A method for detecting chromosome abnormalities based on image analysis

Abstract

The present invention belongs to the technical field of biomedical image processing and analysis, and specifically discloses a chromosome abnormality detection method based on image analysis, comprising: obtaining a user chromosome microscopic image set and extracting a multimodal feature data set for processing to obtain abnormal chromosome feature data of the abnormal tracking area, and collectively processing to obtain an abnormal risk assessment index, and then correcting it in combination with abnormal identification coefficients of multiple historically similar abnormal samples to obtain an abnormal risk correction index, and evaluating and processing the acquired clinical test data set corresponding to the abnormal tracking area in combination with genetic background feature data to obtain a genetic risk determination index of the abnormal tracking area, and then comparing it with the abnormal risk correction index to obtain an abnormal assessment matching coefficient, and verifying the abnormal assessment result through threshold comparison, thereby achieving efficient identification and accurate assessment of multiple complex chromosome abnormality types, and combining genetic background information and clinical data for comprehensive risk assessment to improve the reliability of the test results.

Description

Technical Field

[0001] The present invention belongs to the technical field of biomedical image processing and analysis, and specifically relates to a chromosome abnormality detection method based on image analysis. Background Art

[0002] With the rapid development of medical imaging analysis technology, image-based chromosomal abnormality detection methods have gradually become a research hotspot in the field of molecular diagnostics. By combining computer vision, deep learning, and image processing techniques, this method can significantly improve the efficiency and accuracy of chromosomal abnormality detection, providing important support for clinical diagnosis. However, existing related technical solutions still have shortcomings in image processing accuracy, automation, and the ability to identify complex abnormalities, which limits their promotion and popularization in practical applications.

[0003] In the prior art, the patent with publication number CN115619774B proposes a method for identifying chromosomal abnormalities. This solution mainly targets specific types of chromosomal abnormalities and lacks wide applicability to other complex or rare chromosomal abnormalities. In addition, this method relies on high-quality input images. If the image quality is poor or there is noise, it may lead to a decrease in recognition accuracy. At the same time, its model training process requires a large amount of labeled data, which increases the time and cost of data preparation. Another prior art, the patent with publication number CN112288706B, proposes an automated chromosome karyotype analysis and abnormality detection method. This solution may have certain limitations when dealing with complex chimeras or the coexistence of multiple abnormality types. In addition, because its model design focuses on the coarse positioning and semantic feature extraction of the target area, it may not be sensitive enough to subtle structural abnormalities, resulting in an increased risk of missed detection or false detection. At the same time, this method has high requirements on the computing power of the hardware equipment and may be difficult to widely use in resource-constrained environments.

[0004] The above issues indicate that existing image analysis-based chromosomal abnormality detection methods still have certain shortcomings in terms of wide applicability to abnormality types, adaptability to complex scenarios, sensitivity to subtle structural abnormalities, and demand for hardware resources. Therefore, a technical solution is urgently needed to address these issues.

[0005] At the same time, existing methods for testing chromosomal abnormalities have obvious deficiencies in psychological assessment, case matching, and misdiagnosis control. Summary of the Invention

[0006] To solve the above technical problems, the present invention provides a method for detecting chromosome abnormalities based on image analysis, which includes the following technical solutions:

[0007] Collect multiple chromosome microscopic image sets of the user at multiple time periods within a preset period, and obtain the user's genetic background information and clinical test report;

[0008] performing multimodal feature extraction on the chromosome microscopic image set within each time period to obtain a chromosome microscopic image feature dataset;

[0009] Extracting a clinical test data set according to the clinical test report, including a chromosome structural abnormality index, a chromosome number abnormality index, and a genetic disease risk index, and extracting genetic background feature data according to the genetic background information;

[0010] Processing and identifying the chromosome microscopic image feature data set corresponding to the user in each time period to obtain abnormal chromosome feature data, and marking the corresponding abnormal chromosome identification area as an abnormal tracking area;

[0011] Collecting a plurality of abnormal chromosome feature data corresponding to the abnormal tracking region to obtain an abnormal tracking region feature data set, and processing the data to obtain an abnormal risk assessment index;

[0012] Performing similarity matching based on the abnormal chromosome feature data of the abnormal tracking area through a preset chromosome abnormality feature database to obtain a plurality of historical similar abnormal samples that meet the requirements and their corresponding abnormality identification coefficients, and correcting the abnormal risk assessment index to obtain an abnormal risk correction index;

[0013] The genetic risk determination index of the abnormal tracking area is obtained by performing an evaluation based on the clinical test data set corresponding to the abnormal tracking area in each time period in combination with the genetic background feature data through a preset genetic risk assessment model;

[0014] The abnormality tracking region genetic risk determination index is compared with the abnormality risk correction index to obtain the abnormality assessment matching coefficient of the abnormality tracking region, and the abnormality assessment result is verified by threshold comparison with the preset abnormality identification matching threshold.

[0015] In an optional manner, performing multimodal feature extraction on the chromosome microscopic image set within each time period to obtain a chromosome microscopic image feature dataset includes:

[0016] Picking up image feature information from the chromosome microscopic image set in each time period using a preset multimodal feature extraction model to obtain a chromosome microscopic image feature dataset for each time period;

[0017] Corresponding chromosome microscopic image feature data is extracted according to the chromosome microscopic image feature data set, including chromosome morphological feature data, chromosome distribution feature data and chromosome texture feature data.

[0018] In an optional manner, extracting a clinical test data set according to the clinical test report, including a chromosome structural abnormality index, a chromosome number abnormality index, and a genetic disease risk index, and extracting genetic background feature data according to the genetic background information, includes:

[0019] Extracting a clinical test data set according to the clinical test report, including the chromosome structural abnormality index, the chromosome number abnormality index, and the genetic disease risk index within each time period;

[0020] Genetic background characteristic data are extracted based on the genetic background information, including family genetic disease history data, gene mutation frequency data, and environmental exposure risk data.

