CN110610497A - Live pig carcass tissue content determination method based on CT image processing - Google Patents
Live pig carcass tissue content determination method based on CT image processing Download PDFInfo
- Publication number
- CN110610497A CN110610497A CN201910717613.XA CN201910717613A CN110610497A CN 110610497 A CN110610497 A CN 110610497A CN 201910717613 A CN201910717613 A CN 201910717613A CN 110610497 A CN110610497 A CN 110610497A
- Authority
- CN
- China
- Prior art keywords
- image
- muscle
- bone
- fat
- threshold
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 51
- 238000012545 processing Methods 0.000 title claims abstract description 26
- 210000003205 muscle Anatomy 0.000 claims abstract description 52
- 210000000988 bone and bone Anatomy 0.000 claims abstract description 49
- 210000001835 viscera Anatomy 0.000 claims abstract description 47
- 230000011218 segmentation Effects 0.000 claims abstract description 43
- 210000001519 tissue Anatomy 0.000 claims abstract description 39
- 230000009278 visceral effect Effects 0.000 claims abstract description 19
- 230000007797 corrosion Effects 0.000 claims description 21
- 238000005260 corrosion Methods 0.000 claims description 21
- 238000010586 diagram Methods 0.000 claims description 12
- 210000000577 adipose tissue Anatomy 0.000 claims description 8
- 101100269850 Caenorhabditis elegans mask-1 gene Proteins 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000001914 filtration Methods 0.000 claims description 4
- 238000003709 image segmentation Methods 0.000 claims description 4
- 101150041326 air-2 gene Proteins 0.000 claims description 3
- 150000001875 compounds Chemical class 0.000 claims description 3
- 230000010339 dilation Effects 0.000 claims description 3
- 210000002615 epidermis Anatomy 0.000 claims description 3
- 238000009499 grossing Methods 0.000 claims description 3
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000007781 pre-processing Methods 0.000 claims description 3
- 230000008961 swelling Effects 0.000 claims 1
- 238000004364 calculation method Methods 0.000 abstract description 2
- 238000002591 computed tomography Methods 0.000 description 100
- 210000000579 abdominal fat Anatomy 0.000 description 9
- 238000005516 engineering process Methods 0.000 description 7
- 238000009395 breeding Methods 0.000 description 5
- 230000001488 breeding effect Effects 0.000 description 5
- 238000005530 etching Methods 0.000 description 5
- 238000003307 slaughter Methods 0.000 description 5
- 241000282887 Suidae Species 0.000 description 4
- 210000001185 bone marrow Anatomy 0.000 description 4
- 210000003141 lower extremity Anatomy 0.000 description 4
- 210000001015 abdomen Anatomy 0.000 description 3
- 210000004204 blood vessel Anatomy 0.000 description 3
- 230000000694 effects Effects 0.000 description 3
- 244000144977 poultry Species 0.000 description 3
- 241001465754 Metazoa Species 0.000 description 2
- 210000000079 cloven hoof Anatomy 0.000 description 2
- 210000000003 hoof Anatomy 0.000 description 2
- 239000000463 material Substances 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 210000000056 organ Anatomy 0.000 description 2
- 238000004445 quantitative analysis Methods 0.000 description 2
- 238000011160 research Methods 0.000 description 2
- 241000287828 Gallus gallus Species 0.000 description 1
- 241001493546 Suina Species 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000013170 computed tomography imaging Methods 0.000 description 1
- 238000005520 cutting process Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 231100001261 hazardous Toxicity 0.000 description 1
- 238000003384 imaging method Methods 0.000 description 1
- 238000000338 in vitro Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 230000004083 survival effect Effects 0.000 description 1
Classifications
-
- G06T5/70—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/11—Region-based segmentation
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/136—Segmentation; Edge detection involving thresholding
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T7/00—Image analysis
- G06T7/10—Segmentation; Edge detection
- G06T7/155—Segmentation; Edge detection involving morphological operators
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T2207/00—Indexing scheme for image analysis or image enhancement
- G06T2207/10—Image acquisition modality
- G06T2207/10072—Tomographic images
- G06T2207/10081—Computed x-ray tomography [CT]
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P60/00—Technologies relating to agriculture, livestock or agroalimentary industries
- Y02P60/80—Food processing, e.g. use of renewable energies or variable speed drives in handling, conveying or stacking
- Y02P60/87—Re-use of by-products of food processing for fodder production
Abstract
The invention discloses a live pig carcass tissue content measuring method based on CT image processing; belongs to the technical field of image processing. The invention comprises 6 steps: 1. acquiring a CT image, and carrying out denoising processing on the CT image; 2. dividing and removing a bed plate part in the CT image; 3. extracting a skeleton part region of a CT image main body, and calculating the mass and the proportion of the skeleton part region; 4. extracting a main fat part region of the CT image, and calculating the mass and the proportion of the main fat part region; 5. extracting and removing internal organs of a CT image subject; 6. extracting the muscle part area of the CT image main body, and calculating the mass and the proportion of the muscle part area. The method is based on the characteristics on the CT image, adopts targeted image region segmentation and correlation calculation, can accurately and quickly remove all visceral tissues of the pig carcass at one time, accurately segments and determines the weight and the proportion of bones, muscles and fat tissues of the pig carcass.
Description
Technical Field
The invention belongs to the technical field of image processing, particularly relates to a CT image segmentation and determination algorithm, and particularly relates to a live pig carcass tissue content determination method based on CT image processing.
Background
Computed Tomography (CT) is a product of combining computer and X-ray examination technology, and its principle is that the density of reactive substances is dependent on the degree of absorption of X-rays by various tissues of human body, and it belongs to one of the non-hazardous methods for organ in vitro imaging. CT was first applied in medical clinics with some success. With the development of computer technology and material level, the application field of CT has been greatly expanded. In the aspect of agricultural production, the determination of the content of each tissue by applying the combination of CT and computer technology to living bodies becomes an important research direction in the current field.
