CN101623191A - Device and method for noninvasively detecting property of stomach tissue - Google Patents
Device and method for noninvasively detecting property of stomach tissue Download PDFInfo
- Publication number
- CN101623191A CN101623191A CN200910090920A CN200910090920A CN101623191A CN 101623191 A CN101623191 A CN 101623191A CN 200910090920 A CN200910090920 A CN 200910090920A CN 200910090920 A CN200910090920 A CN 200910090920A CN 101623191 A CN101623191 A CN 101623191A
- Authority
- CN
- China
- Prior art keywords
- image
- tissue
- spectrum
- mid
- patient
- 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
- 210000002784 stomach Anatomy 0.000 title claims abstract description 60
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000001228 spectrum Methods 0.000 claims abstract description 59
- 239000000523 sample Substances 0.000 claims abstract description 34
- 230000003595 spectral effect Effects 0.000 claims abstract description 32
- 238000004458 analytical method Methods 0.000 claims abstract description 28
- 238000001514 detection method Methods 0.000 claims abstract description 26
- 230000002496 gastric effect Effects 0.000 claims abstract description 20
- 238000005102 attenuated total reflection Methods 0.000 claims abstract description 11
- 238000003909 pattern recognition Methods 0.000 claims abstract description 8
- 238000005259 measurement Methods 0.000 claims abstract description 7
- 210000001519 tissue Anatomy 0.000 claims description 98
- 239000013307 optical fiber Substances 0.000 claims description 24
- 208000005718 Stomach Neoplasms Diseases 0.000 claims description 17
- 206010017758 gastric cancer Diseases 0.000 claims description 17
- 201000011549 stomach cancer Diseases 0.000 claims description 17
- 208000004300 Atrophic Gastritis Diseases 0.000 claims description 16
- 208000007882 Gastritis Diseases 0.000 claims description 16
- 208000036495 Gastritis atrophic Diseases 0.000 claims description 16
- 208000016644 chronic atrophic gastritis Diseases 0.000 claims description 16
- 239000013078 crystal Substances 0.000 claims description 11
- 238000010827 pathological analysis Methods 0.000 claims description 11
- 239000000463 material Substances 0.000 claims description 10
- 239000000835 fiber Substances 0.000 claims description 9
- 201000011510 cancer Diseases 0.000 claims description 8
- 230000008878 coupling Effects 0.000 claims description 7
- 238000010168 coupling process Methods 0.000 claims description 7
- 238000005859 coupling reaction Methods 0.000 claims description 7
- 206010028980 Neoplasm Diseases 0.000 claims description 6
- 238000012549 training Methods 0.000 claims description 5
- 238000005452 bending Methods 0.000 claims description 4
- 230000003902 lesion Effects 0.000 claims description 4
- 238000005070 sampling Methods 0.000 claims description 4
- 239000011521 glass Substances 0.000 claims description 3
- 229910052736 halogen Inorganic materials 0.000 claims description 3
- 238000005286 illumination Methods 0.000 claims description 3
- SBIBMFFZSBJNJF-UHFFFAOYSA-N selenium;zinc Chemical compound [Se]=[Zn] SBIBMFFZSBJNJF-UHFFFAOYSA-N 0.000 claims description 3
- 229910052721 tungsten Inorganic materials 0.000 claims description 3
- 239000010937 tungsten Substances 0.000 claims description 3
- 230000004927 fusion Effects 0.000 claims description 2
- 238000000338 in vitro Methods 0.000 claims description 2
- 210000004877 mucosa Anatomy 0.000 claims description 2
- 238000001727 in vivo Methods 0.000 claims 2
- 206010009691 Clubbing Diseases 0.000 claims 1
- 230000002238 attenuated effect Effects 0.000 claims 1
- 238000012569 chemometric method Methods 0.000 claims 1
- 238000013145 classification model Methods 0.000 claims 1
- GNPVGFCGXDBREM-UHFFFAOYSA-N germanium atom Chemical group [Ge] GNPVGFCGXDBREM-UHFFFAOYSA-N 0.000 claims 1
- 239000010453 quartz Substances 0.000 claims 1
- HBMJWWWQQXIZIP-UHFFFAOYSA-N silicon carbide Chemical compound [Si+]#[C-] HBMJWWWQQXIZIP-UHFFFAOYSA-N 0.000 claims 1
- 229910010271 silicon carbide Inorganic materials 0.000 claims 1
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims 1
- 230000008719 thickening Effects 0.000 claims 1
- -1 tungsten halogen Chemical class 0.000 claims 1
- 238000010521 absorption reaction Methods 0.000 abstract 1
- 230000003287 optical effect Effects 0.000 description 25
- 230000006870 function Effects 0.000 description 14
- 238000013528 artificial neural network Methods 0.000 description 5
- 238000002329 infrared spectrum Methods 0.000 description 5
- 239000000203 mixture Substances 0.000 description 5
- 238000012706 support-vector machine Methods 0.000 description 5
- 238000012546 transfer Methods 0.000 description 5
- 239000013598 vector Substances 0.000 description 5
- WSFSSNUMVMOOMR-UHFFFAOYSA-N Formaldehyde Chemical compound O=C WSFSSNUMVMOOMR-UHFFFAOYSA-N 0.000 description 4
- 230000008033 biological extinction Effects 0.000 description 4
- 238000009792 diffusion process Methods 0.000 description 4
- 231100000915 pathological change Toxicity 0.000 description 4
- 230000036285 pathological change Effects 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000005033 Fourier transform infrared spectroscopy Methods 0.000 description 3
- 210000004556 brain Anatomy 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 3
- 210000004027 cell Anatomy 0.000 description 3
- 230000001276 controlling effect Effects 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000008520 organization Effects 0.000 description 3