[0021] In an optional manner, processing and identifying the chromosome microscopic image feature data set corresponding to the user in each time period to obtain abnormal chromosome feature data, and marking the corresponding abnormal chromosome identification area as an abnormal tracking area, includes:

[0022] Processing and identifying the chromosome microscopic image feature data set corresponding to the user in each time period through a preset chromosome abnormality detection model to obtain abnormal chromosome feature data;

[0023] The abnormal chromosome characteristic data includes abnormal chromosome identification data, abnormal chromosome outline size data, abnormal chromosome breakpoint location data and abnormal chromosome recombination pattern data;

[0024] The abnormal chromosome identification area corresponding to the identification is obtained according to the abnormal chromosome identification data, and marked as the abnormal tracking area.

[0025] In an optional manner, the plurality of abnormal chromosome feature data corresponding to the abnormal tracking region are aggregated to obtain an abnormal tracking region feature data set, and processed to obtain an abnormal risk assessment index, including:

[0026] Collecting a plurality of abnormal chromosome feature data corresponding to the abnormal tracking region within the preset period to obtain an abnormal tracking region feature data set;

[0027] The abnormal tracking area feature data set is processed by a preset abnormal risk assessment model to obtain the abnormal risk assessment index of the abnormal tracking area; the calculation formula of the abnormal risk assessment index is: ;in, is the abnormal risk assessment index, For the The chromosome structural abnormality index within a preset time period, For the The chromosome number abnormality index within a preset time period, For the The chromosome texture abnormality index within a preset time period, Preset risk factors for abnormal areas, is the number of time periods within the preset period, 、 and is the first preset weight coefficient.

[0028] In an optional manner, the abnormal chromosome feature data of the abnormal tracking area is matched similarly with a preset chromosome abnormal feature database to obtain a plurality of historical similar abnormal samples that meet the requirements and their corresponding abnormal identification coefficients, and the abnormal risk assessment index is corrected to obtain an abnormal risk correction index, including:

[0029] Performing similarity matching processing on the abnormal chromosome feature data of the abnormal tracking area through a preset chromosome abnormality feature database to obtain multiple historical similar abnormal samples that meet similarity requirements;

[0030] Extracting corresponding abnormality identification coefficients for the final inspection of the sample based on the multiple historical similar abnormal samples;

[0031] The abnormal risk assessment index is corrected according to the plurality of abnormal identification coefficients to obtain an abnormal risk correction index; the correction calculation formula of the abnormal risk correction index is: ;in, is the abnormal risk correction index, For the The anomaly identification coefficient of historically similar anomaly samples, is the number of historical similar abnormal samples, For the The preset weight coefficient of historically similar abnormal samples.

[0032] In an optional manner, the clinical test data set corresponding to the abnormal tracking area in each time period is combined with the genetic background feature data and evaluated by a preset genetic risk assessment model to obtain the abnormal tracking area genetic risk determination index, including:

[0033] According to the chromosome structure abnormality index, chromosome number abnormality index and genetic disease risk index corresponding to the abnormal tracking area in each time period, a preset genetic risk assessment model is used to evaluate and process, thereby obtaining genetic risk identification data of the abnormal tracking area;

[0034] Correction processing is performed based on the abnormal tracking area genetic risk identification data and the family genetic disease history data, gene mutation frequency data, and environmental exposure risk data to obtain the abnormal tracking area genetic risk determination index of the user within the preset period;

[0035] The calculation formula for the abnormal tracking region genetic risk identification data is: ;in, Identify genetic risk data for abnormal tracking regions, For the Genetic disease risk index within a preset time period, 、 、 is the second preset weight coefficient;

[0036] The modified calculation formula for the abnormal tracking region genetic risk determination index is: ;in, To determine the genetic risk index for abnormal tracking regions, For family genetic disease history data, is the gene mutation frequency data, For environmental exposure risk data, 、 、 is the third preset weight coefficient.

[0037] In an optional manner, the abnormality tracking region genetic risk determination index is compared with the abnormality risk correction index to obtain the abnormality assessment matching coefficient of the abnormality tracking region, and the abnormality assessment result is verified by threshold comparison with a preset abnormality identification matching threshold, including:

[0038] Comparing the user's abnormality tracking area genetic risk determination index with the abnormality risk correction index to obtain an abnormality assessment matching coefficient for the abnormality tracking area;

[0039] Performing a threshold comparison between the anomaly assessment matching coefficient and a preset anomaly identification matching threshold, and verifying the anomaly assessment result based on the threshold comparison result;

[0040] The calculation formula of the abnormality assessment matching coefficient is: ;in, is the abnormality assessment matching coefficient, To determine the genetic risk index for abnormal tracking regions, is the abnormal risk correction index, and is the fourth preset weight coefficient.

[0041] In an optional approach, after obtaining the abnormal risk modification index, the following psychological intervention integration steps are performed:

[0042] a) Initiate a three-level psychological assessment mechanism:

[0043] The PHQ-9 and GAD-7 standardized scales were used for electronic assessment to generate psychological status scores;

[0044] Monitor the user's physiological behavior indicator data set (including sleep duration, activity trajectory, and eating frequency) and calculate the deviation from the preset baseline value;

[0045] The structured interview protocol was loaded and the key words were recorded through voice interaction to match the diagnostic awareness level;

[0046] b) Build a dynamic intervention matrix:

[0047] When the mental state score exceeds the first threshold, the cognitive behavioral therapy execution path is activated

[0048] When the behavioral deviation exceeds the second threshold for three consecutive days, a multidisciplinary consultation instruction is generated.

[0049] Generate a three-dimensional heat map visualization interface, with the horizontal axis correlating the abnormality assessment matching coefficient, the vertical axis mapping the psychological state score, and the color scale representing the intervention priority.

