CN-121981984-A - Chromosome counting method and device based on image processing and electronic equipment

CN121981984ACN 121981984 ACN121981984 ACN 121981984ACN-121981984-A

Abstract

The application discloses a chromosome counting method, a chromosome counting device and electronic equipment based on image processing, wherein the method comprises the steps that computer equipment acquires a chromosome karyotype diagram; the method comprises the steps of carrying out projection on each row of pixel points of a chromosome nuclear pattern diagram to obtain a first projection vector, determining a plurality of foreground areas of the chromosome nuclear pattern diagram according to the first projection vector, selecting a plurality of first foreground areas from the plurality of foreground areas, extracting target image areas corresponding to the plurality of first foreground areas, carrying out projection on each column of pixel points of the target image areas to obtain a second projection vector, determining one or more chromosome areas contained in the target image areas according to the second projection vector, selecting a target chromosome area comprising a chromosome of a target type from the one or more chromosome areas contained in the target image areas, and obtaining the number of chromosomes corresponding to the chromosome of the target type. The counting accuracy and efficiency of the chromosome karyotype graph can be improved through the method and the device.

Inventors

CHEN ZIYANG
YU TINGSONG
LI SHIMEI
CHEN FAN
CHEN CHONGQI
LI YINGHUA

Assignees

广州金域医学检验中心有限公司
广州金域医学检验集团股份有限公司

Dates

Publication Date: 20260505
Application Date: 20260120

Claims (10)

