Non-destructive sex identification method for transformed young duck eggs based on singing tube nuclear magnetic images

Abstract

The invention discloses a method for non-destructively identifying the gender of a transformed young duck egg based on a singing tube nuclear magnetic image, and belongs to the technical field of poultry egg detection.The method comprises the steps that a low-field nuclear magnetic resonance technology is utilized, a breeding duck egg is positioned in a nuclear magnetic system, the optimal imaging section of a singing tube is determined, an image is collected and preprocessed, and a high-quality singing tube nuclear magnetic image is obtained; and through analyzing relaxation characteristics, inverting nuclear magnetic signals to identify a buzzer tube structure and extracting characteristics, finally constructing a gender decision-making model, and combining physical constraints to obtain a gender discrimination result as a sorting reference. According to the method, lossless, early-stage and high-accuracy sex identification is realized through a special imaging technology and algorithm by utilizing sex difference nuclear magnetic characteristics of a singing tube structure, hatching and breeding strategies can be optimized in laying duck and meat duck breeding, and intelligent development of the industry is promoted.

Description

Technical Field

[0001] The invention belongs to the technical field of poultry egg detection, and in particular relates to a method for non-destructive sex identification of crossbred duck eggs based on syrinx nuclear magnetic resonance images. Background Art

[0002] In the duck industry, the value of male and female individuals differs significantly. This is especially true in breeding and laying ducks. Accurately identifying the sex of embryos in the early stages of incubation would significantly improve resource allocation efficiency, reduce breeding costs, and increase hatching-to-output ratios. However, traditional sex determination methods, such as DNA testing, hormone labeling, and visual observation, suffer from issues such as shell breakage, low efficiency, or a lack of industrial scalability. In recent years, researchers have explored various advanced detection technologies to achieve non-destructive sex determination of poultry eggs. These include near-infrared spectroscopy and laser scattering to analyze light signals transmitted through the eggshell; ultrasonic imaging and reflectometry to assess embryonic tissue structure or sound velocity differences; and multimodal sensing technologies such as hyperspectral imaging and microwave radioscopy to capture internal optical or electromagnetic signatures through the eggshell. While these methods have achieved some progress, they still suffer from limited sensitivity, high noise levels, significant influence by eggshell thickness and position, and bulky equipment, making them difficult to implement reliably and on a large scale in industrial incubation environments. In particular, existing technologies fail to fully utilize the important physiological characteristics of the transition stage - at this stage the syrinx is fully developed and mature, and male and female individuals show obvious differences in syrinx structure. Summary of the Invention

[0003] In response to the above-mentioned deficiencies in the prior art, the present invention provides a method for non-destructive sex identification of breeding duck eggs based on syrinx MRI images. Based on the characteristic manifestations of the syrinx tympanic structure unique to male breeding duck embryos in MRI images, combined with optimized MRI imaging technology, image processing technology and discrimination algorithm, the method realizes the early non-destructive sex identification of breeding duck eggs.

[0004] In order to achieve the above-mentioned object of the invention, the technical solution adopted by the present invention is: a method for non-destructive sex identification of crossbred duck eggs based on syrinx nuclear magnetic resonance images, comprising the following steps:

[0005] S1. Position the chick breeder duck eggs in a nuclear magnetic resonance system and determine the optimal imaging section of the chick breeder duck egg syrinx structure;

[0006] S2. Based on the optimal imaging section, a combination of specialized MRI sequences for the syrinx structure is used to acquire several syrinx MRI images, which are then preprocessed to obtain high-quality syrinx MRI images.

[0007] In the high-quality syrinx MRI image, there is a bright circular structure on the right side of the trachea terminal end of the male breeder duck embryo;

[0008] S3. Identify the syrinx structure in high-quality syrinx MRI images and quantitatively extract the syrinx structural features through relaxation characteristic analysis and MRI signal inversion.

[0009] S4. Construct a syrinx sex determination model, and combine it with the physical constraints of the syrinx structure to identify the sex discrimination results corresponding to the syrinx structural characteristics, which will serve as a reference for sorting eggs of transfer ducks.

[0010] Furthermore, the step S1 is specifically as follows:

[0011] In the nuclear magnetic resonance system, the eggs of the transgenic duck breeder are placed in the center of the magnetic field through positioning and centralization to obtain the best magnetic field uniformity and optimize the position of the radio frequency coil;

[0012] Based on the positioning of the eggs of the rooster-bred ducklings, several optimal imaging sections of the syrinx structure were determined through multi-plane trial scanning.

[0013] Furthermore, the step S2 includes the following sub-steps:

[0014] S21. Design a dedicated MRI sequence combination for the syrinx structure, including T2-weighted, T1-weighted, susceptibility-weighted, and fat-suppressed sequences;

[0015] S22. Based on a combination of specialized MRI sequences and the optimal imaging section, determine the embryonic position and tracheal bifurcation plane of the ducklings' eggs through multi-plane positioning scanning. Combined with the optimal imaging time window selected during the embryonic developmental stage, several MRI images of the syrinx are acquired under the optimal imaging section of the syrinx structure.

[0016] S23, performing image enhancement processing on the acquired syrinx MRI image to obtain an enhanced syrinx MRI image;

[0017] The image enhancement processing includes contrast enhancement, multi-sequence image fusion, three-dimensional reconstruction and parameter map generation processing;

[0018] S24, performing image quality optimization processing on the enhanced syrinx MRI image to obtain a high-quality syrinx MRI image;

[0019] The image quality optimization process includes motion correction, artifact removal and quality evaluation.

[0020] Furthermore, in step S24, the quality of each enhanced syrinx MRI image is evaluated by constructing an image quality evaluation model, and the enhanced syrinx MRI image with the highest image quality score is selected as the high-quality syrinx MRI image;

[0021] When the quality evaluation scores of all enhanced syrinx MRI images are less than the preset threshold, return to step S1, reposition and acquire syrinx MRI images;

[0022] The expression of the image quality evaluation model is:

[0023] ;

[0024] Where, represents the image quality score, represents the signal-to-noise ratio, represents the contrast-to-noise ratio, Indicates structural clarity, Indicates the degree of artifact, 、 、 and Respectively 、 、 and The weight coefficient of .