- 230000001575 pathological effect Effects 0.000 description 3
- 230000007170 pathology Effects 0.000 description 3
- 230000008054 signal transmission Effects 0.000 description 3
- 238000004611 spectroscopical analysis Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 206010011409 Cross infection Diseases 0.000 description 2
- 206010029803 Nosocomial infection Diseases 0.000 description 2
- 206010070834 Sensitisation Diseases 0.000 description 2
- 208000025865 Ulcer Diseases 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000003745 diagnosis Methods 0.000 description 2
- 230000004069 differentiation Effects 0.000 description 2
- 238000004043 dyeing Methods 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000002575 gastroscopy Methods 0.000 description 2
- 150000002290 germanium Chemical class 0.000 description 2
- 150000002367 halogens Chemical class 0.000 description 2
- 230000007246 mechanism Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 239000012188 paraffin wax Substances 0.000 description 2
- 230000001105 regulatory effect Effects 0.000 description 2
- 230000008313 sensitization Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 230000004083 survival effect Effects 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- WFKWXMTUELFFGS-UHFFFAOYSA-N tungsten Chemical compound [W] WFKWXMTUELFFGS-UHFFFAOYSA-N 0.000 description 2
- 231100000397 ulcer Toxicity 0.000 description 2
- 241000501308 Conus spectrum Species 0.000 description 1
- 206010058314 Dysplasia Diseases 0.000 description 1
- 206010061218 Inflammation Diseases 0.000 description 1
- 241001124569 Lycaenidae Species 0.000 description 1
- 102100029469 WD repeat and HMG-box DNA-binding protein 1 Human genes 0.000 description 1
- 101710097421 WD repeat and HMG-box DNA-binding protein 1 Proteins 0.000 description 1
- 208000027418 Wounds and injury Diseases 0.000 description 1
- 230000008901 benefit Effects 0.000 description 1
- 235000013361 beverage Nutrition 0.000 description 1
- 210000005056 cell body Anatomy 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 210000000080 chela (arthropods) Anatomy 0.000 description 1
- 208000037976 chronic inflammation Diseases 0.000 description 1
- 208000037893 chronic inflammatory disorder Diseases 0.000 description 1
- 238000003759 clinical diagnosis Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 210000001156 gastric mucosa Anatomy 0.000 description 1
- 230000036541 health Effects 0.000 description 1
- 238000003703 image analysis method Methods 0.000 description 1
- 208000015181 infectious disease Diseases 0.000 description 1
- 208000027866 inflammatory disease Diseases 0.000 description 1
- 230000004054 inflammatory process Effects 0.000 description 1
- 230000003834 intracellular effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 201000011591 microinvasive gastric cancer Diseases 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 230000000877 morphologic effect Effects 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 230000007935 neutral effect Effects 0.000 description 1
- 230000035515 penetration Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 239000002893 slag Substances 0.000 description 1
- 230000000391 smoking effect Effects 0.000 description 1
- 238000010183 spectrum analysis Methods 0.000 description 1
- 238000005507 spraying Methods 0.000 description 1
- 208000018556 stomach disease Diseases 0.000 description 1
- 230000001225 therapeutic effect Effects 0.000 description 1
- 210000004881 tumor cell Anatomy 0.000 description 1
Images
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
一种胃部组织性质无创检测装置及方法，装置包括：光源部分，伸入体内的软性部分，光谱采集装置、计算机等，微型图像采集装置采集胃部图像发送至计算机，入射中红外光经二次衰减全反射(ATR)探头后，将胃部组织的吸收信息传至体外光谱采集装置并转化为电信号后发送至计算机，模式识别模块对该处组织的图像与光谱信息进行判别分析后，输出检测组织性质；本发明方法包括：测量前利用在体胃部组织图像与光谱建立判别分析模型后，采集待检测部位的图像与光谱后输入建立好的判别分析模型，得到待检病人胃部组织的分析结果。本发明可实现在体、无创、快速、多点测量，避免漏检，减少了患者痛苦，将图像与全光谱信息相结合建立判别分析模型，准确度高。
A device and method for non-invasive detection of gastric tissue properties, the device includes: a light source part, a soft part extending into the body, a spectrum acquisition device, a computer, etc., the micro image acquisition device collects images of the stomach and sends them to the computer, and the incident mid-infrared light passes through the After the second attenuated total reflection (ATR) probe, the absorption information of the gastric tissue is transmitted to the external spectrum acquisition device and converted into an electrical signal and sent to the computer. The pattern recognition module discriminates and analyzes the image and spectral information of the tissue , output the detected tissue properties; the method of the present invention includes: before the measurement, the discriminant analysis model is established by using the image and spectrum of the stomach tissue in the body, and then the image and spectrum of the part to be detected are collected and then input into the established discriminant analysis model to obtain the patient's gastric The results of the department's analysis. The invention can realize in-body, non-invasive, rapid and multi-point measurement, avoid missed detection, reduce pain of patients, and combine images with full spectrum information to establish a discriminant analysis model with high accuracy.
Description
Technical field
The present invention relates to the biological spectrum analysis technical field, relate in particular to a kind of stomach tissue character noninvasive detection device and method.
Background technology
Cancer is a class disease of serious threat human health even life.Gastric cancer is one of modal malignant tumor, and its mortality rate is in the first place that China occupies malignant tumor, and influencing it, to treat topmost factor be stadium, and 5 years survival rates of early gastric cancer can reach more than 90%.At present, Gastric Diseases by Spraying is checked that effective method is a fibergastroscope, gastroscope can be understood the position and the scope of pathological changes down, and can draw materials to suspicious lesions and carry out pathological diagnosis.In clinical gastroscope testing result, the general very case of small scale is a cancer, and the patient of the overwhelming majority then suffers from various chronic inflammatory diseases, and if inflammatory disorders is treated control timely and made regular check on monitoring, inflammation then may further worsen, and dysplasia takes place, and finally develops into cancer.Correct realize apace that the gastroscope sample is normal, the clinical diagnosis in superficial gastritis, atrophic gastritis or the gastric cancer, and take different therapeutic schemes accordingly, significant for the survival rate and the cure rate that improve sufferer.
At present, though gastroscopy is widely adopted clinically, as patent CN 1004530250 described a kind of endoscopic systems.But gastroscopy still has certain limitation, as needs gripping stomach tissue, thereby wound, easy infection are arranged, easily causes diffusion, and is same, because need gripping tissue, is difficult for realizing so the gripping inspection is carried out at all doubtful positions, so may causes omission.The main examinate's of gastroscopic diagnostic result operating experience influence and subjective judgment, thereby degree of accuracy is lower.Organize formalin fixed after the gripping, paraffin embedding, HE dyeing carries out routine pathology at last and learn and check, thereby need the long period just can obtain diagnostic result, and cost is higher.
Fourier transform infrared spectroscopy (Fourier Transform Infrared Spectroscopy is called for short FTIR) is a kind of new method from molecular level postgraduate fabric texture that development in recent years is got up.Infrared spectrum is the sensitive probe of molecule structure change, can detect the variation of composition, structure and the conformation of intracellular matter from the variation of the corresponding group molecular vibration of some material level in the cell.Therefore, the early stage variation of pathological tissues shows on the infrared spectrum when not being embodied in morphologic variation therein to some extent.Though and some present academic researchs also relate to this field, after needing mostly to gather tissue samples, be positioned over the detection of exsomatizing on the spectrogrph, promptly, hope replaces pathologic finding with the spectrum inspection, needs the gripping tissue so equally, thereby also just has its drawback.The laboratory academic research that minority can be differentiated tissue property at body also all is at the human body superficial tissue, promptly reflects near the pathological changes situation of the tissue skin.And present spectral investigation also still rests on the characteristic spectrum peak comparison stage, wasted the bulk information of full spectrum, and too relied on subjective judgment, thereby precision is not high.
In sum, a kind of stomach tissue character noninvasive detection device and method combine spectroscopic analysis methods with image analysis method, are expected to develop into a kind of noinvasive, the new technique of stomach tissue character detection fast, and can be used for the earlier detection of cancer.
Summary of the invention
Technology of the present invention is dealt with problems: overcome the deficiencies in the prior art, a kind of stomach tissue character noninvasive detection device and method are provided, be implemented in body, multimetering, can avoid omission, do not need gripping patient's stomach tissue to carry out pathological analysis, reduced the patient suffering, avoided cross infection and diffusion, image has been combined with the full gloss spectrum information, programmed by mathematical algorithm, automatically differentiate doubtful tissue property, have higher accuracy.
Technical solution of the present invention: a kind of stomach tissue character noninvasive detection device comprises with the lower part: the Lights section, stretch into the intravital soft component of patient, spectra collection device, computer; The Lights section comprises two parts: infrared incident illumination light source in the used light source of the illumination of visible waveband being provided and providing; Stretching into the intravital soft component of patient comprises: visible light incident optical, miniature image harvester, picture signal outlet line; In infrared incident optical, secondary extinction total reflection (ATR) probe, in infrared outgoing optical fiber, wherein secondary ATR probe is positioned at the miniature image harvester and stretches into the intravital soft component of patient bottom, in infrared incident optical with in infrared emergent ray form Y shape fibre bundle and pop one's head in secondary ATR and be connected; It is flexible to stretch into the intravital soft component of patient, and control by operating flexible part, can make its left and right sides all directions bending up and down, helps its tract that passes through the gastric bending by the direction of regulating bent angle, improves overview function;
The visible light that visible light source sends enters the visible light incident optical and transfers in patient's body after Lens Coupling, illuminate stomach tissue, so that the miniature image harvester is gathered the stomach image, and image information is converted into the signal of telecommunication is sent to external computer by the picture signal outlet line;
Infrared incident optical and transferring to after the inherent secondary ATR probe of patient's body inner surface carries out twice attenuated total reflectance during the mid-infrared light that send in the mid-infrared light source enters after Lens Coupling, the emergent light load Biochemical Information of stomach tissue after outgoing optical fiber is sent to the computer part after reaching external spectra collection device and being converted into spectral signal;
Flexible by controlling, the intravital soft component of patient is stretched in rotation, the miniature image harvester is gathered the image of stomach various piece tissue in real time, after finding the suspected lesion tissue, start the spectra collection device and gather the spectral signal at this place, herein image information and spectral information are saved simultaneously, be transferred to the computer part as input, computer can and show in real time with image and spectrographic storage, simultaneously, the various character stomach tissue spectra databases that pattern recognition module utilization in the computer has been set up in advance, image information and spectral information to this place's tissue carry out discriminant analysis, and it is normal that output that can be real-time detects the organization discrimination tissue, superficial gastritis, the differentiation of atrophic gastritis or gastric cancer.
