CN110680341A - Non-invasive blood sugar detection device based on visible light image - Google Patents
Non-invasive blood sugar detection device based on visible light image Download PDFInfo
- Publication number
- CN110680341A CN110680341A CN201911022815.9A CN201911022815A CN110680341A CN 110680341 A CN110680341 A CN 110680341A CN 201911022815 A CN201911022815 A CN 201911022815A CN 110680341 A CN110680341 A CN 110680341A
- Authority
- CN
- China
- Prior art keywords
- image
- light source
- signal processing
- processing module
- visible light
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Images
Classifications
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/1455—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue using optical sensors, e.g. spectral photometrical oximeters
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/145—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue
- A61B5/14532—Measuring characteristics of blood in vivo, e.g. gas concentration, pH value; Measuring characteristics of body fluids or tissues, e.g. interstitial fluid, cerebral tissue for measuring glucose, e.g. by tissue impedance measurement
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
Landscapes
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Surgery (AREA)
- Medical Informatics (AREA)
- Animal Behavior & Ethology (AREA)
- Public Health (AREA)
- Biomedical Technology (AREA)
- Veterinary Medicine (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Heart & Thoracic Surgery (AREA)
- Optics & Photonics (AREA)
- Biophysics (AREA)
- Pathology (AREA)
- Evolutionary Biology (AREA)
- Emergency Medicine (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The invention relates to a non-invasive blood sugar detection device based on a visible light image, and belongs to the field of test devices. The device comprises an image acquisition module, a signal processing module and a result display module; the signal output end of the image acquisition module is connected with the signal input end of the signal processing module, and the output end of the signal processing module is connected with the signal input end of the result display module; the image acquisition module is composed of an image acquisition module, a light source and an image sensor, the signal processing module can be realized off-line by using a pc as a program carrier or adopting an embedded system, and an output result is displayed by the result display module. The device is simple to operate and low in cost. The detection method has no damage.
Description
Technical Field
The invention relates to a non-invasive blood sugar detection device based on a visible light image, and belongs to the field of test devices.
Background
Diabetes mellitus (Diabetes mellitus) is a common endocrine disease and has become one of the chronic diseases seriously harming the physiological health of human beings. According to the latest diabetes map released by the international diabetes union (IDF) in 2017, Chinese diabetes people reach 1.14 hundred million and live the first place in the world. About 3 percent of people in developed countries such as America and Europe suffer from diabetes in different degrees, the incidence rate of the diabetes is on the rise with the continuous improvement of the living standard of people, and the diabetes is easy to cause diabetic ketosis, cardiovascular and cerebrovascular diseases, renal failure, blindness, heart disease, stroke, hypertension and other complications for a long time, and seriously threatens the health of human beings, so the method has great significance for the diagnosis and treatment of the diabetes. Maintaining a stable blood glucose level in a patient is a major means for treating diabetes, which requires frequent blood glucose measurements.
The current method for detecting blood sugar is to extract blood from a human body for biochemical analysis, belongs to wound detection, not only brings pain to patients and is easy to cause the spread of various body fluid infectious diseases, but also can not carry out in-vivo real-time detection. Currently, the blood glucose meter commonly available on the market is based on colorimetry or electrochemistry, 50 μ L of blood sample is taken from fingertips or other skins of human bodies by a needle punching method, the blood sample is sucked by disposable test paper strips on the blood glucose meter through siphoning, so that the blood glucose concentration is measured, and blood sample collection is required once for measuring one blood glucose value each time, so that the method is invasive, and repeated blood sample taking has the risk of infection and influences disturbing daily life of patients. In addition, a disposable test strip is needed for measuring each blood sugar value, the measurement is complicated, the cost is high, and the frequency of measuring the blood sugar is limited, so that the accurate administration of the dosage of the medicine is influenced. In addition, it has the potential to transmit infectious diseases such as hepatitis, AIDS (HIV) and the like by contact with body fluids. The invention provides a non-invasive blood glucose detection device based on a visible light image to realize non-invasive blood glucose concentration detection.