[0025] Furthermore, step S3 includes the following sub-steps:

[0026] S31. Analyze the relaxation characteristics of the syrinx structure in high-quality syrinx MRI images and determine the T1 and T2 relaxation times of the syrinx structure;

[0027] Based on the relaxation characteristics analysis, the syrinx structure-specific NMR signal inversion was performed to determine the magnetic susceptibility.

[0028] S32. Localize the syrinx structure in high-quality syrinx MRI images using a tracheal tracking algorithm;

[0029] S33. Based on the T1 and T2 relaxation times and magnetic susceptibility of the syrinx structure, perform quantitative feature analysis on high-quality syrinx MRI images to extract multidimensional features of the syrinx structure, including morphological features, signal features, and texture features.

[0030] S34. Based on the extracted multidimensional features, a high-dimensional feature space is constructed, and quantitative syrinx structural features are obtained through feature screening, dimensionality reduction and recursive feature elimination.

[0031] Furthermore, in step S32, locating the syrinx structure in the high-quality syrinx MRI image using a tracheal tracking algorithm includes:

[0032] Initialize seed point In the tracheal area at the top of the egg;

[0033] High-quality syrinx MRI images Apply morphological operations to get the first image ;

[0034] Extract the skeleton in the first image , to extract the skeleton Every point on , calculate its direction vector ;

[0035] From the seed point Start, along the direction Track the trachea and generate the tracheal centerline trajectory ;

[0036] Trajectory of the tracheal centerline The terminal area of ​​the syrinx structure is searched for candidate tympanic cavity areas that meet the conditions;

[0037] The conditions include: being located on the right side of the tracheal terminal, having a circularity greater than 0.8, a signal intensity ratio greater than 1.8, and a diameter within the range of 2.2 to 3.0 mm;

[0038] in, represents the morphological closing operation, represents the morphological opening operation, The size of the structure element representing the opening operation, The size of the structural element representing the closing operation, represents the skeleton extraction function;

[0039] Furthermore, the step S4 includes the following sub-steps:

[0040] S41. Establish a standard system for distinguishing the sex characteristics of the syrinx, wherein the standard includes the presence and location of the syrinx tympanic cavity, the syrinx tympanic cavity diameter threshold, the signal intensity ratio threshold, the T2 relaxation time threshold, the magnetic susceptibility threshold, and the structural consistency in consecutive slices;

[0041] S42. Construct a syrinx sex decision model;

[0042] The syrinx gender decision model includes a gender discrimination layer, a confidence assessment layer, and a decision output layer. The gender discrimination layer is used to pre-screen the syrinx tympanic structure and its basic characteristics based on the established syrinx gender feature discrimination standard system. Then, based on the extracted syrinx structural features and their weights, combined with the physical constraints of the syrinx structure, a quantitative gender discrimination result is obtained through a linear discriminant function. The confidence assessment layer is used to evaluate the accuracy of the gender discrimination result. The decision output layer is used to output the final gender discrimination result based on the gender discrimination result and its confidence.

[0043] S43. Input the syrinx structural features into the syrinx gender decision model and output the corresponding gender discrimination result.

[0044] Furthermore, in step S42, in the gender discrimination layer, the gender discrimination function is:

[0045] ;

[0046] Where, Represents the discriminant function value, when When , the sex discrimination result is male, when When , the sex discrimination result is female, represents the bias term, Represents the structural characteristics of the i-th syrinx The corresponding weight coefficient;

[0047] The physical constraints of the gender discrimination function are:

[0048] ;

[0049] ;

[0050] Where, It represents the actual nuclear magnetic signal intensity after considering the influence of magnetic field inhomogeneity. It indicates the intensity of the nuclear magnetic signal with echo time TE and repetition time TR. represents the gyromagnetic ratio, represents the local magnetic field uncertainty, , represents the difference in magnetic susceptibility, represents the main magnetic field intensity, represents the geometric factor related to the structural orientation, represents the echo time, Indicates the repetition time, express relaxation time, express relaxation time, represents the proton density.

[0051] Furthermore, the step S4 further includes: based on the gender discrimination result, optimizing the display of the syrinx structure in the high-quality syrinx MRI image by using a quantitative enhancement algorithm;

[0052] The enhancement algorithm includes adaptive pseudo-color mapping of the syrinx structure, sharpening and enhancement of the syrinx structure boundary, quantitative superposition display of gender discrimination results, and quantitative evaluation of the enhancement effect.

[0053] Compared with existing non-shell sex detection methods such as spectroscopy and ultrasound, the present invention has the following significant technical advantages and effects:

[0054] 1. Direct identification of differences in syrinx structure:

[0055] The present invention utilizes the unique syrinx and tympanic cavity structure of male breeding duck embryos to directly observe anatomical differences through nuclear magnetic resonance imaging, avoiding the uncertainty of indirect signal inference and achieving accurate identification through "structural visualization".

[0056] 2. Non-destructive deep testing capabilities:

[0057] The nuclear magnetic resonance technology used in the present invention can directly image the internal structure of the embryo through the eggshell without damage, without breaking the shell or external sensor contact, maintaining the integrity of the embryo and effectively improving the hatching rate.

[0058] 3. The best time to test during the chickling stage:

[0059] In the present invention, the detection is performed at the transition stage when the syrinx is mature, making full use of the most significant physiological characteristics of gender differences at this stage, thereby ensuring the accuracy and stability of the detection.

[0060] 4. Intelligent tracheal tracking technology:

[0061] The present invention uses a dedicated tracheal tracking algorithm to automatically locate the syrinx structure and extract multi-dimensional features, achieving a technological breakthrough from manual recognition to intelligent detection.