1. A chromosome counting method based on image processing, the method comprising: The method comprises the steps that a computer device obtains a chromosome karyotype diagram, wherein the chromosome karyotype diagram comprises a plurality of pairs of chromosomes arranged in rows; The computer equipment projects each row of pixel points of the chromosome karyotype diagram according to the length direction of the chromosome karyotype diagram to obtain a first projection vector; the computer device determines a plurality of foreground regions of the chromosome karyotype map according to the first projection vector, each foreground region comprising a plurality of rows of pixel points, and each foreground region comprising one or more pairs of chromosomes, and/or reference symbols corresponding to the one or more pairs of chromosomes; The computer equipment selects a plurality of first foreground areas from the foreground areas and extracts target image areas corresponding to the first foreground areas; The computer equipment projects each column of pixel points of the target image area according to the width direction of the target image area to obtain a second projection vector; The computer equipment determines one or more chromosome areas contained in the target image area according to the second projection vector, wherein each chromosome area comprises one or more pairs of chromosomes and reference symbols corresponding to the chromosomes of each pair; The computer device selecting a target chromosomal region including a chromosome of a target type from one or more chromosomal regions included in the target image region; And the computer equipment identifies the chromosomes contained in the target chromosome region according to the reference symbols contained in the target chromosome region, and obtains the chromosome number corresponding to the target type of chromosome.
2. The method of claim 1, wherein after the computer device acquires a chromosome karyotype map, the method further comprises: The computer equipment carries out binarization processing on each pixel point of the chromosome karyotype graph according to a first pixel threshold value to generate a binarization image corresponding to the chromosome karyotype graph; The computer equipment performs inverting operation on each pixel point in the binary image, and performs normalization processing on each pixel point after inverting to obtain a normalized chromosome nuclear pattern diagram; The computer device projects each row of pixel points of the chromosome karyotype graph according to the length direction of the chromosome karyotype graph to obtain a first projection vector, and the method comprises the following steps: And the computer equipment projects each row of pixel points of the normalized chromosome karyotype graph according to the length direction of the normalized chromosome karyotype graph to obtain a first projection vector.
3. The method of claim 1, wherein the computer device projects each row of pixels of the chromosome karyotype map along a length direction of the chromosome karyotype map to obtain a first projection vector, including: the computer equipment adds up the pixel values corresponding to each row of pixel points of the chromosome karyotype diagram according to the length direction of the chromosome karyotype diagram to obtain the pixel value addition sum corresponding to each row of pixel points; the computer equipment builds the first projection vector according to the accumulated sum of the pixel values corresponding to each row of pixel points, wherein the dimension of the first projection vector is the same as the number of rows of the pixel points contained in the chromosome nuclear type graph; The computer device projects each column of pixel points of the target image area according to the width direction of the target image area to obtain a second projection vector, and the method comprises the following steps: The computer equipment accumulates pixel values corresponding to each column of pixel points of the target image area according to the width direction of the target image area to obtain an accumulated sum of the pixel values corresponding to each column of pixel points; And the computer equipment builds the second projection vector according to the accumulated sum of the pixel values corresponding to each column of pixel points, wherein the dimension of the second projection vector is the same as the column number of the chromosome karyotype graph.
4. The method of claim 3, wherein the computer device determining a plurality of foreground regions of the chromosome karyotype map from the first projection vector comprises: The computer equipment screens out a target pixel value accumulation sum larger than a second pixel threshold value from the first projection vector, and constructs a first index set according to the number of lines corresponding to each target pixel value accumulation sum; The computer equipment performs continuity detection on each row number contained in the first index set, and extracts a plurality of row combinations, wherein each row combination comprises a plurality of continuous row numbers; and the computer equipment determines a foreground area corresponding to each row combination in the chromosome karyotype diagram according to the maximum row number and the minimum row number contained in each row combination.
5. The method of claim 4, wherein the chromosome of the target type comprises a sex chromosome; The computer device selects a plurality of first foreground regions from the plurality of foreground regions, and extracts target image regions corresponding to the plurality of first foreground regions, including: the computer equipment acquires a line combination range corresponding to the sex chromosome, wherein the line combinations are sequentially arranged according to the sequence from small to large or from large to small of the minimum line number of each line combination, and the line combination range comprises a plurality of line combination serial numbers; The computer equipment determines a plurality of first foreground areas of the corresponding row combination belonging to the row combination range according to a plurality of row combination serial numbers included in the row combination range; The computer device extracts a target image region between a minimum number of lines and a maximum number of lines in the plurality of first foreground regions from the chromosome karyotype map.
6. The method according to claim 1, wherein the computer device identifies the chromosome included in the target chromosome region according to the reference symbol included in the target chromosome region, and obtains the number of chromosomes corresponding to the chromosome of the target type, including: the computer equipment determines a subarea corresponding to the chromosome of the target type according to the reference symbols contained in the target chromosome region; The computer equipment carries out contour detection on the subareas to obtain a plurality of first contours; The computer equipment performs morphological image processing on the first contours to obtain second contours; the computer equipment determines center points corresponding to the second profiles respectively, and calculates and obtains the distance between the center points of any two second profiles in the second profiles; The computer equipment calculates and obtains the minimum distance between any two second contours in the plurality of second contours in the width direction; If the minimum distance between the two target second contours in the width direction is smaller than a first distance threshold value and the distance between the center points of the two target second contours is smaller than a second distance threshold value, the computer equipment communicates the two target second contours; and the computer equipment determines the chromosome number corresponding to the chromosome of the target type according to the communicated contour number.
7. The method of claim 6, wherein the chromosome of the target type comprises a sex chromosome, wherein the computer device determining a sub-region corresponding to the chromosome of the target type based on reference symbols contained in the region of the target chromosome comprises: the computer device identifying a symbol type corresponding to a reference symbol contained in the target chromosome region; the computer equipment determines a target equipment type corresponding to the chromosome karyotype graph according to the symbol type; And the computer equipment cuts the target chromosome region corresponding to the sex chromosome according to the template corresponding to the target equipment type to obtain a first subregion corresponding to the X chromosome and a second subregion corresponding to the Y chromosome.
8. A chromosome counting device based on image processing, the device comprising: The image acquisition module is used for acquiring a chromosome karyotype diagram, wherein the chromosome karyotype diagram comprises a plurality of pairs of chromosomes arranged in rows; the projection module is used for projecting each row of pixel points of the chromosome karyotype diagram according to the length direction of the chromosome karyotype diagram to obtain a first projection vector; The region dividing module is used for determining a plurality of foreground regions of the chromosome karyotype map according to the first projection vector, wherein each foreground region comprises a plurality of rows of pixel points, and each foreground region comprises one or more pairs of chromosomes and/or reference symbols corresponding to the one or more pairs of chromosomes; The region merging module is used for selecting a plurality of first foreground regions from the plurality of foreground regions and extracting target image regions corresponding to the plurality of first foreground regions; the projection module is further used for projecting each column of pixel points of the target image area according to the width direction of the target image area to obtain a second projection vector; the region dividing module is further configured to determine one or more chromosome regions included in the target image region according to the second projection vector, where each chromosome region includes one or more pairs of chromosomes and reference symbols corresponding to each pair of chromosomes; a region determining module, configured to select a target chromosome region including a chromosome of a target type from one or more chromosome regions included in the target image region; And the statistics module is used for identifying the chromosomes contained in the target chromosome region according to the reference symbols contained in the target chromosome region to obtain the chromosome number corresponding to the target type of chromosome.
9. An electronic device comprising a memory and a processor, wherein the memory stores a computer program that, when executed by the processor, causes the processor to implement the method of any of claims 1-7.
10. A computer program product comprising a computer program which, when executed by a processor, causes the processor to carry out the method according to any one of claims 1 to 7.