Various researches at home and abroad show that the breeding capability of the cloven-hooves is closely related to the aspects of bone, fat, muscle content and the like. Therefore, the measurement of the skeletal, fat and muscle content of cloven hooves is of great interest to breeding experts and producers. The traditional determination method requires that bones, fat, muscles and the like are separated from living bodies by manual cutting after the living bodies are slaughtered, a certain amount of financial resources, material resources and manpower are required to be invested, and because the determination result is not suitable for the whole population after slaughter, the determination method cannot judge whether the breeding capacity of the living bodies is related to the determination result.
The CT technology can be used for clinically scanning the cloven-hoof in a survival state to construct a complete internal three-dimensional model. And then the content of the tissue is measured by combining with a computer image processing technology. However, the existing method for measuring the content of the tissues of the cloven-hoof type based on CT image processing still has certain defects. If the placement position and shape of the living body are uncertain, the number of slices and image shapes of the generated CT image are different, and the measurement result has a certain deviation, so that the selection of the CT image is usually operated by a professional, and the threshold for measuring the tissue content by using the CT image is high.
Through retrieval, application publication No. CN109009228A, the name of the invention creation is: a method for measuring the fat content of poultry abdomen by adopting an ultrasonic technology; the application discloses a poultry abdomen fat content measuring method, which utilizes an ultrasonic instrument to measure an abdomen measuring area and collect image data, analyzes the image data, establishes a regression equation according to the abdominal fat weight measured by slaughter and the abdominal fat thickness value data measured by ultrasonic, calculates the abdominal fat weight of chicken, reduces the measuring cost of the abdominal fat content, and meets the practical requirements of poultry breeding. However, in this application, regression equations of the half abdominal fat weight and the total abdominal fat weight are established only based on data of abdominal fat weight measured at slaughter and abdominal fat thickness data measured at ultrasonic waves, and the abdominal fat weight of an unbaked individual among individuals is obtained.
Application publication No. CN 104484874a, entitled "new product: according to the application, after CT imaging of a lower limb area of a small living animal is obtained, bones of the lower limb area are removed, sparse weighting and multi-scale linear filtering are carried out, and Coarse to Fine blood vessel segmentation is carried out after normalization processing. The application can provide technical support for the image quantitative analysis of the blood vessels of the lower limbs of the living animals, but the image quantitative analysis of the blood vessels of the lower limbs has particularity of itself, so the scheme is not suitable for measuring the content of the tissues of the artiodactyl.
Disclosure of Invention
1. Technical problem to be solved by the invention
Aiming at the problems of larger deviation of a measuring result, higher measuring threshold and the like in the process of segmenting and measuring the tissues of the hooves by utilizing the CT image in the prior art, the invention provides a live pig carcass tissue content measuring method based on CT image processing; the method can accurately measure the bone, fat and muscle tissue contents of the pig in the CT image.
2. Technical scheme
In order to achieve the purpose, the invention adopts the following technical scheme to solve the problem:
the invention relates to a live pig carcass tissue content measuring method based on CT image processing, which comprises the following steps:
(1) acquiring a CT scanned image of a live pig, and performing Gaussian convolution smoothing denoising pretreatment on the CT scanned image;
(2) removing the bed plate in the preprocessed CT image by adopting a region growing method, and extracting the pig carcass;
(3) extracting skeletal tissues in the pig carcass by utilizing threshold segmentation, and calculating the weight of the skeletal tissues;
(4) segmenting the visceral tissues in the pig carcass in the CT image by combining morphological operations in image segmentation;
(5) extracting adipose tissues in the pig carcass by adopting a threshold segmentation method, and calculating the weight of the adipose tissues;
(6) extracting muscle tissues in the pig carcass by adopting a threshold segmentation method, and calculating the weight of the muscle tissues;
(7) and calculating the total weight of the boar and the proportion of bone, fat and muscle tissues.
Further, the step (1) specifically includes the following steps:
(11) extracting CT image information, obtaining two-dimensional slices of a pig CT image, and overlapping the two-dimensional slices in sequence to generate a three-dimensional matrix f (x, y, z);
(12) preprocessing the acquired CT image, and denoising the image by Gaussian filtering, wherein Gaussian convolution denoising is as follows:
g(x,y,z)＝f*Gσ
in the formula (I), the compound is shown in the specification,denotes convolution, σ is standard deviation; in the denoising process, useGaussian kernel of order 3:the CT image is convolved.
Further, the step (2) specifically includes the following steps:
(21) binarizing the preprocessed image, setting threshold values T1 and T2, setting the CT values of all voxels in the threshold value range as 1, and setting the CT values of the rest voxels as 0 to obtain a binary image:
(22) filling holes in the binary image, determining an initial seed point in bw, filling a background by using a morphological dilation algorithm and adopting a four-connected structural element as a starting point, then performing 'not' operation on the obtained binary image to obtain a new binary image bw1, and performing 'AND' operation on bw1 and bw to obtain a hole-filled binary image bw _ bed _ scanner;
(23) removing the CT bed body by adopting a region growing method, setting a pixel point at the central position of the binary image bw _ bed _ scanner as a growing point, and setting a growing rule as searching a point which is the same as the threshold value of the growing point in a connected domain; then traversing the whole image, if the growth rule is met, adding the main part of the image, otherwise, the main part is the CT bed body part; finally, removing the bed body part to obtain a binary image nobed _ mask of the image main body part;
(24) and (5) carrying out AND operation on the binary image nobed _ mask and the original image f to obtain the original image bw _ nobed without the CT bed body.