[0050] In an optional manner, the historical similar abnormal sample matching process includes:

[0051] Establish a case decision tree engine to associate historical similar case libraries based on diagnostic codes, extract treatment cycle and prognosis timeline maps, family care plan knowledge base, and genetic risk assessment correction parameters;

[0052] When it is detected that the user's search behavior contains preset keywords, similar case disposal records with a matching degree higher than 85% are automatically pushed;

[0053] The topological differences of chromosome breakpoints between the current abnormal tracking region and historical samples are highlighted in the visual interface;

[0054] It also includes uncertainty management mechanisms:

[0055] a) When the confidence level of chromosome image analysis is less than 90%:

[0056] Mark the abnormal tracking area with a dynamic flashing review mark;

[0057] The clinical manifestation database is linked to generate a pop-up window containing at least three differential diagnosis suggestions;

[0058] b) Establish a closed-loop feedback system:

[0059] Automatically initiated on the 7th and 30th day after the abnormal assessment result is generated:

[0060] 1) Chromosome microscopic image re-collection instructions

[0061] 2) Mental status score retest instructions

[0062] The weighting parameters of the preset genetic risk assessment model are dynamically adjusted according to the deviation degree of the retest data from the baseline value.

[0063] Compared with the prior art, the present invention has the following beneficial effects:

[0064] The chromosome abnormality detection method based on image analysis provided by the present invention obtains a user's chromosome microscopic image set and extracts a multimodal feature data set to obtain abnormal chromosome feature data of the abnormal tracking area, and then obtains an abnormal risk assessment index by collective processing. The abnormal identification coefficients of multiple historical similar abnormal samples are then combined to obtain an abnormal risk correction index.

[0065] Based on the acquired clinical test data set corresponding to the abnormal tracking area and combined with the genetic background characteristic data evaluation and processing, the genetic risk determination index of the abnormal tracking area is obtained, which is then compared with the abnormal risk correction index to obtain the abnormal assessment matching coefficient, and the abnormal assessment result is verified by threshold comparison; thereby achieving efficient identification and accurate assessment of various complex chromosomal abnormality types, and combining genetic background information and clinical data for comprehensive risk assessment to improve the reliability of the test results.

[0066] Through a three-tiered psychological assessment mechanism (scale evaluation, behavioral monitoring, and structured interviews), we comprehensively capture patients' subjective experiences and objective physiological changes, significantly improving the accuracy of psychological state identification and the timeliness of intervention. The dynamic intervention matrix can quickly identify patients requiring priority consultation, improving the efficiency of clinical decision support.

[0067] The case matching engine uses a feature matching algorithm to output historical cases with highly similar abnormal regions to the current patient, providing evidence-based medical support and optimizing treatment decisions. Topological difference visualization technology helps doctors quickly interpret the location of chromosomal abnormalities, significantly improving the efficiency of genetic counseling.

[0068] The confidence management system, through its quality assessment submodule, significantly reduces false positive rates and karyotype misclassification rates, and improves the review rate of suspicious results. A closed-loop feedback mechanism optimizes the genetic risk assessment model through retesting data, continuously improving the model's predictive accuracy and key feature recognition sensitivity.

[0069] Regular whole-genome reviews and structured telephone follow-up allow for early detection of chromosomal abnormalities and treatment side effects, ensuring timely prognostic assessments and improving overall treatment outcomes. Video push notifications of treatment records and real-time case comparisons enhance patient understanding of treatment plans, reduce decision-making anxiety, and improve patient compliance and satisfaction with treatment.

[0070] In summary, the present invention, through innovative technical means, fully demonstrates outstanding substantive features and significant technological progress compared to the prior art, and meets the requirements of the patent law for a high degree of creativity.

[0071] Other advantages, objects and features of the present invention will be described in part in the following description and, in part, will be apparent to those skilled in the art based on an examination of the following or may be learned from the practice of the invention. BRIEF DESCRIPTION OF THE DRAWINGS

[0072] To more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. Those skilled in the art can also derive other drawings based on these drawings without inventive effort.

[0073] Figure 1 The figure is a flowchart of a chromosome abnormality detection method based on image analysis. DETAILED DESCRIPTION

[0074] The technical solutions in the embodiments of the present invention will be described clearly and completely below. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments.

[0075] Example 1

[0076] Figure 1 FIG1 shows a flow chart of an embodiment of a chromosome abnormality detection method based on image analysis provided by the present invention. Figure 1 As shown, the method includes the following steps:

[0077] S1. Collect multiple chromosome microscopic image sets of the user at multiple time periods within a preset period, and obtain the user's genetic background information and clinical test report;

[0078] S2. performing multimodal feature extraction on the chromosome microscopic image set within each time period to obtain a chromosome microscopic image feature dataset;

[0079] S3. Extracting a clinical test data set according to the clinical test report, including a chromosome structural abnormality index, a chromosome number abnormality index, and a genetic disease risk index, and extracting genetic background feature data according to the genetic background information;

[0080] S4, processing and identifying the chromosome microscopic image feature data set corresponding to the user in each time period to obtain abnormal chromosome feature data, and marking the corresponding abnormal chromosome identification area as an abnormal tracking area;

[0081] S5. Collecting the multiple abnormal chromosome feature data corresponding to the abnormal tracking region to obtain an abnormal tracking region feature data set, and processing the data to obtain an abnormal risk assessment index;

[0082] S6. Perform similarity matching on the abnormal chromosome feature data of the abnormal tracking area using a preset chromosome abnormality feature database to obtain a plurality of historically similar abnormal samples that meet the requirements and their corresponding abnormality identification coefficients, and perform correction processing on the abnormal risk assessment index to obtain an abnormal risk correction index;

[0083] S7, evaluating and processing the clinical test data set corresponding to the abnormal tracking area in each time period in combination with the genetic background feature data using a preset genetic risk assessment model to obtain a genetic risk determination index for the abnormal tracking area;

[0084] S8. Compare the abnormality tracking region genetic risk determination index with the abnormality risk correction index to obtain the abnormality assessment matching coefficient of the abnormality tracking region, and perform a threshold comparison with a preset abnormality identification matching threshold to verify the abnormality assessment result.

