 is configured to perform down-sampling processing on the microscopic pathological image to obtain a low-resolution image. And carrying out down-sampling on the microscopic pathological image by N times to obtain a low-resolution image.

In this embodiment, the variance calculating unit 122 is configured to sequentially calculate the pixel variance of each image channel at each pixel position along the image channel direction; the pixel determination unit 123 is configured to determine the pixel variance and the staining threshold: if the pixel variance is larger than or equal to the dyeing threshold, the pixel position is marked as a pixel point in a dyeing area, and if the pixel variance is smaller than the dyeing threshold, the pixel position is marked as a pixel point in a background area; the extracting unit 124 is configured to obtain all the pixel points of the dyeing region, form the dyeing region, and obtain the number of the pixels of the dyeing region.

In this embodiment, the pixel number obtaining module 130 is used for obtaining the average pixel number of a single cell.

Specifically, as shown in fig. 7, in the present embodiment, the pixel number obtaining module 130 includes: an area pixel selecting unit 131, a cell dividing unit 132 and a pixel number acquiring unit 133.

In this embodiment, the area pixel selecting unit 131 is configured to select one or more local dyeing areas from the dyeing areas to obtain the number of pixels in the one or more local dyeing areas; the cell segmentation unit 132 performs cell segmentation on the one or more local staining areas by using a cell segmentation model to obtain the number of cells in the one or more local staining areas; the pixel number obtaining unit 133 is configured to obtain the average pixel number of the single cell according to the pixel number of the one or more local staining regions and the cell number of the one or more local staining regions.

Wherein the average pixel count of a single cell is equal to the pixel count of the one or more localized stained areas divided by the cell count of the one or more localized stained areas.

In another embodiment, the pixel number obtaining module 130 may also estimate the average pixel number of the single cell according to the cell type (e.g. lung cell, thyroid cell, breast cell) and the imaging parameters of the microscopic pathology image; the microscopic pathological image shooting parameters comprise microscope magnification and camera resolution.

In this embodiment, the cell number acquiring module 140 is configured to acquire the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell.

Specifically, in this embodiment, the number of cells in the staining area is:

In this embodiment, the cell amount determining module 150 is configured to determine whether the cell number in the staining area is lower than a preset threshold: if yes, judging that the number of cells in the microscopic pathological image is insufficient and prompting; and if not, judging that the number of the cells in the microscopic pathological image is sufficient.

Therefore, the microscopic pathological image cell sufficiency detection system 100 of the embodiment obtains the number of cells in the staining region by extracting the number of pixels in the staining region and the average number of pixels of a single cell in the microscopic pathological image, and can effectively judge whether the number of cells in the microscopic pathological image is sufficient according to whether the number of cells in the staining region is lower than a preset threshold value, so that the quality of the pathological microscopic pathological image used for diagnosis can be effectively improved, and the diagnosis intelligence and accuracy are improved.

Example 3

As shown in fig. 8, the present embodiment further provides an electronic device, which is, but not limited to, a medical examination device, an image processing device, etc., as shown in fig. 8, the electronic device processor 1101 and the memory 1102; the memory 1102 is connected to the processor 1101 through a system bus to complete communication between the processor 1102 and the memory 1101, the processor 1101 is configured to run a computer program, so that the electronic device executes the microscopic pathology image cell sufficiency detection method. The method for detecting the sufficiency of cells in the microscopic pathological image has been described in detail above, and is not repeated herein.

The microscopic pathology image cell sufficiency detection method can be applied to various types of electronic equipment. The electronic device is, for example, a controller, such as an arm (advanced RISC machines) controller, an fpga (field programmable Gate array) controller, a soc (system on chip) controller, a dsp (digital signal processing) controller, or an mcu (micro controller unit) controller. The electronic device may also be, for example, a computer that includes components such as memory, a memory controller, one or more processing units (CPUs), a peripheral interface, RF circuitry, audio circuitry, speakers, a microphone, an input/output (I/O) subsystem, a display screen, other output or control devices, and external ports; the computer includes, but is not limited to, Personal computers such as desktop computers, notebook computers, tablet computers, smart phones, smart televisions, Personal Digital Assistants (PDAs), and the like. In other embodiments, the electronic device may also be a server, and the server may be arranged on one or more entity servers according to various factors such as functions, loads, and the like, or may be formed by a distributed or centralized server cluster, which is not limited in this embodiment.

In an actual implementation manner, the electronic device is, for example, an electronic device installed with an Android operating system or an iOS operating system, or an operating system such as Palm OS, Symbian, Black Berry OS, or Windows Phone.