Further, the step (3) specifically includes the following steps:
(31) performing threshold segmentation on the original image bw _ nobed without the CT bed body, setting a threshold B _ T, setting the CT values of all voxels larger than the threshold to be 1, and setting the CT values of all voxels smaller than the threshold to be 0; the binary image obtained after threshold segmentation is bw _ bone:
(32) filling holes in the image bw _ bone after threshold segmentation to obtain a filled binary image bw _ bone 1;
(33) traversing the filled image bw _ bone1, counting the number num _ bone of voxels with a value of 1, and calculating the weight w of the boneboneThe formula is as follows:
wbone＝num_bone×PixelSpacing×SliceThickness×ρbone
where PixelSpacing is the pixel size of CT, SliceThickness is the slice thickness, ρboneIs the density of the bone.
Further, the step (4) specifically includes the following steps:
(41) performing threshold segmentation on the original image bw _ nobed without the CT bed body, setting a threshold O _ T, setting the CT values of all voxels smaller than the threshold to be 1, setting the CT values of all voxels larger than the threshold to be 0, and obtaining a binary image bw _ air after threshold segmentation:
(42) carrying out corrosion operation on the binary image bw _ air, and removing the epidermis part to avoid influencing the viscera segmentation; performing expansion operation again to restore the image to the original size, and obtaining a binary image bw _ air 1;
and (3) corrosion:
expansion:
s represents an image set after corrosion or expansion, B represents a structural element for corrosion, A represents an original binary image set,indicating corrosion operationIn order to do so,indicating an expansion operation;
(43) filling holes in the obtained binary image bw _ air1 to obtain a complete air binary image bw _ air 2;
(44) performing corrosion operation on the binary image nobed _ mask of the main body part obtained in the step (23), selecting the size of a corrosion structural element so that the size of the corroded main body is approximately the same as the size of the viscera, and obtaining an viscera mask image after corrosion as Internal _ organs _ mask;
(45) selecting structural elements from the binary image bw _ bone1 of the bone obtained in the step (32) for expansion, and performing 'not' operation after the expansion, namely, inverting the binary image bw _ bone1 to obtain a new bone mask image bw _ bone 2;
(46) performing logical AND operation on the visceral mask map Internal _ organiss _ mask and the bone mask map bw _ bone2 obtained in the step (44) and the step (45); selecting structural elements for expansion operation after operation to obtain a new visceral mask image Internal _ organs _ mask 1;
(47) performing logical OR operation on the air binary diagram bw _ air2 obtained in the step (43) and the visceral mask diagram Internal _ organs _ mask1 obtained in the step (46) to obtain a final visceral mask diagram Internal _ organs _ mask 2;
(48) and (3) firstly carrying out 'NOT' operation on the final Internal organ mask image Internal _ organs _ mask2, and then carrying out 'AND' operation on the final Internal organ mask image and the original image bw _ nobed of the removed CT bed body to obtain the original image bw _ nobed _ nogut of the removed Internal organs and the CT bed body.
Further, the step (5) specifically includes the following steps:
(51) performing threshold segmentation on the original image bw _ nobed _ nogut without internal organs and the CT bed body, setting thresholds F _ T1 and F _ T2, setting the CT values of all voxels within the threshold range to be 1, setting the CT values of all voxels smaller than F _ T1 or larger than F _ T2 to be 0, and obtaining a binary image bw _ fat after threshold segmentation:
(52) traversing the filled image bw _ fat, counting the number num _ fat of voxels with the value of 1, and calculating the weight w of the fatfatThe formula is as follows:
wfat＝num_fat×PixelSpacing×SliceThickness×ρfat
where PixelSpacing is the pixel size of CT, SliceThickness is the slice thickness, ρfatIs the density of the fat.
Further, the step (6) specifically includes the following steps:
(61) performing threshold segmentation on the original image bw _ nobed _ nogut without internal organs and the CT bed, setting thresholds M _ T1 and M _ T2, setting the CT values of all voxels within the threshold range to be 1, setting the CT values of all voxels smaller than M _ T1 or larger than M _ T2 to be 0, and obtaining a muscle binary image bw _ muscle after threshold segmentation:
(62) after the binary image bw _ bone1 of the bone obtained in the step (32) is subjected to 'not' operation, and then the binary image bw _ muscle is subjected to 'and' operation with the binary image bw _ muscle to obtain a binary image bw _ muscle1 of the real muscle after the bone and the viscera are removed;
(63) traversing the filled image bw _ muscle1, calculating the number num _ muscle of voxels with a statistical value of 1, and calculating the weight w of the musclemuscleThe formula is as follows:
wmuscle＝num_muscle×PixelSpacing×SliceThickness×ρmuscle
where PixelSpacing is the pixel size of CT, SliceThickness is the slice thickness, ρmuscleIs the density of the muscle.
Further, the step (7) specifically includes the steps of:
(71) calculating the weight w of the bone obtained in the step (33)boneCalculating the weight w of the fat obtained in step (52)fatAnd the muscle weight w calculated in the step (63)muscleAdding to obtain the total weight W:
W＝wbone+wfat+wmuscle
(72) the proportion of the skeleton isThe ratio of fat isThe muscle proportion is3. Advantageous effects
Compared with the prior art, the technical scheme provided by the invention has the following remarkable effects:
(1) according to the live pig carcass tissue content measuring method based on CT image processing, live pigs are subjected to CT scanning, and the contents of bones, muscles and fat tissues of the pigs can be accurately and quickly segmented and measured based on CT slicing without slaughtering, so that the aim of judging the breeding capacity of the live pigs by a method can be fulfilled.
(2) According to the method for measuring the tissue content of the live pig carcass based on CT image processing, a regional growth method is adopted, a growth rule is set to search for a point in a connected domain of a growth point, wherein the point is the same as the threshold value of the point, and a CT bed can be quickly and accurately separated, so that the pig carcass can be quickly and accurately segmented.
(3) The living pig carcass tissue content measuring method based on CT image processing uses a digital image processing technology, based on the characteristics on a CT image, adopts targeted image region segmentation and correlation calculation, and can segment all internal organs of a pig body at one time, thereby eliminating the influence of the internal organs on the measuring precision of fat and muscle tissue content, and precisely segmenting and measuring the weight and the proportion of bones, muscles and fat tissues of the pig body.