[0062] 5. Anti-interference imaging advantages:

[0063] The present invention adopts a special nuclear magnetic resonance imaging sequence combination of T2 weighted, T1 weighted, magnetic susceptibility weighted and fat suppression sequences, which is not affected by external factors such as eggshell thickness and lighting conditions and has strong environmental adaptability. BRIEF DESCRIPTION OF THE DRAWINGS

[0064] Figure 1 This is a flow chart of the method for non-destructive sex identification of crossbred duck eggs based on syrinx nuclear magnetic resonance images provided by the present invention. DETAILED DESCRIPTION

[0065] The specific embodiments of the present invention are described below to facilitate understanding of the present invention by those skilled in the art. However, it should be clear that the present invention is not limited to the scope of the specific embodiments. For those skilled in the art, as long as various changes are within the spirit and scope of the present invention as defined and determined by the appended claims, these changes are obvious, and all inventions and creations utilizing the concepts of the present invention are protected.

[0066] The embodiment of the present invention provides a method for non-destructive sex identification of duck eggs based on syrinx nuclear magnetic resonance images. Figure 1 As shown, the following steps are included:

[0067] S1. Position the chick breeder duck eggs in a nuclear magnetic resonance system and determine the optimal imaging section of the chick breeder duck egg syrinx structure;

[0068] S2. Based on the optimal imaging section, a combination of specialized MRI sequences for the syrinx structure is used to acquire several syrinx MRI images, which are then preprocessed to obtain high-quality syrinx MRI images.

[0069] In the high-quality syrinx MRI image, there is a bright circular structure on the right side of the trachea terminal end of the male breeder duck embryo;

[0070] S3. Identify the syrinx structure in high-quality syrinx MRI images and quantitatively extract the syrinx structural features through relaxation characteristic analysis and MRI signal inversion.

[0071] S4. Construct a syrinx sex determination model, and combine it with the physical constraints of the syrinx structure to identify the sex discrimination results corresponding to the syrinx structural characteristics, which will serve as a reference for sorting eggs of transfer ducks.

[0072] Step S1 of the embodiment of the present invention is specifically as follows:

[0073] In the nuclear magnetic resonance system, the eggs of the transgenic duck breeder are placed in the center of the magnetic field through positioning and centralization to obtain the best magnetic field uniformity and optimize the position of the radio frequency coil;

[0074] Based on the positioning of the eggs of the rooster-bred ducklings, several optimal imaging sections of the syrinx structure were determined through multi-plane trial scanning.

[0075] In order to ensure that the best image of the syrinx structure is obtained in this embodiment, the placement position and direction of the syrinx eggs in the nuclear magnetic resonance system are optimized to ensure the best imaging effect. Specifically, the syrinx eggs are placed in a specific direction so that the long axis of the trachea and the main magnetic field direction are as parallel as possible to minimize magnetic susceptibility artifacts. The syrinx area should be located in the center of the coil sensitive area to maximize the signal. It is usually necessary to place the eggs with the large end facing up and use a special fixing device to ensure stability. This precise positioning technology is a prerequisite for obtaining high-quality syrinx nuclear magnetic resonance images, ensuring that the nuclear magnetic resonance system can image the syrinx area in the best state.

[0076] Based on the reasonable positioning of the egg body, in this embodiment, multi-plane test scanning is used to determine the optimal display section of the syrinx structure, and multi-plane reconstruction is performed using isotropic voxel data to obtain section display at any angle; specifically, the plane perpendicular to the long axis of the trachea, located 0.5-1.5 mm in front of the tracheal bifurcation, is usually the optimal imaging plane for the syrinx structure. The curved surface reconstruction technology is used to reconstruct along the direction of the trachea, so that the entire trachea-syrinx system can be displayed at one time.

[0077] In this embodiment, a complete set of optimization schemes for imaging the syrinx region was established through egg body positioning and section optimization, which provided technical support for obtaining high-quality syrinx MRI images and created favorable conditions for subsequent image analysis and feature extraction.

[0078] In step S2 of the embodiment of the present invention, the key anatomical landmarks for sex identification are first determined based on the study of the anatomical differences in the syringeal structure of male and female duck embryos. Male ducks have a well-developed syringeal bulla, which is an air-filled cavity structure located to the right of the tracheal bifurcation, while the syringeal structure of female ducks is relatively simple, without an obvious tympanic cavity. This anatomical difference manifests as a significant difference in signal characteristics in magnetic resonance imaging, providing a basis for non-destructive sex identification. Specifically, the syringeal bulla of male ducks appears as a high-signal round or spherical bright spot in magnetic resonance imaging, with a diameter usually in the range of 2.2-3.0 mm. In contrast, the terminal region of the trachea of ​​female ducks has a uniform signal, no characteristic bright structure, and a relatively smooth overall morphology. Nuclear magnetic resonance accurately captures this anatomical difference by detecting the distribution density and relaxation characteristics of hydrogen protons in different tissues, providing a reliable imaging basis for sex identification.

[0079] Furthermore, the tissue contrast characteristics of MRI technology are utilized, and based on the different relaxation characteristics of the gas in the syrinx tympanic cavity and the surrounding soft tissue in MRI, signal contrast is formed to achieve a clear display of the syrinx structure. By optimizing the MRI sequence parameters, the signal difference between the syrinx structure and the surrounding tissue is maximized, improving the accuracy of identification. Specifically, the gas-filled syrinx tympanic cavity appears as a clear high signal area in T2-weighted images, with clear boundaries and sharp contrast with the surrounding soft tissue. In particular, the gas-soft tissue interface of the syrinx tympanic cavity produces a unique magnetic susceptibility effect in the gradient echo sequence, further enhancing the accuracy of structural identification.

[0080] In this embodiment, through the above-mentioned in-depth study of the anatomical characteristics of the syrinx structure and the characteristics of the nuclear magnetic resonance signal, a theoretical basis is provided for the subsequent optimization of imaging technology and parameters for the sex identification of crossbred duck eggs, and guidance is provided for the design and optimization of specific nuclear magnetic resonance sequences.