The non-invasive blood sugar detection device based on the visible light image can well meet market requirements, and provides a technical scheme with practical value.
Disclosure of Invention
The invention aims to provide a non-invasive blood sugar detection device based on a visible light image, which can realize non-invasive blood sugar real-time detection. The detection device is mainly applied to non-invasive measurement of blood glucose concentration under the visible light illumination condition. Compared with the current clinical and daily applied blood sugar concentration detection device, the device realizes the non-invasive function of rapidly measuring the blood sugar concentration, relates to the technical fields of optical technology, precision instrument detection technology and the like, and particularly relates to a non-invasive blood sugar detection device.
The purpose of the invention is realized by the following technical scheme.
A non-invasive blood sugar detection device based on visible light images comprises an image acquisition device, a signal processing module, a result display module and data lines among the modules.
The image acquisition device consists of a light source and an image sensor; the signal output end of the image acquisition module is connected with the signal input end of the signal processing module, and the output end of the signal processing module is connected with the signal input end of the result display module. The light source is used for illumination;
the method for detecting the sugar content by the method comprises the following steps:
in the first step, an LED light source is started, and visible light with the wavelength of 625nm is emitted to a sample to be measured.
And secondly, starting the imaging equipment to ensure that the imaging equipment and the light source form an angle of 90 degrees.
And thirdly, placing the object to be measured at the position of an included angle between the light source and the imaging equipment, keeping the object to be measured still for 1s, and collecting a scattering image.
And fourthly, inputting the image in the third step into a deep neural network, and extracting the depth features.
And fifthly, inputting the depth characteristics into the trained model to obtain the predicted blood glucose concentration value.
The deep neural network adopts a noise reduction self-coding neural network algorithm.
The trained model uses a gradient enhanced regression algorithm. Collecting a scattering image of a sample, selecting an interested region of the scattering image as a test region, inputting an original image into a noise-reduction self-coding neural network to extract the characteristics of an intermediate layer of the test region as the characteristic vector of the current sample, inputting the characteristic vector of the sample and the corresponding glucose concentration value into a gradient enhancement regression model for training, and obtaining a high-precision prediction model by adjusting the iteration times, the tree depth and the learning rate.
The main function of the device is to overcome the defects of invasive blood sugar concentration measurement at present, and the invention provides a measuring device for rapidly and non-invasively measuring the blood sugar concentration under the condition of LED or laser light source illumination by using an image acquisition device. The method has the characteristics of rapidness, no wound, multi-dimensional information and the like. The kit is suitable for clinical and common people daily health detection, and has wide development space and application prospect.
Advantageous effects
1. The non-invasive blood sugar detection device based on the visible light image does not have radiation hazard to a detected human body due to the use of the visible light imaging equipment. Since this method is a non-invasive measurement method, it can be applied to critically ill patients and infants.
2. The invention does not need to use a detection instrument to contact with the detected object, improves the comfort, and further avoids the detection error caused by the physiological change generated by the contact stimulation.
2. The non-invasive blood sugar detection device based on the visible light image does not need to be calibrated for an individual and select the measurement time, is a universal model, and realizes the real detection of the non-invasive blood sugar of all people.
3. The non-invasive blood sugar detection device based on the visible light image is simple to operate and low in cost.
Drawings
FIG. 1 is a block diagram of the present invention;
fig. 2 is a schematic configuration of the present invention.
Detailed Description
For the purpose of clearly illustrating the technical solutions proposed by the present invention, the present invention will be described in detail below with reference to the accompanying drawings and examples.
Example 1
As shown in fig. 1 and 2, the image acquisition module is composed of an LED light source and an imaging sensor.
The signal processing module can utilize a pc machine as a program carrier, and the extraction operation of the blood sugar characteristics is realized on the program carrier.
The signal processing module can be implemented in an embedded system in an off-line mode, and blood sugar characteristics are extracted.