Drawings
FIG. 1 is a flow chart of the determination of living pig carcass tissue content based on CT image processing.
Fig. 2 is a three-dimensional display diagram of a CT image according to embodiment 1 of the present invention.
Fig. 3 (a) - (c) are three views of the cross section, sagittal plane and coronal plane of the CT image according to example 1 of the present invention.
FIG. 4 is a pre-removal and post-removal image of a CT image bed according to embodiment 1 of the present invention; wherein, fig. 4 (a) is a CT bed pre-removal image; fig. 4 (b) is an image with the CT bed removed.
FIG. 5 is a binary image and a hole-filled image of the CT image skeleton segment according to embodiment 1 of the present invention; wherein, fig. 5(a) is an image obtained after threshold segmentation; fig. 5(b) shows an image obtained after hole filling.
FIG. 6 is an original image, a mask image and a post-removal image of a CT image with an organ removed according to embodiment 1 of the present invention; wherein (a) in fig. 6 is an original image; fig. 6(b) is a mask diagram of the extracted internal organ portion; fig. 6(c) shows an image with the internal organs removed.
FIG. 7 is a diagram showing the results of fat extraction from a CT image according to embodiment 1 of the present invention.
FIG. 8 is a graph of intermediate and final results of the muscle section evisceration and bone marrow of a CT image according to example 1 of the present invention; wherein (a) in fig. 8 is a muscle image including viscera and bone marrow; fig. 8(b) is an image with internal organs and bone marrow removed.
Detailed Description
To further explain the effects of the present invention, the following detailed description will be given with reference to the accompanying drawings.
Example 1
As shown in fig. 1, the method for measuring the carcass tissue content of a live pig based on CT image processing of the present embodiment includes the following steps:
(1) acquiring a CT scanning image, and performing Gaussian convolution smoothing denoising pretreatment on the CT scanning image; the method specifically comprises the following steps:
(11) extracting CT image information, obtaining two-dimensional slices of a pig CT image, and sequentially overlapping the two-dimensional slices to generate a three-dimensional matrix f (x, y, z), wherein the three-dimensional display of the CT image is shown in figure 2, and the three views of the cross section, the sagittal plane and the coronal plane of the CT image are shown in figure 3;
(12) preprocessing the acquired CT image, and denoising the image by Gaussian filtering, wherein Gaussian convolution denoising is as follows:
g(x,y,z)＝f*Gσ
in the formula (I), the compound is shown in the specification,expressing convolution, taking 0.8 as sigma as standard deviation, and taking (x, y and z) as coordinate points in the image; in the denoising process, a 3-order Gaussian kernel is adopted:the CT image is convolved.
(2) Removing a bed plate in the preprocessed CT image by adopting a three-dimensional region growing method, and extracting the pig carcass; the method specifically comprises the following steps:
(21) the preprocessed image is binarized, and a threshold value T1-800 HU and T2-1500 HU are set, wherein the threshold value range can contain all pixels of the live pig carcass part in the image. The CT values of all voxels within the threshold range are set to 1, and the CT values of all the remaining voxels are set to 0, so as to obtain a binary image bw:
(22) filling holes in the binary image: determining an initial seed point in bw, filling a background by using a four-connected structural element by using a morphological dilation algorithm with the seed point as a starting point, then performing 'not' operation on the obtained binary image to obtain a new binary image bw1, and performing 'and' operation on bw1 and bw to obtain a hole-filled binary image bw _ bed _ scanner;
(23) removing the CT bed body by adopting a region growing method: first, a pixel point at the center of the binary image bw _ bed _ torrer is set as a growth point. Secondly, setting a growth rule to search for points in the connected domain of the growth points, wherein the points are the same as the threshold value of the connected domain of the growth points. And traversing the whole image, if the growth rule is met, adding the main body part of the image, otherwise, the CT bed body part. Finally, removing the bed body part to obtain a binary image nobed _ mask of the image main body part;
(24) and (3) performing AND operation on the binary image nobed _ mask and the original image f to obtain the original image bw _ nobed after the CT bed body is removed, wherein the images before and after the CT bed body is removed are shown in FIG. 4.
(3) Extracting skeletal tissues in the pig carcass by utilizing threshold segmentation, and calculating the weight of the skeletal tissues; the method specifically comprises the following steps:
(31) the original image bw _ nobed from which the CT bed body is removed is subjected to threshold segmentation, a threshold B _ T is set to 200HU, CT values of all voxels greater than the threshold are set to 1, and CT values of all voxels smaller than the threshold are set to 0. Wherein, the voxels larger than the set threshold are skeleton parts, the voxels smaller than the set threshold are background parts, and the binary image obtained after threshold segmentation is bwboneAs shown in fig. 5 (a):
(32) filling holes in the image bw _ bone after threshold segmentation, and filling the bone marrow part in the bone to obtain a filled binary image bw _ bone1, as shown in fig. 5 (b);
(33) traversing the filled image bw _ bone1, counting the number num _ bone of voxels with a value of 1, and calculating the weight w of the boneboneThe formula is as follows:
wbone＝num_bone×PixelSpacing×SliceThickness×ρbone
in the formula, PixelSpacing is the pixel size value of CT, and is 0.977 x 0.977mm2(ii) a SliceThickness is the slice thickness value, which is 4.999 mm; rhoboneThe density value of the bone is 1.4g/cm3(ii) a From this the weight of the bone can be calculated.