[0081] Based on this, step S2 of the embodiment of the present invention includes the following sub-steps:

[0082] S21. Design a dedicated MRI sequence combination for the syrinx structure, including T2-weighted, T1-weighted, susceptibility-weighted, and fat-suppressed sequences;

[0083] S22. Based on a combination of specialized MRI sequences and the optimal imaging section, determine the embryonic position and tracheal bifurcation plane of the ducklings' eggs through multi-plane positioning scanning. Combined with the optimal imaging time window selected during the embryonic developmental stage, several MRI images of the syrinx are acquired under the optimal imaging section of the syrinx structure.

[0084] S23, performing image enhancement processing on the acquired syrinx MRI image to obtain an enhanced syrinx MRI image;

[0085] The image enhancement processing includes contrast enhancement, multi-sequence image fusion, three-dimensional reconstruction and parameter map generation processing;

[0086] S24, performing image quality optimization processing on the enhanced syrinx MRI image to obtain a high-quality syrinx MRI image;

[0087] The image quality optimization process includes motion correction, artifact removal and quality evaluation.

[0088] In step S21 of this embodiment, based on an understanding of the anatomical characteristics and signal signatures of the syrinx, a dedicated MRI sequence combination was designed, optimized for the specific tissue properties of the syrinx. These sequences include T2-weighted, T1-weighted, susceptibility-weighted, and fat-suppressed sequences, to achieve optimal visualization of the syrinx. The combined use of these sequences fully utilizes the multi-parameter imaging capabilities of MRI and is optimized for the physical properties of the syrinx.

[0089] Specifically, a fast spin echo T2-weighted sequence (TR=2500-3500ms, TE=80-100ms, slice thickness 2mm, matrix 256×256, FOV=80mm, NEX=2) was used to highlight the gas-soft tissue contrast; a three-dimensional gradient echo T1-weighted sequence (TR=400-600ms, TE=10-15ms, flip angle=30°, isotropic voxel 0.5mm) was used to finely display the structural boundaries; magnetic susceptibility-weighted imaging (TR=49ms, TE=40ms, flip angle=15°) was used to enhance the gas-tissue interface contrast; and a fat-suppressed sequence using STIR technology (TI=150ms) was used to highlight the syrinx structure.

[0090] In this embodiment, the optimized imaging sequence lays the foundation for obtaining high-quality images of the syrinx structure and provides reliable raw data for subsequent image processing and analysis.

[0091] In step S22 of this embodiment, based on the optimized imaging sequence, a dedicated MRI positioning scanning technology was developed. The embryo position was determined through multi-plane positioning, the tracheal bifurcation plane was determined based on the positioning image, a multi-layer thin-layer scanning strategy was adopted, and the optimal imaging time window was selected according to the embryonic development stage to ensure the acquisition of several syrinx MRI images under the optimal imaging section of the syrinx structure.

[0092] Specifically, a rapid gradient echo sequence (TR / TE = 10 / 4ms) was used for three-plane localization, scanning 8-10 slices (1.5mm slice thickness, 0.2mm slice spacing) from the top of the egg downward. The optimal imaging window occurs during the transition period (after 28 days of incubation), when the syrinx is mature but embryonic movement is minimal. The optimal imaging slices are typically the first four slices downward from the top of the egg. In this region, the syrinx is relatively mature, with distinct structural differences, the highest signal-to-noise ratio, and minimal artifacts.

[0093] In this embodiment, the above-mentioned precise positioning and scanning technology ensures that the syrinx MRI image at the best display level of the syrinx structure can be obtained, providing an accurate anatomical basis for subsequent image analysis and gender determination.

[0094] In step S23 of this embodiment, after acquiring the syrinx MRI image, the display of the syrinx structure is optimized through contrast enhancement, multi-sequence image fusion, three-dimensional reconstruction and parameter map generation to improve the visualization effect of the syrinx structure in the MRI image.

[0095] Specifically, an adaptive contrast enhancement algorithm is used to automatically adjust the window width and window position according to the signal characteristics of the syrinx area, and the T1WI, T2WI and SWI sequence images are aligned and fused. The trachea-syrinx system is reconstructed in three dimensions based on the isosurface extraction algorithm, and T1 and T2 relaxation time maps and magnetic susceptibility maps are generated to provide a basis for quantitative analysis of tissue characteristics.

[0096] In this example, the image enhancement and reconstruction techniques described above significantly improve the quality of syrinx structure in MRI images, laying the foundation for subsequent feature extraction and quantitative analysis. Through optimized imaging sequences, precise slice positioning, and effective image enhancement, a complete high-quality imaging system for syrinx structure has been established.

[0097] In step S24 of this embodiment, during the image quality optimization process:

[0098] In order to solve the impact of embryonic micromotion on MRI image quality, based on the acquisition of enhanced syrinx MRI images, this embodiment uses motion compensation and correction technology, including rapid acquisition sequence, real-time motion detection, post-processing motion correction and encoding direction optimization, to effectively solve the interference of embryonic micromotion on syrinx structure imaging.

[0099] Specifically, single-shot fast spin echo (SS-FSE) and parallel imaging technology (SENSE factor = 2) were used to shorten the single-layer scanning time to <1 second, navigation echo technology was used to monitor embryo movement in real time, the frequency encoding direction was parallel to the expected movement direction, and NSA = 2-3 times averaging was used to improve the signal-to-noise ratio.

[0100] In this embodiment, the motion correction technology effectively reduces the impact of embryonic micro-movement on image quality, ensures the clarity and accuracy of the syrinx structure image, and provides a reliable data basis for subsequent image analysis.

[0101] On the basis of motion correction, this embodiment adopts a series of syrinx region-specific artifact removal methods based on the special structural characteristics of the syrinx region, including motion-insensitive imaging, local field shimming, gradient correction and signal averaging, to significantly improve the quality of MRI images of the syrinx region.

