Method and system for processing thyroid function data based on spectrum technology

Abstract

The invention discloses a method and system for processing thyroid function data based on a spectrum technology, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting a face video through employing a near infrared spectrum imaging technology, determining a face core region in the face video, and obtaining a face core region; the method comprises the following steps: capturing an absorption energy spectrum characteristic value of a human body trace substance in a human face core area to specific wave band light, obtaining spectrum original data associated with thyroid function, and synchronously recording age information of an acquisition object; on the basis of the preset rule, in combination with the age information of the collection object and the substance detection index related to the thyroid function, the thyroid function state of the collection object is graded and judged to obtain the graded judgment result, and the problem that thyroid function data cannot be processed based on the spectrum technology in the prior art is solved.

Description

Technical Field

[0001] The present invention relates to the field of artificial intelligence technology, and in particular to a method and system for processing thyroid function data based on spectral technology. Background Art

[0002] The thyroid gland is located below the thyroid cartilage in the neck, on both sides of the trachea. It is shaped like a butterfly and is an important endocrine organ in the human body. It plays a vital role in human growth and development, metabolism, energy consumption, etc. As the largest endocrine gland in the human body, the good or bad function of the thyroid gland directly affects human metabolism.

[0003] Currently, thyroid function tests mainly include blood tests, thyroid iodine uptake tests, thyroid imaging, physical examinations, B-ultrasound examinations, CT examinations, and thyroid iodine-131 uptake tests. Among them, blood tests are the basic method for examining thyroid function, which assesses the functional status of the thyroid gland by measuring the levels of thyroid hormones (such as total triiodothyronine T3, total thyroxine T4, free triiodothyronine T3, and free thyroxine T4) and thyroid-stimulating hormone (TSH) in the blood.

[0004] Since traditional detection methods require first drawing blood to obtain human serum or plasma, and then using the above methods to detect relevant indicators, the equipment is cumbersome to operate, has a low degree of automation, can easily cause discomfort to the human body, is time-consuming and labor-intensive, and users are not satisfied with traditional detection methods.

[0005] Therefore, there is an urgent need for a fast, convenient, sensitive, highly accurate and non-destructive method for determining thyroid function. Summary of the Invention

[0006] In view of this, the present invention proposes a method and system for processing thyroid function data based on spectral technology, which can realize the processing of thyroid function data based on spectral technology.

[0007] To achieve the above object, the present invention provides the following technical solutions:

[0008] A method for processing thyroid function data based on spectral technology, comprising:

[0009] Near-infrared spectral imaging technology is used to capture facial videos, determine the core area of ​​the face in the video, capture the spectral characteristic values ​​of the absorption energy of trace substances in the human body to light in a specific band within the core area of ​​the face, obtain the original spectral data associated with thyroid function, and simultaneously record the age information of the collected subjects;

[0010] Based on preset rules, combined with the age information of the collected subjects and the detection indicators of substances related to thyroid function, the thyroid function status of the collected subjects is graded and judged to obtain a graded judgment result.

[0011] On the basis of the above technical solution, the present invention can also be improved as follows:

[0012] Optionally, the deep capture of characteristic values ​​of energy spectrum of human body trace substances in the core area of ​​the face to light of a specific wavelength band, and acquisition of raw spectral data associated with thyroid function, includes:

[0013] The absorption energy of light in a specific wavelength band in the core area of ​​the face is detected pixel by pixel, the optical signal is converted into an electrical signal, and the electrical signal is then converted into a digital signal through analog-to-digital conversion;

[0014] A spectrum analysis algorithm is used to extract spectral characteristic values ​​of the absorption of light of different wavelengths by trace substances in the human body from the digital signal, and to obtain original spectrum data associated with thyroid function.