(4) Segmenting the visceral tissues in the pig carcass in the CT image by combining morphological operations in image segmentation; the method specifically comprises the following steps:
(41) the original image bw _ nobed without the CT bed body is subjected to threshold segmentation, a threshold O _ T is set to-200 HU, CT values of all voxels smaller than the threshold are set to 1, and CT values of all voxels larger than the threshold are set to 0. Wherein, the voxels larger than the set threshold are background parts, the voxels smaller than the set threshold are air parts, and the binary image obtained after threshold segmentation is bw _ air:
(42) and carrying out corrosion operation on the binary image bw _ air, and removing the epidermis part to avoid influencing the viscera segmentation. Performing expansion operation again to restore the image to the original size, and obtaining a binary image bw _ air 1;
and (3) corrosion:
expansion:
s represents an image set after corrosion or expansion, B represents a structural element for corrosion, A represents an original binary image set,it is shown that the etching operation is performed,the expansion operation is shown, and all structural elements adopted by corrosion expansion in the embodiment are rectangles with the number of 3 x 3;
(43) filling holes in the obtained binary image bw _ air1 to obtain a complete air binary image bw _ air 2;
(44) performing etching operation on the binary image nobed _ mask of the main body part obtained in the step (23), and selecting proper size of etching structural elements so that the size of the main body after etching is approximately the same as the size of the viscera, wherein the viscera mask image obtained after etching is Internal _ organs _ mask;
(45) selecting proper sizes of structural elements from the binary image bw _ bone1 of the bone obtained in the step (32) for expansion, and performing 'not' operation after expansion, namely, inverting the binary image bw _ bone1 of the bone to obtain a new bone mask image bw _ bone 2;
(46) and logically AND-ing the visceral mask map Internal _ organs _ mask and the bone mask map bw _ bone2 obtained in the steps (44) and (45). Selecting a proper structural element for expansion operation after operation to obtain a new visceral mask image Internal _ organs _ mask 1;
(47) performing logical or operation on the air binary diagram bw _ air2 obtained in the step (43) and the visceral mask diagram Internal _ organs _ mask1 obtained in the step (46) to obtain a final visceral mask diagram Internal _ organs _ mask2, as shown in fig. 6 (b);
(48) the final Internal organ mask image Internal _ organs _ mask2 is first subjected to the "not" operation of itself, and then subjected to the "and" operation with the original image bw _ nobed of the removed CT bed, so as to obtain the original image bw _ nobed _ nogut of the removed Internal organs and CT bed, as shown in fig. 6 (c).
(5) Extracting adipose tissues in the pig carcass by adopting a threshold segmentation method, and calculating the weight of the adipose tissues; the method specifically comprises the following steps:
(51) the original image bw _ nobed _ nogut from the visceral and CT bed is threshold-segmented, and set the threshold F _ T1 to-200 HU, and F _ T to 0HU, sets the CT values of all voxels within the threshold range to 1, and sets the CT values of all voxels smaller than F _ T1 or larger than F _ T2 to 0. The voxels within the threshold range are fat portions, the voxels outside the threshold range are background portions, and the binary image obtained after the threshold segmentation is bw _ fat, as shown in fig. 7:
(52) traversing the filled image bw _ fat, counting the number num _ fat of voxels with the value of 1, and calculating the weight w of the fatfatThe formula is as follows:
wfat＝num_fat×PixelSpacing×SliceThickness×ρfat
in the formula, PixelSpacing is the pixel size value of CT,is 0.977 x 0.977mm2(ii) a SliceThickness is the slice thickness value, which is 4.999 mm; rhofatThe density value of fat is 0.92g/cm3(ii) a From this the weight of fat can be calculated.
(6) Extracting muscle tissues in the pig carcass by adopting a threshold segmentation method, and calculating the weight of the muscle tissues; the method specifically comprises the following steps:
(61) the original image bw _ nobed _ nogut from the visceral and CT bed is subjected to threshold segmentation, and set the threshold M _ T1 to 0HU, and M _ T2 to 200HU to set the CT values of all voxels within the threshold range to 1, and the CT values of all voxels smaller than M _ T1 or larger than M _ T2 to 0. Wherein, the voxels within the threshold range are muscle parts, the voxels outside the threshold range are background parts, and the muscle binary image obtained after the threshold segmentation is bw _ muscle, as shown in fig. 8 (a):
(62) after the binary image bw _ bone1 of the bone obtained in the step (32) is subjected to the "not" operation, the "and" operation is performed on the binary image bw _ muscle of the muscle. Obtaining a binary map bw _ muscle1 of the real muscle after removing the bone and the internal organs, as shown in fig. 8 (b);
(63) traversing the filled image bw _ muscle1, calculating the number num _ muscle of voxels with a statistical value of 1, and calculating the weight w of the musclemuscleThe formula is as follows:
wmuscle＝num_muscle×PixelSpacing×SliceThickness×ρmuscle
in the formula, PixelSpacing is the pixel size value of CT, and is 0.977 x 0.977mm2(ii) a SliceThickness is the slice thickness value, which is 4.999 mm; rhomuscleThe density value of the muscle is 1.06g/cm3(ii) a From which the weight of the muscle can be calculated.
(7) Calculating the total weight of the boar and the proportion of bones, fat and muscle tissues; the method specifically comprises the following steps:
(71) calculating the weight w of the bone obtained in the step (33)boneThe weight of the fat calculated in the step (52) aboveQuantity wfatAnd the muscle weight w calculated in the step (63) abovemuscleAdding to obtain the total weight W:
W＝wbone+wfat+wmuscle
(72) the proportion of the skeleton isThe ratio of fat isThe muscle proportion is
According to the embodiment, the live pigs are subjected to CT scanning, and the content of bones, muscles and adipose tissues of the pig bodies can be accurately and rapidly segmented and measured on the basis of CT slices without slaughtering. Can realize one-time accurate and rapid removal of all visceral tissues of the pig carcass, and accurate segmentation and determination of the weight and the ratio of bones, muscles and adipose tissues of the pig carcass.