[0102] Specifically, PROPELLER technology was used for motion-insensitive imaging, local magnetic field uniformity was optimized in the syrinx region, geometric deformation caused by gradient nonlinearity was compensated, and spatial consistency of multi-layer syrinx images was ensured through inter-layer registration.

[0103] To ensure the controllability and consistency of image quality, an image quality evaluation model was constructed to comprehensively consider factors such as signal-to-noise ratio, contrast, clarity, and artifact degree to evaluate the quality of each enhanced syrinx MRI image, and the enhanced syrinx MRI image with the highest image quality score was selected as the high-quality syrinx MRI image; among them, by constructing an image quality evaluation model, the system can automatically evaluate the quality of each syrinx image, select the best image for gender discrimination, or prompt the need for re-acquisition.

[0104] When the quality evaluation scores of all enhanced syrinx MRI images are less than the preset threshold, return to step S1, reposition and acquire syrinx MRI images;

[0105] Among them, the expression of the image quality evaluation model is:

[0106] ;

[0107] Where, represents the image quality score, represents the signal-to-noise ratio, represents the contrast-to-noise ratio, Indicates structural clarity, Indicates the degree of artifact, 、 、 and Respectively 、 、 and The weight coefficient of .

[0108] In this embodiment, a complete syrinx MRI image quality optimization system was constructed through motion correction, artifact removal and quality evaluation, ensuring the accuracy and reliability of image analysis and feature extraction, and laying a solid data foundation for subsequent gender discrimination.

[0109] In step S3 of the embodiment of the present invention, after obtaining a high-quality syrinx MRI image, the syrinx structure is accurately located and features are extracted using tracheal tracking and an automatic syrinx structure recognition algorithm, providing a reliable data basis for gender determination. Specifically, step S3 includes the following sub-steps:

[0110] S31. Analyze the relaxation characteristics of the syrinx structure in high-quality syrinx MRI images and determine the T1 and T2 relaxation times of the syrinx structure;

[0111] Based on the relaxation characteristics analysis, the syrinx structure-specific NMR signal inversion was performed to determine the magnetic susceptibility.

[0112] S32. Localize the syrinx structure in high-quality syrinx MRI images using a tracheal tracking algorithm;

[0113] S33. Based on the T1 and T2 relaxation times and magnetic susceptibility of the syrinx structure, perform quantitative feature analysis on high-quality syrinx MRI images to extract multidimensional features of the syrinx structure, including morphological features, signal features, and texture features.

[0114] S34. Based on the extracted multidimensional features, a high-dimensional feature space is constructed, and quantitative syrinx structural features are obtained through feature screening, dimensionality reduction and recursive feature elimination.

[0115] In step S31 of this embodiment, a special nuclear magnetic resonance sequence is designed to analyze the relaxation characteristics of the syrinx structure, measure the T1 and T2 relaxation times and magnetic susceptibility characteristics of different tissues, and establish a tissue characteristic map to provide a quantitative basis for gender identification.

[0116] Specifically, a multi-echo spin echo sequence was used to measure T2 relaxation time, and a variable flip angle gradient echo sequence was used to measure T1 relaxation time. The CPMG sequence parameters were set to a sampling bandwidth of 333.333 kHz, 1,333,374 sampling points, and a wait time of 2,500 ms. T2 values ​​in the tympanic region of the male duck's syrinx typically range from 150 to 200 ms, and T1 values ​​from 800 to 1,000 ms, while T2 values ​​in the surrounding soft tissue ranged from 60 to 80 ms and T1 values ​​from 400 to 600 ms.

[0117] Based on the relaxation characteristics analysis, this embodiment adopts a dedicated nuclear magnetic resonance signal inversion analysis method to extract characteristic information of the syrinx structure from complex nuclear magnetic resonance signals, including multi-component T2 inversion, quantitative magnetic susceptibility mapping and diffusion-weighted imaging analysis, which elevates nuclear magnetic resonance from qualitative observation to quantitative evaluation.

[0118] Specifically, a multi-component T2 inversion model based on the non-negative least squares (NNLS) method was used, with a time range of Tmin = 0.01 ms and Tmax = 10,000 ms. Magnetic susceptibility maps were calculated using gradient echo phase information, and the apparent diffusion coefficient (ADC) of the syrinx region was measured to distinguish different tissue components. The susceptibility of the syrinx tympanum in male ducks is typically ≤ -0.02 ppm, while in female ducks, the corresponding region has values ​​> -0.01 ppm.

[0119] In step S32 of this embodiment, locating the syrinx structure in the high-quality syrinx MRI image using a tracheal tracking algorithm includes:

[0120] Initialize seed point In the tracheal area at the top of the egg;

[0121] High-quality syrinx MRI images Apply morphological operations to get the first image ;

[0122] Extract the skeleton in the first image , to extract the skeleton Every point on , calculate its direction vector ;

[0123] From the seed point Start, along the direction Track the trachea and generate the tracheal centerline trajectory ;

[0124] Trajectory of the tracheal centerline The terminal area of ​​the syrinx structure is searched for candidate tympanic cavity areas that meet the conditions;

[0125] The conditions included: location on the right side of the tracheal terminal, circularity greater than 0.8, signal intensity ratio greater than 1.8, and diameter within the range of 2.2–3.0 mm;

[0126] in, represents the morphological closing operation, represents the morphological opening operation, The size of the structure element representing the opening operation, The size of the structural element representing the closing operation, represents the skeleton extraction function;

[0127] In this embodiment, the trachea tracking method described above achieves a trachea tracking accuracy greater than 95%, with a positioning error less than 0.8 mm, providing a reliable technical means for accurate positioning and feature extraction of the syrinx structure.