[0085] In an optional manner, S2 includes:

[0086] Picking up image feature information from the chromosome microscopic image set in each time period using a preset multimodal feature extraction model to obtain a chromosome microscopic image feature dataset for each time period;

[0087] Corresponding chromosome microscopic image feature data is extracted according to the chromosome microscopic image feature data set, including chromosome morphological feature data, chromosome distribution feature data and chromosome texture feature data.

[0088] In an optional manner, S3 includes:

[0089] Extracting a clinical test data set according to the clinical test report, including the chromosome structural abnormality index, the chromosome number abnormality index, and the genetic disease risk index within each time period;

[0090] Genetic background characteristic data are extracted based on the genetic background information, including family genetic disease history data, gene mutation frequency data, and environmental exposure risk data.

[0091] In an optional manner, S4 includes:

[0092] Processing and identifying the chromosome microscopic image feature data set corresponding to the user in each time period through a preset chromosome abnormality detection model to obtain abnormal chromosome feature data;

[0093] The abnormal chromosome characteristic data includes abnormal chromosome identification data, abnormal chromosome outline size data, abnormal chromosome breakpoint location data and abnormal chromosome recombination pattern data;

[0094] The abnormal chromosome identification area corresponding to the identification is obtained according to the abnormal chromosome identification data, and marked as the abnormal tracking area.

[0095] In an optional manner, S5 includes:

[0096] Collecting a plurality of abnormal chromosome feature data corresponding to the abnormal tracking region within the preset period to obtain an abnormal tracking region feature data set;

[0097] The abnormal tracking area feature data set is processed by a preset abnormal risk assessment model to obtain the abnormal risk assessment index of the abnormal tracking area; the calculation formula of the abnormal risk assessment index is: ;in, is the abnormal risk assessment index, For the The chromosome structural abnormality index within a preset time period, For the The chromosome number abnormality index within a preset time period, For the The chromosome texture abnormality index within a preset time period, Preset risk factors for abnormal areas, is the number of time periods within the preset period, 、 and is the first preset weight coefficient.

[0098] In an optional manner, S6 includes:

[0099] Performing similarity matching processing on the abnormal chromosome feature data of the abnormal tracking area through a preset chromosome abnormality feature database to obtain multiple historical similar abnormal samples that meet similarity requirements;

[0100] Extracting corresponding abnormality identification coefficients for the final inspection of the sample based on the multiple historical similar abnormal samples;

[0101] The abnormal risk assessment index is corrected according to the plurality of abnormal identification coefficients to obtain an abnormal risk correction index; the correction calculation formula of the abnormal risk correction index is: ;in, is the abnormal risk correction index, For the The anomaly identification coefficient of historically similar anomaly samples, is the number of historical similar abnormal samples, For the The preset weight coefficient of historically similar abnormal samples.

[0102] In an optional embodiment, S7 includes:

[0103] According to the chromosome structure abnormality index, chromosome number abnormality index and genetic disease risk index corresponding to the abnormal tracking area in each time period, a preset genetic risk assessment model is used to evaluate and process, thereby obtaining genetic risk identification data of the abnormal tracking area;

[0104] Correction processing is performed based on the abnormal tracking area genetic risk identification data and the family genetic disease history data, gene mutation frequency data, and environmental exposure risk data to obtain the abnormal tracking area genetic risk determination index of the user within the preset period;

[0105] The calculation formula for the abnormal tracking region genetic risk identification data is: ;in, Identify genetic risk data for abnormal tracking regions, For the Genetic disease risk index within a preset time period, 、 、 is the second preset weight coefficient;

[0106] The modified calculation formula for the abnormal tracking region genetic risk determination index is: ;in, To determine the genetic risk index for abnormal tracking regions, For family genetic disease history data, is the gene mutation frequency data, For environmental exposure risk data, 、 、 is the third preset weight coefficient.

[0107] In an optional embodiment, S8 includes:

[0108] Comparing the user's abnormality tracking area genetic risk determination index with the abnormality risk correction index to obtain an abnormality assessment matching coefficient for the abnormality tracking area;

[0109] Performing a threshold comparison between the anomaly assessment matching coefficient and a preset anomaly identification matching threshold, and verifying the anomaly assessment result based on the threshold comparison result;

[0110] The calculation formula of the abnormality assessment matching coefficient is: ;in, is the abnormality assessment matching coefficient, To determine the genetic risk index for abnormal tracking regions, is the abnormal risk correction index, and is the fourth preset weight coefficient.

[0111] In this embodiment, it should be noted that:

[0112] The core of the present invention's chromosome abnormality detection method based on image analysis lies in achieving efficient identification and accurate assessment of complex chromosome abnormality types through multimodal feature extraction, a dynamic weight allocation mechanism, and a multi-level abnormality classification model. Specifically:

[0113] 1) According to Figure 1 As shown in the overall process, this embodiment collects multiple sets of chromosome microscopic images of the user within a preset period, and simultaneously obtains the user's genetic background information and clinical test reports. These data form the basis for subsequent analysis. Specifically, the chromosome microscopic image set is obtained through a high-resolution microscope to ensure that the image quality meets the analysis requirements. Genetic background information includes family genetic disease history data, gene mutation frequency data, and environmental exposure risk data, while the clinical test report covers the chromosome structural abnormality index, chromosome number abnormality index, and genetic disease risk index. The collection process of these data must strictly follow standardized operating procedures to ensure the accuracy and consistency of the data.