Claims (8)
1. A live pig carcass tissue content measuring method based on CT image processing is characterized by comprising the following steps:
(1) acquiring a CT scanned image of a live pig, and performing Gaussian convolution smoothing denoising pretreatment on the CT scanned image;
(2) removing the bed plate in the preprocessed CT image by adopting a region growing method, and extracting the pig carcass;
(3) extracting skeletal tissues in the pig carcass by utilizing threshold segmentation, and calculating the weight of the skeletal tissues;
(4) segmenting the visceral tissues in the pig carcass in the CT image by combining morphological operations in image segmentation;
(5) extracting adipose tissues in the pig carcass by adopting a threshold segmentation method, and calculating the weight of the adipose tissues;
(6) extracting muscle tissues in the pig carcass by adopting a threshold segmentation method, and calculating the weight of the muscle tissues;
(7) and calculating the total weight of the boar and the proportion of bone, fat and muscle tissues.
2. The method for measuring the carcass tissue content of the live pig based on the CT image processing as claimed in claim 1, wherein the step (1) comprises the following steps:
(11) extracting CT image information, obtaining two-dimensional slices of a pig CT image, and overlapping the two-dimensional slices in sequence to generate a three-dimensional matrix f (x, y, z);
(12) preprocessing the acquired CT image, and denoising the image by Gaussian filtering, wherein Gaussian convolution denoising is as follows:
g(x,y,z)＝f*Gσ
in the formula (I), the compound is shown in the specification,denotes convolution, σ is standard deviation; in the denoising process, a 3-order Gaussian kernel is adopted:the CT image is convolved.
3. The method for measuring the carcass tissue content of the live pig based on the CT image processing as claimed in claim 1 or 2, wherein the step (2) comprises the following steps:
(21) binarizing the preprocessed image, setting threshold values T1 and T2, setting the CT values of all voxels in the threshold value range as 1, and setting the CT values of the rest voxels as 0 to obtain a binary image:
(22) filling holes in the binary image, determining an initial seed point in bw, filling a background by using a morphological dilation algorithm and adopting a four-connected structural element as a starting point, then performing 'not' operation on the obtained binary image to obtain a new binary image bw1, and performing 'AND' operation on bw1 and bw to obtain a hole-filled binary image bw _ bed _ scanner;
(23) removing the CT bed body by adopting a region growing method, setting a pixel point at the central position of the binary image bw _ bed _ scanner as a growing point, and setting a growing rule as searching a point which is the same as the threshold value of the growing point in a connected domain; then traversing the whole image, if the growth rule is met, adding the main part of the image, otherwise, the main part is the CT bed body part; finally, removing the bed body part to obtain a binary image nobed _ mask of the image main body part;
(24) and (5) carrying out AND operation on the binary image nobed _ mask and the original image f to obtain the original image bw _ nobed without the CT bed body.
4. The method for measuring the carcass tissue content of the live pig based on the CT image processing as claimed in claim 3, wherein the step (3) comprises the following steps:
(31) performing threshold segmentation on the original image bw _ nobed without the CT bed body, setting a threshold B _ T, setting the CT values of all voxels larger than the threshold to be 1, and setting the CT values of all voxels smaller than the threshold to be 0; the binary image obtained after threshold segmentation is bw _ bone:
(32) filling holes in the image bw _ bone after threshold segmentation to obtain a filled binary image bw _ bone 1;
(33) traversing the filled image bw _ bone1, counting the number num _ bone of voxels with a value of 1, and calculating the weight w of the boneboneThe formula is as follows:
wbone＝num_bone×PixelSpacing×SliceThickness×ρbone
where PixelSpacing is the pixel size of CT, SliceThickness is the slice thickness, ρboneIs the density of the bone.
5. The method for measuring the carcass tissue content of the live pig based on the CT image processing as claimed in claim 4, wherein the step (4) comprises the following steps:
(41) performing threshold segmentation on the original image bw _ nobed without the CT bed body, setting a threshold O _ T, setting the CT values of all voxels smaller than the threshold to be 1, setting the CT values of all voxels larger than the threshold to be 0, and obtaining a binary image bw _ air after threshold segmentation:
(42) carrying out corrosion operation on the binary image bw _ air, and removing the epidermis part to avoid influencing the viscera segmentation; performing expansion operation again to restore the image to the original size, and obtaining a binary image bw _ air 1;
and (3) corrosion:
expansion: s ═ a ∈ B ∈ { w ∈ Z ∈ } B ∈2|w＝a+b，a∈A，b∈B}
S represents an image set after corrosion or expansion, B represents a structural element for corrosion, A represents an original binary image set,indicating a corrosion operation, ≧ indicating a swelling operation;
(43) filling holes in the obtained binary image bw _ air1 to obtain a complete air binary image bw _ air 2;
(44) performing corrosion operation on the binary image nobed _ mask of the main body part obtained in the step (23), selecting the size of a corrosion structural element so that the size of the corroded main body is approximately the same as the size of the viscera, and obtaining an viscera mask image after corrosion as Internal _ organs _ mask;
(45) selecting structural elements from the binary image bw _ bone1 of the bone obtained in the step (32) for expansion, and performing 'not' operation after the expansion, namely, inverting the binary image bw _ bone1 to obtain a new bone mask image bw _ bone 2;
(46) performing logical AND operation on the visceral mask map Internal _ organiss _ mask and the bone mask map bw _ bone2 obtained in the step (44) and the step (45); selecting structural elements for expansion operation after operation to obtain a new visceral mask image Internal _ organs _ mask 1;
(47) performing logical OR operation on the air binary diagram bw _ air2 obtained in the step (43) and the visceral mask diagram Internal _ organs _ mask1 obtained in the step (46) to obtain a final visceral mask diagram Internal _ organs _ mask 2;
(48) and (3) firstly carrying out 'NOT' operation on the final Internal organ mask image Internal _ organs _ mask2, and then carrying out 'AND' operation on the final Internal organ mask image and the original image bw _ nobed of the removed CT bed body to obtain the original image bw _ nobed _ nogut of the removed Internal organs and the CT bed body.