In an exemplary embodiment, the electronic device may be implemented by one or more Application Specific Integrated Circuits (ASICs), Digital Signal Processors (DSPs), Digital Signal Processing Devices (DSPDs), programmable logic devices (P L D), Field Programmable Gate Arrays (FPGAs), controllers, micro-controllers, microprocessors, cameras or other electronic components for performing the above-described microscopic pathology image cell sufficiency detection method.

It should be noted that the above-mentioned system bus may be a Peripheral Component Interconnect (PCI) bus, an Extended Industry Standard Architecture (EISA) bus, or the like. The system bus may be divided into an address bus, a data bus, a control bus, and the like. For ease of illustration, only one thick line is shown in FIG. 6, but this is not intended to represent only one bus or type of bus. The communication interface is used for realizing communication between the database access device and other equipment (such as a client, a read-write library and a read-only library). The Memory may include a Random Access Memory (RAM), and may further include a non-volatile Memory (non-volatile Memory), such as at least one disk Memory.

The Processor 1101 may be a general-purpose Processor, and includes a Central Processing Unit (CPU), a Network Processor (NP), and the like; the device can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field Programmable Gate Array (FPGA) or other Programmable logic device, a discrete Gate or transistor logic device, or a discrete hardware component.

Example 4

The present embodiments provide a computer-readable storage medium, such as a memory configured to store various types of data to support operations at a device. Examples of such data include instructions, messages, pictures, etc. for any application or method operating on the electronic device. The memory may be implemented by any type or combination of volatile or non-volatile memory devices, such as Static Random Access Memory (SRAM), high speed random access memory (high speed ram), Electrically Erasable Programmable Read Only Memory (EEPROM), Erasable Programmable Read Only Memory (EPROM), Programmable Read Only Memory (PROM), Read Only Memory (ROM), magnetic memory, flash memory, magnetic or optical disks, or the like. The memory stores program instructions that, when executed, implement the microscopic pathology image cell sufficiency detection method as described above. The method for detecting the sufficiency of cells in the microscopic pathological image has been described in detail above, and is not repeated herein.

Those of ordinary skill in the art will understand that: all or part of the steps for implementing the above method embodiments may be performed by hardware associated with a computer program. The aforementioned computer program may be stored in a computer readable storage medium. When executed, the program performs steps comprising the method embodiments described above; and the aforementioned storage medium includes: various media that can store program codes, such as ROM, RAM, magnetic or optical disks.

Example 5

As shown in fig. 9, the present embodiment provides a pathological microscopic image scanning detection apparatus 200, the pathological microscopic image scanning detection apparatus 200 including: a scanning unit 210, a detecting unit 220, and a display unit 230.

In this embodiment, the scanning unit 210 is configured to scan a pathological sample to obtain a pathological microscopic image.

The scanning unit 210 is a camera for photographing a slide sample to obtain a pathological microscopic image, and in some embodiments, the camera is connected to an eyepiece of a microscope for photographing a microscopic magnified pathological microscopic image.

In this embodiment, the detecting unit 220 is configured to detect whether the cells in the pathological microscopic image are sufficient.

Specifically, in this embodiment, the method for detecting whether the cells in the pathological microscopic image are sufficient by the detecting unit 220 is the method for detecting the cell sufficiency in the microscopic pathological image in embodiment 1.

As shown in fig. 1, the method for detecting whether the cells in the pathological microscopic image are sufficient by the detecting unit 220 includes:

step S100, acquiring a microscopic pathological image;

step S300, obtaining the average pixel number of single cells;

The detailed implementation process of steps S100 to S700 has been described in detail in embodiment 1, and the technical features of the method for detecting whether the cells in the pathological microscopic image are sufficient by the detecting unit 220 in this embodiment are the same as the method for detecting the sufficiency of the cells in the microscopic pathological image in embodiment 1, and the general technical contents between the embodiments are not repeated.

The display unit 230 includes but is not limited to an O L ED, L ED, or L CD display, and the display unit 230 may also include an interactive display device such as a touch screen, and the embodiment is not limited in particular.

In summary, the present invention extracts the number of pixels in the staining area and the average number of pixels in a single cell in the microscopic pathological image to obtain the number of cells in the staining area, and can effectively determine whether the number of cells in the microscopic pathological image is sufficient according to whether the number of cells in the staining area is lower than a preset threshold, thereby effectively improving the quality of the pathological microscopic pathological image used for diagnosis and improving the intellectualization and accuracy of diagnosis. Therefore, the invention effectively overcomes various defects in the prior art and has high industrial utilization value.