Described visible part light source is selected halogen tungsten lamp or white light LEDs for use, and described mid-infrared light source is a siliconit; Be equipped with convex lens respectively in two light source exits, the light that respectively two light sources sent focuses on and is coupled into incident optical separately, through after the Lens Coupling, visible light source and mid-infrared light source advance respectively visible incident optical and in infrared incident optical.
Described visible light incident optical is selected common quartzy material for use.
In described infrared incident optical with in infrared outgoing fiber selection optical fiber material be germanium salt glass, logical optical band is 700-4000cm
-1
It is 45 degree taper ZnSe or Ge crystal that described secondary extinction is launched (ATR) probe entirely, and its section is an isosceles right triangle.
Described miniature image harvester adopts CCD or CMOS sensitization mode.
Described spectra collection device adopts back beam split mode, load the stomach tissue property information in infrared emergent light, extremely external by fiber-optic transfer, after collimated, by being accepted by detector after the light splitting part beam split in the spectra collection device, and being converted into spectral signal, light splitting part can adopt the AOTF crystal, variable filter or grating.
Described pattern recognition module, this module is carried out discriminant analysis by the spectrum and the image information of input to stomach tissue character.Discriminant analysis is a class identification and classification method in the multivariate statistical method, and it is the observation sample result according to two or more parents, according to certain criterion and corresponding discriminant function, differentiates arbitrary individual which kind of parent of ownership of waiting to declare.
Utilize tissue spectrum that has obtained and the tissue property of having differentiated to set up the discriminant analysis model, discriminant analysis is a comparatively sophisticated class identification and classification method in the multivariate statistical method, it is the observation sample result according to two or more parents, according to certain criterion and corresponding discriminant function, differentiate arbitrary individual which kind of parent of ownership of waiting to declare.Its method comprises: the k-nearest neighbor method, and the artificial neural network method, support vector machine methods etc. are multiple, and are not limited to above discriminant analysis method.
K nearest-neighbors method adopts vector space model to classify, and notion is the stomach tissue spectrum similarity height each other of identical category, and can assess the possible classification of unknown classification case by the similarity of calculating with the known class case.As the case may be, choose the nearest k of sample to be discriminated training set sample spectrum, establish in this k sample the sample N that this does not comprise normal, superficial gastritis, atrophic gastritis and gastric cancer
1, N
2, N
3, and N
1+ N
2+ N
3=k.Computational discrimination sample spectrum is to the score that is subordinate to of four class training set samples respectively, formula such as following represented:
D in the formula
iRepresent that i training set sample spectrum is to the distance between the sample spectrum to be discriminated in this classification.D
iIn order to weigh the similarity degree between sample light, can wait with Euclidean distance, mahalanobis distance, city block distance and calculate, and be not limited to above several distance calculating method.
Calculate sample spectra to be discriminated to all kinds of scores after, relatively the score height is judged to be the highest classification of score with sample to be discriminated.
(Artificial Neural Network is to the abstract of human brain or the some fundamental characteristics of natural neutral net (NaturalNeural Network) and simulation ANN) to artificial neural network.Artificial neural network is based on to the physiological Study achievement of brain, and its purpose is to simulate some mechanism and mechanism of brain, realizes the function of certain aspect.ANN is by having the extensive in parallel network that adaptive simple unit is formed, and its tissue can be simulated the cross reaction that biological nervous system has been done real world objects.Use the identification of Artificial Neural Network implementation pattern.It is very complicated to handle some environmental informations, and background knowledge is unclear, and the indefinite problem of rule of inference allows sample spectra that bigger distortion is arranged, and its speed of service is fast, and adaptive performance is good, has higher resolution.
The method that a kind of stomach tissue character noinvasive detects may further comprise the steps:
A. before measurement, gather enough different pathological analysis results at body stomach tissue image and spectrum, set up the discriminant analysis model by chemometrics method;
B. utilize the miniature image harvester to obtain the image information of training set patient stomach tissue;
C. according to the doubtful part of spectral discrimination, gather and write down the image and the spectral information at doubtful position simultaneously;
D. in the discriminant analysis model that the input step a that the image information at doubtful position combined with spectral information sets up, the analysis result that obtains waiting diagnosing patient's stomach tissue is a kind of for normal, superficial gastritis, atrophic gastritis or gastric cancer.
Described steps A specifically comprises:
A. recruit a large amount of trial volunteers, require stomach among the experimenter close for the ratio of normal, superficial gastritis, atrophic gastritis or gastric cancer;
B. soft component is stretched in experimenter's stomach, gather the image of a part, utilize this position tissue spectrum of sampling collecting fiber simultaneously by the miniature image harvester;
C. spectrum position tissue is gathered in gripping, carries out pathological analysis, determines that its character is normal, a kind of in superficial gastritis, atrophic gastritis or the gastric cancer;
D. utilize the tissue spectrum that obtains through device described in the present invention with image information with utilize pathological analysis to obtain the result, by chemometrics method to spectrum set up normally, the disaggregated model of superficial gastritis, atrophic gastritis or gastric cancer four classes,
Step C is according to the doubtful part of spectral discrimination, gather and write down doubtful station diagram picture and spectral information simultaneously, it is characterized in that: utilize the soft component of corresponding device of the present invention to go deep into patient's stomach to be detected, by controlling its pitching or rotation, gather the image of each position of stomach in real time, when finding that pathological tissues can show as ulcer last, be that basilar part has special performance, uneven, hard sense, expose sense, perilesional mucosa has the performance of concentrating picture and fusion phenomenon or the chap of pestle shape, then begins to write down by the miniature image harvester image of this position, notes the image and the spectroscopic data at this position simultaneously.
