Polarization imaging system, biological sample detection method, electronic device, and storage medium

Abstract

The application provides a polarization imaging system and a biological sample detection method, an electronic device and a storage medium, and belongs to the technical field of imaging detection. The method comprises the following steps: controlling the polarization imaging system to image a to-be-detected biological sample, and obtaining a to-be-detected light intensity image matrix; combining a given measurement matrix corresponding to a polarizer included in the polarization imaging system, correcting a polarized light analyzer included in the polarization imaging system by using a standard sample, and obtaining a measurement matrix corresponding to the polarized light analyzer; converting the to-be-detected light intensity image matrix to obtain a to-be-detected Mueller matrix according to the given measurement matrix corresponding to the polarizer and the measurement matrix corresponding to the polarized light analyzer, and then determining a polarization image set and a polarization feature image set; and processing the polarization image set and the polarization feature image set by using a target detection model to obtain a biological target detection result. The application can perform deep learning on the Mueller matrix generated by the device calibration mode and the related polarization features reflected by the Mueller matrix, so that reliable target detection can be realized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of imaging detection, in particular to a polarization imaging system, a biological sample detection method, an electronic device and a storage medium. BACKGROUND

[0002] In the existing target polarization imaging detection technology, a plurality of different light intensity images corresponding to different polarization directions are obtained by imaging the biological sample to be measured by the polarization imaging system, and a Mueller matrix is determined by combining and operating the plurality of different light intensity images, and then the Mueller matrix is further analyzed and explained by relying on the experience of technicians to realize biological target detection. However, due to the influence of environmental factors, element installation errors and element quality in the running process of the polarization imaging system, the imaging quality is poor, so that the Mueller matrix obtained directly by image operation is not accurate enough, and the target detection result obtained by using artificial intervention lacks reliability. SUMMARY

[0003] The main purpose of the present application is to propose a polarization imaging system, a biological sample detection method, an electronic device and a storage medium, which can generate a more accurate Mueller matrix by combining device calibration, and then use deep learning technology to comprehensively analyze the Mueller matrix and the related polarization characteristics reflected thereby to quickly obtain a more reliable target detection result.

[0004] To achieve the above purpose, one aspect of the present application provides a polarization imaging system, which comprises a light source, a collimating lens, a polarizer, a stage, an imaging lens, a non-polarization beam splitter prism, an analyzer, a relay lens and a camera.

[0005] When the sample is placed on the stage, the light emitted by the light source forms a collimated light beam through the collimating lens, the collimated light beam forms polarized light through the polarizer, the polarized light is normally incident to the half-transmission half-reflection film in the non-polarization beam splitter prism to form a 90-degree reflected light, the 90-degree reflected light is normally incident to the sample placed on the stage through the imaging lens to produce sample reflected light, the sample reflected light is normally incident to the half-transmission half-reflection film in the non-polarization beam splitter prism to form transmitted light, and the transmitted light enters the analyzer to be analyzed and then forms an image on the camera through the relay lens.

[0006] Further, the polarizer comprises a first linear polarizer, a first liquid crystal variable phase retarder and a second liquid crystal variable phase retarder arranged along the light path direction, and the analyzer comprises a third liquid crystal variable phase retarder, a fourth liquid crystal variable phase retarder and a second linear polarizer arranged along the light path direction.

[0007] The alignment direction of the liquid crystal molecules included in the first liquid crystal variable phase retarder is at a 45-degree angle to the polarizing direction of the first linear polarizer, and the alignment direction of the liquid crystal molecules included in the second liquid crystal variable phase retarder is parallel to the polarizing direction of the first linear polarizer;

[0008] The alignment direction of the liquid crystal molecules included in the third liquid crystal variable phase retarder is parallel to the polarizing direction of the second linear polarizer, and the alignment direction of the liquid crystal molecules included in the fourth liquid crystal variable phase retarder is at a 45-degree angle to the polarizing direction of the second linear polarizer;

[0009] The polarizing direction of the first linear polarizer is parallel to the polarizing direction of the second linear polarizer.

[0010] To achieve the above object, another aspect of the present application proposes a biological sample detection method applied to the polarization imaging system, the method comprising:

[0011] Controlling the polarization imaging system to image the biological sample to be detected to obtain a to-be-detected light intensity image matrix corresponding to the biological sample to be detected;

[0012] Combining a given measurement matrix corresponding to the polarizer included in the polarization imaging system, calibrating the polarizer included in the polarization imaging system with a standard sample to obtain a measurement matrix corresponding to the analyzer;

[0013] According to the given measurement matrix corresponding to the polarizer and the measurement matrix corresponding to the analyzer, converting the to-be-detected light intensity image matrix to obtain a to-be-detected Mueller matrix corresponding to the biological sample to be detected;

[0014] According to the to-be-detected Mueller matrix, determining a polarization image set and a polarization feature image set;

[0015] Using a target detection model to process the polarization image set and the polarization feature image set to obtain a biological target detection result.

[0016] Further, the controlling the polarization imaging system to image the biological sample to be detected to obtain a to-be-detected light intensity image matrix comprises:

[0017] According to a plurality of different first polarization states corresponding to the polarizer and a plurality of different second polarization states corresponding to the analyzer, determining a plurality of combined polarization states corresponding to the polarization imaging system;

[0018] According to the plurality of combined polarization states, controlling the polarization imaging system to image the biological sample to be detected to obtain a plurality of corresponding to-be-detected light intensity images to form the to-be-detected light intensity image matrix.

[0019] Further, the controlling the polarization imaging system to image the biological sample to be measured under the plurality of combined polarization states to obtain a plurality of corresponding measured light intensity images comprises:

[0020] For any one of the combined polarization states, the combined polarization state comprises a first polarization state corresponding to the polarizer and a second polarization state corresponding to the analyzer;

[0021] According to the first polarization state corresponding to the polarizer, the phase retardation amounts required to be reached by the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder contained in the polarizer are determined;

[0022] According to the second polarization state corresponding to the analyzer, the phase retardation amounts required to be reached by the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder contained in the analyzer are determined;

[0023] According to the phase retardation amounts required to be reached by the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder, the driving voltages of the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder are adjusted;

[0024] According to the phase retardation amounts required to be reached by the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder, the driving voltages of the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder are adjusted;

[0025] The polarization imaging system is controlled to image the biological sample to be measured to obtain the measured light intensity image corresponding to the combined polarization state.

[0026] Further, the calibrating the analyzer contained in the polarization imaging system by using a standard sample according to a given measurement matrix corresponding to the polarizer contained in the polarization imaging system to obtain a measurement matrix corresponding to the analyzer comprises:

[0027] The polarization imaging system is controlled to image the standard sample to obtain a standard light intensity image matrix;

[0028] According to the given measurement matrix corresponding to the polarizer, the given standard Mueller matrix corresponding to the standard sample, and the standard light intensity image matrix, the measurement matrix corresponding to the analyzer is determined.

[0029] Further, the determining a polarization image set and a polarization feature image set according to the measured Mueller matrix comprises:

[0030] The value of the element contained in the measured Mueller matrix and simultaneously falling in the first row and the first column is pseudo-color imaged to obtain an intensity image;

[0031] The Mueller matrix to be measured is normalized to obtain a first Mueller matrix to be measured;

[0032] The first Mueller matrix to be measured contains normalized values of a plurality of elements, and the normalized values of the plurality of elements are pseudo-color imaged to obtain a plurality of corresponding polarization images to form the polarization image set;

[0033] The plurality of polarization characteristic values are obtained by combining and analyzing the normalized values of the plurality of elements;

[0034] The plurality of polarization characteristic images corresponding to the plurality of polarization characteristic values are obtained by pseudo-color imaging the plurality of polarization characteristic values, and the intensity image is combined to form the polarization characteristic image set.