The signal processing module can adopt a noise reduction self-coding neural network algorithm to realize the extraction of the blood sugar characteristics.
The signal processing module may employ a gradient enhanced regression prediction model.
The result display module has two realization forms corresponding to the data processing system, program operation is carried out aiming at the PC, the extracted blood sugar concentration value result is displayed on a display screen or a display carrier controlled by the PC, and the extracted blood sugar concentration result is displayed on the display carrier controlled by the high-speed circuit aiming at the embedded system.
Fig. 2 shows a non-invasive blood glucose detecting device based on visible light images, which performs non-destructive detection of blood glucose concentration through fingertips. The image acquisition module 1 detects image data generated by finger scattering above the finger, acquires the image data, and transmits the data to the signal processing module 2. The signal processing module 2 receives the image transmitted by the image acquisition module 1, performs data noise reduction self-coding feature extraction on the image, inputs the feature into a trained gradient enhancement regression model for prediction, obtains a current predicted concentration value, outputs the current predicted concentration value as the current blood glucose concentration value of the object to be measured, and transmits data to the result display module 3. The result display module 3 receives the result transmitted by the signal processing module 2 and displays the result.
The method for detecting the sugar content by the method comprises the following steps:
in the first step, an LED light source is started, and visible light with the wavelength of 625nm is emitted to a sample to be measured.
And secondly, starting the imaging equipment to ensure that the imaging equipment and the light source form an angle of 90 degrees.
And thirdly, placing the object to be measured at the position of an included angle between the light source and the imaging equipment, keeping the object to be measured still for 1s, and collecting a scattering image.
And fourthly, inputting the image in the third step into a deep neural network, and extracting the depth features.
And fifthly, inputting the depth characteristics into the trained model to obtain the predicted blood glucose concentration value.
The deep neural network adopts a noise reduction self-coding neural network algorithm.
The trained model uses a gradient enhanced regression algorithm. The method comprises the steps of irradiating a sample with light emitted by an LED, imaging the sample to a CCD target surface through sample scattering/reflection by a lens to form a scattering image, collecting the scattering image, selecting an interested region of the scattering image as a test region, inputting an original image into a noise-reduction self-coding neural network to extract the characteristics of an intermediate layer of the test region as the characteristic vector of the current sample, inputting the characteristic vector of the sample and the corresponding glucose concentration value into a gradient enhancement regression model for training, and obtaining a high-precision prediction model by adjusting iteration times, tree depth and learning rate. The sample preparation includes both distilled water and a mock solution, which were obtained by adding glucose powders of different masses. The sugar content of the sample solution is measured by enzyme chemical reaction, and one group of the test results is shown in the table
The actual sugar content is almost consistent with the sugar content result predicted by the device. Therefore, the device can accurately realize the prediction of the glucose content.
While one embodiment of the present invention has been described in detail, the description is only for the purpose of illustrating the preferred embodiments of the present invention and should not be taken as limiting the scope of the invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention should be included in the protection scope of the present invention.
Claims (4)
1. A non-invasive blood sugar detection device based on visible light images is characterized in that: the system comprises an image acquisition device, a signal processing module, a result display module and data lines among the modules;
the image acquisition device consists of a light source and an image sensor; the signal output end of the image acquisition module is connected with the signal input end of the signal processing module, and the output end of the signal processing module is connected with the signal input end of the result display module; the light source is used for illumination.
2. A method for detecting a sugar content using the device according to claim 1, wherein: the method comprises the following steps:
the method comprises the following steps that firstly, an LED light source is started, and visible light with the wavelength of 625nm is emitted to a sample to be detected;
secondly, starting the imaging equipment to ensure that the imaging equipment and the light source form an angle of 90 degrees;
thirdly, placing the object to be measured at the position of an included angle between the light source and the imaging equipment, keeping the object to be measured still for 1s, and collecting a scattering image;
fourthly, inputting the image in the third step into a deep neural network, and extracting a depth feature;
and fifthly, inputting the depth characteristics into the trained model to obtain the predicted blood glucose concentration value.