[0015] Optionally, before the step of grading the thyroid function status of the sampled subject, the method further comprises:

[0016] The sliding average filtering method was used to eliminate the noise of the raw spectral data;

[0017] Correct the baseline drift of the original spectral data after noise elimination;

[0018] The spectral raw data after baseline drift correction were normalized to eliminate the differences in data dimension and distribution caused by differences in acquisition equipment and environment.

[0019] Optionally, the method for processing thyroid function data based on spectral technology further includes:

[0020] Calculating the correlation coefficient between the substance detection index and the thyroid function status;

[0021] Dividing the substance detection indicators into primary indicators and secondary indicators based on the correlation coefficient;

[0022] The main indicators include triiodothyronine, thyroxine, and thyrotropin; the secondary indicators include blood glucose, low-density lipoprotein, high-density lipoprotein, total cholesterol, and triglycerides.

[0023] Optionally, the preset rules include:

[0024] When the user is under 45 years old, when all the main indicators and secondary indicators are normal, it is judged that the thyroid function is normal. If any one of the main indicators and secondary indicators exceeds the normal range, it is judged that the thyroid function is slightly abnormal.

[0025] For users aged 46 ≤ ≤ 50 years, if only one of the secondary indicators is abnormal, it is considered as mild thyroid dysfunction; if ≥ 2 of the secondary indicators are abnormal, it is considered as moderate thyroid dysfunction; if the secondary indicator is abnormal and the primary indicator is abnormal at the same time, it is considered as severe thyroid dysfunction;

[0026] For users aged 51-60, if less than 2 of the secondary indicators are abnormal, it is considered a mild abnormality; if 2 or more of the secondary indicators are abnormal, but the primary indicators are normal, it is considered a moderate abnormality of thyroid function; if 2 or more of the secondary indicators are abnormal, but 1 of the primary indicators is abnormal, it is considered a severe abnormality of thyroid function; if there are no secondary indicators abnormalities but 2 or more of the primary indicators are abnormal, it is considered a severe abnormality of thyroid function.

[0027] If the user is over 60 years old and two of the secondary indicators are abnormal and one of the primary indicators is abnormal, it is judged as moderate abnormality; if the number of abnormal indicators is greater than three, it is judged as severe abnormality.

[0028] A system for processing thyroid function data based on spectral technology, comprising:

[0029] A data acquisition module is used to capture facial videos using near-infrared spectral imaging technology, determine the core area of ​​the face in the facial video, deeply capture the spectral characteristic values ​​of the absorption energy of trace substances in the human body to light of specific wavelengths within the core area of ​​the face, obtain raw spectral data associated with thyroid function, and simultaneously record the age information of the collected subject;

[0030] The discrimination module is used to grade the thyroid function status of the collected object based on preset rules, combined with the age information of the collected object and the substance detection indicators related to thyroid function, to obtain a graded discrimination result.

[0031] Optionally, the data acquisition module is further configured to:

[0032] The absorption energy of light in a specific wavelength band in the core area of ​​the face is detected pixel by pixel, the optical signal is converted into an electrical signal, and the electrical signal is then converted into a digital signal through analog-to-digital conversion;

[0033] A spectrum analysis algorithm is used to extract spectral characteristic values ​​of the absorption of light of different wavelengths by trace substances in the human body from the digital signal, and to obtain original spectrum data associated with thyroid function.

[0034] The system for processing thyroid function data based on spectral technology further includes an indicator classification module, which is further used to:

[0035] Calculating the correlation coefficient between the substance detection index and the thyroid function status;

[0036] Dividing the substance detection indicators into primary indicators and secondary indicators based on the correlation coefficient;

[0037] The main indicators include triiodothyronine, thyroxine, and thyrotropin; the secondary indicators include blood glucose, low-density lipoprotein, high-density lipoprotein, total cholesterol, and triglycerides.

[0038] An electronic device comprises a memory, a processor and a computer program stored in the memory and running on the processor, wherein the steps of the method are implemented when the processor executes the computer program.

[0039] A non-transitory computer-readable storage medium stores a computer program, which implements the steps of the method when executed by a processor.