The present invention compared with prior art has following advantage:
(1) traditional checkout gear and method need utilize the gripping pincers to gather stomach tissue to external, can bring misery to the patient, may cause diffusion simultaneously and infect, and too much collection organize everywhere also and can not realize, thereby cause omission easily.And the present invention adopts soft component to stretch in patient's body, spectrum and the image of gathering patient tissue on body, noinvasive ground carry out discriminant analysis, thereby need not gripping patient's stomach tissue, only need to gather tissue image and spectrum, can not cause suffering and injure the patient, reduce the patient suffering, and be difficult for cross infection, caused diffusion.Simultaneously, also can realize multimetering, can detect easily, can avoid omission position that might pathological changes.
(2) traditional checkout gear and method need the gripping stomach tissue to external, organize formalin fixed after the gripping, paraffin embedding, and HE dyeing carries out routine pathology at last and learn and check, thereby need the long period just can obtain diagnostic result, and cost is higher.And the middle infrared spectrum that intravital soft component gos deep into gathering in patient's body stomach tissue is goed deep in utilization of the present invention, middle infrared spectrum is the character of characterising biological tissue delicately, therefore can be implemented in body, in site measurement, do not need to carry out pathological analysis, shorten the diagnosis required time, can obtain testing result in real time.
(3) traditional checkout gear and method rely on image to determine tissue property, and if cancerous issue can be observed on iconography then, ten million cancerous tumor cell has at least been arranged.And application of spectral of the present invention is diagnosed, infrared spectrum can be in cell the variation of the corresponding group molecular vibration of some material level detect the spatial arrangements of existence, composition, content and molecule of some material the cell and the variation of structure, thereby the present invention can detect the pathological changes of tissue as early as possible, can be used for the early stage inspection of gastric cancer.
(4) traditional checkout gear and method mainly rely on image detection, in the present research then are to rely on the tissue spectrum that exsomatizes to analyze.And the present invention utilizes image and spectral information as diagnosis basis simultaneously, and quantity of information is bigger, thereby more may obtain right judgement.
(5) in the research at present, be primarily aimed in vitro tissue spectrum characteristics peak and compare, analyze, and the pattern recognition module among the present invention is at setting up the discriminant analysis model at the full spectral coverage spectrum of soma, detect more accurate sensitivity, specificity is higher.
(6) common spectra collection mode is: mid-infrared light enters the mode that skin enters outgoing optical fiber more after reflection by incident optical, and the mid-infrared light penetration depth is very shallow, thereby it is few to carry quantity of information, and organizational information is easy to be submerged in instrument and the background noise.And the present invention adopts secondary extinction total reflection (ATR) probe, has improved spectral signal intensity and signal to noise ratio, for subsequent analysis provides possibility.
Description of drawings
Fig. 1 is a kind of stomach tissue character of the present invention noninvasive detection device composition frame chart;
Fig. 2 is the present invention and the bonded composition frame chart of stomach tissue;
Fig. 3 is a secondary ATR probe profile in apparatus of the present invention;
Fig. 4 is the structure chart of secondary ATR probe in apparatus of the present invention;
Fig. 5 is method flow diagram among the present invention;
Fig. 6 is used AOTF spectrometer architecture figure in the embodiment of the invention;
The stomach tissue image of Fig. 7 for collecting in the embodiment of the invention;
The stomach tissue spectrum of Fig. 8 for collecting in the embodiment of the invention.
Among the figure: 1 the Lights section, 2 visible light sources, 3 mid-infrared light sources, 4 visible light incident opticals, 5 mid-infrared light incident opticals, 6 secondary ATR probe, 7 stomach tissue, 8 mid-infrared light outgoing optical fiber, 9 spectra collection equipment, 10 miniature image collecting devices, 11 image signal transmission circuits, 12 spectral signal transmission lines, 13 computers, 14 pattern recognition modules, 15 stretch into the intravital soft component of patient, the device of 16 fixed fibers and atr crystal, 17 secondary atr crystals.
The specific embodiment
Below in conjunction with the drawings and specific embodiments technical scheme of the present invention is done further and to be elaborated:
As shown in Figures 1 to 4, stomach tissue character noninvasive detection device of the present invention comprises as the lower part:
The visible light that visible light source 2 sends enters visible light incident optical 4 and transfers in patient's body after Lens Coupling, illuminate stomach tissue, so that miniature image 10 harvesters are gathered the stomach image, and image information is converted into the signal of telecommunication is sent to external computer 13 by picture signal 11 outlet lines;
Infrared incident optical 5 and transferring to after the inherent secondary atr crystal of patient's body 17 inner surfacies carry out twice attenuated total reflectance during the mid-infrared light that send in mid-infrared light source 3 enters after Lens Coupling, the emergent light load Biochemical Information of stomach tissue after after outgoing optical fiber 8 reaches external spectra collection device 9 and be converted into spectral signal, be sent to computer part 13 through spectral signal transmission line 12;
Flexible by controlling, the intravital soft component 15 of patient is stretched in rotation, miniature image harvester 10 is gathered the image of stomach various piece tissue in real time, after finding the suspected lesion tissue, start spectra collection device 9 and gather the spectral signal at this place, herein image information and spectral information are saved simultaneously, be transferred to computer part 13 as input, computer can and show in real time with image and spectrographic storage, simultaneously, pattern recognition module 14 in the computer utilizes the various character stomach tissue spectra databases of having set up in advance, image information and spectral information to this place's tissue carry out discriminant analysis, and it is normal that output that can be real-time detects the organization discrimination tissue, superficial gastritis, the differentiation of atrophic gastritis or gastric cancer character.
