阅读说明：本技术 细胞微型显微图像采集装置及图像识别方法 (Cell micro microscopic image acquisition device and image identification method ) 是由 庞宝川 罗强 孙小蓉 于 2019-11-14 设计创作，主要内容包括：本发明提供一种细胞微型显微图像采集装置及图像识别方法,包括支座,在支座上设有活动的模组平台,在模组平台上设有摄像头模组；在摄像头模组的摄像头下方相对固定的设有显微镜头,显微镜头的下方设有玻片座,玻片座的下方设有照明光源；所述的玻片座与摄像头模组之间设有沿X、Y轴做扫描运动的扫描驱动模组,以使玻片座与摄像头模组之间沿X、Y轴做扫描运动,以使玻片的图像被以扫描的方式通过摄像头模组采集。被采集到摄像头模组内的玻片样本图像能够进行图像的拼接和图像的识别,且可以将图像上传到云端,由云上AI进行处理,大幅提高细胞识别的准确度和识别效率,极大降低了医疗成本,使更多的偏远医疗机构也能够应用该技术进行诊断。(The invention provides a cell micro-microscopic image acquisition device and an image identification method, comprising a support, wherein a movable module platform is arranged on the support, and a camera module is arranged on the module platform; a microscope lens is relatively fixedly arranged below a camera of the camera module, a slide seat is arranged below the microscope lens, and an illumination light source is arranged below the slide seat; the scanning driving module which is used for scanning along the X, Y axis is arranged between the slide seat and the camera module, so that the scanning movement is carried out along the X, Y axis between the slide seat and the camera module, and the image of the slide is collected by the camera module in a scanning mode. The splicing of the image and the identification of the image can be carried out by the slide sample image collected in the camera module, the image can be uploaded to the cloud, and the image is processed by the cloud AI, so that the accuracy and the identification efficiency of cell identification are greatly improved, the medical cost is greatly reduced, and more remote medical institutions can also use the technology for diagnosis.)

1. The utility model provides a cell miniature microscopic image acquisition device, includes support (4), characterized by: a movable module platform (2) is arranged on the support (4), and a camera module (1) is arranged on the module platform (2);

a microscope lens (3) is relatively and fixedly arranged below a camera (111) of the camera module (1), a slide seat (5) is arranged below the microscope lens (3), and an illumination light source (8) is arranged below the slide seat (5);

and a scanning driving module which performs scanning motion along an X, Y axis is arranged between the slide seat (5) and the camera module (1) so as to perform scanning motion along a X, Y axis between the slide seat (5) and the camera module (1) and acquire an image of the slide (7) through the camera module (1) in a scanning mode.

2. The cell microscopic image collecting device according to claim 1, wherein: the microscope lens (3) comprises a cantilever rod (32) arranged on the module platform (2), one end of the cantilever rod (32) is fixedly connected with the module platform (2), the other end of the cantilever rod is provided with a microscope lens, and the microscope lens is positioned below the camera;

the magnification of the micro lens is 2-10 times.

3. The cell microscopic image collecting device according to claim 2, wherein: a sunken step (21) is arranged near the camera (111) on the module platform (2), the cantilever rod (32) is in sliding connection with the step (21) through a plurality of positioning pins (22), an adjusting screw (23) is in threaded connection with the cantilever rod (32), the end of the adjusting screw (23) is propped against the step (21), and the distance between the cantilever rod (32) and the step (21) is adjusted through the rotation of the adjusting screw (23);

the micro lens is a replaceable micro lens (31).

4. The cell microscopic image collecting device according to claim 1, wherein: the scanning driving module is also provided with a control box (9), a main control chip (91) is arranged in the control box (9), the main control chip (91) is electrically connected with the camera (111), the main control chip (91) is also electrically connected with a control button (112) and/or a touch screen (113) of the camera module (1), and the main control chip (91) is also electrically connected with a driving motor of the scanning driving module;

the camera (111) adopts a mobile phone camera accessory.