[0114] 2) Entering the multimodal feature extraction stage, this embodiment uses a preset multimodal feature extraction model to process the chromosome microscopic image set within each time period to extract chromosome morphological feature data, chromosome distribution feature data, and chromosome texture feature data. These feature data together constitute the chromosome microscopic image feature data set. Among them, the chromosome morphological feature data is used to describe the overall shape and outline of the chromosome; the chromosome distribution feature data reflects the spatial distribution pattern of the chromosome in the cell nucleus; and the chromosome texture feature data captures the microscopic texture changes on the chromosome surface. The key to this stage lies in the design of the multimodal feature extraction model, which uses a deep learning algorithm to automatically learn and extract key features in the image, thereby improving the efficiency and accuracy of feature extraction.

[0115] 3) This embodiment processes and identifies the user's chromosome microscopic image feature data set in each time period, obtains abnormal chromosome feature data, and marks the corresponding abnormal chromosome identification area as the abnormal tracking area. This process relies on a preset chromosome abnormality detection model, which can accurately identify the identification data, contour size data, breakpoint location data and recombination pattern data of abnormal chromosomes by learning from a large number of historical samples. The generation of the abnormal tracking area is completed by mapping the abnormal chromosome identification data to the original image, and the marking results are presented in a visual form to facilitate subsequent analysis. The technical difficulty at this stage lies in how to design an efficient abnormality detection model so that it can accurately distinguish between normal and abnormal chromosomes in a complex background.

[0116] 4) After obtaining the abnormal tracking area, the system collects multiple abnormal chromosome feature data within a preset period to form an abnormal tracking area feature data set, and calculates the abnormal risk assessment index using the preset abnormal risk assessment model. The calculation formula for the abnormal risk assessment index is: The physical significance of this formula lies in its comprehensive consideration of abnormalities in chromosome structure, number, and texture, and its dynamic weighting mechanism emphasizes the importance of different features. For example, in certain diseases, chromosome structural abnormalities may be more diagnostically valuable than numerical abnormalities, and the weight coefficients can be adjusted to reflect this characteristic.

[0117] 5) To further improve the accuracy of abnormality risk assessment, this embodiment performs similarity matching on the abnormal chromosome feature data of the abnormality tracking area with a preset chromosome abnormality feature database to obtain multiple historically similar abnormal samples that meet the requirements and their corresponding abnormality identification coefficients. Subsequently, the system corrects the abnormality risk assessment index based on these abnormality identification coefficients to obtain the abnormality risk correction index. The correction calculation formula is: The core idea of ​​this formula is to correct the current evaluation results by introducing the abnormal identification coefficient of historical samples, thereby reducing the errors that may be caused by a single model.

[0118] 6) At the same time, this embodiment also combines the user's clinical test data set and genetic background feature data to calculate the abnormal tracking area genetic risk determination index through a preset genetic risk assessment model. The calculation of the genetic risk determination index is divided into two steps: First, the abnormal tracking area genetic risk identification data is calculated based on the chromosome structure abnormality index, chromosome number abnormality index and genetic disease risk index, and the formula is: Secondly, the genetic risk identification data is corrected by combining family genetic disease history data, gene mutation frequency data, and environmental exposure risk data to obtain the final genetic risk determination index, the formula of which is: ; This process fully demonstrates the importance of genetic background information and clinical data in the detection of chromosomal abnormalities.

[0119] 7) After obtaining the abnormal risk correction index and the genetic risk determination index, this embodiment compares the two, calculates the abnormality assessment matching coefficient, and verifies the abnormality assessment result through threshold comparison. The calculation formula for the abnormality assessment matching coefficient is: This formula is designed to comprehensively consider both genetic risk and abnormality risk, balancing their impact through a dynamic weighting mechanism. Ultimately, the system compares the abnormality assessment match coefficient with a preset abnormality identification match threshold. If the match coefficient exceeds the threshold, the test is considered abnormal; otherwise, it is considered normal.

[0120] For example, suppose a user undergoes chromosome testing in three preset time periods (n=3), and the genetic background information includes: family genetic disease history data (F) = 0.8 (significant family history), gene mutation frequency data (M) = 0.6 (medium-high frequency), and environmental exposure risk data (E) = 0.4 (medium exposure). In the clinical test report: the chromosome structural abnormality index ( =0.5, =0.7, =0.6), chromosome number abnormality index ( =0.3, =0.4, =0.5), genetic disease risk index ( =0.6, =0.7, =0.8). Extract chromosome microscopic image feature data of three time periods: chromosome morphological feature data (such as outline size), chromosome distribution feature data (spatial arrangement), chromosome texture feature chromosome distribution feature (surface details). Assume that the chromosome texture abnormality index ( =0.4, =0.5, =0.6). Abnormal risk assessment index =0.664. Two historically similar anomaly samples (m=2) were matched from the historical database: Sample 1: =0.8 (high risk), weight =0.6; Sample 2: =0.5 (medium risk), weight =0.4; Abnormal risk correction index =1.004. Abnormal tracking region genetic risk identification data The calculated value is 2.05, and the abnormal tracking region genetic risk determination index is calculated to be 2.71, so the abnormal assessment matching coefficient The default abnormality identification matching threshold is 5.0. Since 5.476>5.0, the user's chromosome is determined to be abnormal.

[0121] The technical solution of this embodiment obtains the user's chromosome microscopic image set and extracts the multimodal feature data set for processing to obtain the abnormal chromosome feature data of the abnormal tracking area, and then performs collective processing to obtain the abnormal risk assessment index, which is then corrected by combining the abnormal identification coefficients of multiple historical similar abnormal samples to obtain the abnormal risk correction index. According to the obtained clinical test data set corresponding to the abnormal tracking area, combined with the genetic background feature data, the genetic risk determination index of the abnormal tracking area is obtained for evaluation and processing, which is then compared with the abnormal risk correction index to obtain the abnormal assessment matching coefficient, and the abnormal assessment result is verified by threshold comparison; thereby, efficient identification and accurate assessment of various complex chromosomal abnormality types are achieved, and comprehensive risk assessment is performed in combination with genetic background information and clinical data to improve the reliability of the test results.

