Western blot detection method based on western blot interpretoscope

Abstract

The invention provides an immunoblotting detection method based on an immunoblotting interpretoscope, and relates to the technical field of biochemical detection.The immunoblotting detection method comprises the steps that a basic gray level image of a membrane strip is collected, and strip image subareas and spatial position parameters are recognized; performing gray enhancement and noise reduction preprocessing on the film strip image, performing segmentation identification on a strip region, and extracting characteristics such as a strip average gray value, a background average gray value, a strip edge gradient parameter, a gray discrete parameter and a strip area parameter; respectively constructing a strip signal definition index and a strip reaction intensity index, evaluating the strip image quality and the reaction signal intensity, and executing an image quality enhancement and strip signal compensation strategy under an abnormal condition; further, comprehensive interpretation is carried out on the stability of the whole reaction signal of the membrane strip by constructing a comprehensive interpretation index of the immunoblotting, and a re-checking strategy is triggered when necessary. According to the invention, the accuracy and reliability of judging and reading the immunoblotting detection result can be improved.

Description

Technical Field

[0001] This invention relates to the field of biochemical detection technology, specifically to an immunoblotting detection method based on an immunoblotting interpreter. Background Technology

[0002] Immunoblotting is an important detection technique widely used in clinical immunodiagnostics, commonly used for confirmatory detection of antibodies associated with autoimmune diseases, such as antinuclear antibody profiles, anti-neutrophil cytoplasmic antibodies, and other autoantibodies. This technique typically involves immobilizing antigens on a membrane strip, which, after a colorimetric reaction, forms bands of varying positions and intensities. The presence and intensity of these bands are interpreted to achieve qualitative or semi-quantitative analysis of the target antibody. Due to its high specificity and intuitive results, immunoblotting is widely used in clinical immunodiagnostic laboratories.

[0003] Current technologies mostly rely on image scanning with interpreters and depend on a single grayscale parameter or simple threshold for automatic strip identification. However, due to the influence of reaction conditions and environmental factors, actual membrane strip images often suffer from defects such as blurred boundaries, high background noise, and uneven color development. Existing judgment methods do not fully consider the clarity and edge features of the strip images, and are prone to recognition errors when processing low-quality images or weak reaction signals. At the same time, existing processes lack effective automated quality assessment and alert mechanisms for abnormal signals or weak reaction strips, and the test results heavily rely on manual review, which not only increases the workload of routine inspections but also makes it difficult to ensure the objectivity and consistency of the interpretation results and the overall detection efficiency. Summary of the Invention

[0004] The purpose of this invention is to provide an immunoblotting detection method based on an immunoblotting interpreter to solve the problems mentioned in the background art.

[0005] To achieve the above objectives, the present invention provides the following technical solution: The immunoblotting detection method based on an immunoblotting interpreter includes the following steps: Step 1: Automatically locate and scan the immunoblot strips entering the detection area to obtain the basic grayscale image of the strips, and complete the identification of sub-regions of the strip image and extraction of spatial position parameters to construct the basic image dataset for immunoblot detection. Step 2: Enhance and denoise the basic grayscale images of the membrane strips in the basic image dataset for immunoblotting detection, and perform strip region segmentation and connected component identification. Statistically extract the average grayscale value of the strip, the average grayscale value of the background, the gradient parameters of the strip edges, the grayscale discrete parameters of the strip, and the area parameters of the strip. Step 3: Calculate the clarity index of the i-th band signal and compare it with the clarity threshold to determine whether the clarity of the i-th band image signal in the current immunoblot membrane strip meets the clinical immunoblot detection interpretation requirements. If it meets the requirements, generate a clear band feature set; otherwise, execute an image quality enhancement strategy. Step 4: Calculate the band reaction intensity index of the i-th band and compare it with the reaction intensity threshold to determine whether the reaction signal intensity of the i-th band in the current immunoblot membrane strip meets the standard. If it meets the standard, establish an effective reaction band set and integrate the data to form an effective reaction band feature set; if it does not meet the standard, execute the band reaction signal compensation strategy. Step 5: Calculate the immunoblot comprehensive interpretation index and compare it with the comprehensive interpretation threshold to determine whether the overall reaction signal stability of the current immunoblot membrane strip is qualified. If qualified, generate the corresponding immunoblot detection interpretation result; if not qualified, implement the immunoblot detection result stability verification strategy.

[0006] Further, step one includes: S11. Real-time monitoring of the membrane strip imaging status during the immunoblotting process for confirmatory detection of autoimmune antibodies in clinical immunodiagnostic laboratories. By setting a membrane strip positioning guide and an optical positioning sensor at the membrane strip sample inlet channel of the immunoblotting interpreter, the immunoblotting membrane strip entering the detection area is automatically positioned and its position is identified. The time information of the membrane strip entering the detection area and the membrane strip number information are recorded, and the correspondence between the membrane strip sample and the detection data is established. S12. Based on the correspondence between the membrane strip samples and the detection data, the immunoblot membrane strip entering the detection area is scanned line by line by the linear CCD scanning module and the LED linear cold light source illumination system set in the immunoblot interpreter to obtain the original grayscale images of the strip surface area and the background area. The obtained original grayscale images are associated with the corresponding membrane strip sample number to form the basic grayscale image data of the membrane strip. S13. Based on the basic grayscale image data of the membrane strip, according to the distribution characteristics of the color strips in the membrane strip image, the basic grayscale image is initially divided into regions, the pixel matrix data of the strip region is identified and extracted, and the corresponding strip image sub-region is generated according to the identification result. S14. Based on the sub-regions of the strip image, perform spatial localization analysis on each sub-region of the strip image, extract the center coordinates of the strip, the boundary range of the strip, and the width information of the strip to form the spatial location parameters of the strip. S15. Integrate the basic grayscale image data of the membrane strip, the sub-regions of the strip image, and the spatial location parameters of the strip to construct the basic image dataset for immunoblotting detection.

[0007] Furthermore, step two includes: S21. Based on the basic image dataset of immunoblotting detection, image preprocessing is performed on the basic grayscale image data of the membrane strip, and grayscale enhancement processing is performed on the membrane strip image through the adaptive histogram equalization method to improve the grayscale contrast between the strip area and the background area. S22. By using Gaussian filtering to suppress noise in the enhanced image, random noise interference generated during the color development process is reduced, and standard membrane strip image data is formed.