6. The method for measuring the carcass tissue content of the live pig based on the CT image processing as claimed in claim 5, wherein the step (5) comprises the following steps:
(51) performing threshold segmentation on the original image bw _ nobed _ nogut without internal organs and the CT bed body, setting thresholds F _ T1 and F _ T2, setting the CT values of all voxels within the threshold range to be 1, setting the CT values of all voxels smaller than F _ T1 or larger than F _ T2 to be 0, and obtaining a binary image bw _ fat after threshold segmentation:
(52) traversing the filled image bw _ fat, counting the number num _ fat of voxels with the value of 1, and calculating the weight w of the fatfatThe formula is as follows:
wfat＝num_fat×PixelSpacing×SliceThickness×ρfat
where PixelSpacing is the pixel size of CT, SliceThickness is the slice thickness, ρfatIs the density of the fat.
7. The method for measuring the carcass tissue content of the live pig based on the CT image processing as claimed in claim 6, wherein the step (6) comprises the following steps:
(61) performing threshold segmentation on the original image bw _ nobed _ nogut without internal organs and the CT bed, setting thresholds M _ T1 and M _ T2, setting the CT values of all voxels within the threshold range to be 1, setting the CT values of all voxels smaller than M _ T1 or larger than M _ T2 to be 0, and obtaining a muscle binary image bw _ muscle after threshold segmentation:
(62) after the binary image bw _ bone1 of the bone obtained in the step (32) is subjected to 'not' operation, and then the binary image bw _ muscle is subjected to 'and' operation with the binary image bw _ muscle to obtain a binary image bw _ muscle1 of the real muscle after the bone and the viscera are removed;
(63) traversing the filled image bw _ muscle1, calculating the number num _ muscle of voxels with a statistical value of 1, and calculating the weight w of the musclemuscleThe formula is as follows:
wmuscle＝num_muscle×PixelSpacing×SliceThickness×ρmuscle
where PixelSpacing is the pixel size of CT, SliceThickness is the slice thickness, ρmuscleIs the density of the muscle.
8. The method for measuring the carcass tissue content of the live pig based on the CT image processing as claimed in claim 7, wherein the step (7) comprises the following steps:
(71) calculating the weight w of the bone obtained in the step (33)boneCalculating the weight w of the fat obtained in step (52)fatAnd the muscle weight w calculated in the step (63)muscleAdding to obtain the total weight W:
W＝wbone+wfat+wmuscle
(72) the proportion of the skeleton isThe ratio of fat isThe muscle proportion is
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717613.XA CN110610497B (en) | 2019-08-05 | 2019-08-05 | Method for determining content of living pig carcass tissue based on CT image processing |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910717613.XA CN110610497B (en) | 2019-08-05 | 2019-08-05 | Method for determining content of living pig carcass tissue based on CT image processing |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110610497A true CN110610497A (en) | 2019-12-24 |
| CN110610497B CN110610497B (en) | 2023-06-16 |
Family
ID=68890285
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910717613.XA Active CN110610497B (en) | 2019-08-05 | 2019-08-05 | Method for determining content of living pig carcass tissue based on CT image processing |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110610497B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112164073A (en) * | 2020-09-22 | 2021-01-01 | 江南大学 | Image three-dimensional tissue segmentation and determination method based on deep neural network |
| CN112168211A (en) * | 2020-03-26 | 2021-01-05 | 成都思多科医疗科技有限公司 | Fat thickness and muscle thickness measuring method and system of abdomen ultrasonic image |
| CN112184631A (en) * | 2020-09-08 | 2021-01-05 | 上海交通大学附属第六人民医院 | Image processing method, device and computer readable storage medium |
| CN113177963A (en) * | 2021-04-25 | 2021-07-27 | 明峰医疗系统股份有限公司 | CT (computed tomography) sickbed removing method |
| CN113516624A (en) * | 2021-04-28 | 2021-10-19 | 武汉联影智融医疗科技有限公司 | Determination of puncture forbidden zone, path planning method, surgical system and computer equipment |
| CN113643319A (en) * | 2021-10-18 | 2021-11-12 | 成都汇声科技有限公司 | Fat thickness starting line calibrated on image and fat thickness measuring method |
| CN115187600A (en) * | 2022-09-13 | 2022-10-14 | 杭州涿溪脑与智能研究所 | Brain hemorrhage volume calculation method based on neural network |
| CN113077474B (en) * | 2021-03-02 | 2024-05-17 | 心医国际数字医疗系统(大连)有限公司 | CT image-based bed board removing method, system, electronic equipment and storage medium |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576997A (en) * | 2009-06-19 | 2009-11-11 | 西安电子科技大学 | Abdominal organ segmentation method based on secondary three-dimensional region growth |
| CN104809723A (en) * | 2015-04-13 | 2015-07-29 | 北京工业大学 | Three-dimensional liver CT (computed tomography) image automatically segmenting method based on hyper voxels and graph cut algorithm |
| CN106296664A (en) * | 2016-07-30 | 2017-01-04 | 上海联影医疗科技有限公司 | Vessel extraction method |
| CN109523561A (en) * | 2018-12-19 | 2019-03-26 | 睿仁佳心(上海)科技有限公司 | Muscle and fat image dividing method in automatic abdomen |
-
2019
- 2019-08-05 CN CN201910717613.XA patent/CN110610497B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101576997A (en) * | 2009-06-19 | 2009-11-11 | 西安电子科技大学 | Abdominal organ segmentation method based on secondary three-dimensional region growth |
| CN104809723A (en) * | 2015-04-13 | 2015-07-29 | 北京工业大学 | Three-dimensional liver CT (computed tomography) image automatically segmenting method based on hyper voxels and graph cut algorithm |
| CN106296664A (en) * | 2016-07-30 | 2017-01-04 | 上海联影医疗科技有限公司 | Vessel extraction method |
| CN109523561A (en) * | 2018-12-19 | 2019-03-26 | 睿仁佳心(上海)科技有限公司 | Muscle and fat image dividing method in automatic abdomen |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112168211A (en) * | 2020-03-26 | 2021-01-05 | 成都思多科医疗科技有限公司 | Fat thickness and muscle thickness measuring method and system of abdomen ultrasonic image |
| CN112184631A (en) * | 2020-09-08 | 2021-01-05 | 上海交通大学附属第六人民医院 | Image processing method, device and computer readable storage medium |
| CN112164073A (en) * | 2020-09-22 | 2021-01-01 | 江南大学 | Image three-dimensional tissue segmentation and determination method based on deep neural network |
| CN113077474B (en) * | 2021-03-02 | 2024-05-17 | 心医国际数字医疗系统(大连)有限公司 | CT image-based bed board removing method, system, electronic equipment and storage medium |
| CN113177963A (en) * | 2021-04-25 | 2021-07-27 | 明峰医疗系统股份有限公司 | CT (computed tomography) sickbed removing method |
| CN113177963B (en) * | 2021-04-25 | 2022-05-20 | 明峰医疗系统股份有限公司 | CT (computed tomography) sickbed removing method |
| CN113516624A (en) * | 2021-04-28 | 2021-10-19 | 武汉联影智融医疗科技有限公司 | Determination of puncture forbidden zone, path planning method, surgical system and computer equipment |
| CN113643319A (en) * | 2021-10-18 | 2021-11-12 | 成都汇声科技有限公司 | Fat thickness starting line calibrated on image and fat thickness measuring method |
| CN113643319B (en) * | 2021-10-18 | 2021-12-10 | 成都汇声科技有限公司 | Fat thickness starting line calibrated on image and fat thickness measuring method |
| CN115187600A (en) * | 2022-09-13 | 2022-10-14 | 杭州涿溪脑与智能研究所 | Brain hemorrhage volume calculation method based on neural network |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110610497B (en) | 2023-06-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110610497B (en) | Method for determining content of living pig carcass tissue based on CT image processing | |
| US10083515B2 (en) | Method and system for segmenting medical imaging data according to a skeletal atlas | |
| US7315639B2 (en) | Method of lung lobe segmentation and computer system | |
| JP2021002339A (en) | Method and system for machine learning classification based on structure or material segmentation in image | |
| Thein et al. | An image preprocessing method for kidney stone segmentation in CT scan images | |
| Rahmatullah et al. | Quality control of fetal ultrasound images: Detection of abdomen anatomical landmarks using adaboost | |
| Tuncer et al. | Spinal Cord Based Kidney Segmentation Using Connected Component Labeling and K-Means Clustering Algorithm. | |
| CN112164073A (en) | Image three-dimensional tissue segmentation and determination method based on deep neural network | |
| Balasooriya et al. | Intelligent brain hemorrhage diagnosis using artificial neural networks | |
| Murray et al. | Magnetic resonance imaging of the equine digit with chronic laminitis | |
| Köse et al. | An automatic diagnosis method for the knee meniscus tears in MR images | |
| CN113870098A (en) | Automatic Cobb angle measurement method based on spinal layered reconstruction | |
| Romvári et al. | Development of a computed tomographic calibration method for the determination of lean meat content in pig carcasses | |
| Gangsei et al. | Building an in vivo anatomical atlas to close the phenomic gap in animal breeding | |
| Ang et al. | An algorithm for automated separation of trabecular bone from variably thick cortices in high-resolution computed tomography data | |
| Johansen et al. | Calibration models for lamb carcass composition analysis using computerized tomography (CT) imaging | |
| EP1447772B1 (en) | A method of lung lobe segmentation and computer system | |
| Wulandari et al. | Automatic lung cancer detection using color histogram calculation | |
| US20180192944A1 (en) | Methods for monitoring compositional changes in a body | |
| JP2018512188A (en) | Segment objects in image data using channel detection | |
| Wald et al. | Automated quantification of adipose and skeletal muscle tissue in whole-body MRI data for epidemiological studies | |
| Pan et al. | Research on the three-dimensional segmentation of tissue content based on CT | |
| CN111292289B (en) | CT lung tumor segmentation method, device, equipment and medium based on segmentation network | |
| El Soufi et al. | CIMOR: An automatic segmentation to extract bone tissue in hand x-ray images | |
| Romão et al. | MUSCULAR ANATOMY OF THE THORAX AND THORACIC LIMB OF Caiman Crocodilus (LINNAEUS, 1758)(CROCODYLIA: ALLIGATORIDAE) BY MEANS OF DIGITAL DISSECTION AND THREE-DIMENSIONAL MODELS |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| TA01 | Transfer of patent application right |
Effective date of registration: 20230511 Address after: No. 10-919 Fenghuang Street, Jiangpu Street, Pukou District, Nanjing City, Jiangsu Province, 211800 Applicant after: Shiji Biotechnology (Nanjing) Co.,Ltd. Applicant after: ANHUI GONGDA INFORMATION TECHNOLOGY CO.,LTD. Address before: 243000 Tongjiang Avenue, Wujiang Town Industrial Park, Ma'anshan City and County, Anhui Province Applicant before: HANSWINE FOOD GROUP Co.,Ltd. Applicant before: ANHUI GONGDA INFORMATION TECHNOLOGY CO.,LTD. |
|
| TA01 | Transfer of patent application right | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP03 | Change of name, title or address |
Address after: Room 1515, Building 23, Block A02, Nanqi Garden, No. 9 Wangjiang West Road, Shushan District, Hefei City, Anhui Province, 230000 Patentee after: Shiji Biotechnology Co.,Ltd. Country or region after: China Patentee after: ANHUI GONGDA INFORMATION TECHNOLOGY CO.,LTD. Address before: No. 10-919 Fenghuang Street, Jiangpu Street, Pukou District, Nanjing City, Jiangsu Province, 211800 Patentee before: Shiji Biotechnology (Nanjing) Co.,Ltd. Country or region before: China Patentee before: ANHUI GONGDA INFORMATION TECHNOLOGY CO.,LTD. |