[0035] Further, the target detection model is trained based on an improved YOLOv8 model, the improved YOLOv8 model includes an improved main network, an improved neck network and an original head network connected in sequence, the improved main network is constructed based on an improved CSPDarknet framework, the improved CSPDarknet framework is obtained by introducing a double-scale attention module into each residual block contained in the original CSPDarknet framework, the improved neck network includes a spatial pyramid pooling network based on local attention enhancement, a feature pyramid network and a path aggregation network connected in sequence; the biological target detection result is obtained by processing the polarization image set and the polarization characteristic image set using the target detection model, and the processing includes:

[0036] The polarization image set and the polarization characteristic image set are preprocessed to obtain a first polarization image set and a first polarization characteristic image set corresponding thereto;

[0037] The first polarization image set and the first polarization characteristic image set are input into the improved main network for feature extraction to obtain key visual feature information;

[0038] The key visual feature information is input into the improved neck network to fuse and encode features of different scales to obtain visual coding feature information;

[0039] The visual coding feature information is input into the original head network for feature mapping to obtain the biological target detection result.

[0040] To achieve the above-mentioned purposes, another aspect of the present application proposes an electronic device, which includes a memory and a processor, the memory stores a computer program, and the processor executes the computer program to realize the above-mentioned method.

[0041] To achieve the above object, another aspect of the present application provides a computer readable storage medium storing a computer program, which, when executed by a processor, implements the above method.

[0042] The present application has at least the following beneficial effects: by integrating the polarizer and the analyzer in the polarization imaging system to modulate the polarization state, the polarization imaging system can more efficiently and flexibly obtain a plurality of different light intensity images corresponding to a plurality of different polarization directions when imaging the biological sample to be measured. By combining the given measurement matrix corresponding to the polarizer, and using the standard sample device calibration method to determine the measurement matrix corresponding to the analyzer, the plurality of different light intensity images obtained by the polarization imaging system are further converted to obtain a more accurate Mueller matrix, and then the Mueller matrix and the related polarization features reflected thereby are comprehensively analyzed by using the deep learning technology, so that more reliable target detection results can be quickly obtained with greatly reduced manual intervention. BRIEF DESCRIPTION OF DRAWINGS

[0043] Figure 1 is a structural schematic diagram of a polarization imaging system provided by an embodiment of the present application;

[0044] Figure 2 is a flowchart of a biological sample detection method provided by an embodiment of the present application;

[0045] Figure 3 is a schematic diagram of a microsphere polarization image set provided by an embodiment of the present application;

[0046] Figure 4 is a schematic diagram of a microsphere polarization feature image set provided by an embodiment of the present application;

[0047] Figure 5 is a schematic diagram of a microsphere detection result provided by an embodiment of the present application;

[0048] Figure 6 is a hardware structural schematic diagram of an electronic device provided by an embodiment of the present application. DETAILED DESCRIPTION

[0049] In order to make the objects, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and do not limit the present application. When the following description refers to the drawings, the same numbers in different drawings represent the same or similar elements unless otherwise indicated. The implementation described in the following exemplary embodiments does not represent all the implementations consistent with the embodiments of the present application, but is only an example of systems and methods consistent with some aspects of the embodiments of the present application as detailed in the appended claims.

[0050] It can be understood that the terms "first", "second", etc. used in the present application can be used herein to describe various concepts, but unless specifically stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of the present application, the first information can also be referred to as the second information, and similarly, the second information can also be referred to as the first information. Depending on the context, the word "if" as used herein can be interpreted as "when" or "upon determining" or "in response to determining".

[0051] The terms "at least one", "multiple", "each", "any" and the like used in the present application include one, two or more than two, multiple includes two or more than two, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0052] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which the present application belongs. The terms used herein are only for the purpose of describing the embodiments of the present application and are not intended to limit the present application.

[0053] Polarization measurement is an advanced optical technology that uses the polarization state of light waves to obtain information about the structure of an object. Its unique characteristics of non-invasive, non-marking, non-contact and easy expansion make it show significant application advantages in the field of sample observation and analysis, especially in analyzing the anisotropic structure of an object. Polarization optics provides a unique solution.

[0054] In the existing target polarization imaging detection technology, a plurality of different light intensity images corresponding to a plurality of different polarization directions are obtained by imaging the biological sample to be measured by the polarization imaging system. A combination operation is usually performed on the plurality of different light intensity images to determine the Mueller matrix, and further analysis and interpretation of the Mueller matrix by the experience of the technician is relied on to realize biological target detection. However, due to the influence of environmental factors, element installation errors and element quality during the operation of the polarization imaging system, the imaging quality is poor, which makes the Mueller matrix obtained directly by image operation not accurate enough, and the target detection result obtained by manual intervention lacks reliability.

[0055] In the field of polarized optics, the Mueller matrix is an important tool for describing all the polarization properties of a measurement target, and it contains complete polarization information, thus showing its strong analytical ability in the study of anisotropic characteristics of micron-level samples. Mueller matrix microscopic imaging technology, as a method of using Mueller matrix to explore the characteristics of samples in detail, has been widely used in the fields of biomedical science and material science. At the same time, in the field of modern image processing and pattern recognition, especially in the study of target recognition using neural networks, how to integrate polarization information into the design of convolutional neural networks to optimize the learning process has become a hot research direction. By decomposing the Mueller matrix into various polarization information such as degree of polarization, degree of polarization purity, dichroism, etc., and using it as important information for analyzing the anisotropic structure of samples and marking samples, the complex image information can be simplified, the contrast of similar information can be enhanced, and the visualization of invisible information can be realized, thereby greatly enhancing the ability of convolutional neural networks based on polarization information in data mining and feature recognition. It can be seen that convolutional neural networks based on polarization information have strong development potential.

[0056] Therefore, the embodiments of the present application provide a polarization imaging system and a biological sample detection method, an electronic device and a storage medium. The scheme integrates a polarizer and an analyzer in the polarization imaging system to modulate the polarization state, so that the polarization imaging system can more efficiently and flexibly obtain a plurality of different light intensity images corresponding to a plurality of different polarization directions when imaging the biological sample to be measured. By combining the given measurement matrix corresponding to the polarizer, and using a standard sample-based device calibration method to determine the measurement matrix corresponding to the analyzer, the plurality of different light intensity images obtained by the polarization imaging system are further converted to obtain a more accurate Mueller matrix. Subsequently, the Mueller matrix and the related polarization characteristics reflected thereby are comprehensively analyzed by using deep learning technology, so that more reliable target detection results can be quickly obtained with a significant reduction in manual intervention.

[0057] Figure 1 is an optional structural schematic diagram of a polarization imaging system provided by the embodiments of the present application, which includes a light source 101, a collimating lens 102, a polarizer 103, a non-polarized light splitting prism 104, a stage 105, an imaging lens 106, an analyzer 107, a relay lens 108 and a camera 109; wherein the imaging lens 106 preferably adopts a microscope objective, and the relay lens 108 preferably adopts a barrel lens.