The foregoing embodiments are merely illustrative of the principles and utilities of the present invention and are not intended to limit the invention. Any person skilled in the art can modify or change the above-mentioned embodiments without departing from the spirit and scope of the present invention. Accordingly, it is intended that all equivalent modifications or changes which can be made by those skilled in the art without departing from the spirit and technical spirit of the present invention be covered by the claims of the present invention.

Claims

1. A microscopic pathology image cell sufficiency detection method is characterized by comprising the following steps: the method comprises the following steps:

acquiring a microscopic pathological image;

extracting a dyeing area in the microscopic pathological image to obtain the number of pixels of the dyeing area;

obtaining the average pixel number of single cells;

acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell;

judging whether the cell number of the staining area is lower than a preset threshold value:

if yes, judging that the number of cells in the microscopic pathological image is insufficient and prompting;

and if not, judging that the number of the cells in the microscopic pathological image is sufficient.

2. The microscopic pathology image cell sufficiency detection method according to claim 1, characterized in that: the extracting of the stained area in the microscopic pathology image comprises:

performing down-sampling processing on the microscopic pathological image to obtain a low-resolution image;

a stained area in the low resolution image is extracted.

3. The microscopic pathology image cell sufficiency detection method according to claim 1 or 2, characterized in that: one implementation of extracting the stained area includes:

sequentially calculating the pixel variance of each image channel at each pixel position along the image channel direction;

judging the pixel variance and the dyeing threshold, if the pixel variance is larger than or equal to the dyeing threshold, marking the pixel position as a pixel point in a dyeing area, and if the pixel variance is smaller than the dyeing threshold, marking the pixel position as a pixel point in a background area;

and acquiring all the pixel points of the dyeing area to form the dyeing area, and acquiring the number of the pixel points of the dyeing area.

4. The microscopic pathology image cell sufficiency detection method according to claim 1, characterized in that: one implementation manner of obtaining the average pixel number of the single cell includes:

selecting one or more local dyeing areas from the dyeing area to obtain the number of pixels of the one or more local dyeing areas;

performing cell segmentation on the one or more local staining areas by using a cell segmentation model to obtain the number of cells in the one or more local staining areas;

and obtaining the average pixel number of the single cell according to the pixel number of the one or more local staining areas and the cell number of the one or more local staining areas.

5. The microscopic pathology image cell sufficiency detection method according to claim 3, characterized in that: one implementation manner of obtaining the average pixel number of the single cell includes:

estimating the average pixel number of the single cell according to the cell type and the shooting parameters of the microscopic pathological image; the microscopic pathological image shooting parameters comprise microscope magnification and camera resolution.

6. The microscopic pathology image cell sufficiency detection method according to claim 2, characterized in that: the cell number of the staining area is as follows:

7. A microscopic pathology image cell sufficiency detection system is characterized in that: the method comprises the following steps:

the image acquisition module is used for acquiring a microscopic pathological image;

the staining region extraction module is used for extracting a staining region in the microscopic pathological image to obtain the number of pixels of the staining region;

the pixel number acquisition module is used for acquiring the average pixel number of the single cell;

the cell number acquisition module is used for acquiring the cell number of the staining area according to the pixel number of the staining area and the average pixel number of the single cell;

the cell quantity judging module is used for judging whether the cell number of the staining area is lower than a preset threshold value: if yes, judging that the number of cells in the microscopic pathological image is insufficient and prompting; and if not, judging that the number of the cells in the microscopic pathological image is sufficient.

8. A computer-readable storage medium having stored thereon a computer program, characterized in that: the program, when executed by a processor, implements a microscopic pathology image cell sufficiency detection method according to any one of claims 1 to 6.

9. An electronic device, characterized in that: comprising a processor and a memory, said memory storing program instructions; the processor executes the program instructions to implement the microscopic pathology image cell sufficiency detection method according to any one of claims 1 to 6.

10. A pathological microscopic image scanning detection device is characterized in that: the method comprises the following steps:

the scanning unit is configured to scan the pathological sample to obtain a pathological microscopic image;

a detection unit configured to detect whether or not cells are sufficient in the pathology microscope image;

a display unit configured to display a prompt indicating whether the cells are sufficient.

11. The pathological microscopic image scanning detection device according to claim 10, characterized in that: the method for detecting whether the cells in the pathological microscopic image are sufficient comprises the following steps:

acquiring a microscopic pathological image;

obtaining the average pixel number of single cells;

if yes, judging that the number of cells in the microscopic pathological image is insufficient;