Visible part light source 2 is selected halogen tungsten lamp for use; Siliconit is selected in mid-infrared light source 3 for use; Be equipped with convex lens respectively at visible part light source 2 and 3 exits, mid-infrared light source, the light that respectively two light sources is sent focuses on and is coupled into incident optical separately, through after the Lens Coupling, visible light source 2 and mid-infrared light source 3 advance respectively visible incident optical 4 with in infrared incident optical 5.
Visible light incident optical 4 is selected common quartzy material for use.
In infrared incident optical 5 with in infrared outgoing optical fiber 8 to select the optical fiber material for use be germanium salt glass, logical optical band is 700-4000cm
-1
It is 45 degree taper ZnSe crystal that secondary extinction is launched (ATR) crystal 17 entirely, and its section is an isosceles right triangle.
It is the back beam splitting type spectrogrph of light splitting part that the spectra collection device adopts AOTF.The population structure block diagram of used AOTF mid-infrared light spectrometer system as shown in Figure 6.Load the stomach tissue property information in infrared emergent light, to external, behind the optically focused colimated light system, enter the AOTF crystal by fiber-optic transfer.Under the effect of ultrasonic frequency, diffraction takes place in AOTF, and zero level transillumination and-1 order diffraction light are radiated at respectively on two middle Infrared Detectorss through focusing on.The optical signal that detector receives changes into direct current signal through interlock circuit, by the single-chip microcomputer computing in the spectrogrph, with the diffraction light signal divided by optical signal transmissive.Because two paths of signals passed through light path much at one, thereby the result of being divided by compensated various interference equal errors in the fluctuating, light path of the intensity of light source, improved certainty of measurement.Digital frequency synthesizer is used for the diffraction light wavelength is carried out continuously or single step scanning, finally generates spectral signal and transfers to computer.
Computer 13 adopts general purpose computer, minimalist configuration P41.7GHz, 512M ram.
Embodiments of the invention adopt support vector machine as Discrimination Analysis Algorithm.Set up by gathering a large amount of experimenter's stomach tissue information before using apparatus of the present invention, module support vector machine sorting algorithm is that the optimal classification face (Optimal Hyperplane) under the linear separability situation proposes.Require classifying face can both correctly classify, require it to satisfy exactly all samples
y
i(w
Tx
i+b)-1≥0，i＝1，2，...，n
Those samples that equal sign is set up are called support vector (Support Vectors).The gap size in the classification space (Margin) of two class samples:
Therefore, optimal classification face problem can be expressed as the minima of following constrained optimization problems.For this reason, the Lagrange function that can be defined as follows:
Wherein, a
i〉=0 is the Lagrange coefficient, and problem is that w and b are asked Lagrange minimum of a function value.By finding the solution this optimization problem, obtain the optimal classification function and be:
Wherein, sgn () is a sign function.
At first the input space is transformed to a higher dimensional space, in this new space, ask for the optimum linearity classifying face then, and this nonlinear transformation is to realize by defining suitable kernel function (inner product function), order by nonlinear transformation Φ:
K(x
i，x
j)＝<Φ(x
i)·Φ(x
j)>
With kernel function K (x
i, x
j) replace the dot product x in the optimal classification plane
i Tx
j, just being equivalent to former feature space has been transformed to a certain new feature space, corresponding discriminant function formula then is:
X wherein
iBe support vector, x is a unknown vector,
It is as follows to adopt the described checkout gear of claim 1 to carry out the specific embodiment of the method that stomach tissue character noinvasive detects:
Recruit trial volunteer totally 118 people, adopt the soft component of device of the present invention to stretch in experimenter's stomach, gather the image of a part, utilize this position tissue spectrum of sampling collecting fiber simultaneously by miniature image harvester wherein;
Spectrum position tissue is gathered in gripping, carries out pathological analysis, verifies gastric cancer 35 examples through the HE of Pathology Deparment, superficial gastritis 31 examples, atrophic gastritis 33 examples, normal gastric mucosa 19 examples;
Set up aforesaid support vector machine discriminant analysis model, extract a patient to be diagnosed again in addition immediately, after checking 8 o'clock evenings before that day, do not take food thing and beverage, no smoking.The previous day, supper was eaten the digestible food of few slag.The probe that will have the optical fiber of sampling stretches in patient's stomach, open the probe light source of being with and illuminate stomach tissue, gather the image of each position of stomach in real time, find that place's tissue shows as ulcer, this place's tissue image assert that then this place is doubtful position shown in Figure of description 7, note the spectrum picture of this place's tissue, gather and note the image and the spectroscopic data at this position simultaneously, this place organizes spectrogram as shown in Figure 8.
With the support vector machine discriminant analysis module that the spectral information and the image information at this place are brought foundation into, judge that this place is gastric cancer.Gripping then should be organized to external at the place, carries out conventional analysis of cases, and the result is consistent with testing result of the present invention.
The above is preferred embodiment of the present invention only, is not to be used to limit protection scope of the present invention.