[0122] Example 2

[0123] On the other hand, the present invention provides an embodiment of a chromosome abnormality detection system based on image analysis based on embodiment 1, the system comprising:

[0124] The first processing module is used to collect multiple chromosome microscopic image sets of the user at multiple time periods within a preset period, and obtain the user's genetic background information and clinical test report;

[0125] a second processing module, configured to perform multimodal feature extraction on the chromosome microscopic image set within each time period to obtain a chromosome microscopic image feature dataset;

[0126] A third processing module is used to extract a clinical test data set according to the clinical test report, including a chromosome structural abnormality index, a chromosome number abnormality index, and a genetic disease risk index, and to extract genetic background feature data according to the genetic background information;

[0127] a fourth processing module, configured to process and identify the chromosome microscopic image feature data set corresponding to the user in each time period, obtain abnormal chromosome feature data, and mark the corresponding abnormal chromosome identification area as an abnormal tracking area;

[0128] a fifth processing module, configured to aggregate the plurality of abnormal chromosome feature data corresponding to the abnormal tracking region to obtain an abnormal tracking region feature data set, and perform processing to obtain an abnormal risk assessment index;

[0129] a sixth processing module, configured to perform similarity matching based on the abnormal chromosome feature data of the abnormal tracking area through a preset chromosome abnormality feature database, obtain a plurality of historical similar abnormal samples that meet the requirements and their corresponding abnormality identification coefficients, and perform correction processing on the abnormal risk assessment index to obtain an abnormal risk correction index;

[0130] A seventh processing module is configured to evaluate and process the clinical test data set corresponding to the abnormal tracking area in each time period in combination with the genetic background feature data using a preset genetic risk assessment model to obtain a genetic risk determination index for the abnormal tracking area;

[0131] The abnormality verification module is used to compare the genetic risk determination index of the abnormal tracking area with the abnormal risk correction index to obtain the abnormality assessment matching coefficient of the abnormal tracking area, and compare the threshold with the preset abnormality identification matching threshold to verify the abnormality assessment result.

[0132] In an optional manner, the second processing module is specifically configured to:

[0133] Picking up image feature information from the chromosome microscopic image set in each time period using a preset multimodal feature extraction model to obtain a chromosome microscopic image feature dataset for each time period;

[0134] Corresponding chromosome microscopic image feature data is extracted according to the chromosome microscopic image feature data set, including chromosome morphological feature data, chromosome distribution feature data and chromosome texture feature data.

[0135] It should be noted that the beneficial effects of the chromosome abnormality detection system based on image analysis provided in the above embodiment are the same as the beneficial effects of the chromosome abnormality detection method based on image analysis provided above, and will not be repeated here.

[0136] Example 3

[0137] This embodiment introduces new steps based on embodiment 1: such as the psychological intervention integration step and the uncertainty management mechanism, which are specifically implemented as follows:

[0138] After obtaining the abnormal risk modification index, perform the following psychological intervention integration steps:

[0139] The system integrates the PHQ-9 and GAD-7 electronic assessment systems, generating a dynamic questionnaire interface on the user's terminal. Based on the user's real-time response data, the system automatically calculates depression and anxiety index scores and generates a time-stamped psychological status change curve.

[0140] Smart wearable devices (such as smartwatches) continuously collect user physiological behavioral data, including sleep duration, activity patterns, and meal frequency. Accelerometers are used to measure nighttime limb movement frequency to assess sleep duration. GPS location data and geofencing technology are combined to calculate the user's daily activity radius. Meal frequency data is obtained through a pre-set voice input interface for meal logging. A baseline calculation model is established, using the moving average of the user's data from the previous seven days as a dynamic baseline, and the deviation percentage is calculated in real time.

[0141] Deploy a voice interaction robot and load a library of 20 standard interview questions (e.g., "Are you aware of the impact of chromosomal abnormalities on offspring?"). Use natural language processing to extract keywords (e.g., "don't understand" and "fear of hereditary"). Then match them to a pre-set awareness level (low, medium, or high).

[0142] When the PHQ-9 score is >15 points and persists for 3 days, the cognitive behavioral therapy (CBT) digital course push system will be activated, and the treatment units (such as cognitive reconstruction training and exposure therapy simulation) will be unlocked according to the preset path.

[0143] If the activity radius deviates from the baseline by more than 40% for 72 hours, a multidisciplinary consultation order generator is triggered. A consultation request document containing chromosome testing data, psychological assessment reports, and behavioral monitoring charts is automatically generated and sent simultaneously to the genetics, psychiatry, and social work departments through the hospital's HIS system.

[0144] The visualization engine generates a three-dimensional heat map based on real-time data. The X-axis correlates the abnormality assessment match coefficient (normalized to 0-1), the Y-axis maps the comprehensive psychological status score (weighted PHQ-9 + GAD-7), and the color scale indicates the intervention priority (red: intervention required within 24 hours; yellow: intervention required within 72 hours; green: routine monitoring). Abnormal areas on the heat map are highlighted on the doctor's workstation interface and linked to the corresponding patient's whole genome data visualization panel.

[0145] In an optional manner, the historically similar abnormal sample matching process includes the following:

[0146] Case decision tree engine: Establish a structured case database, each historical case contains chromosome breakpoint coordinates (based on the GRCh38 genome reference sequence), treatment cycle map (marking chemotherapy / surgery / follow-up key time nodes) and prognostic parameter set (5-year survival rate, complication rate, etc.).

[0147] Develop a feature matching algorithm. The input layer receives the coordinates of the abnormal tracking area of ​​the current patient, the hidden layer calculates the overlap of the breakpoints with historical cases (using the Jaccard similarity coefficient), and the output layer outputs the top 5 similar cases with a matching degree >85% and extracts their home care plans (such as nutritional supplement formulas and rehabilitation training plans).