[0008] Furthermore, step two also includes: S23. Based on standard membrane strip image data, an adaptive threshold segmentation method is used to segment the membrane strip image into strip regions and identify the strip regions and background regions; then, a connected component analysis method is used to spatially identify the strip regions and determine the actual range of each strip region. S24. Based on the actual range of each strip region, the grayscale values ​​of the pixels in the strip region are statistically analyzed to obtain the average grayscale value of the strip; and the grayscale values ​​of the pixels in the background region surrounding the strip are statistically analyzed to obtain the average grayscale value of the background. S25. Based on the actual range of each strip region, the Sobel edge detection algorithm is used to perform edge detection on the strip region, and the average gradient of the strip edge is calculated to obtain the strip edge gradient parameters. S26. Based on the actual range of each strip region, calculate the standard deviation of the pixel gray values ​​in the strip region to obtain the strip gray discrete parameters. S27. Based on the actual range of each strip region, obtain the strip area parameter by counting the number of pixels in the strip region.

[0009] Furthermore, step three includes: S31. For each strip, perform signal sharpness evaluation. By calling the average gray value of the i-th strip, the average gray value of the background, the edge gradient parameter, and the gray-level discrete parameter, after dimensionless processing, calculate and obtain the strip signal sharpness index of the i-th strip.

[0010] Furthermore, step three also includes: S32. By setting a sharpness threshold, and comparing the sharpness index of the i-th strip signal with the sharpness threshold, the first evaluation result is obtained, including: When the clarity index of the i-th band is greater than or equal to the clarity threshold, it means that the clarity of the i-th band image signal in the current immunoblot membrane strip meets the clinical immunoblot detection interpretation requirements, and a clear band feature set is generated for continuous monitoring. When the clarity index of the i-th band is less than the clarity threshold, it indicates that the clarity of the i-th band image signal in the current immunoblot membrane does not meet the requirements for clinical immunoblot detection interpretation, and there is a risk of blurred band boundaries or background noise interference. This triggers the first warning instruction and generates the first strategy: perform image quality adjustment, perform local contrast enhancement processing on the current band image sub-region to increase the grayscale difference between the band region and the background region; perform adaptive noise suppression processing on the enhanced band image to reduce background noise interference; recalculate after adjustment until the clarity index of the i-th band is greater than or equal to the clarity threshold.

[0011] Furthermore, step four includes: S41. Based on standard membrane strip image data and background area pixel gray values, gray-scale statistical analysis method is used to perform gray-scale fluctuation analysis on the background area of ​​the entire immunoblot membrane strip. By calculating the standard deviation and mean change ratio of background area pixel gray values, background noise stability is evaluated and background noise stability coefficient is obtained. S42. Based on the set of clear strip features, evaluate the response intensity of each strip in the set of clear strip features. Call the average gray value of the i-th strip, the average gray value of the background, and the strip area parameter. Combined with the background noise stability coefficient, perform dimensionless processing on the feature parameters of each strip and calculate the strip response intensity index of the i-th strip.

[0012] Furthermore, step four also includes: S43. By setting a preset reaction intensity threshold, and comparing the band reaction intensity index of the i-th band with the reaction intensity threshold, the second evaluation result is obtained, including: When the band reaction intensity index of the i-th band is greater than or equal to the reaction intensity threshold, it means that the reaction signal intensity of the i-th band in the current immunoblot membrane strip meets the standard. An effective reaction band set is established, and the data is integrated to form an effective reaction band feature set. When the band reaction intensity index of the i-th band is less than the reaction intensity threshold, it indicates that the reaction signal intensity of the i-th band in the current immunoblot membrane strip does not meet the standard, and there is a risk of insufficient band color development reaction or background interference leading to misjudgment. This triggers a second warning instruction and generates a second strategy: Analyze the gray-level change trend of adjacent bands in the current band image sub-region, and calculate gray-level compensation for the current band by analyzing the gray-level gradient changes in adjacent band regions; combine the band area parameter and the band gray-level distribution to perform local gray-level enhancement and region reassessment processing on the band region; after adjustment and recalculation, if the band reaction intensity index of the i-th band is still less than the reaction intensity threshold, then the current band is marked as a suspected reaction band and included in the suspected band review list for manual review and risk warning during the interpretation of immunoblot detection results.

[0013] Furthermore, step five includes: S51. Based on the feature set of effective reaction bands, perform comprehensive interpretation analysis on each effective reaction band in the set, call the band signal clarity index and band reaction intensity index of the corresponding band, and after dimensionless processing, calculate and obtain the comprehensive interpretation index of immunoblot.

[0014] Furthermore, step five also includes: S52. By setting a comprehensive interpretation threshold and comparing the comprehensive interpretation index of the immunoblot with the comprehensive interpretation threshold, the third evaluation results are obtained, including: When the comprehensive interpretation index of immunoblot is greater than or equal to the comprehensive interpretation threshold, it indicates that the overall reaction signal stability of the current immunoblot membrane strip is qualified, and the corresponding immunoblot detection interpretation result is generated. When the overall interpretation index of the immunoblot is less than the overall interpretation threshold, it indicates that the overall reaction signal stability of the current immunoblot membrane strip is unqualified, and there is a risk of abnormal band color development or background noise interference leading to deviation in the test results. This triggers the third warning instruction and generates the third strategy: to perform a band reaction stability review analysis on each band in the effective reaction band feature set; to mark the corresponding bands for key review in conjunction with the suspected band review list; to generate review prompt information; and to include the current test sample in the manual review process for manual interpretation and confirmation of the immunoblot test results.

[0015] Compared with the prior art, the beneficial effects of the present invention are: This invention introduces an automatic membrane strip positioning and linear CCD line-by-line scanning acquisition mechanism into the immunoblotting detection process, combined with adaptive histogram equalization, Gaussian filtering noise reduction, and strip region segmentation and recognition techniques. This enables standardized acquisition and preprocessing of immunoblotting membrane strip images, improves the grayscale contrast between the strip region and the background region, and reduces random noise interference during the color development process. As a result, it improves the stability and analyzability of the membrane strip image data, providing a reliable data foundation for subsequent quantitative analysis of strip signals.

[0016] This invention also constructs a multi-parameter evaluation model for the clarity index and reaction intensity index of the band signal, and combines the clarity threshold and reaction intensity threshold for graded judgment, which can quantitatively evaluate the image clarity and reaction signal intensity of immunoblot bands. When an abnormal band signal is detected, the image quality enhancement strategy and the band reaction signal compensation strategy are triggered to perform contrast enhancement, noise suppression and grayscale compensation processing on the band region, thereby effectively reducing the impact of band boundary blurring, insufficient color development or background interference on the detection results and improving the accuracy of immunoblot detection results interpretation.