[0058] In a specific implementation, a reflective imaging light path is formed by the light source 101, the collimating lens 102, the polarizer 103, the non-polarizing beam splitter prism 104, the stage 105, the imaging lens 106, the analyzer 107, the relay lens 108, and the camera 109. When a sample is placed on the stage 105, the sample can be a transparent sample or a non-transparent sample. The light emitted by the light source 101 forms a collimated light beam via the collimating lens 102. The light emitted by the light source 101 can be high-brightness quasi-monochromatic light. The collimated light beam forms polarized light via the polarizer 103. The polarized light is normally incident on the half-transmission half-reflection film in the non-polarizing beam splitter prism 104 to form 90-degree reflected light. The 90-degree reflected light is normally incident on the sample placed on the stage 105 via the imaging lens 106 to generate sample reflected light. The sample reflected light is normally incident on the half-transmission half-reflection film in the non-polarizing beam splitter prism 104 via the imaging lens 106 to form transmitted light. After the transmitted light passes through the analyzer 107, an image is formed on the camera 109 via the relay lens 108. It can be understood that the normal incidence operation refers to the light being normally incident on the plane of the component.

[0059] By integrating the polarizer and the analyzer in the polarization imaging system to modulate the polarization state, the polarization imaging system can more efficiently and flexibly obtain a plurality of different light intensity images corresponding to a plurality of different polarization directions when imaging a biological sample to be measured.

[0060] In some embodiments, the polarizer 103 includes a first linear polarizer, a first liquid crystal variable phase retarder, and a second liquid crystal variable phase retarder arranged along the direction of the light path. The arrangement direction of the liquid crystal molecules in the first liquid crystal variable phase retarder is at a 45-degree angle with the polarization direction of the first linear polarizer. The arrangement direction of the liquid crystal molecules in the second liquid crystal variable phase retarder is parallel to the polarization direction of the first linear polarizer, i.e., the arrangement direction of the liquid crystal molecules in the second liquid crystal variable phase retarder is at a 0-degree angle with the polarization direction of the first linear polarizer. In actual application, when the polarizer 103 receives the collimated light beam output by the collimating lens 102, the collimated light beam forms linearly polarized light via the first linear polarizer. The linearly polarized light changes its polarization direction or polarization state via the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder in sequence to form the polarized light.

[0061] In some embodiments, the polarizer 107 comprises a third liquid crystal variable phase retarder, a fourth liquid crystal variable phase retarder and a second linear polarizer arranged along the light path direction, the arrangement direction of the liquid crystal molecules contained in the third liquid crystal variable phase retarder is parallel to the polarization direction of the second linear polarizer, i.e. the arrangement direction of the liquid crystal molecules contained in the third liquid crystal variable phase retarder is parallel to the polarization direction of the second linear polarizer at an angle of 0 degrees, the arrangement direction of the liquid crystal molecules contained in the fourth liquid crystal variable phase retarder is parallel to the polarization direction of the second linear polarizer at an angle of 45 degrees, and the polarization direction of the second linear polarizer is parallel to the polarization direction of the first linear polarizer, i.e. the polarization direction of the second linear polarizer is parallel to the polarization direction of the first linear polarizer at an angle of 0 degrees; in actual application, when the polarizer 107 receives the transmitted light output by the non-polarizing beam splitter prism 104, the transmitted light is polarized in turn by the third liquid crystal variable phase retarder, the fourth liquid crystal variable phase retarder and the second linear polarizer.

[0062] It should be noted that the first liquid crystal variable phase retarder, the second liquid crystal variable phase retarder, the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder are the most common nematic liquid crystal variable phase retarders, which are adjusted by setting the arrangement direction of the liquid crystal molecules inside to adapt to any polarization state; and the modulation of different polarization states can be realized by specifically driving each liquid crystal variable phase retarder contained in the polarizer 103 and the polarizer 107 in an electrically controlled manner, without manually or configuring a stepping motor to adjust the angle of the polarizer 103 and the polarizer 107, which provides strong technical support for high-speed polarization imaging and is also conducive to improving imaging quality.

[0063] In this application, the polarizer 103 and the polarizer 107 are not limited to being built by linear polarizers and liquid crystal variable phase retarders with two different liquid crystal arrangement directions, but can also be built by components such as rotatable polarizers, half-wave plates, quarter-wave plates and photoelastic modulators.

[0064] In some embodiments, the polarization imaging system can further comprise a first light source 110, a first collimating lens 111 and a first polarizer 112, as shown in Figure 1 The first light source 110, the first collimating lens 111, the first polarizer 112, the object table 105, the imaging lens 106, the non-polarizing beam splitter prism 104, the polarizer 107, the relay lens 108 and the camera 109 constitute a transmission type imaging light path; it should be noted that the internal structure and implementation principle of the first polarizer 112 are the same as those of the polarizer 103, which will not be described here.

[0065] In a specific implementation, when a transparent sample is placed on the stage 105, the light emitted by the first light source 110 forms a first collimated light beam via the first collimating lens 111, the light emitted by the first light source 110 can be high-brightness quasi-monochromatic light, the first collimated light beam forms first polarized light via the first polarizer 112, the first polarized light is normally incident to the transparent sample placed on the stage 105 to generate sample transmission light, the sample transmission light is normally incident to the half-transmission half-reflection film in the non-polarizing beam splitter prism 104 via the imaging lens 106 to form first transmission light, and the first transmission light enters the analyzer 107 for analysis and then forms an image on the camera 109 via the relay lens 108.

[0066] Optionally, the 90-degree reflected light or the first polarized light is preferentially passed through a ground glass before being normally incident to the stage 105 to eliminate part of the interference.

[0067] By arranging the reflective imaging light path and the transmissive imaging light path in the polarized imaging system, the imaging light path can be selected by the technician according to the properties of the sample, so that the polarized imaging system can be flexibly adapted to different measurement requirements, that is, the application range of the polarized imaging system can be expanded.

[0068] In some embodiments, the polarized imaging system can further include an external control device (not labeled in Figure 1 The external control device is connected with the polarizer 103, the first polarizer 112, the stage 105, the analyzer 107 and the camera 109 respectively, and is used to at least realize the following functions: controlling the polarized imaging system to image the biological sample to be measured to obtain a measured light intensity image matrix; combining the given measurement matrix corresponding to the polarizer included in the polarized imaging system, calibrating the analyzer included in the polarized imaging system by using a standard sample to obtain a measurement matrix corresponding to the analyzer; converting the measured light intensity image matrix according to the given measurement matrix corresponding to the polarizer and the measurement matrix corresponding to the analyzer to obtain a measured Mueller matrix; determining a polarized image set and a polarized feature image set according to the measured Mueller matrix; processing the polarized image set and the polarized feature image set by a target detection model to obtain a biological target detection result.

[0069] In the process of controlling the polarization imaging system to image the biological sample to be tested, the external control device needs to at least complete the following tasks: first, according to the attributes of the biological sample to be tested input by the technician, the reflection imaging light path or the transmission imaging light path is selected, and in general, the reflection imaging light path with wider application range is preferred; second, the objective table 105 is adjusted so that the biological sample to be tested can be clearly imaged on the target surface of the camera 109; third, the driving voltage of each liquid crystal variable phase retarder contained in the polarizer 103 (or the first polarizer 112) and the analyzer 107 is adjusted to receive the corresponding light intensity images under different polarization state combinations collected by the camera 109.

[0070] Figure 2 is an optional flowchart of a biological sample detection method provided by the embodiment of the present application, mainly applied to the polarization imaging system described above, Figure 2 The method in the above embodiment can include but is not limited to steps S201 to S205:

[0071] Step S201, controlling the polarization imaging system to image the biological sample to be tested to obtain a corresponding biological sample to be tested light intensity image matrix.

[0072] In this step, by selecting the reflection imaging light path or the transmission imaging light path provided in the polarization imaging system according to the attributes of the biological sample to be tested: when the biological sample to be tested belongs to a transparent sample, the reflection imaging light path or the transmission imaging light path can be used for imaging; when the biological sample to be tested belongs to a non-transparent sample, only the reflection imaging light path can be used for imaging.

[0073] Step S202, combining the given measurement matrix corresponding to the polarizer, calibrating the analyzer contained in the polarization imaging system by using a standard sample to obtain a measurement matrix corresponding to the analyzer.

[0074] The given measurement matrix corresponding to the polarizer can be understood as the Mueller matrix of the polarizer, which is used to describe how the polarizer converts non-polarized light or partially polarized light into light with a specific polarization state; the measurement matrix corresponding to the analyzer can be understood as the Mueller matrix of the analyzer, which is used to assist the analyzer in analyzing the state of the polarized light processed by the polarizer.

[0075] Step S203, converting the biological sample to be tested light intensity image matrix according to the given measurement matrix corresponding to the polarizer and the measurement matrix corresponding to the analyzer to obtain a corresponding biological sample to be tested Mueller matrix.

[0076] Step S204, determining the polarization image set and the polarization feature image set according to the to-be-tested Mueller matrix.

[0077] Step S205, processing the polarization image set and the polarization feature image set by using the target detection model to obtain a biological target detection result.

[0078] The steps S201 to S205 shown in the embodiments of the present application can generate a more accurate Mueller matrix in combination with the device calibration method, and then use deep learning technology to comprehensively analyze the Mueller matrix and the related polarization features reflected thereby to quickly obtain a more reliable target detection result.

[0079] In some embodiments, the above step S201 can include but is not limited to steps S301 to S302:

[0080] Step S301, determining a plurality of combined polarization states corresponding to the polarization imaging system according to a plurality of different first polarization states corresponding to the polarizer and a plurality of different second polarization states corresponding to the analyzer.

[0081] In this step, when the polarizer is allowed to work in N polarization states and the analyzer is allowed to work in M polarization states, N and M are both positive integers greater than 1, then the polarization imaging system is allowed to work in N x M combined polarization states, wherein each combined polarization state includes a single first polarization state corresponding to the polarizer and a single second polarization state corresponding to the analyzer, and the single first polarization state corresponding to the polarizer and the single second polarization state corresponding to the analyzer can be the same.

[0082] Exemplarily, the plurality of different first polarization states corresponding to the polarizer include horizontal linear polarization state, vertical linear polarization state, 135° linear polarization state, 45° linear polarization state, right circular polarization state and left circular polarization state, and the plurality of different second polarization states corresponding to the analyzer also include horizontal linear polarization state, vertical linear polarization state, 135° linear polarization state, 45° linear polarization state, right circular polarization state and left circular polarization state, and then the plurality of combined polarization states corresponding to the polarization imaging system include H-H, H-V, H-P, H-M, H-R, H-L, V-H, V-V, V-P, V-M, V-R, V-L, P-H, P-V, P-P, P-M, P-R, P-L, M-H, M-V, M-P, M-M, M-R, M-L, R-H, R-V, R-P, R-M, R-R, R-L, L-H, L-V, L-P, L-M, L-R and L-L; wherein the left side of the horizontal line represents the first polarization state corresponding to the polarizer, the right side of the horizontal line represents the second polarization state corresponding to the analyzer, H represents horizontal linear polarization state, V represents vertical linear polarization state, P represents 135° linear polarization state, M represents 45° linear polarization state, R represents right circular polarization state, and L represents left circular polarization state.

[0083] In step S302, the polarization imaging system is controlled to image the biological sample to be measured according to the plurality of combined polarization states corresponding to the polarization imaging system, and a plurality of corresponding images of light intensity to be measured are obtained to form an image matrix of light intensity to be measured.

[0084] In this step, the polarization imaging system is controlled to work in the i th combined polarization state, and the biological sample to be measured is imaged to obtain the i th image of light intensity to be measured, i = 1, 2, …, N × M; according to this embodiment, N × M imaging and collection are performed, and then the N × M images of light intensity to be measured collected are combined to form the image matrix of light intensity to be measured.

[0085] The steps S301 to S302 shown in the embodiments of the present application adjust the first polarization state corresponding to the polarizer and the second polarization state corresponding to the analyzer, so that the polarization imaging system performs diversified imaging on the biological sample to be measured, which is beneficial to the subsequent calculation of the measured Mueller matrix that can cover more structural information about the biological sample to be measured.

[0086] In step S302 of some embodiments, taking any one combined polarization state as an example, the combined polarization state includes the first polarization state corresponding to the polarizer and the second polarization state corresponding to the analyzer, the polarization imaging system is controlled to work in the combined polarization state, and the biological sample to be measured is imaged to obtain the corresponding image of light intensity to be measured, and the corresponding implementation process can include but is not limited to steps S401 to S405:

[0087] Step S401, according to the first polarization state corresponding to the polarizer, determine the phase retardation required to be reached by the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder contained in the polarizer.

[0088] In this step, the phase retardation corresponding to the polarizer can be obtained by directly querying the first data statistical table, the first data statistical table is used to record the phase retardation required to be reached by all liquid crystal variable phase retarders contained in the polarizer when the polarizer works in different polarization states, the first data statistical table is prepared by the technician according to his own experience, please refer to table 1, the polarizer and the analyzer are collectively referred to as the polarizer, the first liquid crystal variable phase retarder contained in the polarizer and the fourth liquid crystal variable phase retarder contained in the analyzer are collectively referred to as 45° orientation liquid crystal variable phase retarder, the second liquid crystal variable phase retarder contained in the polarizer and the third liquid crystal variable phase retarder contained in the analyzer are collectively referred to as 0° orientation liquid crystal variable phase retarder.

[0089] Table 1 first data statistical table

[0090]

[0091] Step S402, according to the second polarization state corresponding to the analyzer, determine the phase retardation required to be reached by the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder contained in the analyzer.

[0092] In this step, the phase retardation corresponding to the analyzer can also be obtained by directly querying the first data statistical table.

[0093] Step S403, according to the phase retardation required to be reached by the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder contained in the polarizer, adjust the driving voltage of the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder.

[0094] In this step, the driving voltage corresponding to the polarizer can be obtained by directly querying the second data statistical table, the second data statistical table is used to record the driving voltage required by each liquid crystal variable phase retarder (whether it is 45° orientation liquid crystal variable phase retarder or 0° orientation liquid crystal variable phase retarder) contained in the polarizer when the liquid crystal variable phase retarder reaches different phase retardation, the second data statistical table is prepared by the technician through pre-experiment, please refer to table 2.

[0095] Table 2 second data statistical table

[0096] Phase delay amount Drive voltage π / 2 3.12V π 2.6V 2π 3.64V

[0097] Step S404, according to the phase retardation amount required to be reached by the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder contained in the analyser, adjusting the driving voltage of the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder.

[0098] In this step, the driving voltage corresponding to the analyser can also be obtained by directly querying the second data statistical table.

[0099] Step S405, when the polarizer works in the first polarization state and the analyser works in the second polarization state, controlling the polarization imaging system to image the biological sample to be measured to obtain the corresponding measured light intensity image in the combined polarization state.

[0100] It should be noted that the phase retardation amount required to be reached by all liquid crystal variable phase retarders contained in the polarizer and the analyser can be determined first, and then the driving voltage of all liquid crystal variable phase retarders contained in the polarizer and the analyser is adjusted, or the phase retardation amount required to be reached by all liquid crystal variable phase retarders contained in the polarizer is determined first and the driving voltage is adjusted, and then the phase retardation amount required to be reached by all liquid crystal variable phase retarders contained in the analyser is determined and the driving voltage is adjusted, or the phase retardation amount required to be reached by all liquid crystal variable phase retarders contained in the analyser is determined first and the driving voltage is adjusted, and then the phase retardation amount required to be reached by all liquid crystal variable phase retarders contained in the analyser is determined and the driving voltage is adjusted, which is not limited in the present application.