[0128] In step S33 of this embodiment, based on the automatic identification of the syrinx structure, a comprehensive feature quantitative analysis is performed on the syrinx MRI image to measure morphological features, signal features, and texture features, analyze the consistency of the syrinx structure in continuous layers, and establish a multidimensional feature space to provide data support for gender discrimination.

[0129] Specifically, morphological features include area, circumference, roundness and diameter; signal features include signal intensity ratio, signal uniformity and signal-to-noise ratio; and texture features include gray-level co-occurrence matrix features (energy, contrast, correlation and entropy), local binary patterns, and multi-scale texture features of wavelet decomposition.

[0130] In this embodiment, a complete characteristic description of the syrinx structure was established through quantitative analysis of the above characteristics, providing comprehensive data support for subsequent gender determination.

[0131] In step S34 of this embodiment, based on comprehensive feature quantification analysis, a high-dimensional feature space of syrinx features is constructed, and through feature screening, dimensionality reduction and recursive feature elimination processing, quantitative syrinx structural features are obtained to improve the accuracy and efficiency of gender discrimination.

[0132] Specifically, features were screened by calculating the feature importance based on information gain and Fisher score, feature dimensionality reduction was performed using PCA and LDA methods, and feature elimination was performed by determining feature weights and removing the feature with the smallest weight until the target number of features was reached, thereby forming the final quantitative syrinx structural characteristics.

[0133] In this embodiment, through feature space construction and dimensionality reduction, efficient expression and extraction of syrinx features are achieved, providing high-quality feature input for the subsequent gender discrimination algorithm, ensuring the accuracy and efficiency of the discrimination process.

[0134] Step S4 of the embodiment of the present invention includes the following sub-steps:

[0135] S41. Establish a standard system for distinguishing the sex characteristics of the syrinx, wherein the standard includes the presence and location of the syrinx tympanic cavity, the syrinx tympanic cavity diameter threshold, the signal intensity ratio threshold, the T2 relaxation time threshold, the magnetic susceptibility threshold, and the structural consistency in consecutive slices;

[0136] S42. Construct a syrinx sex decision model;

[0137] The syrinx gender decision model includes a gender discrimination layer, a confidence assessment layer, and a decision output layer. The gender discrimination layer is used to pre-screen the syrinx tympanic structure and its basic characteristics based on the established syrinx gender feature discrimination standard system. Then, based on the extracted syrinx structural features and their weights, combined with the physical constraints of the syrinx structure, a quantitative gender discrimination result is obtained through a linear discriminant function. The confidence assessment layer is used to evaluate the accuracy of the gender discrimination result. The decision output layer is used to output the final gender discrimination result based on the gender discrimination result and its confidence.

[0138] S43. Input the syrinx structural features into the syrinx gender decision model and output the corresponding gender discrimination result.

[0139] In step S41 of this embodiment, based on the above-mentioned analysis of the structural characteristics of the syrinx, a standard system for distinguishing the gender characteristics of the syrinx is constructed. By comprehensively considering morphological characteristics, signal characteristics, and quantitative parameters, a multidimensional discrimination space is constructed to achieve accurate gender determination. Specifically, the discrimination criteria include the presence and location of the syrinx tympanic cavity, the syrinx tympanic cavity diameter threshold, the signal intensity ratio threshold, the T2 relaxation time threshold, the magnetic susceptibility threshold, and structural consistency in continuous layers. This discrimination standard system is an important link in converting the aforementioned feature analysis results into actual discrimination basis, and provides a theoretical basis for the subsequent automatic discrimination algorithm.

[0140] In step S42 of this embodiment, in the gender discrimination layer, the gender discrimination function is:

[0141] ;

[0142] Where, Represents the discriminant function value, when When , the sex discrimination result is male, when When , the sex discrimination result is female, represents the bias term, Represents the structural characteristics of the i-th syrinx The corresponding weight coefficient;

[0143] Among them, the physical constraints of the gender discriminant function are:

[0144] ;

[0145] ;

[0146] Where, It represents the actual nuclear magnetic signal intensity after considering the influence of magnetic field inhomogeneity. It indicates the intensity of the nuclear magnetic signal with echo time TE and repetition time TR. represents the gyromagnetic ratio, represents the local magnetic field uncertainty, , represents the difference in magnetic susceptibility, represents the main magnetic field intensity, represents the geometric factor related to the structural orientation, represents the echo time, Indicates the repetition time, express relaxation time, express relaxation time, represents the proton density.

[0147] In this embodiment, the confidence assessment layer evaluates the reliability of gender discrimination results based on feature consistency and image quality. When multiple features indicate different genders, the confidence level is lowered; when image quality is poor, it is marked as "needs retest." The decision output layer outputs the final gender discrimination result based on the comprehensive discrimination indicators and the confidence threshold. If the result is confirmed, "male" or "female" and the confidence percentage are output; if the result is uncertain, "uncertain" is output and a retest recommendation is recommended; if the result is abnormal, "test failed" and the reason for failure are output.

[0148] In step S4 of the embodiment of the present invention, it also includes: based on the gender discrimination result, the syrinx structure in the high-quality syrinx MRI image is displayed and optimized by a quantitative enhancement algorithm, so as to provide the operator with a reliable means of verifying the discrimination result.

[0149] Among them, the enhancement algorithm includes adaptive pseudo-color mapping of the syrinx structure, sharpening and enhancement of the syrinx structure boundaries, quantitative overlay display of gender discrimination results, and quantitative evaluation of the enhancement effect.

[0150] Specifically, an adaptive pseudo-color mapping model is established based on the T2 relaxation time of the syrinx structure region:

[0151] ;

[0152] Where, Represents pixel points The color map output value of Indicates the T2 relaxation time value of the pixel point, The threshold for distinguishing male from female is determined by statistically analyzing the T2 relaxation time distribution of male and female samples. The threshold that maximizes the classification accuracy is selected, usually in the range of 100-150ms. represents the mapping sensitivity parameter, represents the hyperbolic tangent function, which is used to achieve smooth color transitions. represents the color gain coefficient, Represents the color shift coefficient. Both are optimized and determined based on the characteristics of the display device and the visual characteristics of the human eye. The male syrinx tympanic cavity area (T2 value is higher than the threshold) is mapped to a warm color display, while the female area maintains the original grayscale display.