[0017] This invention also establishes a comprehensive immunoblot interpretation index and combines it with the feature set of effective reaction bands for overall stability assessment. At the same time, it introduces a suspected band verification list and a manual verification mechanism, which automatically triggers the verification strategy when there is an abnormal risk in the test results. This achieves multi-level quality control and risk warning for the immunoblot detection process, which can not only improve the stability and reliability of the test results, but also reduce the risk of misjudgment or omission, thereby improving the interpretation quality and detection safety of autoimmune antibody confirmatory testing in clinical immunodiagnostic laboratories. Attached Figure Description

[0018] Figure 1 This is a schematic diagram illustrating the overall execution of the method of the present invention; Figure 2 This is a schematic diagram of the overall method flow of the present invention. Detailed Implementation

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0020] Many specific details are set forth in the following description in order to provide a full understanding of the invention. However, the invention may also be practiced in other ways different from those described herein, and those skilled in the art can make similar extensions without departing from the spirit of the invention. Therefore, the invention is not limited to the specific embodiments disclosed below.

[0021] Example 1 Please see Figures 1 to 2 This invention provides a technical solution: an immunoblotting detection method based on an immunoblotting interpreter, the specific steps of which include: Step 1: Automatically locate and scan the immunoblot strips entering the detection area to obtain the basic grayscale image of the strips, and complete the identification of sub-regions of the strip image and extraction of spatial position parameters to construct the basic image dataset for immunoblot detection. Step 2: Enhance and denoise the basic grayscale images of the membrane strips in the basic image dataset for immunoblotting detection, and perform strip region segmentation and connected component identification. Statistically extract the average grayscale value of the strip, the average grayscale value of the background, the gradient parameters of the strip edges, the grayscale discrete parameters of the strip, and the area parameters of the strip. Step 3: Calculate the clarity index of the i-th band signal and compare it with the clarity threshold to determine whether the clarity of the i-th band image signal in the current immunoblot membrane strip meets the clinical immunoblot detection interpretation requirements. If it meets the requirements, generate a clear band feature set; otherwise, execute an image quality enhancement strategy. Step 4: Calculate the band reaction intensity index of the i-th band and compare it with the reaction intensity threshold to determine whether the reaction signal intensity of the i-th band in the current immunoblot membrane strip meets the standard. If it meets the standard, establish an effective reaction band set and integrate the data to form an effective reaction band feature set; if it does not meet the standard, execute the band reaction signal compensation strategy. Step 5: Calculate the immunoblot comprehensive interpretation index and compare it with the comprehensive interpretation threshold to determine whether the overall reaction signal stability of the current immunoblot membrane strip is qualified. If qualified, generate the corresponding immunoblot detection interpretation result; if not qualified, implement the immunoblot detection result stability verification strategy.

[0022] like Figure 1 As shown, the left side represents the hardware component of the immunoblot interpreter for implementing the method of this invention, comprising a detection area, a membrane strip support mechanism, and a linear CCD scanning assembly. This interpreter is used to automatically position and scan the immunoblot membrane strip placed on it line by line to obtain a high-precision grayscale image of the membrane strip. Figure 1 The flowchart on the right details the detection method steps: Image acquisition corresponds to step one, where the interpreter scans the membrane strip entering the detection area to obtain a basic grayscale image, identifies sub-regions of the strip image, and extracts spatial location parameters to construct a basic image dataset; Feature extraction corresponds to step two, where enhancement and noise reduction preprocessing are performed on the acquired basic grayscale image, and key features such as the average grayscale value of the strip, the average grayscale value of the background, and edge gradient parameters are extracted through segmentation and recognition algorithms; Signal evaluation corresponds to steps three and four, where the system calculates the strip signal clarity index and the strip reaction intensity index based on the feature parameters, determines the signal quality according to the clarity threshold and reaction intensity threshold, and executes image quality enhancement strategies or reaction signal compensation strategies when the standards are not met; Comprehensive analysis corresponds to step five, where the overall reaction signal stability of the membrane strip is evaluated by calculating the immunoblot comprehensive interpretation index, and a stability verification strategy is triggered when necessary, finally generating the detection interpretation result.

[0023] In this embodiment, by automatically acquiring and preprocessing images of immunoblot membrane strips, and constructing a multi-level interpretation and evaluation mechanism based on the strip signal clarity index, strip reaction intensity index, and immunoblot comprehensive interpretation index, the quality of immunoblot membrane strip images, reaction signal intensity, and overall reaction stability can be quantitatively analyzed. When the strip image quality is insufficient or the reaction signal is abnormal, image quality enhancement strategy, strip reaction signal compensation strategy, and detection result stability verification strategy are automatically executed, thereby effectively reducing the impact of background noise interference and abnormal strip color development on the detection results and improving the accuracy and reliability of immunoblot detection results.

[0024] Example 2 Please see Figures 1 to 2In the explanation of Example 1, this embodiment specifically includes step one: S11. Real-time monitoring of the membrane strip imaging status during the immunoblotting process for confirmatory detection of autoimmune antibodies in clinical immunodiagnostic laboratories. By setting a membrane strip positioning guide and an optical positioning sensor at the membrane strip sample inlet channel of the immunoblotting interpreter, the immunoblotting membrane strip entering the detection area is automatically positioned and its position is identified. The time information of the membrane strip entering the detection area and the membrane strip number information are recorded, and the correspondence between the membrane strip sample and the detection data is established. S12. Based on the correspondence between the membrane strip samples and the detection data, the immunoblot membrane strip entering the detection area is scanned line by line by the linear CCD scanning module and the LED linear cold light source illumination system set in the immunoblot interpreter to obtain the original grayscale images of the strip surface area and the background area. The obtained original grayscale images are associated with the corresponding membrane strip sample number to form the basic grayscale image data of the membrane strip. S13. Based on the basic grayscale image data of the membrane strip, according to the distribution characteristics of the color strips in the membrane strip image, the basic grayscale image is initially divided into regions, the pixel matrix data of the strip region is identified and extracted, and the corresponding strip image sub-region is generated according to the identification result. S14. Based on the sub-regions of the strip image, perform spatial localization analysis on each sub-region of the strip image, extract the center coordinates of the strip, the boundary range of the strip, and the width information of the strip to form the spatial location parameters of the strip. S15. Integrate the basic grayscale image data of the membrane strip, the sub-regions of the strip image, and the spatial location parameters of the strip to construct the basic image dataset for immunoblotting detection.

[0025] In this embodiment, by setting a membrane strip positioning guide rail and an optical positioning sensor at the membrane strip injection channel of the immunoblotting interpreter, the immunoblotting membrane strips entering the detection area are automatically positioned and numbered. Combined with a linear CCD scanning module and an LED linear cold light source illumination system, the membrane strips are scanned line by line. At the same time, the colored bands in the membrane strip images are identified and spatially located. This allows the construction of a structured basic image dataset for immunoblotting detection, improving the standardization of membrane strip image acquisition and the accuracy of data correspondence, and providing a stable and reliable data foundation for subsequent quantitative analysis of band signals and interpretation of detection results.