Description

Chromosome counting method and device based on image processing and electronic equipment Technical Field The present application relates to the field of image processing technologies, and in particular, to a chromosome counting method and apparatus based on image processing, and an electronic device. Background The chromosome karyotype analysis is a core technology for prenatal screening and diagnosis of genetic diseases (such as Tener syndrome and Kjeldahl syndrome), one of the core links is to count one or more pairs of chromosomes of a chromosome karyotype map, and whether a user has genetic lesions with abnormal chromosome numbers is assisted by the chromosome number of a target chromosome. However, in the high-throughput clinical detection scenario, the clinical detection mechanism needs to process a large number of chromosome karyograms of samples every day, and the analysis accuracy and the processing efficiency of the chromosome karyograms are seriously affected due to the fact that the analysis is time-consuming and labor-consuming by relying on manual reading one by one. Disclosure of Invention The embodiment of the application discloses a chromosome counting method and device based on image processing and electronic equipment, which can improve the counting accuracy and efficiency of a chromosome karyotype map. A first aspect of an embodiment of the present application discloses a chromosome counting method based on image processing, the method comprising: The method comprises the steps that a computer device obtains a chromosome karyotype diagram, wherein the chromosome karyotype diagram comprises a plurality of pairs of chromosomes arranged in rows; The computer equipment projects each row of pixel points of the chromosome karyotype diagram according to the length direction of the chromosome karyotype diagram to obtain a first projection vector; the computer device determines a plurality of foreground regions of the chromosome karyotype map according to the first projection vector, each foreground region comprising a plurality of rows of pixel points, and each foreground region comprising one or more pairs of chromosomes, and/or reference symbols corresponding to the one or more pairs of chromosomes; The computer equipment selects a plurality of first foreground areas from the foreground areas and extracts target image areas corresponding to the first foreground areas; The computer equipment projects each column of pixel points of the target image area according to the width direction of the target image area to obtain a second projection vector; The computer equipment determines one or more chromosome areas contained in the target image area according to the second projection vector, wherein each chromosome area comprises one or more pairs of chromosomes and reference symbols corresponding to the chromosomes of each pair; The computer device selecting a target chromosomal region including a chromosome of a target type from one or more chromosomal regions included in the target image region; And the computer equipment identifies the chromosomes contained in the target chromosome region according to the reference symbols contained in the target chromosome region, and obtains the chromosome number corresponding to the target type of chromosome. In some possible embodiments, after the computer device acquires a chromosome karyotype map, the method further comprises: The computer equipment carries out binarization processing on each pixel point of the chromosome karyotype graph according to a first pixel threshold value to generate a binarization image corresponding to the chromosome karyotype graph; The computer equipment performs inverting operation on each pixel point in the binary image, and performs normalization processing on each pixel point after inverting to obtain a normalized chromosome nuclear pattern diagram; The computer device projects each row of pixel points of the chromosome karyotype graph according to the length direction of the chromosome karyotype graph to obtain a first projection vector, and the method comprises the following steps: And the computer equipment projects each row of pixel points of the normalized chromosome karyotype graph according to the length direction of the normalized chromosome karyotype graph to obtain a first projection vector. In some possible embodiments, the computer device projects each row of pixels of the chromosome karyotype map according to a length direction of the chromosome karyotype map to obtain a first projection vector, including: the computer equipment adds up the pixel values corresponding to each row of pixel points of the chromosome karyotype diagram according to the length direction of the chromosome karyotype diagram to obtain the pixel value addition sum corresponding to each row of pixel points; the computer equipment builds the first projection vector according to the accumulated sum of the pixel values corresponding to each row