3. The method of claim 2, wherein: the training method of the trained model in the fifth step comprises the following steps: training by adopting a gradient enhanced regression algorithm; collecting a scattering image of a sample, selecting an interested region of the scattering image as a test region, inputting an original image into a noise-reduction self-coding neural network to extract the characteristics of an intermediate layer of the test region as the characteristic vector of the current sample, inputting the characteristic vector of the sample and the corresponding glucose concentration value into a gradient enhancement regression model for training, and obtaining a high-precision prediction model by adjusting the iteration times, the tree depth and the learning rate.
4. The method of claim 2, wherein: the deep neural network adopts a noise reduction self-coding neural network algorithm.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911022815.9A CN110680341B (en) | 2019-10-25 | 2019-10-25 | Non-invasive blood sugar detection device based on visible light image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911022815.9A CN110680341B (en) | 2019-10-25 | 2019-10-25 | Non-invasive blood sugar detection device based on visible light image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110680341A true CN110680341A (en) | 2020-01-14 |
CN110680341B CN110680341B (en) | 2021-05-18 |
Family
ID=69114068
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911022815.9A Active CN110680341B (en) | 2019-10-25 | 2019-10-25 | Non-invasive blood sugar detection device based on visible light image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN110680341B (en) |
Cited By (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113143264A (en) * | 2021-04-16 | 2021-07-23 | 北京理工大学 | Blood glucose detection area selection device and method based on blood perfusion imaging |
CN115040095A (en) * | 2022-08-15 | 2022-09-13 | 北京九叁有方物联网科技有限公司 | Aging-suitable multifunctional autonomous non-invasive dynamic physiological signal monitoring and analyzing system |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5321265A (en) * | 1992-07-15 | 1994-06-14 | Block Myron J | Non-invasive testing |
WO1997036540A1 (en) * | 1993-11-30 | 1997-10-09 | Florida Institute Of Technology | Determination of concentrations of biological substances using raman spectroscopy and artificial neural network discriminator |
CN1822788A (en) * | 2003-06-10 | 2006-08-23 | 福威光学公司 | Non-invasive measurement of blood glucose |
CN106803062A (en) * | 2016-12-20 | 2017-06-06 | 陕西师范大学 | The recognition methods of stack noise reduction own coding neutral net images of gestures |
CN107505268A (en) * | 2017-08-04 | 2017-12-22 | 中国科学院半导体研究所 | Blood sugar detecting method and system |
CN109662720A (en) * | 2018-11-27 | 2019-04-23 | 中国科学院深圳先进技术研究院 | Multiband optoacoustic Woundless blood sugar concentration prediction system based on deep learning |
CN109758160A (en) * | 2019-01-11 | 2019-05-17 | 南京邮电大学 | A kind of Woundless blood sugar prediction technique based on LSTM-RNN model |
CN110147878A (en) * | 2018-11-28 | 2019-08-20 | 腾讯科技(深圳)有限公司 | Data processing method, device and equipment |
-
2019
- 2019-10-25 CN CN201911022815.9A patent/CN110680341B/en active Active
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5321265A (en) * | 1992-07-15 | 1994-06-14 | Block Myron J | Non-invasive testing |
WO1997036540A1 (en) * | 1993-11-30 | 1997-10-09 | Florida Institute Of Technology | Determination of concentrations of biological substances using raman spectroscopy and artificial neural network discriminator |
CN1822788A (en) * | 2003-06-10 | 2006-08-23 | 福威光学公司 | Non-invasive measurement of blood glucose |
CN106803062A (en) * | 2016-12-20 | 2017-06-06 | 陕西师范大学 | The recognition methods of stack noise reduction own coding neutral net images of gestures |
CN107505268A (en) * | 2017-08-04 | 2017-12-22 | 中国科学院半导体研究所 | Blood sugar detecting method and system |