[0101] The steps S401 to S405 shown in the embodiments of the present application adjust the driving voltage of each liquid crystal variable phase retarder contained in the polarizer and the analyser to realize the modulation of different polarization states, without manually or configuring a stepping motor to adjust the angle of the polarizer and the analyser, and the speed of polarization imaging can be improved by this electric control method.

[0102] In some embodiments, the source of the second data statistical table is as follows:

[0103] An experimental light path is built, which includes a second light source, a 0° polarizer, a 90° polarizer and a spectrometer, a liquid crystal variable phase retarder is placed between the 0° polarizer and the 90° polarizer, the liquid crystal variable phase retarder can be a 45° oriented liquid crystal variable phase retarder or a 0° oriented liquid crystal variable phase retarder, and the arrangement direction of the liquid crystal molecules contained in the liquid crystal variable phase retarder is at an angle of 45 degrees with the transmission axis of the 0° polarizer, and the arrangement direction of the liquid crystal molecules contained in the liquid crystal variable phase retarder is at an angle of 45 degrees with the transmission axis of the 90° polarizer; in the specific implementation process, the light emitted by the second light source is sequentially processed by the 0° polarizer, the liquid crystal variable phase retarder and the 90° polarizer, and then enters the spectrometer for light intensity measurement;

[0104] By applying different driving voltages to the liquid crystal variable phase retarder, the spectrometer measures different light intensities, and finally the first relationship between light intensity and driving voltage is generated by data collection and curve fitting, and the second relationship between phase retardation and light intensity is obtained in advance, the third relationship between phase retardation and driving voltage is obtained by mathematical conversion of the first relationship and the second relationship, and finally the required phase retardation of the liquid crystal variable phase retarder is substituted into the third relationship, the corresponding driving voltage of the liquid crystal variable phase retarder can be solved; wherein the second relationship is:

[0105]

[0106] In the formula, is the phase retardation, and T is the light intensity.

[0107] In the prior art, the Mueller matrix is usually determined by combining all the measured light intensity images contained in the measured light intensity image matrix after obtaining the measured light intensity image matrix, and the corresponding implementation mode can be described by the following expression:

[0108]

[0109] In the formula, M0 is the Mueller matrix, YZ is a single measured light intensity image contained in the measured light intensity image matrix, which can be understood as a measured light intensity image obtained by imaging a measured biological sample by a polarization imaging system when a polarizer works in a first polarization state Y and a polarizer works in a second polarization state Z, Y=H, V, L, P, M, R, Z=H, V, L, P, M, R.

[0110] However, since polarization imaging systems are easily affected by environmental factors, component installation errors, and the quality of the components themselves during operation, the imaging quality is poor, making the Mueller matrix obtained directly through image calculation inaccurate. Therefore, it is proposed to combine equipment calibration methods to generate a more accurate Mueller matrix, as detailed in steps S202 and S203 above.

[0111] In some embodiments, step S202 may include, but is not limited to, steps S501 to S502:

[0112] Step S501: Control the polarization imaging system to image the standard sample and obtain a standard light intensity image matrix; wherein, the standard sample is preferably air, and the given standard Mueller matrix corresponding to air is generally a 4×4 identity matrix. The entire imaging acquisition process is similar to step S201 above, and will not be described again here.

[0113] Step S502: Determine the measurement matrix corresponding to the analyzer based on the given measurement matrix corresponding to the polarizer, the given standard Mueller matrix corresponding to the standard sample, and the standard light intensity image matrix.

[0114] In this step, the first thing to understand is the basic imaging principle of this polarization imaging system: natural light After being modulated multiple times by different polarization states by the polarizer, the incident light illuminates the sample on the stage. The outgoing light is then modulated multiple times by the analyzer to obtain multiple light intensity images to form a light intensity image matrix. The corresponding implementation method can be described by the following first expression:

[0115]

[0116] In the formula, I0 is the light intensity image matrix, A0 is the initial measurement matrix corresponding to the analyzer, M0 is the Mueller matrix corresponding to the sample, P0 is the initial measurement matrix corresponding to the polarizer, and T represents the matrix transpose symbol.

[0117] Substituting the given measurement matrix corresponding to the polarizer, the given standard Mueller matrix corresponding to the standard sample, and the standard light intensity image matrix corresponding to the standard sample into the first expression above for transformation, the measurement matrix corresponding to the analyzer can be solved as follows:

[0118]

[0119] In the formula, A1 is the measurement matrix corresponding to the analyzer, M1 is the given standard Mueller matrix corresponding to the standard sample, P1 is the given measurement matrix corresponding to the polarizer, I1 is the standard light intensity image matrix corresponding to the standard sample, and -1 represents the matrix inversion symbol.

[0120] In step S203 of some embodiments, the given measurement matrix corresponding to the polarizer, the measurement matrix corresponding to the polarizer, and the to-be-measured light intensity image matrix corresponding to the to-be-measured biological sample are substituted into the above-mentioned first expression for conversion, and the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample can be solved as follows:

[0121]

[0122] In the formula, M2 is the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample, I2 is the to-be-measured light intensity image matrix corresponding to the to-be-measured biological sample, M ij is an element contained in the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample, i = 1, 2, 3, 4, j = 1, 2, 3, 4, and it can be seen that the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample contains 16 elements.

[0123] In some embodiments, the above-mentioned step S204 can include but is not limited to steps S601 to S605:

[0124] In step S601, the value of the element contained in the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample and falling in the first row and the first column is pseudo-color imaged to obtain an intensity image.

[0125] In this step, the value of the element M 11 contained in the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample is converted into the intensity image represented by a specific color through a first pseudo-color mapping bar, and the first pseudo-color mapping bar represents a transition from black to white.

[0126] In step S602, the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample is normalized to obtain a first to-be-measured Mueller matrix.

[0127] In this step, the value of all elements contained in the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample is divided by the value of the element contained in the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample and falling in the first row and the first column (i.e., the value of the element M 11 ), so as to complete the normalization operation, which facilitates subsequent extraction of the related polarization information corresponding to the to-be-measured biological sample. In this implementation process, the normalization formula used is as follows:

[0128]

[0129] In the formula, M3 is the first to-be-measured Mueller matrix, i.e., the normalized result of the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample, m ij is the normalized value of the element contained in the first to-be-measured Mueller matrix.

[0130] Step S603, pseudo-color imaging is performed on the normalized values of the elements contained in the first to-be-measured Mueller matrix to obtain a plurality of polarization images corresponding to the normalized values of the elements to form a polarization image set.

[0131] In this step, for the normalized value of any element contained in the first to-be-measured Mueller matrix, the normalized value of the element is converted into a polarization image represented by a specific color through a second pseudo-color mapping bar, and the second pseudo-color mapping bar represents a transition from blue to red.

[0132] Step S604, combined analysis is performed on the normalized values of the elements contained in the first to-be-measured Mueller matrix to obtain the values of a plurality of polarization characteristics.

[0133] In this step, the plurality of polarization characteristics obtained by analyzing the first to-be-measured Mueller matrix can include but are not limited to a first type of anisotropy angle orientation, a second type of anisotropy angle orientation, a normalized anisotropy, an extinction degree, and a polarization degree. The calculation formulas of the polarization characteristics are as follows:

[0134]

[0135]

[0136] In the formula, X3 is the first type of anisotropy angle orientation, X is the second type of anisotropy angle orientation, D is the extinction degree, P is the polarization degree, A is the normalized anisotropy, and b and t1 are reference parameters set for convenient description.

[0137] Step S605, pseudo-color imaging is performed on the values of the plurality of polarization characteristics obtained by analysis to obtain a plurality of polarization characteristic images corresponding to the values of the plurality of polarization characteristics, and then the intensity image is combined to form a polarization characteristic image set.

[0138] In this step, for the value of any polarization characteristic obtained by analysis, the value of the polarization characteristic is converted into a polarization characteristic image represented by a specific color through the second pseudo-color mapping bar.

[0139] The steps S601 to S605 shown in the embodiments of the present application decompose the to-be-measured Mueller matrix corresponding to the to-be-measured biological sample after normalization to quickly extract key polarization characteristics, and then convert the to-be-measured Mueller matrix after normalization and the key polarization characteristics into image forms to facilitate subsequent input into a deep learning model, which is beneficial to enhancing the multidimensionality and depth of model analysis.

[0140] In step S205 of some embodiments, the target detection model is trained based on an improved YOLOv8 (You Only Look Once v8) model. Since the original YOLOv8 model is not optimized for specific target objects, it cannot fully exploit and utilize the unique morphological features of target objects, such as shape, texture, edge details, etc., resulting in low accuracy of the final detection results. Therefore, the original YOLOv8 model is improved, and the improved YOLOv8 model includes an improved backbone network, an improved neck network, and an original head network connected in sequence. The structure of each network is described below.

[0141] Specifically, the improved backbone network is constructed based on an improved CSPDarknet (Cross Stage Partial Darknet) framework. The original CSPDarknet framework is composed of multiple convolutional layers and multiple residual blocks connected alternately. The improved CSPDarknet framework is generated by introducing a BSAM (Bi-Scale Attention Module) into each residual block in the original CSPDarknet framework. The improved backbone network can efficiently extract key features from input images while reducing network parameter quantity and computational complexity.

[0142] Taking any one residual block as an example, the improvement of the residual block is completed by connecting a BSAM at the output end of the residual block. The BSAM includes a first convolutional layer, a BSAM mechanism layer, and a weighting layer. The first convolutional layer is used to process the output of the residual block to obtain first feature information. The BSAM mechanism layer is used to process the output of the residual block to obtain second feature information. The weighting layer is used to combine the first feature information and the second feature information by addition operation or concatenation and then output.

[0143] The introduction of the BSAM enables the model to pay more attention to the feature differences between small and large targets when processing images, thereby effectively improving the model's recognition ability for target objects of various sizes. In the field of biological sample image analysis, the BSAM can help the model more accurately distinguish biological samples of different sizes and materials, even in low-light or complex background conditions, while maintaining a high recognition rate.

[0144] Specifically, the improved neck network includes a spatial pyramid pooling enhanced with local attention network (SPPELAN), a feature pyramid network (FPN), and a path aggregation network (PAN) connected in sequence. By combining spatial pyramid pooling (SPP) and local attention mechanism in the spatial pyramid pooling enhanced with local attention network, fixed-size feature maps can be extracted in windows of different scales, and spatial information and scale invariance can be effectively preserved. By combining the feature pyramid network and the path aggregation network, different scales of features can be fused and encoded by bottom-up and top-down paths. The improved neck network can enhance the detection capability of the model for targets of different scales, so that the model can more accurately process targets of various sizes.

[0145] By introducing the spatial pyramid pooling enhanced with local attention network, the model can perform feature analysis at different levels from local to global, thereby enhancing the control ability of fine-grained features. In particular, when processing high-density biological sample images, such as densely distributed microsphere individuals in water samples, the spatial pyramid pooling enhanced with local attention network can accurately identify and separate multiple microsphere individuals that are closely adjacent by using the local attention mechanism.

[0146] Specifically, the original head network refers to the head network included in the original YOLOv8 model. The original head network includes multiple convolutional layers and is mainly responsible for mapping the features output by the improved neck network to specific target detection results using an adaptive anchor box generation strategy. The target detection results include an intensity image labeled with relevant detection information, i.e., the target bounding box, the position information of the target bounding box, the category information of the target object contained in the target bounding box, and the category prediction probability are labeled on the intensity image.

[0147] In some embodiments, the above step S205 can include, but is not limited to, steps S701-S702:

[0148] Step S701, pre-processing the polarization image set and the polarization feature image set converted by the Mueller matrix corresponding to the biological sample to be tested to obtain a corresponding first polarization image set and a first polarization feature image set.

[0149] In this step, the numerical stability can be improved by performing pixel value normalization on each polarized image included in the polarized image set and each polarized feature image included in the polarized feature image set, or the key biological morphological features such as edges and textures in the images can be strengthened by adjusting the visual parameters, including at least one of the contrast parameter, the brightness parameter, the sharpness parameter, etc. The image preprocessing method is not limited in this application. Only basic pixel value normalization can be performed, or visual parameter adjustment can be continued.

[0150] In step S702, the first polarized image set and the first polarized feature image set are input into the target detection model for processing, which specifically includes: inputting the first polarized image set and the first polarized feature image set into the improved backbone network for feature extraction to obtain key visual feature information; inputting the key visual feature information into the improved neck network to fuse and encode features of different scales to obtain visual coding feature information; and inputting the visual coding feature information into the original head network for feature mapping to obtain a biological target detection result.

[0151] In this application, the improved YOLOv8 model is trained to obtain the target detection model, and the corresponding implementation process can include but is not limited to the following steps:

[0152] A plurality of training samples corresponding to a plurality of measured biological samples are obtained, each measured biological sample carrying a biological individual of a known class, each training sample corresponding to an analyzed polarized image set and an analyzed polarized feature image set, and each training sample corresponding to a biological individual class label;

[0153] The plurality of training samples are preprocessed and data enhanced, and the corresponding preprocessing operations include basic image pixel value normalization and further image visual parameter adjustment. The corresponding data enhancement operations include image rotation, scaling, cropping, and flipping, etc. to adapt to actual application scenarios such as biological samples carrying biological individuals of different sizes and the position changes of biological individuals carried by biological samples during imaging processing, thereby obtaining a plurality of training samples;

[0154] The plurality of training samples are divided into a training set, a validation set, and a test set according to a ratio of 8:1:1, and the training samples included in the training set, the validation set, and the test set are not repeated;

[0155] The improved YOLOv8 model is iteratively trained multiple times using the training set, with an initial learning rate of 0.001 and a training batch size of 32. In each iteration, the output prediction results are calculated by forward propagation, and the Focal Loss function is used as the loss function to measure the error between the prediction results and the true labels. Then, the model parameters are updated by the Ranger optimizer to minimize the loss function. After each iteration, the hyperparameters of the improved YOLOv8 model are adjusted using the validation set to prevent overfitting on the training set. After each iteration, the performance of the current improved YOLOv8 model is evaluated using the test set. The model detection performance can be quantified by existing evaluation indicators such as accuracy, recall, F1 score, and mean average precision (mAP). Thus, the final target detection model is obtained.

[0156] The biological sample detection method provided by the embodiments of the present application further converts a plurality of different light intensity images obtained by the polarization imaging system to obtain more accurate Mueller matrices by combining the given measurement matrix corresponding to the polarizer and using a standard sample device calibration method to determine the measurement matrix corresponding to the analyzer. Then, the Mueller matrices and the related polarization features reflected thereby are comprehensively analyzed using deep learning technology, so that more reliable target detection results can be quickly obtained with significantly reduced manual intervention.