[0026] Example 3 Please see Figures 1 to 2 In the explanation of Example 2, this embodiment specifically includes the following steps: S21. Based on the basic image dataset of immunoblotting detection, image preprocessing is performed on the basic grayscale image data of the membrane strip, and grayscale enhancement processing is performed on the membrane strip image through the adaptive histogram equalization method to improve the grayscale contrast between the strip area and the background area. S22. By using Gaussian filtering to suppress noise in the enhanced image, random noise interference generated during the color development process is reduced, and standard membrane strip image data is formed.

[0027] In this embodiment, by performing adaptive histogram equalization grayscale enhancement processing on the basic grayscale image data of the membrane strip, and combining it with Gaussian filtering to suppress noise in the enhanced image, the grayscale contrast between the strip region and the background region can be effectively improved, and the random noise interference generated during the color development process can be reduced. This results in obtaining standard membrane strip image data with stable quality, and improving the accuracy and reliability of subsequent strip region recognition and feature parameter extraction.

[0028] Example 4 Please see Figures 1 to 2 In the explanation of Embodiment 3, specifically, step two further includes: S23. Based on standard membrane strip image data, an adaptive threshold segmentation method is used to segment the membrane strip image into strip regions and identify the strip regions and background regions; then, a connected component analysis method is used to spatially identify the strip regions and determine the actual range of each strip region. S24. Based on the actual range of each strip region, the pixel grayscale values ​​of the strip region are statistically analyzed to obtain the average grayscale value of the strip, denoted as G; and the pixel grayscale values ​​of the background region surrounding the strip are statistically analyzed to obtain the average grayscale value of the background, denoted as B. S25. Based on the actual range of each strip region, the Sobel edge detection algorithm is used to perform edge detection on the strip region, and the average gradient of the strip edge is calculated to obtain the strip edge gradient parameter, denoted as E. S26. Based on the actual range of each strip region, calculate the standard deviation of the pixel gray values ​​in the strip region to obtain the strip gray discrete parameter, denoted as S; S27. Based on the actual range of each strip region, obtain the strip area parameter by counting the number of pixels in the strip region, denoted as A.

[0029] In this embodiment, an adaptive threshold segmentation and connected component analysis method is used to accurately identify and spatially locate the strip regions in the standard membrane strip image data. Furthermore, multi-dimensional strip feature parameters such as the average gray value of the strip, the average gray value of the background, the strip edge gradient parameters, the strip gray-level discrete parameters, and the strip area parameters are statistically obtained. This enables a comprehensive quantitative characterization of the color development characteristics of the immunoblot membrane strips, improving the objectivity and precision of the strip signal analysis and providing reliable data support for subsequent strip signal clarity assessment and reaction intensity analysis.

[0030] Example 5 Please see Figures 1 to 2 In the explanation of Embodiment 4, specifically, step three includes: S31. Evaluate the signal sharpness of each band by calling the average gray value of the i-th band, denoted as . The average gray value of the background is denoted as... The edge gradient parameters are denoted as follows: And the grayscale discrete parameter, denoted as After dimensionless processing, the signal sharpness index of the i-th strip is calculated and denoted as . The formula is as follows:

[0031] The physical principle of the formula: This formula characterizes the sharpness of a striped image by comprehensively considering the strip signal intensity, boundary sharpness, and grayscale stability. This indicates the grayscale difference between the striped area and the background area, used to reflect the intensity of the striped color signal; The edge gradient parameter is used to characterize the steepness of the strip boundary change; the larger the edge gradient, the clearer the strip outline. This is the gray-level dispersion parameter for the strip region, used to reflect the stability of the gray-level distribution within the strip. A higher degree of gray-level dispersion indicates a higher level of noise or non-uniformity within the strip. Therefore, it is introduced into the denominator... Signal suppression reduces the impact of grayscale fluctuations on sharpness evaluation; through the combined effect of the above parameters, the sharpness index of the i-th strip signal is improved. It can comprehensively reflect the signal clarity of immunoblot band images.

[0032] In this embodiment, by introducing a strip signal clarity index and comprehensively quantifying the strip image signal by considering the average gray value of the strip, the average gray value of the background, the edge gradient parameter, and the gray-level discrete parameter, the strip signal intensity, boundary clarity, and gray-level stability can be reflected simultaneously. This enables an objective assessment of the clarity of the immunoblot strip image, improves the accuracy of strip image quality determination, and provides a reliable basis for subsequent detection result interpretation.

[0033] Example 6 Please see Figures 1 to 2 In the explanation of Example 5, specifically, step three further includes: S32. Using a preset sharpness threshold, denoted as Bth, the sharpness index of the i-th strip signal is... A comparative analysis was performed with the sharpness threshold Bth to obtain the first evaluation results, including: When the signal clarity index of the i-th stripe When the image signal of the i-th band in the current immunoblot membrane strip is ≥ the clarity threshold Bth, it means that the clarity of the image signal of the i-th band in the current immunoblot membrane strip meets the clinical immunoblot detection interpretation requirements, and a clear band feature set is generated for continuous monitoring. When the signal clarity index of the i-th stripe When the clarity index is less than the clarity threshold Bth, it indicates that the clarity of the i-th band image signal in the current immunoblot membrane does not meet the requirements for clinical immunoblot detection interpretation, and there is a risk of blurred band boundaries or background noise interference. This triggers the first warning instruction and generates the first strategy: perform image quality adjustment, apply local contrast enhancement processing to the current band image sub-region to increase the grayscale difference between the band region and the background region; apply adaptive noise suppression processing to the enhanced band image to reduce background noise interference; and recalculate the clarity index of the i-th band signal until the desired clarity index is achieved. Until the resolution threshold Bth is reached.