Claims (10)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100909206A CN101623191B (en) | 2009-08-14 | 2009-08-14 | Device for noninvasively detecting property of stomach tissue |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2009100909206A CN101623191B (en) | 2009-08-14 | 2009-08-14 | Device for noninvasively detecting property of stomach tissue |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101623191A true CN101623191A (en) | 2010-01-13 |
| CN101623191B CN101623191B (en) | 2011-02-16 |
Family
ID=41519294
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2009100909206A Active CN101623191B (en) | 2009-08-14 | 2009-08-14 | Device for noninvasively detecting property of stomach tissue |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101623191B (en) |
Cited By (19)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012075702A1 (en) * | 2010-12-10 | 2012-06-14 | 广州宝胆医疗器械科技有限公司 | Electronic gastroscope system with infrared thermal scanning function |
| CN102512134A (en) * | 2011-11-17 | 2012-06-27 | 蔡信东 | Intelligent diagnostic enteroscope |
| CN103398948A (en) * | 2013-08-14 | 2013-11-20 | 武汉大学 | ATR (attenuated total reflectance) probe for Fourier transform infrared spectrometer |
| CN103750807A (en) * | 2011-12-30 | 2014-04-30 | 广州宝胆医疗器械科技有限公司 | Electronic gastroscope system with night vision function |
| CN105520719A (en) * | 2016-01-25 | 2016-04-27 | 上海电力学院 | Early cancer cell detection system based on infrared spectrum |
| CN107967946A (en) * | 2017-12-21 | 2018-04-27 | 武汉大学 | Operating gastroscope real-time auxiliary system and method based on deep learning |
| CN108140240A (en) * | 2015-08-12 | 2018-06-08 | 分子装置有限公司 | For automatically analyzing the system and method for the phenotypic response of cell |
| CN108185974A (en) * | 2018-02-08 | 2018-06-22 | 北京数字精准医疗科技有限公司 | A kind of endoscopic fluorescence ultrasound merges radiography navigation system |
| CN108245121A (en) * | 2016-12-29 | 2018-07-06 | 刘小华 | Endoscope and its imaging method and intelligent diagnosis system |
| CN108272437A (en) * | 2017-12-27 | 2018-07-13 | 中国科学院西安光学精密机械研究所 | Spectrum detection system for skin disease diagnosis and classifier model construction method |
| CN108670203A (en) * | 2018-06-01 | 2018-10-19 | 深圳开立生物医疗科技股份有限公司 | A kind of imaging device |
| CN108742490A (en) * | 2018-05-30 | 2018-11-06 | 广州众健医疗科技有限公司 | A kind of spectral detection system of diagnosing gastric cancer gastroscope |
| CN108784642A (en) * | 2018-05-30 | 2018-11-13 | 广州众健医疗科技有限公司 | A kind of spectrum biopsy instrument for early carcinoma of stomach diagnosis |
| CN109330550A (en) * | 2018-10-17 | 2019-02-15 | 孙静 | A kind of ultra-fine scope intelligence check device of Respiratory Medicine spectrum-type |
| CN111358573A (en) * | 2020-02-26 | 2020-07-03 | 西安交通大学医学院第二附属医院 | Hyperspectral imaging surgical area rapid detection and marking device and detection method |
| CN111568348A (en) * | 2020-06-04 | 2020-08-25 | 中国医学科学院生物医学工程研究所 | Optical diagnosis and treatment capsule endoscope with external power supply and control |
| CN112823396A (en) * | 2018-10-02 | 2021-05-18 | 翰林大学产学合作团 | Endoscope device and method for diagnosing gastric lesion based on gastric endoscope image obtained in real time |
| CN113324944A (en) * | 2021-06-08 | 2021-08-31 | 晶格码（青岛）智能科技有限公司 | In-situ on-line infrared spectrum monitoring equipment, system and method for crystallization process control |
| CN114305260A (en) * | 2021-12-20 | 2022-04-12 | 珠海格力电器股份有限公司 | Control method and device of cleaning robot, medium and cleaning robot |
-
2009
- 2009-08-14 CN CN2009100909206A patent/CN101623191B/en active Active
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2012075702A1 (en) * | 2010-12-10 | 2012-06-14 | 广州宝胆医疗器械科技有限公司 | Electronic gastroscope system with infrared thermal scanning function |
| CN102512134A (en) * | 2011-11-17 | 2012-06-27 | 蔡信东 | Intelligent diagnostic enteroscope |
| CN103750807A (en) * | 2011-12-30 | 2014-04-30 | 广州宝胆医疗器械科技有限公司 | Electronic gastroscope system with night vision function |
| CN103398948A (en) * | 2013-08-14 | 2013-11-20 | 武汉大学 | ATR (attenuated total reflectance) probe for Fourier transform infrared spectrometer |
| CN103398948B (en) * | 2013-08-14 | 2015-09-16 | 武汉大学 | A kind of ATR for Fourier transform infrared spectrometer pops one's head in |
| CN108140240A (en) * | 2015-08-12 | 2018-06-08 | 分子装置有限公司 | For automatically analyzing the system and method for the phenotypic response of cell |
| CN105520719A (en) * | 2016-01-25 | 2016-04-27 | 上海电力学院 | Early cancer cell detection system based on infrared spectrum |
| CN108245121A (en) * | 2016-12-29 | 2018-07-06 | 刘小华 | Endoscope and its imaging method and intelligent diagnosis system |
| CN107967946B (en) * | 2017-12-21 | 2021-05-11 | 武汉楚精灵医疗科技有限公司 | Gastroscope operation real-time auxiliary system and method based on deep learning |
| CN107967946A (en) * | 2017-12-21 | 2018-04-27 | 武汉大学 | Operating gastroscope real-time auxiliary system and method based on deep learning |