[0157] Next, the scheme provided by the embodiments of the present application will be further described in combination with specific application examples, which specifically include the following operation steps:

[0158] The polarization imaging system is controlled to image a pre-prepared biological sample carrying microsphere individuals of an unknown category, to obtain a light intensity image matrix. A standard sample is used to calibrate an analyzer included in the polarization imaging system in combination with a given measurement matrix corresponding to a polarizer included in the polarization imaging system, to obtain a measurement matrix corresponding to the analyzer. The light intensity image matrix is converted according to the given measurement matrix corresponding to the polarizer and the measurement matrix corresponding to the analyzer, to obtain a microsphere Mueller matrix. The values of elements in the microsphere Mueller matrix that fall in the first row and the first column at the same time are pseudo-color imaged, to obtain an intensity image. The microsphere Mueller matrix is normalized, to obtain a first microsphere Mueller matrix. The first microsphere Mueller matrix is pseudo-color imaged, to obtain a microsphere polarization image set as shown in Figure 3 The first microsphere Mueller matrix is converted and analyzed to obtain the values of a plurality of microsphere polarization features and further complete pseudo-color imaging, to form a microsphere polarization feature image set together with the intensity image as shown in Figure 4 The target detection model is used to process the microsphere polarization image set and the microsphere polarization feature image set, to obtain a target detection result as shown inFigure 5 The microsphere detection result shown in the table indicates that PS represents the category to which the microsphere in the bounding box is predicted by the model, PS is a pre-set category code, and the number after PS represents the probability value of the microsphere in the bounding box being predicted by the model to belong to the category PS.

[0159] The embodiments of the present application also provide an electronic device, which includes a memory and a processor. The memory stores a computer program, and the processor implements the biological sample detection method described above when executing the computer program. The electronic device can include a tablet computer, a vehicle-mounted computer, or any smart terminal.

[0160] It can be understood that the contents in the method embodiments described above are applicable to the device embodiments, the device embodiments specifically implement the same functions as the method embodiments, and achieve the same beneficial effects as the method embodiments.

[0161] Please refer to Figure 6 , Figure 6 The hardware structure of the electronic device of another embodiment is shown in the figure, which includes:

[0162] The processor 801 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an ASIC (Application Specific Integrated Circuit), or one or more integrated circuits, and is used to execute related programs to implement the technical solutions provided by the embodiments of the present application.

[0163] The memory 802 can be implemented in the form of a ROM (Read-Only Memory), a static storage device, a dynamic storage device, or a RAM (Random Access Memory). The memory 802 can store an operating system and other application programs. When the technical solutions provided by the embodiments of the present application are implemented by software or firmware, the related program codes are stored in the memory 802 and called and executed by the processor 801 to implement the technical solutions provided by the embodiments of the present application.

[0164] The input / output interface 803 is used to realize information input and output.

[0165] The communication interface 804 is used to realize the communication interaction between the device and other devices. The communication can be realized by wired means (such as USB, network cable, etc.), or by wireless means (such as mobile network, WIFI, Bluetooth, etc.).

[0166] A bus 805 is used to transmit information between the various components (e.g., the processor 801, the memory 802, the input / output interface 803, and the communication interface 804) of the device.

[0167] The processor 801, the memory 802, the input / output interface 803, and the communication interface 804 are communicatively connected to each other within the device through the bus 805.

[0168] The computer readable storage medium stores a computer program, and the computer program is executed by the processor to implement the biological sample detection method.

[0169] It can be understood that the contents in the above method embodiments are applicable to the storage medium embodiments, the storage medium embodiments specifically implement the functions of the above method embodiments, and achieve the same beneficial effects as the above method embodiments.

[0170] The memory, as a non-transitory computer readable storage medium, can be used to store non-transitory software programs and non-transitory computer executable programs. In addition, the memory can include a high-speed random access memory, and can also include a non-transitory memory, such as at least one magnetic disk storage device, a flash memory device, or other non-transitory solid-state memory device. In some embodiments, the memory can optionally include a memory remotely arranged relative to the processor, and these remote memories can be connected to the processor through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0171] The embodiments described in the embodiments of the present application are used to more clearly illustrate the technical solutions of the embodiments of the present application, and do not constitute a limitation on the technical solutions provided by the embodiments of the present application. Those skilled in the art can know that, with the evolution of technology and the appearance of new application scenarios, the technical solutions provided by the embodiments of the present application are also applicable to similar technical problems.

[0172] Those skilled in the art can understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of the present application, and can include more or fewer steps than the figures shown, or combine certain steps, or different steps.

[0173] The system embodiments described above are only schematic, and the units described as separate components can or can not be physically separate, that is, can be located in one place, or can be distributed on multiple network units. According to actual needs, part or all of the modules can be selected to achieve the purpose of the embodiments of the present application.

[0174] Those skilled in the art can understand that all or some of the steps in the method disclosed above, the function modules / units in the system and the device can be implemented as software, firmware, hardware or appropriate combination thereof.

[0175] The terms "first", "second", "third", "fourth" etc. (if any) in the description of the application and in the claims that follow are used for distinguishing between similar elements and not necessarily for describing a sequential or chronological order. It is to be understood that the use of these terms herein is to be construed to cover the embodiments of the application whether or not the embodiments are described using the same term. Furthermore, the terms "comprise", "comprising", "include", "including", and "has", "having" and variants thereof are to be construed in a non-exclusive manner when used in this description and in the claims that follow. For example, when used in the context of a process, method, system, product or apparatus, the term "comprising" means that the process, method, system, product or apparatus includes the recited steps or units, but can also include additional steps or units not specifically recited.

[0176] It should be understood that, in the present application, "at least one" means one or more, and "multiple" means two or more. "And / or" is used to describe the relationship between associated objects, which means that there can be three relationships, for example, "A and / or B" can mean that there are three cases: only A, only B, and A and B at the same time, where A and B can be singular or plural. The character " / " generally represents an "or" relationship between the associated objects. "At least one of the following" or similar expressions means any combination of these items, including any combination of single or multiple items. For example, at least one of a, b or c can mean a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be singular or plural.

[0177] In several embodiments provided in the present application, it should be understood that the disclosed system and method can be implemented in other ways. For example, the above-described system embodiments are only illustrative, for example, the division of the above-mentioned units is only a logical function division, and actual implementation can have another division manner, for example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the coupling or direct coupling or communication connection between the displayed or discussed each other can be through some interface, indirect coupling or communication connection between the system or unit, which can be electrical, mechanical or other forms.

[0178] The units described as separate components above can or can not be physically separate, and the components shown as units can or can not be physical units, that is, can be located in one place, or can be distributed to multiple network units. Part or all of the units can be selected according to actual needs to achieve the purpose of the embodiment scheme.

[0179] In addition, each functional unit in each embodiment of the present application can be integrated in one processing unit, or each unit can exist physically, or two or more units can be integrated in one unit. The integrated unit can be realized in the form of hardware or in the form of a software functional unit.

[0180] If the integrated unit is realized in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer readable storage medium. Based on this understanding, the technical scheme of the present application or the part that contributes to the prior art or the whole or part of the technical scheme can be embodied in the form of a software product. The computer software product is stored in a storage medium, including multiple instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method of each embodiment of the present application. The foregoing storage medium includes: a U disk, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk, and various program storage media.

[0181] The preferred embodiments of the embodiments of the present application are described above with reference to the accompanying drawings, but this does not limit the scope of the embodiments of the present application. Any modifications, equivalent replacements and improvements made by those skilled in the art without departing from the scope and essence of the embodiments of the present application shall be within the scope of the embodiments of the present application.

Claims

1. A method of detecting a biological sample, characterized by, The method comprises: controlling a polarization imaging system to image a biological sample to be tested to obtain a corresponding to-be-tested light intensity image matrix of the biological sample to be tested; combining a given measurement matrix corresponding to a polarizer included in the polarization imaging system, calibrating a polarizer included in the polarization imaging system using a standard sample to obtain a measurement matrix corresponding to the polarizer; According to the given measurement matrix corresponding to the polarizer and the measurement matrix corresponding to the polarizer, the to-be-tested light intensity image matrix is converted to obtain a to-be-tested Mueller matrix corresponding to the biological sample to be tested; According to the to-be-tested Mueller matrix, a polarization image set and a polarization feature image set are determined; using a target detection model to process the polarization image set and the polarization feature image set to obtain a biological target detection result; The target detection model is trained based on an improved YOLOv8 model, the improved YOLOv8 model includes an improved main network, an improved neck network and an original head network connected in sequence, the improved main network is built based on an improved CSPDarknet framework, the improved CSPDarknet framework is obtained by introducing a double-scale attention module into each residual block included in the original CSPDarknet framework, and the improved neck network includes a spatial pyramid pooling network based on local attention enhancement, a feature pyramid network and a path aggregation network connected in sequence; the target detection model is used to process the polarization image set and the polarization feature image set to obtain a biological target detection result, which comprises: preprocessing the polarization image set and the polarization feature image set to obtain a corresponding first polarization image set and a first polarization feature image set; input the first polarization image set and the first polarization feature image set into the improved main network for feature extraction to obtain key visual feature information; input the key visual feature information into the improved neck network to fuse and encode features of different scales to obtain visual coding feature information; input the visual coding feature information into the original head network for feature mapping to obtain the biological target detection result.

2. The biological sample detection method according to claim 1, wherein, The control of the polarization imaging system to image the biological sample to be tested to obtain the to-be-tested light intensity image matrix comprises: determining a plurality of different first polarization states corresponding to the polarizer and a plurality of different second polarization states corresponding to the polarizer, and determining a plurality of different first polarization states corresponding to the polarizer and a plurality of different second polarization states corresponding to the polarizer; a plurality of combined polarization states corresponding to the polarization imaging system are determined; controlling the polarization imaging system to image the biological sample to be tested according to the plurality of combined polarization states to obtain a plurality of corresponding to-be-tested light intensity images to form the to-be-tested light intensity image matrix.

3. The biological sample detection method according to claim 2, wherein, The control of the polarization imaging system to image the biological sample to be tested according to the plurality of combined polarization states to obtain a plurality of corresponding to-be-tested light intensity images comprises: for any one of the combined polarization states, the combined polarization state includes a first polarization state corresponding to the polarizer and a second polarization state corresponding to the polarizer; determining phase retardation amounts required to be reached by a first liquid crystal variable phase retarder and a second liquid crystal variable phase retarder comprised by the polarizer according to a first polarization state corresponding to the polarizer; determining phase retardation amounts required to be reached by a third liquid crystal variable phase retarder and a fourth liquid crystal variable phase retarder comprised by the analyzer according to a second polarization state corresponding to the analyzer; adjusting driving voltages of the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder according to the phase retardation amounts required to be reached by the first liquid crystal variable phase retarder and the second liquid crystal variable phase retarder; adjusting driving voltages of the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder according to the phase retardation amounts required to be reached by the third liquid crystal variable phase retarder and the fourth liquid crystal variable phase retarder; controlling the polarization imaging system to image the biological sample to be measured to obtain the light intensity image corresponding to the combined polarization state.

4. The biological sample detection method of claim 1, wherein, calibrating the analyzer comprised by the polarization imaging system by using a standard sample according to a given measurement matrix corresponding to the polarizer comprised by the polarization imaging system to obtain a measurement matrix corresponding to the analyzer comprises: controlling the polarization imaging system to image the standard sample to obtain a standard light intensity image matrix; determining the measurement matrix corresponding to the analyzer according to the given measurement matrix corresponding to the polarizer, a given standard Mueller matrix corresponding to the standard sample and the standard light intensity image matrix.

5. The biological sample detection method of claim 1, wherein, determining a polarization image set and a polarization feature image set according to the measured Mueller matrix comprises: performing pseudo-color imaging on a value of an element in the measured Mueller matrix which falls in a first row and a first column simultaneously to obtain an intensity image; performing normalization processing on the measured Mueller matrix to obtain a first measured Mueller matrix; performing pseudo-color imaging on normalized values of a plurality of elements comprised by the first measured Mueller matrix to obtain a plurality of polarization images corresponding to the plurality of elements to form the polarization image set; performing combined analysis on the normalized values of the plurality of elements to obtain values of a plurality of polarization features; performing pseudo-color imaging on the values of the plurality of polarization features to obtain a plurality of polarization feature images corresponding to the values of the plurality of polarization features to form the polarization feature image set together with the intensity image.

6. A polarimetric imaging system characterized by, The polarization imaging system comprises a light source, a collimating lens, a polarizer, a stage, an imaging lens, a non-polarization beam splitter prism, an analyzer, a relay lens, a camera and an external control device; the external control device is connected with the polarizer, the stage, the analyzer and the camera respectively, and is used to implement the biological sample detection method in any one of claims 1 to 5. When a sample is placed on the sample stage, light emitted by the light source forms a collimated light beam via the collimating lens, the collimated light beam forms polarized light via the polarizer, the polarized light is normally incident to the half-mirror in the non-polarizing beam splitter prism to form a 90-degree reflected light, the 90-degree reflected light is normally incident to the sample placed on the sample stage via the imaging lens to generate sample reflected light, the sample reflected light is normally incident to the half-mirror in the non-polarizing beam splitter prism via the imaging lens to form transmitted light, and the transmitted light is imaged into the camera via the relay lens after being depolarized by the analyzer.

7. The polarimetric imaging system of claim 6, wherein, The polarizer comprises a first linear polarizer, a first liquid crystal variable phase retarder and a second liquid crystal variable phase retarder arranged along the direction of the light path, and the analyzer comprises a third liquid crystal variable phase retarder, a fourth liquid crystal variable phase retarder and a second linear polarizer arranged along the direction of the light path; The first liquid crystal variable phase retarder comprises liquid crystal molecules arranged in a direction at a 45-degree angle with the polarization direction of the first linear polarizer, and the second liquid crystal variable phase retarder comprises liquid crystal molecules arranged in a direction parallel to the polarization direction of the first linear polarizer; The third liquid crystal variable phase retarder comprises liquid crystal molecules arranged in a direction parallel to the polarization direction of the second linear polarizer, and the fourth liquid crystal variable phase retarder comprises liquid crystal molecules arranged in a direction at a 45-degree angle with the polarization direction of the second linear polarizer; The polarization direction of the first linear polarizer is parallel to the polarization direction of the second linear polarizer.

8. An electronic device, comprising: The electronic device comprises a memory and a processor, the memory stores a computer program, and the processor implements the biological sample detection method of any one of claims 1 to 5 when executing the computer program.

9. A computer-readable storage medium storing a computer program, the computer program comprising instructions that, when executed by a computer, cause the computer to perform the method of any one of claims 1 to 8. The computer program is executed by the processor to implement the biological sample detection method of any one of claims 1 to 5.

Images