[0040] The present invention has the following advantages:

[0041] The method of processing thyroid function data based on spectral technology in the present invention uses spectral technology to non-invasively collect facial spectra and age information, breaking through the trauma and limitations of traditional blood sampling tests to achieve convenient and discomfort-free testing; constructing an age-thyroid function abnormality assessment model that integrates age and component-disease associations, adapts to all age groups, and accurately stratifies to reduce misdiagnosis; forming a closed loop of detection-modeling-evaluation, assisting personalized diagnosis and treatment, and promoting the management of thyroid diseases to be non-invasive, precise, and intelligent, thereby improving medical efficiency and patient experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] For purposes of illustration and not limitation, the present invention will now be described with reference to embodiments thereof and the accompanying drawings, in which:

[0043] Figure 1 Schematic diagram of a process for processing thyroid function data based on spectral technology in an embodiment of the present invention;

[0044] Figure 2 Schematic diagram of the main components of a system for processing thyroid function data based on spectroscopy technology in an embodiment of the present invention;

[0045] Figure 3 This is a schematic diagram of the physical structure of the electronic device provided by the present invention. DETAILED DESCRIPTION

[0046] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work should fall within the scope of protection of the present invention.

[0047] It should be noted that the terms "first," "second," and the like in the description of the present invention and the accompanying drawings are used to distinguish similar objects and are not necessarily used to describe a particular order or precedence. It should be understood that the terms used in this manner are interchangeable where appropriate for the embodiments of the present invention described herein. In addition, the terms "including," "having," and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product, or apparatus comprising a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units that are not explicitly listed or that are inherent to these processes, methods, products, or apparatuses.

[0048] It should be noted that, in the absence of conflict, the embodiments of the present invention and the features thereof can be combined with each other. The embodiments of the present invention will be described in detail below with reference to the accompanying drawings.

[0049] Figure 1 FIG. 1 is a flow chart of a method for processing thyroid function data based on spectral technology in an embodiment of the present invention, as shown in FIG. Figure 1 As shown, the method for processing thyroid function data based on spectral technology provided by an embodiment of the present invention includes the following steps S101 to S102.

[0050] S101 uses near-infrared spectral imaging technology to capture facial videos, determine the core area of ​​the face in the facial video, capture the spectral characteristic values ​​of the absorption energy of trace substances in the human body to light in a specific band in the core area of ​​the face, obtain the original spectral data associated with thyroid function, and simultaneously record the age information of the collected subject.

[0051] Using a near-infrared imaging camera with both spectral and imaging capabilities, we collect facial videos and age information of patients with abnormal thyroid function, and obtain the components and contents of the pulsating arterial blood under the user's facial skin, including triiodothyronine (T3), thyroxine (T4), thyroid-stimulating hormone (TSH), as well as blood sugar, low-density lipoprotein, high-density lipoprotein, total cholesterol, triglycerides, etc. Specifically, it includes:

[0052] A certain amount of facial video data is collected through binocular cameras (visible light and near-infrared); a certain amount of clinical trial data of patients with abnormal thyroid function is obtained.

[0053] Here, the method of scanning the face of the subject and collecting the face video, and obtaining the levels of triiodothyronine (T3), thyroxine (T4), thyroid-stimulating hormone (TSH), as well as blood sugar, low-density lipoprotein, high-density lipoprotein, total cholesterol, triglycerides, etc. in the blood of the subject includes:

[0054] Scan the faces of the test group at least once, use the Dlib model to detect the face target area in the scanned image, and generate a face detection box (x1, x2, x3, x4), where x i It is a tuple of pixel point i, indicating the row and column pixel value of the pixel point.

[0055] The core area of ​​the face is cropped according to the face detection frame, and at least one scan data of the core area of ​​the face is averaged and converted.