[0153] The boundary between the syrinx and the surrounding tissue structures is enhanced by anisotropic diffusion filtering based on the gradient direction. The calculation formula is:

[0154] ;

[0155] Where, Represents the signal intensity distribution function of each pixel in the nuclear magnetic image, represents the diffusion iteration time parameter, It represents the rate of change of signal strength over time. represents the spatial gradient vector of signal strength, represents the magnitude of the gradient vector, represents the divergence operator, represents the diffusion coefficient function based on the gradient amplitude, where the diffusion coefficient function is defined as:

[0156] ;

[0157] Where, represents the gradient amplitude, Represents the corresponding diffusion coefficient, which controls the degree of anisotropy of diffusion. represents the diffusion control parameter, which is adaptively determined based on the gradient contrast between the syrinx structure and the surrounding tissue. The calculation method is the ratio of the average gradient of the syrinx area to the average gradient of the background area multiplied by the adjustment factor. The number of iterations is determined according to the image quality and enhancement effect requirements.

[0158] The process of achieving quantitative overlay display of gender discrimination results includes: automatically outlining the outline of the syrinx and tympanic cavity, numerically displaying and labeling the syrinx diameter, signal intensity ratio, and discrimination confidence, and graded color coding according to confidence, including high confidence using green, medium confidence using yellow, and low confidence using red. The demarcation threshold is determined according to actual application requirements and the cost of misjudgment.

[0159] The enhancement effect is quantitatively evaluated by constructing an objective evaluation model, which is:

[0160] ;

[0161] Where, represents the comprehensive enhancement effect evaluation score, Indicates the improvement of contrast noise after enhancement relative to the original image, Represents the edge sharpness index calculated by the edge detection operator, represents the amount of visual contrast improvement, 、 and Represents the corresponding weight coefficient, which is determined through user evaluation tests and cross-validation to maximize the correlation between the evaluation score and the manual visual evaluation results and satisfy Normalization constraints.

[0162] In this embodiment, through the above-mentioned quantitative enhancement algorithm, the visual recognition effect of the syrinx structure is significantly improved, providing the operator with a clear and intuitive discrimination result verification interface, ensuring the reliability and operability of the entire gender identification system, and forming a complete technical chain with the aforementioned syrinx detection, feature extraction, and gender discrimination algorithms, realizing full process optimization from image acquisition to result presentation.

[0163] In an embodiment of the present invention, after the technical development of the above-mentioned syrinx nuclear magnetic resonance image analysis and gender discrimination is completed, it is integrated with the automatic sorting system to build a complete breeding duck egg gender identification and sorting pipeline. The system includes a nuclear magnetic resonance detection unit, an image analysis unit, a sorting control unit and a mechanical sorting unit, which realizes the automation of the entire process from detection to sorting. Among them, the nuclear magnetic resonance detection unit adopts a low-field nuclear magnetic resonance system, equipped with a special imaging sequence and parameter presets, and obtains high-quality syrinx structure images based on the aforementioned imaging technology; the image analysis unit performs image processing, feature extraction and gender discrimination, and automatically identifies the gender of the breeding duck eggs based on the aforementioned discrimination algorithm; the sorting control unit receives the discrimination results and controls the action of the sorting mechanism; the mechanical sorting unit diverts the breeding duck eggs to different collection devices according to the gender discrimination results.

[0164] Specific embodiments are used in the present invention to illustrate the principles and implementation methods of the present invention. The description of the above embodiments is only used to help understand the method of the present invention and its core ideas. At the same time, for those skilled in the art, according to the ideas of the present invention, there may be changes in the specific implementation methods and application scopes. In summary, the contents of this specification should not be understood as limiting the present invention.

[0165] Those skilled in the art will appreciate that the embodiments described herein are intended to help readers understand the principles of the present invention, and it should be understood that the scope of protection of the present invention is not limited to such specific descriptions and embodiments. Those skilled in the art can make various other specific variations and combinations based on the technical teachings disclosed in the present invention without departing from the essence of the present invention, and such variations and combinations are still within the scope of protection of the present invention.

Claims

1. A non-destructive sex identification method for crossbred duck eggs based on syrinx nuclear magnetic resonance imaging, characterized in that: The following steps are involved: S1. Position the chick breeder duck eggs in a nuclear magnetic resonance system and determine the optimal imaging section of the chick breeder duck egg syrinx structure; S2. Based on the optimal imaging section, a combination of specialized MRI sequences for the syrinx structure is used to acquire several syrinx MRI images, which are then preprocessed to obtain high-quality syrinx MRI images. In the high-quality syrinx MRI image, there is a bright circular structure on the right side of the trachea terminal end of the male breeder duck embryo; S3. Identify the syrinx structure in high-quality syrinx MRI images and quantitatively extract the syrinx structural features through relaxation characteristic analysis and MRI signal inversion. S4. Construct a syrinx sex determination model, and combine it with the physical constraints of the syrinx structure to identify the sex discrimination results corresponding to the syrinx structural characteristics, which will serve as a reference for sorting eggs of transfer ducks.

2. The method for non-destructive sex identification of duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 1, wherein: The step S1 is specifically as follows: In the nuclear magnetic resonance system, the eggs of the transgenic duck breeder are placed in the center of the magnetic field through positioning and centralization to obtain the best magnetic field uniformity and optimize the position of the radio frequency coil; Based on the positioning of the eggs of the rooster-bred ducklings, several optimal imaging sections of the syrinx structure were determined through multi-plane trial scanning.

3. The method for non-destructive sex identification of duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 1, wherein: The step S2 comprises the following sub-steps: S21. Design a dedicated MRI sequence combination for the syrinx structure, including T2-weighted, T1-weighted, susceptibility-weighted, and fat-suppressed sequences; S22. Based on a combination of specialized MRI sequences and the optimal imaging section, determine the embryonic position and tracheal bifurcation plane of the ducklings' eggs through multi-plane positioning scanning. Combined with the optimal imaging time window selected during the embryonic developmental stage, several MRI images of the syrinx are acquired under the optimal imaging section of the syrinx structure. S23, performing image enhancement processing on the acquired syrinx MRI image to obtain an enhanced syrinx MRI image; The image enhancement processing includes contrast enhancement, multi-sequence image fusion, three-dimensional reconstruction and parameter map generation processing; S24, performing image quality optimization processing on the enhanced syrinx MRI image to obtain a high-quality syrinx MRI image; The image quality optimization process includes motion correction, artifact removal and quality evaluation.

4. The method for non-destructive sex identification of duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 3, wherein: In step S24, the quality of each enhanced syrinx MRI image is evaluated by constructing an image quality evaluation model, and the enhanced syrinx MRI image with the highest image quality score is selected as the high-quality syrinx MRI image; When the quality evaluation scores of all enhanced syrinx MRI images are less than the preset threshold, return to step S1, reposition and acquire syrinx MRI images; The expression of the image quality evaluation model is: ； Where, represents the image quality score, represents the signal-to-noise ratio, represents the contrast-to-noise ratio, Indicates structural clarity, Indicates the degree of artifact, 、 、 and Respectively 、 、 and The weight coefficient of .

5. The method for non-destructive sex identification of duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 1, wherein: The step S3 includes the following sub-steps: S31. Analyze the relaxation characteristics of the syrinx structure in high-quality syrinx MRI images and determine the T1 and T2 relaxation times of the syrinx structure; Based on the relaxation characteristics analysis, the syrinx structure-specific NMR signal inversion was performed to determine the magnetic susceptibility. S32. Localize the syrinx structure in high-quality syrinx MRI images using a tracheal tracking algorithm; S33. Based on the T1 and T2 relaxation times and magnetic susceptibility of the syrinx structure, perform quantitative feature analysis on high-quality syrinx MRI images to extract multidimensional features of the syrinx structure, including morphological features, signal features, and texture features. S34. Based on the extracted multidimensional features, a high-dimensional feature space is constructed, and quantitative syrinx structural features are obtained through feature screening, dimensionality reduction and recursive feature elimination.

6. The method for non-destructive sex identification of duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 5, wherein: In step S32, locating the syrinx structure in the high-quality syrinx MRI image using a tracheal tracking algorithm includes: Initialize seed point In the tracheal area at the top of the egg; High-quality syrinx MRI images Apply morphological operations to get the first image ; Extract the skeleton in the first image , to extract the skeleton Every point on , calculate its direction vector ; From the seed point Start, along the direction Track the trachea and generate the tracheal centerline trajectory ; Trajectory of the tracheal centerline The terminal area of ​​the syrinx structure is searched for candidate tympanic cavity areas that meet the conditions; The conditions include: being located on the right side of the tracheal terminal, having a circularity greater than 0.8, a signal intensity ratio greater than 1.8, and a diameter within the range of 2.2 to 3.0 mm; in, represents the morphological closing operation, represents the morphological opening operation, The size of the structure element representing the opening operation, The size of the structural element representing the closing operation, Represents the skeleton extraction function.

7. The method for non-destructive sex identification of duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 1, wherein: The step S4 comprises the following sub-steps: S41. Establish a standard system for distinguishing the sex characteristics of the syrinx, wherein the standard includes the presence and location of the syrinx tympanic cavity, the syrinx tympanic cavity diameter threshold, the signal intensity ratio threshold, the T2 relaxation time threshold, the magnetic susceptibility threshold, and the structural consistency in consecutive slices; S42. Construct a syrinx sex decision model; The syrinx gender decision model includes a gender discrimination layer, a confidence assessment layer, and a decision output layer. The gender discrimination layer is used to pre-screen the syrinx tympanic structure and its basic characteristics based on the established syrinx gender feature discrimination standard system. Then, based on the extracted syrinx structural features and their weights, combined with the physical constraints of the syrinx structure, a quantitative gender discrimination result is obtained through a linear discriminant function. The confidence assessment layer is used to evaluate the accuracy of the gender discrimination result. The decision output layer is used to output the final gender discrimination result based on the gender discrimination result and its confidence. S43. Input the syrinx structural features into the syrinx gender decision model and output the corresponding gender discrimination result.

8. The method for non-destructive sex identification of crossbred duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 7, wherein: In step S42, in the gender discrimination layer, the gender discrimination function is: ； Where, Represents the discriminant function value, when When , the sex discrimination result is male, when When , the sex discrimination result is female, represents the bias term, Represents the structural characteristics of the i-th syrinx The corresponding weight coefficient; The physical constraints of the gender discrimination function are: ； ； Where, It represents the actual nuclear magnetic signal intensity after considering the influence of magnetic field inhomogeneity. It indicates the intensity of the nuclear magnetic signal with echo time TE and repetition time TR. represents the gyromagnetic ratio, represents the local magnetic field uncertainty, , represents the difference in magnetic susceptibility, represents the main magnetic field intensity, represents the geometric factor related to the structural orientation, represents the echo time, Indicates the repetition time, express relaxation time, express relaxation time, represents the proton density.

9. The method for non-destructive sex identification of crossbred duck eggs based on syrinx nuclear magnetic resonance imaging according to claim 1, wherein: The step S4 further includes: optimizing the display of the syrinx structure in the high-quality syrinx MRI image using a quantitative enhancement algorithm based on the gender discrimination result; The enhancement algorithm includes adaptive pseudo-color mapping of the syrinx structure, sharpening and enhancement of the syrinx structure boundary, quantitative superposition display of gender discrimination results, and quantitative evaluation of the enhancement effect.

Images