[0148] Intelligent push system: A keyword monitoring module is deployed on the patient's mobile terminal. When it detects that the search record contains preset keywords such as genetic risks and fertility advice, the case matching interface is automatically called to push the treatment record video of similar cases (including medical animation explanation).

[0149] A chromosome topology comparison tool was developed, using Circos visualization technology to present the current abnormal region and the breakpoints of historical cases in the form of concentric circles, and flashing polygon boxes were used to identify the microdeletion / microduplication regions unique to the current patient.

[0150] In an optional approach, uncertainty management mechanisms are also included:

[0151] Confidence management system: A quality assessment submodule is embedded in the chromosome image analysis module to calculate the confidence index of karyotype analysis based on the chromosome banding clarity (grayscale gradient value) and the number of mitotic phases (≥20 valid mitotic phases).

[0152] When the confidence level is <90%, the abnormal area is marked with an orange flashing border (frequency 2 Hz) in the electronic report, and a pop-up window displays a list of differential diagnosis recommendations (such as the recommendation to perform additional FISH to verify the interarm inversion of chromosome 9).

[0153] Closed-loop feedback system: On day 7 after initial diagnosis, chromosome resampling instructions (including specific banding pattern retesting requirements) are automatically sent to the laboratory's LIS system, and psychological retesting instructions (a shortened version of the PHQ-4 scale) are sent to the patient's mobile device. On day 30, instructions for whole-genome microarray retesting (comparing CNV changes found in the initial test) and a structured follow-up telephone call (including 10 prognostic assessment questions) are initiated.

[0154] The retest data is fed into the genetic risk assessment model, and the back-propagation algorithm is used to adjust feature weights. If the psychological score deteriorates, the behavioral data weight coefficient is increased; if the chromosomal abnormality area expands, the microscopic image feature weight is increased.

[0155] The above embodiments are exemplary and should not be construed as limiting the present invention. A person skilled in the art may change, modify, replace and modify the above embodiments within the scope of the present invention.

Claims

1. A chromosome abnormality detection method based on image analysis, characterized in that: include: Collect multiple chromosome microscopic image sets of the user at multiple time periods within a preset period, and obtain the user's genetic background information and clinical test report; performing multimodal feature extraction on the chromosome microscopic image set within each time period to obtain a chromosome microscopic image feature dataset; Extracting a clinical test data set according to the clinical test report, including a chromosome structural abnormality index, a chromosome number abnormality index, and a genetic disease risk index, and extracting genetic background feature data according to the genetic background information; Processing and identifying the chromosome microscopic image feature data set corresponding to the user in each time period to obtain abnormal chromosome feature data, and marking the corresponding abnormal chromosome identification area as an abnormal tracking area; Collecting a plurality of abnormal chromosome feature data corresponding to the abnormal tracking region to obtain an abnormal tracking region feature data set, and processing the data to obtain an abnormal risk assessment index; Performing similarity matching based on the abnormal chromosome feature data of the abnormal tracking area through a preset chromosome abnormality feature database to obtain a plurality of historical similar abnormal samples that meet the requirements and their corresponding abnormality identification coefficients, and correcting the abnormal risk assessment index to obtain an abnormal risk correction index; The genetic risk determination index of the abnormal tracking area is obtained by performing an evaluation based on the clinical test data set corresponding to the abnormal tracking area in each time period in combination with the genetic background feature data through a preset genetic risk assessment model; The abnormality tracking region genetic risk determination index is compared with the abnormality risk correction index to obtain the abnormality assessment matching coefficient of the abnormality tracking region, and the abnormality assessment result is verified by threshold comparison with the preset abnormality identification matching threshold.

2. The method for detecting chromosome abnormalities based on image analysis according to claim 1, wherein: The multimodal feature extraction is performed on the chromosome microscopic image set in each time period to obtain a chromosome microscopic image feature data set, including: Picking up image feature information from the chromosome microscopic image set in each time period using a preset multimodal feature extraction model to obtain a chromosome microscopic image feature dataset for each time period; Corresponding chromosome microscopic image feature data is extracted according to the chromosome microscopic image feature data set, including chromosome morphological feature data, chromosome distribution feature data and chromosome texture feature data.

3. The method for detecting chromosome abnormalities based on image analysis according to claim 1, wherein: The extracting of a clinical test data set according to the clinical test report, including a chromosome structural abnormality index, a chromosome number abnormality index, and a genetic disease risk index, and extracting genetic background feature data according to the genetic background information, includes: Extracting a clinical test data set according to the clinical test report, including the chromosome structural abnormality index, the chromosome number abnormality index, and the genetic disease risk index within each time period; Genetic background characteristic data are extracted based on the genetic background information, including family genetic disease history data, gene mutation frequency data, and environmental exposure risk data.

4. The method for detecting chromosome abnormalities based on image analysis according to claim 1, wherein: The processing and identifying of the chromosome microscopic image feature data set corresponding to the user in each time period to obtain abnormal chromosome feature data, and marking the corresponding abnormal chromosome identification area as an abnormal tracking area, includes: Processing and identifying the chromosome microscopic image feature data set corresponding to the user in each time period through a preset chromosome abnormality detection model to obtain abnormal chromosome feature data; The abnormal chromosome characteristic data includes abnormal chromosome identification data, abnormal chromosome outline size data, abnormal chromosome breakpoint location data and abnormal chromosome recombination pattern data; The abnormal chromosome identification area corresponding to the identification is obtained according to the abnormal chromosome identification data, and marked as the abnormal tracking area.