[0056] Blood tests were used to detect triiodothyronine (T3), thyroxine (T4), thyroid-stimulating hormone (TSH), as well as blood sugar, low-density lipoprotein, high-density lipoprotein, total cholesterol, triglycerides and other levels in the blood of the subjects to obtain the levels of the above markers.

[0057] Combined with the user's age, and taking the degree of influence of the above-mentioned substance content on thyroid diseases (hyperthyroidism, hypothyroidism) as the starting point, an age-thyroid dysfunction assessment model is established, and the facial video data is preprocessed to obtain preprocessed data. A correspondence is established between the facial spectrum sample data of the tested population and the levels of triiodothyronine (T3), thyroxine (T4), thyroid-stimulating hormone (TSH), as well as blood sugar, low-density lipoprotein, high-density lipoprotein, total cholesterol, triglycerides, etc., to construct an age-thyroid dysfunction risk prediction and assessment model. At the same time, it corresponds to four levels of thyroid function: no abnormality, mild abnormality, moderate abnormality, and severe abnormality, as well as an evaluation from 0 to 100 years old, thereby achieving thyroid function evaluation and discrimination.

[0058] The sliding average filtering method was used to eliminate the noise of the raw spectral data;

[0059] Correct the baseline drift of the original spectral data after noise elimination;

[0060] The raw spectral data after baseline drift correction were normalized.

[0061] S102, based on preset rules, combined with the age information of the collection subject and the detection indicators of substances related to thyroid function, the thyroid function status of the collection subject is graded and judged to obtain a graded judgment result.

[0062] Calculating the correlation coefficient between the substance detection index and the thyroid function status;

[0063] Dividing the substance detection indicators into primary indicators and secondary indicators based on the correlation coefficient;

[0064] The main indicators include triiodothyronine, thyroxine, and thyrotropin; the secondary indicators include blood glucose, low-density lipoprotein, high-density lipoprotein, total cholesterol, and triglycerides.

[0065] When the user is under 45 years old, when all the main indicators and secondary indicators are normal, it is judged that the thyroid function is normal. If any one of the main indicators and secondary indicators exceeds the normal range, it is judged that the thyroid function is slightly abnormal.

[0066] For users aged 46 ≤ ≤ 50 years, if only one of the secondary indicators is abnormal, it is considered as mild thyroid dysfunction; if ≥ 2 of the secondary indicators are abnormal, it is considered as moderate thyroid dysfunction; if the secondary indicator is abnormal and the primary indicator is abnormal at the same time, it is considered as severe thyroid dysfunction;

[0067] For users aged 51-60, if less than 2 of the secondary indicators are abnormal, it is considered a mild abnormality; if 2 or more of the secondary indicators are abnormal, but the primary indicators are normal, it is considered a moderate abnormality of thyroid function; if 2 or more of the secondary indicators are abnormal, but 1 of the primary indicators is abnormal, it is considered a severe abnormality of thyroid function; if there are no secondary indicators abnormalities but 2 or more of the primary indicators are abnormal, it is considered a severe abnormality of thyroid function.

[0068] If the user is over 60 years old and two of the secondary indicators are abnormal and one of the primary indicators is abnormal, it is judged as moderate abnormality; if the number of abnormal indicators is greater than three, it is judged as severe abnormality.

[0069] When the number of abnormal secondary indicators exceeds the allowable range but the primary indicators are normal, a warning of thyroid dysfunction is triggered.

[0070] Figure 2 Schematic diagram of the main components of the system for processing thyroid function data based on spectral technology in an embodiment of the present invention. Figure 2 As shown, the system 1 for processing thyroid function data based on spectral technology provided by an embodiment of the present invention includes a data acquisition module 10 and a discrimination module 20 .

[0071] Data acquisition module 10 is used to capture facial video using near-infrared spectral imaging technology, determine the core area of ​​the face in the facial video, deeply capture the characteristic values ​​of the absorption energy spectrum of trace substances in the human body to light of a specific wavelength band within the core area of ​​the face, obtain raw spectral data associated with thyroid function, and simultaneously record the age information of the collected subject;

[0072] The discrimination module 20 is used to perform a graded discrimination on the thyroid function status of the subject based on preset rules, combined with the age information of the subject and the detection indicators of substances related to thyroid function, to obtain a graded discrimination result.

[0073] The data acquisition module 10 is further configured to:

[0074] The absorption energy of light in a specific wavelength band in the core area of ​​the face is detected pixel by pixel, the optical signal is converted into an electrical signal, and the electrical signal is then converted into a digital signal through analog-to-digital conversion;

[0075] A spectrum analysis algorithm is used to extract spectral characteristic values ​​of the absorption of light of different wavelengths by trace substances in the human body from the digital signal, and to obtain original spectrum data associated with thyroid function.

[0076] The system for processing thyroid function data based on spectral technology further includes an indicator classification module, which is further used to:

[0077] Calculating the correlation coefficient between the substance detection index and the thyroid function status;

[0078] Dividing the substance detection indicators into primary indicators and secondary indicators based on the correlation coefficient;

[0079] The main indicators include triiodothyronine, thyroxine, and thyrotropin; the secondary indicators include blood glucose, low-density lipoprotein, high-density lipoprotein, total cholesterol, and triglycerides.

[0080] Figure 3 A schematic diagram of the physical structure of an electronic device provided in an embodiment of the present invention, such as Figure 3 As shown, the electronic device 30 includes: a processor 301 (processor), a memory 302 (memory) and a bus 303;

[0081] The processor 301 and the memory 302 communicate with each other via the bus 303.

[0082] The processor 301 is used to call the program instructions in the memory 302 to execute the methods provided by the above-mentioned method embodiments, so as to execute the methods provided by the implementation methods of the present invention.

[0083] This embodiment provides a non-transitory computer-readable storage medium, which stores computer instructions. The computer instructions enable a computer to execute the method provided by the embodiment of the present invention.

[0084] Those skilled in the art will understand that all or part of the steps of implementing the above-mentioned method embodiment can be completed by hardware related to program instructions, and the aforementioned program can be stored in a computer-readable storage medium. When the program is executed, it executes the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: ROM, RAM, disk or optical disk, etc. Various storage media that can store program codes.

[0085] The above specific embodiments do not limit the scope of protection of the present invention. Those skilled in the art will appreciate that various modifications, combinations, sub-combinations, and substitutions may occur depending on design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principles of the present invention are intended to be included within the scope of protection of the present invention.

Claims

1. A method for processing thyroid function data based on spectral technology, characterized in that: include: Near-infrared spectral imaging technology is used to capture facial videos, determine the core area of ​​the face in the video, capture the spectral characteristic values ​​of the absorption energy of trace substances in the human body to light in a specific band within the core area of ​​the face, obtain the original spectral data associated with thyroid function, and simultaneously record the age information of the collected subjects; Based on preset rules, combined with the age information of the collected subjects and the detection indicators of substances related to thyroid function, the thyroid function status of the collected subjects is graded and judged to obtain a graded judgment result.

2. The method for processing thyroid function data based on spectral technology according to claim 1, characterized in that: The method of deeply capturing the absorption energy spectrum characteristic values ​​of trace substances in the human body in the core area of ​​the face to light of a specific wavelength band, and obtaining the original spectrum data associated with thyroid function, includes: The absorption energy of light in a specific wavelength band in the core area of ​​the face is detected pixel by pixel, the optical signal is converted into an electrical signal, and the electrical signal is then converted into a digital signal through analog-to-digital conversion; A spectrum analysis algorithm is used to extract spectral characteristic values ​​of the absorption of light of different wavelengths by trace substances in the human body from the digital signal, and to obtain original spectrum data associated with thyroid function.

3. The method for processing thyroid function data based on spectral technology according to claim 1, characterized in that: Before the step of grading and judging the thyroid function status of the sample subject, the method further includes: The sliding average filtering method was used to eliminate the noise of the raw spectral data; Correct the baseline drift of the original spectral data after noise elimination; The spectral raw data after baseline drift correction were normalized to eliminate the differences in data dimension and distribution caused by differences in acquisition equipment and environment.

4. The method for processing thyroid function data based on spectral technology according to claim 1, characterized in that: The method for processing thyroid function data based on spectral technology further includes: Calculating the correlation coefficient between the substance detection index and the thyroid function status; Dividing the substance detection indicators into primary indicators and secondary indicators based on the correlation coefficient; The main indicators include triiodothyronine, thyroxine, and thyrotropin; the secondary indicators include blood glucose, low-density lipoprotein, high-density lipoprotein, total cholesterol, and triglycerides.

5. The method for processing thyroid function data based on spectral technology according to claim 4, characterized in that: The preset rules include: When the user is under 45 years old, when all the main indicators and secondary indicators are normal, it is judged that the thyroid function is normal. If any one of the main indicators and secondary indicators exceeds the normal range, it is judged that the thyroid function is slightly abnormal. For users aged 46 ≤ ≤ 50 years, if only one of the secondary indicators is abnormal, it is considered as mild thyroid dysfunction; if ≥ 2 of the secondary indicators are abnormal, it is considered as moderate thyroid dysfunction; if the secondary indicator is abnormal and the primary indicator is abnormal at the same time, it is considered as severe thyroid dysfunction; For users aged 51-60, if less than 2 of the secondary indicators are abnormal, it is considered a mild abnormality; if 2 or more of the secondary indicators are abnormal, but the primary indicators are normal, it is considered a moderate abnormality of thyroid function; if 2 or more of the secondary indicators are abnormal, but 1 of the primary indicators is abnormal, it is considered a severe abnormality of thyroid function; if there are no secondary indicators abnormalities but 2 or more of the primary indicators are abnormal, it is considered a severe abnormality of thyroid function. If the user is over 60 years old and two of the secondary indicators are abnormal and one of the primary indicators is abnormal, it is judged as moderate abnormality; if the number of abnormal indicators is greater than three, it is judged as severe abnormality.

6. A system for processing thyroid function data based on spectral technology, characterized in that: include: A data acquisition module is used to capture facial videos using near-infrared spectral imaging technology, determine the core area of ​​the face in the facial video, deeply capture the spectral characteristic values ​​of the absorption energy of trace substances in the human body to light of specific wavelengths within the core area of ​​the face, obtain raw spectral data associated with thyroid function, and simultaneously record the age information of the collected subject; The discrimination module is used to grade the thyroid function status of the collected object based on preset rules, combined with the age information of the collected object and the substance detection indicators related to thyroid function, to obtain a graded discrimination result.

7. The system for processing thyroid function data based on spectral technology according to claim 6, characterized in that: The data acquisition module is further used to: The absorption energy of light in a specific wavelength band in the core area of ​​the face is detected pixel by pixel, the optical signal is converted into an electrical signal, and the electrical signal is then converted into a digital signal through analog-to-digital conversion; A spectrum analysis algorithm is used to extract spectral characteristic values ​​of the absorption of light of different wavelengths by trace substances in the human body from the digital signal, and to obtain original spectrum data associated with thyroid function.

8. The system for processing thyroid function data based on spectral technology according to claim 6, characterized in that: The system for processing thyroid function data based on spectral technology further includes an indicator classification module, which is further used to: Calculating the correlation coefficient between the substance detection index and the thyroid function status; Dividing the substance detection indicators into primary indicators and secondary indicators based on the correlation coefficient; The main indicators include triiodothyronine, thyroxine, and thyrotropin; the secondary indicators include blood glucose, low-density lipoprotein, high-density lipoprotein, total cholesterol, and triglycerides.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and running on the processor, characterized in that: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

10. A non-transitory computer readable medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images