[0034] The specific calibration steps for the sharpness threshold Bth are as follows: The goal of the sharpness threshold Bth calibration process is to determine a critical BCI that can efficiently distinguish between the "sharp and acceptable" and "quality risk" bands. i Value. Construct a standard image database of immunoblot strips, containing at least 500 samples, covering strongly positive, weakly positive, and negative results. This database should be labeled with "gold standard" annotation by three or more senior clinical immunodiagnostic technicians according to clinical interpretation requirements, clearly classifying each strip image as "clear and acceptable" or "blurred and unacceptable" (including cases with blurred boundaries, high background noise, weak signal, etc.). Subsequently, run BCI in S31 on all strip images in the database. iThe calculation formula yields the Quantitative Clarity Index (BCI) for each band. Next, the BCI is compared between the "Clarity Passable" and "Blurry Unacceptable" groups. i Statistical distribution analysis is performed on the values, and their probability density function curves are plotted. Theoretically, the distributions of the two sets of data will form two partially overlapping peaks. The Bth value should be selected at the critical point that best separates these two distributions. ROC curve analysis is usually used to determine the BCI corresponding to the point with the largest Youden index. i This value represents the optimal balance between sensitivity and specificity. Combining the above statistical results with the long-accumulated interpretation experience of clinical experts (e.g., experts believe BCI...), i Below a certain value, the risk of false positives increases significantly, ultimately determining a reasonable threshold. In this embodiment, using the above method, Bth is preferably 0.75. This value achieves high automated processing efficiency while ensuring an extremely low false negative rate (below 1%, meaning non-compliant bands are falsely judged as compliant). When the BCI of the i-th band is detected... i When the value is less than 0.75, the system triggers the first strategy for automatic image quality optimization. This strategy is not a one-time process, but an iterative optimization closed-loop process. A specific implementation example is as follows: The maximum number of iterations is set to 3 to prevent infinite loops and avoid overprocessing that could lead to image distortion. In the first iteration, the system first performs local contrast enhancement on the current stripe image sub-region, specifically using the contrast-limited adaptive histogram equalization (CLAHE) algorithm. The initial cropping limit is set to 2.0, and the grid size is an 8×8 pixel block covering the stripe width. These moderate parameters aim to enhance the grayscale difference between the stripe and the background while suppressing excessive amplification of potential noise. After enhancement, adaptive noise suppression processing is immediately performed using the non-local mean filtering (NLM) algorithm, as it effectively smooths noise and preserves stripe edge details to the greatest extent (which is beneficial for BCI). i The Ei parameter in the formula is crucial. The filter intensity parameter h is set to 10, the search window to 21x21 pixels, and the template window to 7x7 pixels. After these two steps, the system recalculates the BCI based on the processed image. i If the new BCIi value is still below 0.75, the system proceeds to the second iteration. In this iteration, the processing intensity is increased, raising the CLAHE cropping limit by 25% to 2.5 and the NLM filter strength h by 20% to 12 to address more severe image degradation. The BCIi value is then recalculated after processing. i If the target is still not met, a third and final iteration will be performed, using stronger parameters, such as increasing the CLAHE clipping limit by approximately 28% to 3.2 and the NLM filter strength h by 25% to 15. After each iteration, the system will determine whether the BCI (Band Sharpness Index) of the i-th stripe is met. iIf the value is ≥0.75, the optimization process terminates immediately and successfully. The band is determined to be clear, and its feature data is stored in the clear band feature set. If, after all three iterations of optimization, the BCI... i If the value still does not reach 0.75, the system determines that the image quality of the band has a serious problem, automatic optimization fails, and the system will stop trying and trigger a manual intervention command. Simultaneously, the system refers to relevant technical specifications for immunoblotting detection, image acquisition performance parameters provided by the immunoblotting interpreter manufacturer, and detection quality control standards. These specifications typically provide a reference range for band image quality assessment. This threshold is used to effectively distinguish between a state where the band image clarity meets the detection and interpretation requirements and a state where there is image quality risk, thereby ensuring the reliability of immunoblotting detection image data.

[0035] In this embodiment, by setting a sharpness threshold and comparing the sharpness index of the strip signal with the threshold, the sharpness of each strip image signal in the immunoblot strip is determined. When the sharpness of the strip image is insufficient, an image quality adjustment strategy is automatically triggered. By performing local contrast enhancement and adaptive noise suppression processing on the sub-regions of the strip image and re-evaluating the sharpness, the problems of blurred strip boundaries and background noise interference can be effectively improved, thereby improving the quality of the strip image and the reliability of detection and interpretation.

[0036] Example 7 Please see Figures 1 to 2 In the explanation of Example Six, this embodiment specifically includes step four: S41. Based on standard membrane strip image data and background region pixel gray values, gray-scale statistical analysis method is used to perform gray-scale fluctuation analysis on the background region of the entire immunoblot membrane strip. By calculating the standard deviation and mean change ratio of background region pixel gray values, background noise stability is evaluated, and background noise stability coefficient is obtained, denoted as λ. S42. Based on the set of clear strip features, evaluate the response intensity of each strip in the set of clear strip features, and call the average gray value of the i-th strip. Average gray value of the background and strip area parameters After combining the background noise stability coefficient λ, dimensionless processing is performed on the characteristic parameters of each strip, and the strip response intensity index of the i-th strip is calculated and denoted as . The calculation formula is as follows:

[0037] The physical principle of the formula: This formula characterizes the band response intensity by comprehensively considering the band signal intensity, the influence of background noise, and the band color rendering range. The ratio of the average gray value of the strip region to the average gray value of the background is used to reflect the strength of the strip color development signal relative to the background noise; λ is the background noise stability coefficient, which is used to characterize the stability of the gray value fluctuation of the background region of the entire immunoblot strip. By incorporating it into the calculation together with the strip area related terms, the reaction intensity assessment can be dynamically corrected when there are fluctuations in the background noise. This is used to logarithmically scale the band area parameter, ensuring that the band's colorimetric range is reasonably reflected in the reaction intensity assessment, while avoiding excessive amplification of the results due to an excessively large area, thus improving the band reaction intensity index of the i-th band. It can more objectively reflect the true reaction intensity of immunoblot bands by comprehensively considering the band signal intensity, background noise stability, and band color development range.

[0038] In this embodiment, by performing statistical analysis of grayscale fluctuations in the background area of ​​the immunoblot membrane strip, a background noise stability coefficient is obtained. The strip reaction intensity index is constructed by combining the average grayscale value of the strip, the average grayscale value of the background, and the strip area parameter. The reaction signal intensity of each strip is quantitatively evaluated, thereby more accurately reflecting the true reaction intensity of the strip while considering the influence of background noise interference, and improving the objectivity and reliability of immunoblot detection result analysis.

[0039] Example 8 Please see Figures 1 to 2 In the explanation of Example 7, specifically, step four further includes: S43. Using a preset reaction intensity threshold, denoted as Fth, the band reaction intensity index of the i-th band is... A comparative analysis with the reaction intensity threshold Fth was performed to obtain the second evaluation results, including: When the band reaction intensity index of the i-th band When the reaction intensity threshold Fth is greater than or equal to the reaction intensity threshold, it means that the reaction signal intensity of the i-th band in the current immunoblot membrane strip meets the standard. An effective reaction band set is established, and the data is integrated to form an effective reaction band feature set. When the band reaction intensity index of the i-th band When the reaction intensity index is less than the reaction intensity threshold Fth, it indicates that the reaction signal intensity of the i-th band in the current immunoblot membrane strip is insufficient, posing a risk of inadequate band development or background interference leading to misjudgment. This triggers a second warning instruction and generates a second strategy: Analyze the grayscale change trend of adjacent bands in the current band image sub-region; calculate grayscale compensation for the current band by analyzing the grayscale gradient changes in adjacent band regions; combine the band area parameter and the band grayscale distribution to perform local grayscale enhancement and region reassessment processing on the band region; recalculate after adjustment; if the band reaction intensity index of the i-th band is still insufficient... If the band is less than the reaction intensity threshold Fth, the current band is marked as a suspected reaction band and added to the suspected band review list for manual review and risk warning during the interpretation of immunoblot test results.

[0040] The second strategy is used to perform a salvage analysis and enhancement of weak response bands using neighborhood information and local image features to distinguish between genuine weak positive signals and background artifacts. The specific steps are as follows: First, the system triggers a second warning command and initiates an analysis of the grayscale change trends of adjacent bands in the current band image sub-region. This analysis locates the two bands closest to the current i-th band that have been included in the "effective response band set" (i.e., FRI). i ≥Fth bands), calculate the "gray-area ratio" (i.e., G) of these two strong reactive bands. i / A i The system calculates a weighted average of the pixels based on their positional relationship with the target strip to predict a theoretically desirable gray-to-area ratio for the current position. This prediction, in turn, yields a gray-level compensation coefficient designed to boost the signal strength of the current strip to a theoretically reliable lower limit. Next, the system performs local gray-level enhancement and region reassessment on the current strip based on this compensation coefficient. Specifically, it employs a targeted nonlinear gray-level mapping function (such as Gamma correction) to adjust only the pixels within the sub-region of the strip. The adjustment aims to increase the average gray-level value of the strip, avgG. i The grayscale is selectively increased by 15% to 35% based on the original value. This specific percentage increase is dynamically determined by the grayscale compensation coefficient and has an upper limit to prevent over-enhancement artifacts. After grayscale enhancement, since some previously blurry edge pixels below the detection threshold become clear, the system immediately performs a fast region re-segmentation on the enhanced sub-region to obtain a more accurate strip area A. i Parameters. Use the adjusted new average grayscale value avgG i 'and the area of ​​the new strip A i The system then recalculates the reaction intensity index FRIi' of the band, combining the unchanged background grayscale value Bi and the background noise stability coefficient λ. If the recalculated FRIi' is still less than the reaction intensity threshold Fth, the system determines that the band cannot be confirmed as a valid reaction through the automated strategy, and ultimately marks it as a "suspected reaction band," adding it to the suspected band review list. This list is used to provide a high-risk warning to the operator in the final test result interpretation report, requiring manual review.

[0041] The reaction intensity threshold Fth is obtained by statistically analyzing a large amount of immunoblotting sample data to extract the range of band reaction intensity index variation under normal and weak reaction band conditions. This range is then combined with clinical experience in interpreting immunoblotting results and the judgment of professional technicians to determine a reasonable reaction intensity threshold. Simultaneously, the technical specifications for immunoblotting detection, the band color intensity reference standards provided by reagent kit manufacturers, and the detection quality control requirements are referenced. These specifications typically provide a judgment range for band reaction signal intensity. This threshold is used to effectively distinguish between a band reaction signal intensity that meets the standard and a state of insufficient reaction signal or potential interference, thereby improving the accuracy of immunoblotting result interpretation.

[0042] In this embodiment, by setting a reaction intensity threshold and comparing the strip reaction intensity index with the threshold, the reaction signal intensity of each strip in the immunoblot membrane strip is determined. When the strip reaction signal intensity does not meet the standard, the strip reaction signal compensation strategy is automatically triggered. By analyzing the gray-level change trend of adjacent strips in the strip image sub-region, calculating gray-level compensation, and performing local gray-level enhancement processing, and combining the strip area parameter for regional re-evaluation, the influence of insufficient strip color development reaction or background interference on the detection results can be effectively reduced. At the same time, by establishing a suspected strip review list, risk warnings are provided, improving the accuracy and reliability of immunoblot detection result interpretation.

[0043] Example 9 Please see Figures 1 to 2 In the explanation of Embodiment Eight, specifically, step five includes: S51. Based on the feature set of effective response bands, perform comprehensive interpretation and analysis on each effective response band in the set, and call the band signal clarity index of the corresponding band. and the band reaction intensity index After dimensionless processing, the immunoblot comprehensive interpretation index, denoted as IDI, is calculated and obtained, as follows:

[0044] In the formula, n represents the number of bands in the effective response band set, and w1 and w2 represent weighting coefficients.

[0045] : Represents the clarity index of the i-th stripe signal. The weighting coefficient in the comprehensive interpretation index of immunoblotting is used to characterize the impact of the clarity of the strip image on the reliability of the immunoblotting detection results. It has the second highest weight, indicating that the clarity of the strip boundary and the signal stability have an important impact on the detection interpretation. : Represents the band response intensity index of the i-th band. The weighting coefficient in the comprehensive interpretation index of immunoblotting is used to characterize the importance of the intensity of the band color reaction to the interpretation of immunoblotting detection results. It has the highest weight and reflects the dominant role of the intensity of the band reaction signal in the interpretation of immunoblotting detection. This formula uses the band signal clarity index of the i-th band in the effective response band set. Band reaction intensity index with the i-th band Weighted fusion was performed, and all effective bands were averaged to comprehensively characterize the overall signal quality of the immunoblot strips. The band signal clarity index of the i-th band was used. The strip response intensity index is used to reflect image quality characteristics such as the sharpness of the striped image boundaries, the contrast between the signal and the background, and the grayscale stability. This method is used to reflect the intensity of the band colorimetric reaction and the signal response level. By setting weighting coefficients to weight the two types of indicators, the overall reaction status of the immunoblot strip can be quantitatively evaluated while considering both image clarity and reaction signal intensity. Furthermore, by averaging the number of effective reaction bands n, the Integrated Interpretation Index (IDI) can objectively reflect the overall detection quality and reaction stability of the entire immunoblot strip, thus providing a reliable quantitative basis for the interpretation of immunoblot detection results.

[0046] In this embodiment, by comprehensively analyzing each band in the effective reaction band feature set, and combining the band signal clarity index and the band reaction intensity index to construct an immunoblot comprehensive interpretation index, a comprehensive quantitative evaluation of the overall reaction signal quality of the immunoblot membrane strip is achieved. This improves the overall integrity and objectivity of the immunoblot detection result interpretation while simultaneously considering the clarity of the band image and the reaction signal intensity.

[0047] Example 10 Please see Figures 1 to 2 In the explanation of Embodiment Nine, specifically, step five further includes: S52. By setting a comprehensive interpretation threshold, denoted as Ith, and comparing the immunoblot comprehensive interpretation index IDI with the comprehensive interpretation threshold Ith, the third evaluation results are obtained, including: When the immunoblot comprehensive interpretation index IDI is greater than or equal to the comprehensive interpretation threshold Ith, it indicates that the overall reaction signal stability of the current immunoblot membrane strip is qualified, and the corresponding immunoblot detection interpretation result is generated. When the immunoblot comprehensive interpretation index IDI is less than the comprehensive interpretation threshold Ith, it indicates that the overall reaction signal stability of the current immunoblot membrane strip is unqualified, and there is a risk of abnormal band color development or background noise interference leading to deviation in the test results. This triggers the third warning instruction and generates the third strategy: to perform a band reaction stability review analysis on each band in the effective reaction band feature set; to mark the corresponding bands for key review in conjunction with the suspected band review list; to generate review prompt information; and to include the current test sample in the manual review process for manual interpretation and confirmation of the immunoblot test results.

[0048] The comprehensive interpretation threshold (Ith) is obtained by statistically analyzing a large amount of immunoblotting test results data to extract the distribution range of the comprehensive interpretation index of immunoblotting under stable and abnormal test signal states. This is then combined with the testing experience of clinical immunodiagnostic laboratories and the comprehensive interpretation experience of professional technicians to determine a reasonable comprehensive interpretation value. Simultaneously, relevant technical specifications for immunoblotting testing, system performance indicators provided by testing equipment manufacturers, and laboratory quality control standards are referenced. These specifications typically provide a reference range for overall test stability. This threshold is used to effectively distinguish between stable and reliable immunoblotting test results and states with overall abnormal reactions or background interference risks, thereby ensuring the stability and safety of immunoblotting test result interpretation.

[0049] In this embodiment, by setting a comprehensive interpretation threshold and comparing the comprehensive interpretation index of immunoblot with the threshold, the overall reaction signal stability of the immunoblot membrane strip is determined. When the overall reaction signal stability is unqualified, a verification strategy is automatically triggered. By performing stability verification analysis on the effective reaction strips and combining the suspected strip verification list for key marking and manual verification prompts, it is possible to identify test samples that may have abnormal color development or background noise interference in a timely manner, reduce the risk of test result deviation, and improve the reliability and safety of immunoblot test result interpretation.

[0050] It should be noted that all calculation formulas in this application employ regression analysis, including but not limited to machine learning algorithms, to deeply analyze the collected parameters and identify their natural trends and interrelationships. Specialized software, such as Python's Scikit-learn library or the R language, is used to automatically generate mathematical models that match the data. Then, cross-validation and other methods are used to objectively evaluate the model performance, and continuous feedback and optimization are combined to ensure that the created formulas truly reflect the inherent laws of the data, thereby guaranteeing their effectiveness and accuracy. In all calculation formulas in this application, the parameters in each formula undergo dimensionless processing within a consistent range to ensure that different physical quantities are compared on the same scale; dimensionless processing techniques include, but are not limited to, min-max-normalization and Z-score standardization. The algorithm of this invention is implemented as a Python script. Before executing the core logic, the program first executes a data loading module (e.g., using the widely used pandas library in Python) configured to read the aforementioned spreadsheet file and load its contents into the program's working memory (e.g., a DataFrame data structure). Subsequent algorithm steps will directly query and retrieve the required configuration parameters from this in-memory data structure.

[0051] It should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. An immunoblotting detection method based on an immunoblotting interpreter, characterized in that: The specific steps include: Step 1: Automatically locate and scan the immunoblot strips entering the detection area to obtain the basic grayscale image of the strips, and complete the identification of sub-regions of the strip image and extraction of spatial position parameters to construct the basic image dataset for immunoblot detection. Step 2: Enhance and denoise the basic grayscale images of the membrane strips in the basic image dataset for immunoblotting detection, and perform strip region segmentation and connected component identification. Statistically extract the average grayscale value of the strip, the average grayscale value of the background, the gradient parameters of the strip edges, the grayscale discrete parameters of the strip, and the area parameters of the strip. Step 3: Calculate the clarity index of the i-th band signal and compare it with the clarity threshold to determine whether the clarity of the i-th band image signal in the current immunoblot membrane strip meets the clinical immunoblot detection interpretation requirements. If it meets the requirements, generate a clear band feature set; otherwise, execute an image quality enhancement strategy. Step 4: Calculate the band reaction intensity index of the i-th band and compare it with the reaction intensity threshold to determine whether the reaction signal intensity of the i-th band in the current immunoblot membrane strip meets the standard. If it meets the standard, establish an effective reaction band set and integrate the data to form an effective reaction band feature set; if it does not meet the standard, execute the band reaction signal compensation strategy. Step 5: Calculate the immunoblot comprehensive interpretation index and compare it with the comprehensive interpretation threshold to determine whether the overall reaction signal stability of the current immunoblot membrane strip is qualified. If qualified, generate the corresponding immunoblot detection interpretation result; if not qualified, implement the immunoblot detection result stability verification strategy.

2. The immunoblotting detection method based on an immunoblotting interpreter according to claim 1, characterized in that: Step one includes: S11. Real-time monitoring of the membrane strip imaging status during the immunoblotting process for confirmatory detection of autoimmune antibodies in clinical immunodiagnostic laboratories. By setting a membrane strip positioning guide and an optical positioning sensor at the membrane strip sample inlet channel of the immunoblotting interpreter, the immunoblotting membrane strip entering the detection area is automatically positioned and its position is identified. The time information of the membrane strip entering the detection area and the membrane strip number information are recorded, and the correspondence between the membrane strip sample and the detection data is established. S12. Based on the correspondence between the membrane strip samples and the detection data, the immunoblot membrane strip entering the detection area is scanned line by line by the linear CCD scanning module and the LED linear cold light source illumination system set in the immunoblot interpreter to obtain the original grayscale images of the strip surface area and the background area. The obtained original grayscale images are associated with the corresponding membrane strip sample number to form the basic grayscale image data of the membrane strip. S13. Based on the basic grayscale image data of the membrane strip, according to the distribution characteristics of the color strips in the membrane strip image, the basic grayscale image is initially divided into regions, the pixel matrix data of the strip region is identified and extracted, and the corresponding strip image sub-region is generated according to the identification result. S14. Based on the sub-regions of the strip image, perform spatial localization analysis on each sub-region of the strip image, extract the center coordinates of the strip, the boundary range of the strip, and the width information of the strip to form the spatial location parameters of the strip. S15. Integrate the basic grayscale image data of the membrane strip, the sub-regions of the strip image, and the spatial location parameters of the strip to construct the basic image dataset for immunoblotting detection.

3. The immunoblotting detection method based on an immunoblotting interpreter according to claim 2, characterized in that: Step two includes: S21. Based on the basic image dataset of immunoblotting detection, image preprocessing is performed on the basic grayscale image data of the membrane strip, and grayscale enhancement processing is performed on the membrane strip image through the adaptive histogram equalization method to improve the grayscale contrast between the strip area and the background area. S22. By using Gaussian filtering to suppress noise in the enhanced image, random noise interference generated during the color development process is reduced, and standard membrane strip image data is formed.

4. The immunoblotting detection method based on an immunoblotting interpreter according to claim 3, characterized in that: Step two also includes: S23. Based on standard membrane strip image data, an adaptive threshold segmentation method is used to segment the membrane strip image into strip regions and identify the strip regions and background regions; then, a connected component analysis method is used to spatially identify the strip regions and determine the actual range of each strip region. S24. Based on the actual range of each strip region, the grayscale values ​​of the pixels in the strip region are statistically analyzed to obtain the average grayscale value of the strip; and the grayscale values ​​of the pixels in the background region surrounding the strip are statistically analyzed to obtain the average grayscale value of the background. S25. Based on the actual range of each strip region, the Sobel edge detection algorithm is used to perform edge detection on the strip region, and the average gradient of the strip edge is calculated to obtain the strip edge gradient parameters. S26. Based on the actual range of each strip region, calculate the standard deviation of the pixel gray values ​​in the strip region to obtain the strip gray discrete parameters. S27. Based on the actual range of each strip region, obtain the strip area parameter by counting the number of pixels in the strip region.

5. The immunoblotting detection method based on an immunoblotting interpreter according to claim 4, characterized in that: Step three includes: S31. For each strip, perform signal sharpness evaluation. By calling the average gray value of the i-th strip, the average gray value of the background, the edge gradient parameter, and the gray-level discrete parameter, after dimensionless processing, calculate and obtain the strip signal sharpness index of the i-th strip.

6. The immunoblotting detection method based on an immunoblotting interpreter according to claim 5, characterized in that: Step three also includes: S32. By setting a sharpness threshold, and comparing the sharpness index of the i-th strip signal with the sharpness threshold, the first evaluation result is obtained, including: When the clarity index of the i-th band is greater than or equal to the clarity threshold, it means that the clarity of the i-th band image signal in the current immunoblot membrane strip meets the clinical immunoblot detection interpretation requirements, and a clear band feature set is generated for continuous monitoring. When the clarity index of the i-th band is less than the clarity threshold, it indicates that the clarity of the i-th band image signal in the current immunoblot membrane does not meet the requirements for clinical immunoblot detection interpretation, and there is a risk of blurred band boundaries or background noise interference. This triggers the first warning instruction and generates the first strategy: perform image quality adjustment, perform local contrast enhancement processing on the current band image sub-region to increase the grayscale difference between the band region and the background region; perform adaptive noise suppression processing on the enhanced band image to reduce background noise interference; recalculate after adjustment until the clarity index of the i-th band is greater than or equal to the clarity threshold.

7. The immunoblotting detection method based on an immunoblotting interpreter according to claim 6, characterized in that: Step four includes: S41. Based on standard membrane strip image data and background area pixel gray values, gray-scale statistical analysis method is used to perform gray-scale fluctuation analysis on the background area of ​​the entire immunoblot membrane strip. By calculating the standard deviation and mean change ratio of background area pixel gray values, background noise stability is evaluated and background noise stability coefficient is obtained. S42. Based on the set of clear strip features, evaluate the response intensity of each strip in the set of clear strip features. Call the average gray value of the i-th strip, the average gray value of the background, and the strip area parameter. Combined with the background noise stability coefficient, perform dimensionless processing on the feature parameters of each strip and calculate the strip response intensity index of the i-th strip.

8. The immunoblotting detection method based on an immunoblotting interpreter according to claim 7, characterized in that: Step four also includes: S43. By setting a preset reaction intensity threshold, and comparing the band reaction intensity index of the i-th band with the reaction intensity threshold, the second evaluation result is obtained, including: When the band reaction intensity index of the i-th band is greater than or equal to the reaction intensity threshold, it means that the reaction signal intensity of the i-th band in the current immunoblot membrane strip meets the standard. An effective reaction band set is established, and the data is integrated to form an effective reaction band feature set. When the band reaction intensity index of the i-th band is less than the reaction intensity threshold, it indicates that the reaction signal intensity of the i-th band in the current immunoblot membrane strip does not meet the standard, and there is a risk of insufficient band color development reaction or background interference leading to misjudgment. This triggers a second warning instruction and generates a second strategy: Analyze the gray-level change trend of adjacent bands in the current band image sub-region, and calculate gray-level compensation for the current band by analyzing the gray-level gradient changes in adjacent band regions; combine the band area parameter and the band gray-level distribution to perform local gray-level enhancement and region reassessment processing on the band region; after adjustment and recalculation, if the band reaction intensity index of the i-th band is still less than the reaction intensity threshold, then the current band is marked as a suspected reaction band and included in the suspected band review list for manual review and risk warning during the interpretation of immunoblot detection results.

9. The immunoblotting detection method based on an immunoblotting interpreter according to claim 8, characterized in that: Step five includes: S51. Based on the feature set of effective reaction bands, perform comprehensive interpretation analysis on each effective reaction band in the set, call the band signal clarity index and band reaction intensity index of the corresponding band, and after dimensionless processing, calculate and obtain the comprehensive interpretation index of immunoblot.

10. The immunoblotting detection method based on an immunoblotting interpreter according to claim 9, characterized in that: Step five also includes: S52. By setting a comprehensive interpretation threshold and comparing the comprehensive interpretation index of the immunoblot with the comprehensive interpretation threshold, the third evaluation results are obtained, including: When the comprehensive interpretation index of immunoblot is greater than or equal to the comprehensive interpretation threshold, it indicates that the overall reaction signal stability of the current immunoblot membrane strip is qualified, and the corresponding immunoblot detection interpretation result is generated. When the overall interpretation index of the immunoblot is less than the overall interpretation threshold, it indicates that the overall reaction signal stability of the current immunoblot membrane strip is unqualified, and there is a risk of abnormal band color development or background noise interference leading to deviation in the test results. This triggers the third warning instruction and generates the third strategy: to perform a band reaction stability review analysis on each band in the effective reaction band feature set; to mark the corresponding bands for key review in conjunction with the suspected band review list; to generate review prompt information; and to include the current test sample in the manual review process for manual interpretation and confirmation of the immunoblot test results.

Images