5. The method for detecting chromosome abnormalities based on image analysis according to claim 3, wherein: The step of aggregating the plurality of abnormal chromosome feature data corresponding to the abnormal tracking region to obtain an abnormal tracking region feature data set, and processing the data to obtain an abnormal risk assessment index includes: Collecting a plurality of abnormal chromosome feature data corresponding to the abnormal tracking region within the preset period to obtain an abnormal tracking region feature data set; The abnormal tracking area feature data set is processed by a preset abnormal risk assessment model to obtain the abnormal risk assessment index of the abnormal tracking area; the calculation formula of the abnormal risk assessment index is: ;in, is the abnormal risk assessment index, For the The chromosome structural abnormality index within a preset time period, For the The chromosome number abnormality index within a preset time period, For the The chromosome texture abnormality index within a preset time period, Preset risk factors for abnormal areas, is the number of time periods within the preset period, 、 and is the first preset weight coefficient.

6. The method for detecting chromosome abnormalities based on image analysis according to claim 5, characterized in that: The abnormal chromosome feature data of the abnormal tracking area is matched similarly with a preset chromosome abnormal feature database to obtain a plurality of historical similar abnormal samples that meet the requirements and their corresponding abnormal identification coefficients, and the abnormal risk assessment index is corrected to obtain an abnormal risk correction index, including: Performing similarity matching processing on the abnormal chromosome feature data of the abnormal tracking area through a preset chromosome abnormality feature database to obtain multiple historical similar abnormal samples that meet similarity requirements; Extracting corresponding abnormality identification coefficients for the final inspection of the sample based on the multiple historical similar abnormal samples; The abnormal risk assessment index is corrected according to the plurality of abnormal identification coefficients to obtain an abnormal risk correction index; the correction calculation formula of the abnormal risk correction index is: ;in, is the abnormal risk correction index, For the The anomaly identification coefficient of historically similar anomaly samples, is the number of historical similar abnormal samples, For the The preset weight coefficient of historically similar abnormal samples.

7. The method for detecting chromosome abnormalities based on image analysis according to claim 6, characterized in that: The step of performing evaluation and processing based on the clinical test data set corresponding to the abnormal tracking area in each time period in combination with the genetic background feature data using a preset genetic risk assessment model to obtain a genetic risk determination index for the abnormal tracking area includes: According to the chromosome structure abnormality index, chromosome number abnormality index and genetic disease risk index corresponding to the abnormal tracking area in each time period, a preset genetic risk assessment model is used to evaluate and process, thereby obtaining genetic risk identification data of the abnormal tracking area; Correction processing is performed based on the abnormal tracking area genetic risk identification data and the family genetic disease history data, gene mutation frequency data, and environmental exposure risk data to obtain the abnormal tracking area genetic risk determination index of the user within the preset period; The calculation formula for the abnormal tracking region genetic risk identification data is: ;in, Identify genetic risk data for abnormal tracking regions, For the Genetic disease risk index within a preset time period, 、 、 is the second preset weight coefficient; The modified calculation formula for the abnormal tracking region genetic risk determination index is: ;in, To determine the genetic risk index for abnormal tracking regions, For family genetic disease history data, is the gene mutation frequency data, For environmental exposure risk data, 、 、 is the third preset weight coefficient.

8. The method for detecting chromosome abnormalities based on image analysis according to claim 7, characterized in that: The step of comparing the abnormality tracking region genetic risk determination index with the abnormality risk correction index to obtain an abnormality assessment matching coefficient for the abnormality tracking region, and performing a threshold comparison with a preset abnormality identification matching threshold to verify the abnormality assessment result includes: Comparing the user's abnormality tracking area genetic risk determination index with the abnormality risk correction index to obtain an abnormality assessment matching coefficient for the abnormality tracking area; Performing a threshold comparison between the anomaly assessment matching coefficient and a preset anomaly identification matching threshold, and verifying the anomaly assessment result based on the threshold comparison result; The calculation formula of the abnormality assessment matching coefficient is: ;in, is the abnormality assessment matching coefficient, To determine the genetic risk index for abnormal tracking regions, is the abnormal risk correction index, and is the fourth preset weight coefficient.

9. The method for detecting chromosome abnormalities based on image analysis according to claim 1, wherein: After obtaining the abnormal risk modification index, perform the following psychological intervention integration steps: a) Initiate a three-level psychological assessment mechanism: The PHQ-9 and GAD-7 standardized scales were used for electronic assessment to generate psychological status scores; Monitor the user's physiological behavior indicator data set and calculate the deviation from the preset baseline value; The structured interview protocol was loaded and the key words were recorded through voice interaction to match the diagnostic awareness level; b) Build a dynamic intervention matrix: When the mental state score exceeds the first threshold, the cognitive behavioral therapy execution path is activated When the behavioral deviation exceeds the second threshold for three consecutive days, a multidisciplinary consultation instruction is generated. Generate a three-dimensional heat map visualization interface, with the horizontal axis correlating the abnormality assessment matching coefficient, the vertical axis mapping the psychological state score, and the color scale representing the intervention priority.

10. The method for detecting chromosome abnormalities based on image analysis according to claim 1, wherein: The historical similar abnormal sample matching process includes: Establish a case decision tree engine to associate historical similar case libraries based on diagnostic codes, extract treatment cycle and prognosis timeline maps, family care plan knowledge base, and genetic risk assessment correction parameters; When it is detected that the user's search behavior contains preset keywords, similar case disposal records with a matching degree higher than 85% are automatically pushed; The topological differences of chromosome breakpoints between the current abnormal tracking region and historical samples are highlighted in the visual interface; It also includes uncertainty management mechanisms: a) When the confidence level of chromosome image analysis is less than 90%: Mark the abnormal tracking area with a dynamic flashing review mark; The clinical manifestation database is linked to generate a pop-up window containing at least three differential diagnosis suggestions; b) Establish a closed-loop feedback system: Automatically initiated on the 7th and 30th day after the abnormal assessment result is generated: 1) Chromosome microscopic image re-collection instructions 2) Mental status score retest instructions The weighting parameters of the preset genetic risk assessment model are dynamically adjusted according to the deviation degree of the retest data from the baseline value.

Images