5. The cell microscopic image collecting device according to claim 4, wherein: the module platform (2) is connected with the scanning driving module so as to enable the camera (111) to do scanning motion along an X, Y axis;

the slide seat (5) is fixedly connected with the support (4) and is fixed;

the structure of the scanning driving module is as follows:

an X-axis sliding rail (102) is fixedly arranged on a support (4), an X-axis sliding block (64) is slidably arranged on the X-axis sliding rail (102), an X-axis nut (103) is fixedly arranged on the X-axis sliding block (64), an X-axis screw rod (101) is rotatably arranged on the support (4), the X-axis nut (103) is in threaded connection with the X-axis screw rod (101), an X-axis driving motor (10) is fixedly arranged on the support (4), and an output shaft of the X-axis driving motor (10) is fixedly connected with the X-axis screw rod (101) so that the X-axis driving motor (10) drives the X-axis sliding block (64) to reciprocate along the X-axis sliding rail (102);

a Y-axis sliding rail (62) is fixedly arranged on an X-axis sliding block (64), a module platform (2) is slidably arranged on the Y-axis sliding rail (62), a Y-axis nut (63) is fixedly arranged on the module platform (2), a Y-axis screw (61) is rotatably arranged on the X-axis sliding block (64), the Y-axis nut (63) is in threaded connection with the Y-axis screw (61), a Y-axis driving motor (6) is fixedly arranged on the X-axis sliding block (64), and an output shaft of the Y-axis driving motor (6) is fixedly connected with the Y-axis screw (61) so that the Y-axis driving motor (6) drives the module platform (2) to reciprocate along the Y-axis sliding rail (62);

the camera module is also provided with a control box (9), and the control box (9) outputs a switch signal to be connected with the camera module (1) so as to control the camera module (1) to acquire images;

the control box (9) outputs pulse signals which are respectively connected with the Y-axis driving motor (6) and the X-axis driving motor (10) to respectively drive the X-axis driving motor (10) and the Y-axis driving motor (6) to rotate.

6. The cell microscopic image collecting device according to claim 4, wherein: the module platform (2) is fixedly connected with the support (4) and is fixed, and the slide seat (5) is connected with the scanning driving module so that the slide seat (5) can perform scanning motion along an X, Y axis;

the structure of the scanning driving module is as follows:

the X-axis driving motor (10) is fixedly connected with the support (4), a sliding rail along the X-axis direction is arranged on the support (4), the sliding platform (104) is installed on the sliding rail along the X-axis direction in a sliding mode, and the X-axis driving motor (10) is connected with the sliding platform (104) through a screw and nut mechanism to drive the sliding platform (104) to slide in a reciprocating mode along the X-axis direction;

a Y-axis driving motor (6) and a sliding rail along the Y-axis direction are fixedly arranged on the sliding platform (104), the slide holder (5) is slidably arranged on the sliding rail along the Y-axis direction, and the Y-axis driving motor (6) is connected with the slide holder (5) through a screw and nut mechanism so as to drive the slide holder (5) to slide in a reciprocating manner along the Y-axis direction;

the camera module is also provided with a control box (9), and the control box (9) outputs a switch signal to be connected with the camera module (1) so as to control the camera module (1) to acquire images;

the control box (9) outputs pulse signals which are respectively connected with the Y-axis driving motor (6) and the X-axis driving motor (10) to respectively drive the X-axis driving motor (10) and the Y-axis driving motor (6) to rotate.

7. The cell microscopic image collecting apparatus according to claim 5 or 6, wherein: the Y-axis driving motor (6) and the X-axis driving motor (10) are stepping motors;

the control box (9) is also internally provided with a storage chip (92), an interface chip (93) and a wireless transmission chip (95), and the storage chip (92), the interface chip (93) and the wireless transmission chip (95) are electrically connected with the main control chip (91);

the memory chip (92) is used for storing data, and the interface chip (93) and the wireless transmission chip (95) are used for transmitting data;

and the power supply chip (94) is also arranged and used for supplying power to the main control chip (91), the storage chip (92), the interface chip (93) and the wireless transmission chip (95).