CN109662720A (en) * | 2018-11-27 | 2019-04-23 | 中国科学院深圳先进技术研究院 | Multiband optoacoustic Woundless blood sugar concentration prediction system based on deep learning |
CN110147878A (en) * | 2018-11-28 | 2019-08-20 | 腾讯科技(深圳)有限公司 | Data processing method, device and equipment |
CN109758160A (en) * | 2019-01-11 | 2019-05-17 | 南京邮电大学 | A kind of Woundless blood sugar prediction technique based on LSTM-RNN model |
Non-Patent Citations (2)
Title |
---|
BOB ZHANG 等: "《Noninvasive Diabetes Mellitus Detection Using Facial Block Color With a Sparse Representation Classifier》", 《IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING》 * |
HAIDER ALI 等: "《Novel Approach to Non-Invasive Blood Glucose Monitoring Based on Transmittance and Refraction of Visible Laser Light》", 《IEEE ACCESS》 * |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN113143264A (en) * | 2021-04-16 | 2021-07-23 | 北京理工大学 | Blood glucose detection area selection device and method based on blood perfusion imaging |
CN113143264B (en) * | 2021-04-16 | 2023-08-01 | 北京理工大学 | Blood glucose detection area selection method based on blood perfusion imaging |
CN115040095A (en) * | 2022-08-15 | 2022-09-13 | 北京九叁有方物联网科技有限公司 | Aging-suitable multifunctional autonomous non-invasive dynamic physiological signal monitoring and analyzing system |
Also Published As
Publication number | Publication date |
---|---|
CN110680341B (en) | 2021-05-18 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Pan et al. | Vein pattern locating technology for cannulation: a review of the low-cost vein finder prototypes utilizing near infrared (NIR) light to improve peripheral subcutaneous vein selection for phlebotomy | |
WO2018107915A1 (en) | General noninvasive blood glucose prediction method based on timing analysis | |
CN105433915B (en) | A kind of traditional Chinese pulse-diagnosis instrument and its pulse condition detection method | |
US20160228008A1 (en) | Image diagnosis device for photographing breast by using matching of tactile image and near-infrared image and method for aquiring breast tissue image | |
CN110680341B (en) | Non-invasive blood sugar detection device based on visible light image | |
CN205568958U (en) | Noninvasive glucose monitoring based on wrist detects | |
CN103892802B (en) | Novel tongue imaging intelligent auxiliary device | |
CN205433706U (en) | Noninvasive glucose monitoring based on finger detects | |
Li et al. | Research on non-invasive glucose concentration measurement by NIR transmission | |
CN103263271A (en) | Non-contact automatic blood oxygen saturation degree measurement system and measurement method | |
CN104013411A (en) | Transmission type noninvasive blood sugar detection device | |
CN108324286B (en) | Infrared noninvasive blood glucose detection device based on PCA-NARX correction algorithm | |
CN110192866A (en) | The monitoring method and equipment of noninvasive capillary arterial blood concentration of component | |
CN112568902A (en) | Noninvasive blood glucose calibration method based on blood glucose value | |
CN104983430B (en) | The blood-sugar detecting instrument of non-intrusion type | |
CN102512179A (en) | Non-destructive detector for human blood sugar | |
CN110575182A (en) | Method and device for detecting blood sugar | |
Abbas et al. | Haemoglobin detection in blood by signal to image scanning using Photo-Plethysmo-Graphic-Technique (PPG) | |
Mirtaheri et al. | Wearable biomedical devices: state of the art, challenges, and future perspectives | |
CN204971302U (en) | Diabetes detect therapeutic instrument | |
CN204049622U (en) | A kind of traditional Chinese pulse-diagnosis instrument | |
US11089979B2 (en) | Device and method for measurement of glycated hemoglobin (A1c) | |
CN203861194U (en) | Novel intelligent tongue image assisting device | |
CN203591264U (en) | Noninvasive hemoglobin tester | |
CN112754479A (en) | Method and equipment for detecting blood glucose concentration |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |