CN-121010751-B - Intelligent interpretation method and system for weak positive samples of immune test

CN121010751BCN 121010751 BCN121010751 BCN 121010751BCN-121010751-B

Abstract

The application provides an intelligent interpretation method and system for an immune test weak positive sample, which are characterized in that a weak positive sample image containing a detection line and a quality control line area in an immune chromatography test strip is divided into a plurality of local area blocks, structural similarity between each group of adjacent local area blocks is determined, candidate line areas and background areas of the detection line are screened out from the weak positive sample image based on all the structural similarity, a probability thermodynamic diagram of the detection line is generated according to gray gradient distribution of the candidate line areas, contribution characteristics of the background areas to the weak positive sample image are determined, background correction characteristic areas of the detection line in the weak positive sample image are determined through the contribution characteristics, contrast indexes of the detection line corresponding to the signal to noise ratio in the immune chromatography test strip are determined according to the signal to noise ratio of the detection line in the background correction characteristic areas, and a classification report of the weak positive sample is generated. By adopting the scheme of the application, the influence of the continuity of the detection line on the weak positive sample detection can be reduced.

Inventors

CHEN LONGQING
YANG HUAN
LV CHUNLI
ZHAO JUANJUAN
ZHONG QINGLIN

Assignees

遵义医科大学附属医院

Dates

Publication Date: 20260512
Application Date: 20250725

Claims (10)

1. The intelligent interpretation method for the weak positive sample of the immune test is applied to detection of an immune chromatography test strip, wherein the immune chromatography test strip comprises a detection line and a quality control line, and the image acquisition is carried out after the reaction of the immune chromatography test strip and the weak positive sample is completed, and the method is characterized by comprising the following steps: Acquiring a weak positive sample image containing a detection line and a quality control line area in the immunochromatographic test strip based on an image sensor; dividing the weak positive sample image into a plurality of local area blocks according to the chromatographic flow direction of the immunochromatographic test strip; Determining the structural similarity between each group of adjacent local area blocks, and screening candidate line areas and background areas of detection lines from the weak positive sample image based on all the structural similarity; Generating a probability thermodynamic diagram of the detection line according to the gray gradient distribution of the candidate line region, determining the contribution characteristic of the background region to the weak positive sample image, and carrying out background constraint on the continuity of the detection line in the probability thermodynamic diagram through the contribution characteristic to obtain a background correction characteristic region of the detection line in the weak positive sample image; And constructing a contrast index of the detection line corresponding to the signal-to-noise ratio in the immunochromatographic test strip according to the signal-to-noise ratio of the detection line in the background correction characteristic region and the signal-to-noise ratio of the quality control line in the weak positive sample image, and comparing the contrast index based on the signal-to-noise ratio with a weak positive interpretation interval preset by the weak positive sample so as to generate a grading report of the weak positive sample.
2. The method of claim 1, wherein dividing the weak positive sample image into a plurality of local area blocks according to the chromatographic flow direction of the immunochromatographic test strip specifically comprises: determining the chromatographic flow direction of the immunochromatographic test strip; determining a smooth window when the weak positive sample image is divided; and smoothly dividing the weak positive sample image according to the chromatographic flow direction based on the smooth window to obtain a plurality of local area blocks.
3. The method of claim 1, wherein determining structural similarity between each set of adjacent local region blocks comprises: Selecting a group of adjacent local area blocks as selected adjacent local area blocks, and determining the structural characteristics of each local area block in the selected adjacent local area blocks; determining the structural similarity between the selected adjacent local area blocks according to the structural characteristics of each local area block in the selected adjacent local area blocks; The structural similarity between the remaining adjacent local area blocks continues to be determined.
4. The method of claim 1, wherein screening candidate line areas and background areas of detection lines from the weak positive sample image based on all structural similarities specifically comprises: performing enhancement treatment on the weak positive sample image to obtain an enhanced image of the weak positive sample; determining a similarity map of the detection line according to all the structural similarities; and determining candidate line areas and background areas of the detection lines according to the similarity mapping diagram and the enhanced image.
5. The method of claim 1, wherein generating a probability thermodynamic diagram of the detection line from a gray gradient distribution of the candidate line region comprises: determining a horizontal gray gradient value and a vertical gray gradient value of each pixel point in the candidate line area, and further obtaining gray gradient distribution of the candidate line area; determining a plurality of probability values of the detection line according to the gray gradient distribution; And determining a probability thermodynamic diagram of the detection line through all probability values.
6. The method of claim 1, wherein determining the contribution characteristic of the background region to the weak positive sample image specifically comprises: Determining brightness characteristics and fluctuation characteristics of the background area; extracting texture detail features in the background area; And determining the contribution characteristic of the background area to the weak positive sample image according to the brightness characteristic, the fluctuation characteristic and the detail characteristic.
7. The method of claim 1, wherein obtaining a background corrected feature region of the detection line in the weak positive sample image by background constraining the continuity of the detection line in the probability thermodynamic diagram by the contribution feature specifically comprises: Extracting suspected fracture areas and candidate continuous areas of detection lines from the probability thermodynamic diagram; Smoothing the suspected fracture area of the detection line according to the contribution characteristic to obtain a fracture smooth state of the detection line; and determining a background correction characteristic region of the detection line in the weak positive sample image according to the fracture smooth state and the candidate continuous region.
8. The utility model provides an immune assay weak positive sample intelligence interpretation system, is applied to immune chromatography test paper strip and detects, wherein, immune chromatography test paper strip is including detection line and matter control line, carries out image acquisition after immune chromatography test paper strip and weak positive sample reaction are accomplished, its characterized in that, this system includes: The acquisition module is used for acquiring a weak positive sample image containing a detection line and a quality control line area in the immunochromatographic test strip based on an image sensor; The processing module is used for dividing the weak positive sample image into a plurality of local area blocks according to the chromatographic flow direction of the immunochromatographic test strip; The processing module is further used for determining the structural similarity between each group of adjacent local area blocks, and screening candidate line areas and background areas of the detection lines from the weak positive sample image based on all the structural similarity; The processing module is further configured to generate a probability thermodynamic diagram of the detection line according to gray gradient distribution of the candidate line region, determine contribution features of the background region to the weak positive sample image, and perform background constraint on continuity of the detection line in the probability thermodynamic diagram through the contribution features to obtain a background correction feature region of the detection line in the weak positive sample image; And the execution module is used for constructing a contrast index of the detection line corresponding to the signal-to-noise ratio in the immunochromatographic test strip according to the signal-to-noise ratio of the detection line in the background correction characteristic area and the signal-to-noise ratio of the quality control line in the weak positive sample image, comparing the contrast index of the signal-to-noise ratio with a weak positive interpretation interval preset by the weak positive sample, and further generating a grading report of the weak positive sample.
9. A computer device comprising a memory storing code and a processor configured to obtain the code and to perform the method of intelligent interpretation of an immunoassay weak positive sample as claimed in any one of claims 1 to 7.
10. A computer readable storage medium storing a computer program, wherein the computer program when executed by a processor implements the method of intelligent interpretation of an immunometric weak positive sample as claimed in any one of claims 1 to 7.

Description

Intelligent interpretation method and system for weak positive samples of immune test Technical Field The application relates to the technical field of sample interpretation, in particular to an intelligent interpretation method and system for a weak positive sample in immune test. Background The intelligent sample interpretation refers to the process of carrying out automatic analysis and hierarchical judgment on images or data corresponding to various detection samples (such as immunochromatographic test strips, medical images, biological samples and the like) by means of technologies such as an image sensor, computer vision, machine learning and the like. The immunochromatography test strip detection technology is widely applied to a plurality of fields of disease diagnosis, health screening and the like due to the advantages of simplicity and convenience in operation, low cost and the like. The working principle is based on antigen-antibody specificity combination, whether a target object exists in a sample is reflected through the color development condition of a detection line and a quality control line, in practical application, in order to acquire a detection result, an image after the reaction of an immunochromatographic test strip is acquired by means of an image sensor, and then the image is analyzed and processed, along with technological development, the requirements on the accuracy and the refinement degree of the detection result are continuously improved, especially the interpretation of a weak positive sample are difficult to meet, at present, the conventional simple visual interpretation or basic image analysis method is difficult to meet the requirements, at present, part of research attempts are made to improve the interpretation accuracy by utilizing an image processing technology and a machine learning algorithm, but in the aspects of accurate screening of a detection line area, signal continuity analysis, hierarchical interpretation of comprehensive multidimensional information and the like, the continuity analysis of the detection line is not perfect, and the influence of micro-fracture on the result is easy to be ignored, so how to reduce the influence of the continuity of the detection line on the weak positive sample detection becomes a problem in the industry. Disclosure of Invention The application provides an intelligent interpretation method and system for a weak positive sample in immune test, which can reduce the influence of continuity of a detection line on the weak positive sample test. In a first aspect, the application provides an intelligent interpretation method for a weak positive sample in immune test, which is applied to detection of an immune chromatography test strip, wherein the immune chromatography test strip comprises a detection line and a quality control line, and when the immune chromatography test strip and the weak positive sample react, image acquisition is performed, and the method comprises the following steps: Acquiring a weak positive sample image containing a detection line and a quality control line area in the immunochromatographic test strip based on an image sensor; dividing the weak positive sample image into a plurality of local area blocks according to the chromatographic flow direction of the immunochromatographic test strip; Determining the structural similarity between each group of adjacent local area blocks, and screening candidate line areas and background areas of detection lines from the weak positive sample image based on all the structural similarity; Generating a probability thermodynamic diagram of the detection line according to the gray gradient distribution of the candidate line region, determining the contribution characteristic of the background region to the weak positive sample image, and carrying out background constraint on the continuity of the detection line in the probability thermodynamic diagram through the contribution characteristic to obtain a background correction characteristic region of the detection line in the weak positive sample image; And constructing a contrast index of the detection line corresponding to the signal-to-noise ratio in the immunochromatographic test strip according to the signal-to-noise ratio of the detection line in the background correction characteristic region and the signal-to-noise ratio of the quality control line in the weak positive sample image, and comparing the contrast index based on the signal-to-noise ratio with a weak positive interpretation interval preset by the weak positive sample so as to generate a grading report of the weak positive sample. In some embodiments, dividing the weak positive sample image into a plurality of local area blocks according to the chromatographic flow direction of the immunochromatographic test strip specifically includes: determining the chromatographic flow direction of the immunochromatographic test strip; determining a smooth window when