8. An image stitching method using a cell microscopic image collecting apparatus according to any one of claims 1 to 7, characterized in that: the visual field sub-block matching module, the visual field position fitting module and the block extraction module are included;

the visual field sub-block matching module is used for identifying the overlapping area between the images and judging the adjacent position relationship between the sub-images, so that the sub-images acquired by the micro-scanning device are automatically arranged according to the splicing sequence of the images;

the visual field position fitting module is used for finely adjusting the position according to the overlapping area between the sub-images so as to accurately splice the cell positions;

the block extraction module is used for automatically extracting a spliced complete image;

the method comprises the following specific steps:

s1, matching view sub-blocks; the visual field sub-block matching module is used for identifying the overlapping area between the images and judging the adjacent position relationship between the sub-images, so that the sub-images acquired by the micro-scanning device are automatically arranged according to the splicing sequence of the images;

s2, fitting the view field position; the visual field position fitting module is used for finely adjusting the position according to the overlapping area between the sub-images so as to accurately splice the cell positions;

s3, extracting blocks; the block extraction module is used for automatically extracting a spliced complete image;

the operation process of the field sub-block matching in the step S1 is as follows:

sa01, inputting, and initializing a result set M;

sa02, setting the current view i as a first view;

sa03, obtaining all adjacent view sets J of the current view i;

sa04, setting the current adjacent view J as the first view in J;

sa05, calculating possible overlapping areas Ri and Rj of the visual field i and the visual field j;

sa06, rasterizing the template region Ri into a template sub-block set Pi;

sa07, arranging the template sub-block sets Pi in descending order according to the dynamic range of the sub-blocks;

sa08, setting the current template sub-block P as the first one in the template sub-block set Pi;

sa09, finding a possible overlapping area s of the template sub-block P in the view J;

sa10, performing template matching search by taking the template sub-block P as a template and s as a search area;

sa11, adding the best matching M into the result set M;

sa12, finding all matching set visual field sets N consistent with M in the result set M;

sa13, comparing and judging whether the sum of the weights in the N is greater than a threshold value v;

if not, setting the current template sub-block P as the next template sub-block in the template sub-block set Pi, and returning to Sa 09;

if yes, the next step is carried out;

sa14, and comparing and judging whether the view J is the last view in the view set J;

if not, setting the view J as the next view in the view set J, and returning to Sa 05;

if yes, the next step is carried out;

sa15, and comparing and judging, wherein the visual field i is the last visual field;

if not, setting i as the next visual field and returning to Sa 03;

if yes, outputting a result;

the process of the field position fitting in step S2 is:

sa16, inputting, initializing all view positions Xi and Yi;

sa17, setting the current view i as a first view;

sa18, obtaining a matching subset Mi containing the view i in the sub-block matching set M;

sa19, recalculating the positions Xi, Yi of the field of view i according to the matching subset Mi;

sa20, judging that all the visual fields are updated;

if not, setting the view i as the next view;

if yes, the next step is carried out;

sa21, calculating the deviation average value L of the current wheel visual field position and the upper wheel visual field position;

sa22, comparing and judging, wherein the deviation average value L is smaller than a threshold value 1;

if not, returning to Sa 17;

if yes, the next step is carried out;

sa23, visual field position normalization adjustment;

outputting all the visual fields;

the process of block extraction in step S3 is:

sa24, extracting the full graph size W, H;

sa25, dividing the whole image into a set B of blocks according to the block size;

sa26, calculating the positions of all blocks B in the set B;

sa27, setting block B as the first block in set B;

sa28, calculating a set Fb of all views overlapping block b;

sa29, setting the field of view f to be the first field of view in Fb;

sa30, finding the overlapping regions Rb and Rf of the field of view f and the block b;

sa31, copy Rf in image to Rb;

sa32, judging that the view f is the last view in the set Fb;

if not, setting the visual field f as the next visual field in the Fb, and returning to the Sa 29;

if yes, the next step is carried out;

sa33, save block b image;

sa34, judging that the block B is the last block in the set B;

if not, setting the block B as the first block in the set B, and returning to the Sa 28;

and if so, outputting the result.

9. An image recognition method using a cell microscopic image capturing device according to any one of claims 1 to 7, wherein: the method comprises the following steps: s1, acquiring a microscopic image;

s2, splicing a plurality of images of a single sample, and extracting the spliced images according to the characteristics of cell nuclei to obtain a single cell nucleus microscopic image;

s3, classifying the single cell nucleus microscopic image by using an artificial intelligence program after model training according to the marked cells;

obtaining classified cell data based on the sample through the steps;

the step of acquiring the microscopic image of the single cell nucleus in the step S2 is as follows:

s100, detecting characteristic points of cell nucleuses;

reducing the image to a plurality of different proportions, and respectively extracting feature points;

s101, primarily screening, namely screening out excessively similar characteristic points according to the characteristic point coordinates, and reducing repeated cell extraction;

s102, subdividing and dividing by using a color difference threshold value;

converting the picture into an LAB format, and performing Otsu threshold segmentation on the weighted sum of the B channel and the A channel after phase inversion to obtain a cell nucleus mask picture;

the weight is 0.7 of the phase reversal of the channel B and 0.3 of the channel A;

s103, performing image morphology operation;

one or more combination of erosion and dilation operations;

s104, screening, namely screening non-cells with the nuclear ratio lower than 0.3, the nuclear radius higher than 150 pixels and the nuclear radius lower than 10 pixels according to the nuclear ratio parameter; the kernel ratio = the kernel area/detection feature point radius circle area subdivided by the color difference threshold.

10. The method for processing image on cloud by using the cell micro-microscopic image acquisition device according to any one of claims 1 to 7, wherein: the method comprises the following steps:

s1, numbering the slide (7) samples, and determining the sample number in the system on the cloud;

s2, registration: inputting the information of the examinee corresponding to the slide (7) into a system, and inputting a sample number;

scanning: scanning the image of the slide (7) by using the camera module (1);

s3, uploading: uploading the scanned image sample to a cloud system;

s4, splicing and classifying: processing the digitized sample on the cloud AI;

s5, connection: correlating the registration information with the digital sample information in the system;

s6, diagnosis: the doctor diagnoses and rechecks the image sample and submits diagnosis opinions;

s7, report rendering: the rendering program polls the data which is diagnosed in the system and renders the data according to a corresponding report template to obtain files in PDF, JPG and WORD formats;

the cloud processing of the image is realized through the steps.

Technical Field

The invention relates to the field of medical image acquisition, in particular to a cell micro-microscopic image acquisition device and an image splicing, identifying and cloud processing method.

Background

Cell and tissue slice scanning is an important data for disease diagnosis, scientific research and teaching, and the tissue slices in the glass slices are scanned by a digital tissue slice scanner and converted into digital images, so that the digital images are convenient to store, transmit and remotely diagnose, but the existing digital tissue slice scanner is very expensive, and each digital tissue slice scanner is about five hundred thousand yuan, such as the scheme described in Chinese patent document CN 107543792A, which limits the popularization of diagnosis, scientific research and teaching means of the tissue slices. In order to solve the technical problem, the prior art also adopts some improved schemes to reduce the equipment cost, and chinese patent document CN 106226897A describes a tissue slice scanning device based on a common optical microscope and a smart phone, which is composed of a microscope fixing frame, a common optical microscope, a smart phone, a focusing and slice moving device, a smart phone fixing frame and a computer. The functions of a smart phone, a computer and a microscope are integrated together, and the tissue section is digitized in a low-cost and convenient mode. But the structure is still large in size, inconvenient to move and high in price. And the optical path is longer, which affects the collection precision of the pattern.

Disclosure of Invention

The invention aims to solve the technical problem of providing a cell micro-microscopic image acquisition device and an image splicing and identifying method, which can greatly reduce the cost and the volume, realize automatic scanning acquisition, and splice and identify images and perform cloud processing.

In order to solve the technical problems, the technical scheme adopted by the invention is as follows: the cell miniature microscopic image acquisition device comprises a support, and is characterized in that: a movable module platform is arranged on the support, and a camera module is arranged on the module platform;

a microscope lens is relatively fixedly arranged below a camera of the camera module, a slide seat is arranged below the microscope lens, and an illumination light source is arranged below the slide seat;

the scanning driving module which is used for scanning along the X, Y axis is arranged between the slide seat and the camera module, so that the scanning movement is carried out along the X, Y axis between the slide seat and the camera module, and the image of the slide is collected by the camera module in a scanning mode.

In a preferred scheme, the microscope lens comprises a cantilever rod arranged on the module platform, one end of the cantilever rod is fixedly connected with the module platform, the other end of the cantilever rod is provided with a microscope lens, and the microscope lens is positioned below the camera;

the magnification of the micro lens is 2-10 times.

In the preferred scheme, a sunken step is arranged near the camera on the module platform, the cantilever rod is in sliding connection with the step through a plurality of positioning pins, an adjusting screw is in threaded connection with the cantilever rod, the end of the adjusting screw abuts against the step, and the distance between the cantilever rod and the step is adjusted through the rotation of the adjusting screw;

the micro lens is a replaceable micro lens.

In the preferred scheme, a control box is further arranged, a main control chip is arranged in the control box, the main control chip is electrically connected with the camera, the main control chip is also electrically connected with a control button and/or a touch screen of the camera module, and the main control chip is also electrically connected with a driving motor of the scanning driving module;

the camera adopts a mobile phone camera accessory.

In a preferred scheme, the module platform is connected with a scanning driving module so as to enable the camera to perform scanning motion along an X, Y axis;

the slide seat is fixedly connected with the support and is fixed;

the structure of the scanning driving module is as follows:

an X-axis sliding rail is fixedly arranged on the support, an X-axis sliding block is slidably arranged on the X-axis sliding rail, an X-axis nut is fixedly arranged on the X-axis sliding block, an X-axis screw rod is rotatably arranged on the support, the X-axis nut is in threaded connection with the X-axis screw rod, an X-axis driving motor is fixedly arranged on the support, and an output shaft of the X-axis driving motor is fixedly connected with the X-axis screw rod so that the X-axis driving motor drives the X-axis sliding block to reciprocate along the X-axis sliding rail;

a Y-axis slide rail is fixedly arranged on the X-axis slide block, the module platform is slidably arranged on the Y-axis slide rail, a Y-axis nut is fixedly arranged on the module platform, a Y-axis screw rod is rotatably arranged on the X-axis slide block, the Y-axis nut is in threaded connection with the Y-axis screw rod, a Y-axis driving motor is fixedly arranged on the X-axis slide block, and an output shaft of the Y-axis driving motor is fixedly connected with the Y-axis screw rod so as to enable the Y-axis driving motor to drive the module platform to reciprocate along the Y-axis slide rail;

the control box is also arranged and outputs a switching signal to be connected with the camera module so as to control the camera module to acquire images;

the control box outputs pulse signals which are respectively connected with the Y-axis driving motor and the X-axis driving motor so as to respectively drive the X-axis driving motor and the Y-axis driving motor to rotate.

In the preferred scheme, the module platform is fixedly connected with the support and is fixed, and the slide seat is connected with the scanning driving module so as to enable the slide seat to do scanning motion along an X, Y axis;

the structure of the scanning driving module is as follows:

the X-axis driving motor is fixedly connected with the support, a sliding rail along the X-axis direction is arranged on the support, the sliding platform is slidably mounted on the sliding rail along the X-axis direction, and the X-axis driving motor is connected with the sliding platform through a screw and nut mechanism so as to drive the sliding platform to slide in a reciprocating manner along the X-axis direction;

a Y-axis driving motor and a slide rail along the Y-axis direction are fixedly arranged on the sliding platform, the slide seat is slidably arranged on the slide rail along the Y-axis direction, and the Y-axis driving motor is connected with the slide seat through a screw and nut mechanism so as to drive the slide seat to slide in a reciprocating manner along the Y-axis direction;

the control box is also arranged and outputs a switching signal to be connected with the camera module so as to control the camera module to acquire images;

the control box outputs pulse signals which are respectively connected with the Y-axis driving motor and the X-axis driving motor so as to respectively drive the X-axis driving motor and the Y-axis driving motor to rotate.

In a preferred scheme, the Y-axis driving motor and the X-axis driving motor are stepping motors;

the control box is internally provided with a storage chip, an interface chip and a wireless transmission chip which are all electrically connected with the main control chip;

the memory chip is used for storing data, and the interface chip and the wireless transmission chip are used for transmitting data;

and the power supply chip is also arranged and used for supplying power to the main control chip, the storage chip, the interface chip and the wireless transmission chip.

An image splicing method adopting the cell micro-microscopic image acquisition device comprises a visual field sub-block matching module, a visual field position fitting module and a block extraction module;

the visual field sub-block matching module is used for identifying the overlapping area between the images and judging the adjacent position relationship between the sub-images, so that the sub-images acquired by the micro-scanning device are automatically arranged according to the splicing sequence of the images;

the visual field position fitting module is used for finely adjusting the position according to the overlapping area between the sub-images so as to accurately splice the cell positions;

the block extraction module is used for automatically extracting a spliced complete image;

the method comprises the following specific steps:

s1, matching view sub-blocks; the visual field sub-block matching module is used for identifying the overlapping area between the images and judging the adjacent position relationship between the sub-images, so that the sub-images acquired by the micro-scanning device are automatically arranged according to the splicing sequence of the images;

s2, fitting the view field position; the visual field position fitting module is used for finely adjusting the position according to the overlapping area between the sub-images so as to accurately splice the cell positions;

s3, extracting blocks; the block extraction module is used for automatically extracting a spliced complete image;

the operation process of the field sub-block matching in the step S1 is as follows:

sa01, inputting, and initializing a result set M;

sa02, setting the current view i as a first view;

sa03, obtaining all adjacent view sets J of the current view i;

sa04, setting the current adjacent view J as the first view in J;

sa05, calculating possible overlapping areas Ri and Rj of the visual field i and the visual field j;

sa06, rasterizing the template region Ri into a template sub-block set Pi;

sa07, arranging the template sub-block sets Pi in descending order according to the dynamic range of the sub-blocks;

sa08, setting the current template sub-block P as the first one in the template sub-block set Pi;

sa09, finding a possible overlapping area s of the template sub-block P in the view J;

sa10, performing template matching search by taking the template sub-block P as a template and s as a search area;

sa11, adding the best matching M into the result set M;

sa12, finding all matching set visual field sets N consistent with M in the result set M;

sa13, comparing and judging whether the sum of the weights in the N is greater than a threshold value v;

if not, setting the current template sub-block P as the next template sub-block in the template sub-block set Pi, and returning to Sa 09;

if yes, the next step is carried out;

sa14, and comparing and judging whether the view J is the last view in the view set J;

if not, setting the view J as the next view in the view set J, and returning to Sa 05;

if yes, the next step is carried out;

sa15, and comparing and judging, wherein the visual field i is the last visual field;

if not, setting i as the next visual field and returning to Sa 03;

if yes, outputting a result;

the process of the field position fitting in step S2 is:

sa16, inputting, initializing all view positions Xi and Yi;

sa17, setting the current view i as a first view;

sa18, obtaining a matching subset Mi containing the view i in the sub-block matching set M;

sa19, recalculating the positions Xi, Yi of the field of view i according to the matching subset Mi;

sa20, judging that all the visual fields are updated;

if not, setting the view i as the next view;

if yes, the next step is carried out;

sa21, calculating the deviation average value L of the current wheel visual field position and the upper wheel visual field position;

sa22, comparing and judging, wherein the deviation average value L is smaller than a threshold value 1;

if not, returning to Sa 17;

if yes, the next step is carried out;

sa23, visual field position normalization adjustment;

outputting all the visual fields;

the process of block extraction in step S3 is:

sa24, extracting the full graph size W, H;

sa25, dividing the whole image into a set B of blocks according to the block size;

sa26, calculating the positions of all blocks B in the set B;

sa27, setting block B as the first block in set B;

sa28, calculating a set Fb of all views overlapping block b;

sa29, setting the field of view f to be the first field of view in Fb;

sa30, finding the overlapping regions Rb and Rf of the field of view f and the block b;

sa31, copy Rf in image to Rb;

sa32, judging that the view f is the last view in the set Fb;

if not, setting the visual field f as the next visual field in the Fb, and returning to the Sa 29;

if yes, the next step is carried out;

sa33, save block b image;

sa34, judging that the block B is the last block in the set B;

if not, setting the block B as the first block in the set B, and returning to the Sa 28;

and if so, outputting the result.

An image identification method adopting the cell micro-microscopic image acquisition device is realized by the following steps: s1, acquiring a microscopic image;

s2, splicing a plurality of images of a single sample, and extracting the spliced images according to the characteristics of cell nuclei to obtain a single cell nucleus microscopic image;

s3, classifying the single cell nucleus microscopic image by using an artificial intelligence program after model training according to the marked cells;

obtaining classified cell data based on the sample through the steps;

the step of acquiring the microscopic image of the single cell nucleus in the step S2 is as follows:

s100, detecting characteristic points of cell nucleuses;

reducing the image to a plurality of different proportions, and respectively extracting feature points;

s101, primarily screening, namely screening out excessively similar characteristic points according to the characteristic point coordinates, and reducing repeated cell extraction;

s102, subdividing and dividing by using a color difference threshold value;

converting the picture into an LAB format, and performing Otsu threshold segmentation on the weighted sum of the B channel and the A channel after phase inversion to obtain a cell nucleus mask picture;

the weight is 0.7 of the phase reversal of the channel B and 0.3 of the channel A;

s103, performing image morphology operation;

one or more combination of erosion and dilation operations;

s104, screening, namely screening non-cells with the nuclear ratio lower than 0.3, the nuclear radius higher than 150 pixels and the nuclear radius lower than 10 pixels according to the nuclear ratio parameter; the kernel ratio = the kernel area/detection feature point radius circle area subdivided by the color difference threshold.

A method for processing images on the cloud by adopting the cell micro microscopic image acquisition device comprises the following steps:

s1, numbering the slide samples, and determining the sample numbers in the system on the cloud;

s2, registration: inputting the information of the examinee corresponding to the slide into a system, and inputting a sample number;

scanning: scanning the image of the slide by using a camera module;

s3, uploading: uploading the scanned image sample to a cloud system;

s4, splicing and classifying: processing the digitized sample on the cloud AI;

s5, connection: correlating the registration information with the digital sample information in the system;

s6, diagnosis: the doctor diagnoses and rechecks the image sample and submits diagnosis opinions;

s7, report rendering: the rendering program polls the data which is diagnosed in the system and renders the data according to a corresponding report template to obtain files in PDF, JPG and WORD formats;

the cloud processing of the image is realized through the steps.

The cell micro-microscopic image acquisition device provided by the invention can greatly reduce the price of a digital tissue section scanner in the prior art and greatly reduce the medical cost, the volume can be greatly reduced by adopting the structure of the micro lens with the cantilever structure, the carrying and the popularization are convenient, preferably, accessories with high resolution and low price can be obtained under the mass production scale by adopting the accessories of the mobile phone camera, and the main control chip can adopt the mobile phone main control chip without certain baseband function modules and can also reduce the overall cost on the premise of reducing the authorization use cost. The invention also provides an image splicing method of the cell micro-microscopic image acquisition device, which realizes the subarea scanning and combination of the images, improves the image scanning speed, ensures the integrity of the slide sample, also provides an image identification method of the cell micro-microscopic image acquisition device, greatly improves the accuracy and the identification efficiency of cell identification, can also transmit the slide sample obtained by scanning to the cloud end by the method for processing the image on the cloud of the cell micro-microscopic image acquisition device, the image splicing and identification are carried out on the cloud, the remote AI diagnosis and doctor review are realized, the detection efficiency is improved, the requirement of the sample detection on the locality is reduced, the original sample data of the detection can be reserved, and further study of the data enables more remote medical institutions to apply the technique for diagnosis.

Drawings

The invention is further illustrated by the following examples in conjunction with the accompanying drawings:

fig. 1 is a schematic perspective view of the present invention.

Fig. 2 is a schematic partial top view of the present invention.

Fig. 3 is a front sectional structural view of the present invention.

Fig. 4 is a schematic top view of another preferred embodiment of the present invention.

Fig. 5 is a schematic perspective view of another preferred embodiment of the present invention.

Fig. 6 is a schematic structural diagram of a microlens in the present invention.

Fig. 7 is a control diagram of the control box of the present invention.

Fig. 8 is a block diagram of a control structure in the present invention.

FIG. 9 is a schematic view of the picture processing of sub-field sub-block matching after scanning a slide according to the present invention.

FIG. 10 is a schematic diagram of the present invention after splicing of scanned pictures.

FIG. 11 is a flowchart illustrating an image stitching process according to the present invention.

Fig. 12 is a schematic flow chart of view sub-block matching according to the present invention.

FIG. 13 is a schematic view of a process of fitting the position of the field of view according to the present invention.

FIG. 14 is a schematic flow chart of block extraction in the present invention.

Fig. 15 is an exemplary diagram of the present invention after image recognition.

FIG. 16 is a diagram illustrating a process of classifying cells in the present invention.

FIG. 17 is a characteristic morphology map of a single cell nucleus of cytopathology capable of characterizing a user, acquired in the present invention.

FIG. 18 is a schematic diagram of a single cell nucleus microscopic image acquisition process in the present invention.

FIG. 19 is a flowchart of an image recognition method according to the present invention.

FIG. 20 is a flowchart of a method for processing images on a cloud in accordance with the present invention.

In the figure: the microscope camera comprises a camera module 1, a camera 111, a control button 112, a touch screen 113, a module platform 2, a step 21, a positioning pin 22, an adjusting screw 23, a microscope lens 3, a replaceable microscope lens 31, a cantilever rod 32, a support 4, a slide seat 5, a first slide stopper 51, a second slide stopper 52, a Y-axis driving motor 6, a Y-axis screw 61, a Y-axis slide rail 62, a Y-axis nut 63, an X-axis slide block 64, a slide 7, an illumination light source 8, a control box 9, a main control chip 91, a storage chip 92, an interface chip 93, a power supply chip 94, a wireless transmission chip 95, an X-axis driving motor 10, an X-axis screw 101, an X-axis slide rail 102, an X-axis nut 103 and a sliding platform 104.

Detailed Description