| CN108272437A (en) * | 2017-12-27 | 2018-07-13 | 中国科学院西安光学精密机械研究所 | Spectrum detection system for skin disease diagnosis and classifier model construction method |
| CN108185974A (en) * | 2018-02-08 | 2018-06-22 | 北京数字精准医疗科技有限公司 | A kind of endoscopic fluorescence ultrasound merges radiography navigation system |
| CN108742490A (en) * | 2018-05-30 | 2018-11-06 | 广州众健医疗科技有限公司 | A kind of spectral detection system of diagnosing gastric cancer gastroscope |
| CN108784642A (en) * | 2018-05-30 | 2018-11-13 | 广州众健医疗科技有限公司 | A kind of spectrum biopsy instrument for early carcinoma of stomach diagnosis |
| CN108670203A (en) * | 2018-06-01 | 2018-10-19 | 深圳开立生物医疗科技股份有限公司 | A kind of imaging device |
| CN112823396A (en) * | 2018-10-02 | 2021-05-18 | 翰林大学产学合作团 | Endoscope device and method for diagnosing gastric lesion based on gastric endoscope image obtained in real time |
| CN109330550A (en) * | 2018-10-17 | 2019-02-15 | 孙静 | A kind of ultra-fine scope intelligence check device of Respiratory Medicine spectrum-type |
| CN109330550B (en) * | 2018-10-17 | 2021-01-15 | 孙静 | Breathe superfine scope intelligent inspection device of spectrum formula for internal medicine |
| CN111358573A (en) * | 2020-02-26 | 2020-07-03 | 西安交通大学医学院第二附属医院 | Hyperspectral imaging surgical area rapid detection and marking device and detection method |
| CN111358573B (en) * | 2020-02-26 | 2023-06-20 | 西安交通大学医学院第二附属医院 | Device and method for rapidly detecting and marking hyperspectral imaging operation area |
| CN111568348A (en) * | 2020-06-04 | 2020-08-25 | 中国医学科学院生物医学工程研究所 | Optical diagnosis and treatment capsule endoscope with external power supply and control |
| CN113324944A (en) * | 2021-06-08 | 2021-08-31 | 晶格码（青岛）智能科技有限公司 | In-situ on-line infrared spectrum monitoring equipment, system and method for crystallization process control |
| CN114305260A (en) * | 2021-12-20 | 2022-04-12 | 珠海格力电器股份有限公司 | Control method and device of cleaning robot, medium and cleaning robot |
| CN114305260B (en) * | 2021-12-20 | 2022-11-01 | 珠海格力电器股份有限公司 | Control method and device of cleaning robot, medium and cleaning robot |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101623191B (en) | 2011-02-16 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101623191A (en) | Device and method for noninvasively detecting property of stomach tissue | |
| CN102088906A (en) | Improved method and apparatus for determination of a measure of a glycation end-product or disease state using tissue fluorescence | |
| Shim et al. | In vivo Near‐infrared Raman Spectroscopy: Demonstration of Feasibility During Clinical Gastrointestinal Endoscopy¶ | |
| Duraipandian et al. | Real-time Raman spectroscopy for in vivo, online gastric cancer diagnosis during clinical endoscopic examination | |
| US7440659B2 (en) | Depth-resolved reflectance instrument and method for its use | |
| US9931039B2 (en) | Methods related to real-time cancer diagnostics at endoscopy utilizing fiber-optic Raman spectroscopy | |
| US20030191378A1 (en) | Apparatus and method for spectroscopic analysis of tissue to detect diabetes in an individual | |
| US20030026762A1 (en) | Bio-spectral imaging system and methods for diagnosing cell disease state | |
| US20030023152A1 (en) | System for non-invasive measurement of glucose in humans | |
| US20090326383A1 (en) | Systems and methods for hyperspectral imaging | |
| US20110028808A1 (en) | Method and apparatus for examination of cancer, systemic lupus erythematosus (sle), or antiphospholipid antibody syndrome using near-infrared light | |
| CN1341209A (en) | Imaging of tissue using polarized light | |
| CA2429045A1 (en) | A diagnostic system for the ear | |
| AU2013341327A1 (en) | System and method for serum based cancer detection | |
| JP2003511693A (en) | Optimization of fiber optic probe for spectrophotometry | |
| WO2009043050A2 (en) | Optical assay system with a multi-probe imaging array | |
| JP2013544151A (en) | In vivo imaging apparatus and method for performing spectral analysis | |
| JP2013511341A (en) | Method and apparatus for detecting coronary artery calcification or coronary artery disease | |
| CN104856653A (en) | Device and method for detecting blood vessel | |
| JP2004526141A (en) | A method for processing broadband elastic scattering spectra obtained from tissue. | |
| JPH11510254A (en) | Optical microprobe and method for spectral analysis of materials | |
| Shaikh et al. | A comparative evaluation of diffuse reflectance and Raman spectroscopy in the detection of cervical cancer | |
| Fabelo et al. | Surgical aid visualization system for glioblastoma tumor identification based on deep learning and in-vivo hyperspectral images of human patients | |
| CN102046070A (en) | Rapid diagnosis of a disease condition using infrared spectroscopy | |
| Chang et al. | Deep learning methods for oral cancer detection using Raman spectroscopy |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |