Spectral domain optical coherence tomography crosssectional image of optic nerve head during intraocular pressure elevation

AIM: To analyze changes of the optic nerve head(ONH) and peripapillary region during intraocular pressure(IOP) elevation in patients using spectral domain optical coherence tomography(SD-OCT).METHODS: Both an optic disc 200×200 cube scan and a high-definition 5-line raster scan were obtained from open angle glaucoma patients presented with monocular elevation of IOP(≥30 mm Hg) using SD-OCT. Additional baseline characteristics included age, gender, diagnosis,best-corrected visual acuity, refractive error, findings of slit lamp biomicroscopy, findings of dilated stereoscopic examination of the ONH and fundus, IOP, pachymetry findings, and the results of visual field.RESULTS: The 24 patients were selected and divided into two groups: group 1 patients had no history of IOP elevation or glaucoma(n =14), and group 2 patients did have history of IOP elevation or glaucoma(n =10). In each patient, the study eye with elevated IOP was classified into group H(high), and the fellow eye was classified into group L(low). The mean deviation(MD)differed significantly between groups H and L when all eyes were considered(P =0.047) and in group 2(P =0.042), not in group 1(P =0.893). Retinal nerve fiber layer(RNFL) average thickness(P =0.050), rim area(P =0.015),vertical cup/disc ratio(P =0.011), cup volume(P =0.028),inferior quadrant RNFL thickness(P =0.017), and clockhour(1, 5, and 6) RNFL thicknesses(P =0.050, 0.012, and0.018, respectively), cup depth(P =0.008), central prelaminar layer thickness(P =0.023), mid-inferior prelaminar layer thickness(P =0.023), and nasal retinal slope(P =0.034)were significantly different between the eyes with groups H and L.CONCLUSION:RNFLaveragethickness,rim area,vertical cup/disc ratio, cup volume, inferior quadrant RNFL thickness, and clock-hour(1, 5, and 6) RNFL thicknesses significantly changed during acute IOP elevation.

Systematic review of macular ganglion cell complex analysis using spectral domain optical coherence tomography for glaucoma assessment

AIM: To review the use of spectral domain optical coherence tomography(SD-OCT) for macular retinal ganglion cells(RGC) and ganglion cell complex(GCC) measurement in glaucoma assessment, specifically for early detection and detection of disease progression. METHODS: A systematic review was performed by searching Pub Med, Medline, and Web of Science for articles published in English through July 2014 describing the various macular SD-OCT scanning strategies developed for glaucoma assessment. The review focused on papers evaluating the use of macular RGC/GCC SDOCT to detect early glaucoma and its progression. The search included keywords corresponding to the index test(macular ganglion cell/RGC/GCC/Spectral domain OCT), the target condition(glaucoma), and diagnostic performance. The RGC/GCC SD-OCT scanning strategies used to assess glaucoma of most commonly used SD-OCT instruments were described and compared. These included the Cirrus high definition-OCT(Carl Zeiss Meditec, Inc., Dublin, CA, United States), RTVue(Optovue, Inc., Fremont, CA, United States), Spectralis(Heidelberg Engineering, Heidelberg, Germany) and the 3D OCT 2000(Topcon Corporation, Tokyo, Japan). Studies focusing on the ability of RGC/GCC SD-OCT to detect early glaucomatous damage and on the correlation between glaucomatous progression and RGC/GCC measurement by SD-OCT were reviewed.RESULTS: According to the literature, macular RGC/GCC SD-OCT has high diagnostic power of preperimetric glaucoma, reliable discrimination ability to differentiate between healthy eyes and glaucomatous eyes, with good correlation with visual filed damage. The current data suggests that it may serve as a sensitive detection tool for glaucomatous structural progression even with mild functional progression as the rate of change of RGC/GCC thickness was found to be significantly higher in progressing than in stable eyes. Glaucoma assessment with RGC/GCC SD-OCT was comparable with and sometimes better than circumpapillary retinal nerve fiber layer thickness measurement.CONCLUSION: An increasing body of evidence supports using macular RGC/GCC thickness as an indicator for early glaucoma. This might be a useful tool for monitoring disease progression.

Predefined Exponential Basis Set for Half-Bounded Multi Domain Spectral Method

A non-orthogonal predefined exponential basis set is used to handle half-bounded domains in multi domain spectral method (MDSM). This approach works extremely well for real-valued semi-infinite differential problems. It spans simultaneously wide range of exponential decay rates with multi scaling and does not suffer from zero crossing. These two conditions are necessary for many physical problems. For comparison, the method is used to solve different problems and compared with analytical and published results. The comparison exhibits the strengths and accuracy of the presented basis set.

Single-Channel Speech Enhancement Based on Improved Frame-Iterative Spectral Subtraction in the Modulation Domain

Aiming at the problem of music noise introduced by classical spectral subtraction,a shorttime modulation domain(STM)spectral subtraction method has been successfully applied for singlechannel speech enhancement.However,due to the inaccurate voice activity detection(VAD),the residual music noise and enhanced performance still need to be further improved,especially in the low signal to noise ratio(SNR)scenarios.To address this issue,an improved frame iterative spectral subtraction in the STM domain(IMModSSub)is proposed.More specifically,with the inter-frame correlation,the noise subtraction is directly applied to handle the noisy signal for each frame in the STM domain.Then,the noisy signal is classified into speech or silence frames based on a predefined threshold of segmented SNR.With these classification results,a corresponding mask function is developed for noisy speech after noise subtraction.Finally,exploiting the increased sparsity of speech signal in the modulation domain,the orthogonal matching pursuit(OMP)technique is employed to the speech frames for improving the speech quality and intelligibility.The effectiveness of the proposed method is evaluated with three types of noise,including white noise,pink noise,and hfchannel noise.The obtained results show that the proposed method outperforms some established baselines at lower SNRs(-5 to +5 dB).

Microperimetry and spectral domain optical coherence tomography in myelinated retinal nerve fibers

Dear Sir,I write to present the correlation between microperimetric （MP） values and the density of myelinated retinal nerve fibers （MNFs） in optical coherence tomography （OCT） imaging.

Light-scattering model for aerosol particles with irregular shapes and inhomogeneous compositions using a parallelized pseudo-spectral time-domain technique

To improve the modeling accuracy of radiative transfer, the scattering properties of aerosol particles with irregular shapes and inhomogeneous compositions should be simulated accurately. To this end, a light-scattering model for nonspherical particles is established based on the pseudo-spectral time domain（PSTD） technique. In this model, the perfectly matched layer with auxiliary differential equation（ADE-PML）, an excellent absorption boundary condition（ABC） in the finite difference time domain generalized for the PSTD, and the weighted total field/scattered field（TF/SF） technique is employed to introduce the incident light into 3 D computational domain. To improve computational efficiency, the model is further parallelized using the Open MP technique. The modeling accuracy of the PSTD scheme is validated against Lorenz–Mie, Aden–Kerker, T-matrix theory and DDA for spheres, inhomogeneous particles and nonspherical particles, and the influence of the spatial resolution and thickness of ADE-PML on the modeling accuracy is discussed as well. Finally, the parallel computational efficiency of the model is also analyzed. The results show that an excellent agreement is achieved between the results of PSTD and well-tested scattering models, where the simulation errors of extinction efficiencies are generally smaller than 1%, indicating the high accuracy of our model. Despite its low spatial resolution, reliable modeling precision can still be achieved by using the PSTD technique, especially for large particles. To suppress the electromagnetic wave reflected by the absorption layers, a six-layer ADE-PML should be set in the computational domain at least.

Spectral Domain Optical Coherence Tomography of Vogt-Koyanagi-Harada Disease: Novel Findings and New Insights into the Pathogenesis

Objective To provide novel spectral domain optical coherence tomography (SD OCT) findings of Vogt-Koyanagi-Harada (VKH) disease as well as new insights into the pathogenesis of this disease. Methods Detailed SD OCT and fluorescein angiography (FA) findings of 18 consecutive VKH patients (11 women and 7 men) from December 2007 to April 2009 who were in acute uveitic stage at presentation were reviewed. All the patients had been followed up for at least 6 months with reevaluation(s) of SD OCT performed in 10 patients. Results Intraretinal cysts were found to be located in various layers of the outer retina. In addition to the photoreceptor layer, they could also be found between the outer plexiform layer and the outer nuclear layer, or spanning the external limiting membrane. On FA, intraretinal cysts could be hypofluorescent, normofluorescent, or hyperfluorescent. Some intraretinal cysts had a characteristic FA pattern, in which a small round hypofluorescent area was surrounded by a ring of hyperfluorescence (donut-shaped dye pooling). Subretinal fibrinoid deposit appeared in acute uveitic stage in two severe VKH patients and seemed to develop from subretinal exudates and evolved into typical subretinal fibrosis. Gradual transfiguration/migration and progressive proliferation/pigmentation of the subretinal fibrinoid deposit/subretinal fibrosis was observed in one patient. Conclusions Intraretinal cysts could form in various layers of the outer retina and may result from extension of choroidal inflammation. Subretinal fibrosis may develop from subretinal exudates in VKH patients and may cause substantial visual impairment.

Comparison of ultrasound biomicroscopy and spectraldomain anterior segment optical coherence tomography in evaluation of anterior segment after laser peripheral iridotomy

AIM：To quantitatively assess narrow anterior chamber angle using spectral-domain anterior segment optical coherence tomography（SD-AS-OCT） and ultrasound biomicroscopy（UBM）,and to evaluate the correlations and consistency between SD-AS-OCT and UBM.· METHODS：Fifty-five eyes from 40 patients were examined.Patients were diagnosed with primary angleclosure glaucoma（PACG） remission（11 eyes from 8patients）,primary angle closure（PAC,20 eyes from 20patients） and PAC suspect（24 eyes from 12 patients）.Each eye was examined by SD-AS-OCT and UBM after laser peripheral iridotomy（LPI）.The measurements of SD-AS-OCT were angle open distance（AOD）,anterior chamber angle（ACA）,trabecular iris angle（TIA）,and trabecular iris space area（TISA）.UBM measurements were AOD and TIA.Correlations of AOD500 and TIA500 between UBM and AS-OCT were assessed.All parameters were analysed by SPSS 16.0 and MedCalc.· RESULTS：ACA,TIA and AOD measured by SD-ASOCT reached a maximum at the temporal quadrant and minimum at the nasal quadrant.Group parameters of AOD500 and AOD750 showed a linear positive correlation,and AOD750 had less variability.UBM outcomes of AOD500 and TIA500 were significantly smaller than those of SD-AS-OCT.The results of the two techniques were correlated at the superior,nasal and inferior quadrants.CONCLUSION：Both UBM and SD-AS-OCT are efficient tools for follow-up during the course of PACG.We recommended using parameters at 750 μm anterior to the sclera spur for the screening and follow-up of PACG and PAC.The two methods might be alternatives to each other.

Direct spectral domain decomposition method for 2D incompressible Navier-Stokes equations

An efficient direct spectral domain decomposition method is developed coupled with Chebyshev spectral approximation for the solution of 2D, unsteady and in- compressible Navier-Stokes equations in complex geometries. In this numerical approach, the spatial domains of interest are decomposed into several non-overlapping rectangu- lar sub-domains. In each sub-domain, an improved projection scheme with second-order accuracy is used to deal with the coupling of velocity and pressure, and the Chebyshev collocation spectral method （CSM） is adopted to execute the spatial discretization. The influence matrix technique is employed to enforce the continuities of both variables and their normal derivatives between the adjacent sub-domains. The imposing of the Neu- mann boundary conditions to the Poisson equations of pressure and intermediate variable will result in the indeterminate solution. A new strategy of assuming the Dirichlet bound- ary conditions on interface and using the first-order normal derivatives as transmission conditions to keep the continuities of variables is proposed to overcome this trouble. Three test cases are used to verify the accuracy and efficiency, and the detailed comparison be- tween the numerical results and the available solutions is done. The results indicate that the present method is efficiency, stability, and accuracy.

Parallel Spectral-Domain Optical Coherence Tomography for Non-Scattering Object Imaging

The parallel spectral-domain optical coherence tomography(PSDOCT) is described for high-speed optical coherence tomography(OCT) without lateral scanning. In this setup, the self-elimination of auto-correlation(AC) interference algorithm was used for eradicating the AC interference and ghost images. However, when performed in free space OCT, this algorithm still generated a weak DC component. The algorithm was improved by adding the background intensity part to compensate for the mutual interference between object and reference arms. The results demonstrate that the DC component can be eradicated. Compared with conventional OCT and complex Fourier-domain optical coherence tomography, the advantages of PSDOCT with the improved algorithm in free space are that it has no moving parts to generate consecutive phase shift, the structure of the object can be reconstructed immediately and automatically, and the speed is approximately 16 times faster than those of the other two in the same case.

Agreement of angle closure assessments between gonioscopy, anterior segment optical coherence tomography and spectral domain optical coherence tomography

AIM: To determine angle closure agreements between gonioscopy and anterior segment optical coherence tomography(AS-OCT), as well as gonioscopy and spectral domain OCT(SD-OCT). A secondary objective was to quantify inter-observer agreements of AS-OCT and SD-OCT assessments.METHODS: Seventeen consecutive subjects(33 eyes)were recruited from the study hospital’s Glaucoma clinic.Gonioscopy was performed by a glaucomatologist masked to OCT results. OCT images were read independently by 2 other glaucomatologists masked to gonioscopy findings as well as each other’s analyses of OCT images.RESULTS: Totally 84.8% and 45.5% of scleral spurs were visualized in AS-OCT and SD-OCT images respectively(P 【0.01). The agreement for angle closure between AS-OCT and gonioscopy was fair at k =0.31(95% confidence interval, CI: 0.03-0.59) and k =0.35(95%CI: 0.07-0.63) for reader 1 and 2 respectively. The agreement for angle closure between SD-OCT and gonioscopy was fair at k =0.21(95% CI: 0.07-0.49) and slight at k =0.17(95% CI: 0.08-0.42) for reader 1 and 2 respectively. The inter-reader agreement for angle closure in AS-OCT images was moderate at 0.51(95% CI: 0.13-0.88). The inter-reader agreement for angle closure in SD-OCT images was slight at 0.18(95% CI: 0.08-0.45).CONCLUSION: Significant proportion of scleral spurs were not visualised with SD-OCT imaging resulting in weaker inter-reader agreements. Identifying other angle landmarks in SD-OCT images will allow more consistent angle closure assessments. Gonioscopy and OCT imaging do not always agree in angle closure assessments but have their own advantages, and should be used together and not exclusively.

Time-Spectral Solution of Initial-Value Problems—Subdomain Approach

Temporal and spatial subdomain techniques are proposed for a time-spectral method for solution of initial-value problems. The spectral method, called the generalised weighted residual method (GWRM), is a generalisation of weighted residual methods to the time and parameter domains [1]. A semi-analytical Chebyshev polynomial ansatz is employed, and the problem reduces to determine the coefficients of the ansatz from linear or nonlinear algebraic systems of equations. In order to avoid large memory storage and computational cost, it is preferable to subdivide the temporal and spatial domains into subdomains. Methods and examples of this article demonstrate how this can be achieved.

Comment on “The diurnal variation pattern of choroidal thickness in macular region of young healthy female individuals using spectral domain optical coherence tomography”

Dear Editor,We have read and reviewed the article entitled＂The diurnal variation pattern of choroidal thickness in macular region of young healthy female individuals using spectral domain optical coherence tomography＂by Zhao et al^（[1]）with great interest.

Importance of 3-D image reconstruction of spectraldomain OCT on outcome of grid laser photocoagulation for diffuse diabetic macular edema

AIM:To present the outcome of modified grid laser photocoagulation(GLP)in diffuse diabetic macular edema(DDME)in eyes without extrafoveal and/or vitreofoveal traction.METHODS:Inclusion criteria for the retrospective study were DDME eyes of patients with typeⅡdiabetes mellitus that had≥4 months of follow-up following GLP.Only one eye per patient was analyzed.Using 3-D spectral-domain optical coherence tomography(3-D SDOCT),eyes that had either extrafoveal or vitreofoveal traction,or had been previously treated by an intravitreal medication(s)were excluded.Treated DDME eyes were divided into 4 groups:A)"Classic"DDME that involved the central macula;B)edema did not involve the macular center;C)eyes associated with central epiretinal membrane(ERM);D)DDME that was associated with macular capillary dropout≥2 disc-diameter(DD).RESULTS:GLP outcome in 35 DDME eyes after 4-24(mean,13.1±6.9)months was as follows:Group A)18eyes with"classic"DDME.Following one or 2(mean,1.2)GLP treatments,best-corrected visual acuity(BCVA)improved by 1-2 Snellen lines in 44.4%(8/18)of eyes,and worsened by 1 line in 11.1%(2/18).Central macular thickness(CMT)improved by 7%-49%(mean,26.6%)in77.8%(14/18)of eyes.Causes of CMT worsening(n=4)were commonly explainable,predominantly(n=3)associated with emergence of extrafoveal traction,5-9months post-GLP.Group B)GLP(s)in DDME that did not involve the macular center(n=6)resulted in improved BCVA by 1-2 lines in 2 eyes.However,the central macula became involved in the edema process after the GLP in 3(50%)eyes,associated with an emergence of extrafoveal traction in one of these eyes 4months following the GLP.Group C)GLP failed in all 5eyes associated with central ERM.Group D)GLP was of partial benefit in 2 of 6 treated eyes with macular capillary dropout≥2DD.CONCLUSION:Eyes with DDME that involved the macular center were found to achieve favourable outcomes after GLP(s)during mid-term follow-up,unless complicated pre-GLP or post-GLP by vltreoretinal interface abnormalities,often extrafoveal traction or ERM,or by capillary dropout≥2DD.Prospective studies with larger cohorts are required.

A Service-Based Intelligent Time-Domain and Spectral-Domain Flow Aggregation in IP-over-EON Based on SDON

The rapid growth of IP traffic has contributed to wide deployment of optical devices in elastic optical network.However,the passband shape of wavelength selective switches(WSSs)that are used in reconfigurable optical add-drop multiplexer(ROADM)/optical cross connect(OXC)is not ideal,causing the narrowing of spectrum.Spectral narrowing will lead to signal impairment.Therefore,guard-bands need to be inserted between adjacent paths which will cause the waste of resources.In this paper,we propose a service-based intelligent aggregation node selection and area division(ANS-AD)algorithm.For the rationality of the aggregation node selection,the ANS-AD algorithm chooses the aggregation nodes according to historical traffic information based on big data analysis.Then the ANS-AD algorithm divides the topology into areas according to the result of the aggregation node selection.Based on the ANS-AD algorithm,we propose a time-domain and spectral-domain flow aggregation(TS-FA)algorithm.For the purpose of reducing resources'waste,the TS-FA algorithm attempts to reduce the insertion of guard-bands by time-domain and spectral-domain flow aggregation.Moreover,we design a time-domain and spectral-domain flow aggregation module on software defined optical network(SDON)architecture.Finally,a simulation is designed to evaluate the performance of the proposed algorithms and the results show that our proposed algorithms can effectively reduce the resource waste.

A SPECTRAL-DOMAIN IMMITTANCE APPROACH FOR THE CHARACTERISTICS OF FINLINES LOADED WITH ANISOTROPIC MEDIUM

The equations of electrodynamics for a gyrotropic medium by using Maxwell’s equa-tions are deduced.Through Fourier transformation,the admittances of TM and TE modes inthe electrically gyrotropic substrate and magnetically gyrotropic substrate are given.Numericalresults of the dominant mode in magnetized ferrite-loaded double-layered finlines are presentedwhich could be used in designing finline ferrite devices.

Comparison of central macular thickness between two spectral-domain optical coherence tomography in elderly non-mydriatic eyes

AIM: To compare central macular thickness (CMT) measurements obtained by two spectral-domain optical coherence tomography (SD-OCT) exams, and to evaluate measurement reproducibility and agreement between these two exams, and to investigate the relationship between CMT and possible influencing factors such as age, sex, eye (OD/OS), and operators in elderly non-mydriatic eyes. METHODS: Seventy-two normal subjects were included. Every subject underwent CMT measurement twice using one of two SD-OCT (OSE-2000, Moptim, Shenzhen, China & 3-D OCT-1000, Topcon, Tokyo, Japan) instruments respectively where we randomly chose one eye in each patient for the test; these exams were performed by two operators over an hour period with a brief rest between sessions. Comparison of the OSE-2000 and 3-D OCT-1000 CMT measurements was based on paired- t test The mean difference between the CMT measurements was calculated. General linear model analyzed the relationships among eye (OD/OS), operator, sex, and CMT values using age as co-variant. All tests were considered statistically significant at P <0.05. The main outcome measures included CMT. RESULTS: When evaluated with general linear model analysis, CMT measurements were found to have high reproducibility across the two instruments between the two operators for the OSE-2000 single line scan and 3-D OCT-1000 macular scans (P=0.731; P=0.443). There was statistically significant difference in CMT values between the two instruments (P<0.001) and the mean difference was -46.83 mu m at 95% confidence limits (-49.15,-44.51). Age was positively correlated with CMT (beta coefficient =0.516, P=0.001; beta coefficient=0.453, P =0.009) and sex was correlated with CMT from the OSE-2000 (P=0.021) but not with the 3-D OCT-1000 (P=0.056). According to the actual thickness measurements, the CMT of the male was thicker than the female's but there was no statistical difference. There was interaction between sex and eye in OSE-2000 and not in 3-D OCT-1000 (P=0.02; P =0.374). No significant correlation was found between CMT and the influencing factor of eye in both of the instruments (P=0.884; P=0.492). CONCLUSION: Reproducibility of CMT measurement using the two SD-OCTs is excellent in normal eyes according to the operator factor analysis. OSE-2000 has a different posterior retinal boundary of CMT measurement, which results in the CMT value differences, compared with the 3-D OCT-1000. Age is positively correlated with CMT measurement while sex is correlated with CMT in the OSE-2000 but not in the 3-D OCT-1000 and eye (OD/OS) had no correlation with CMT values. Mydriatic drops may not be necessary for CMT measurement using high scan rate SD-OCT in normal eyes in dark room.

Choroidal Analysis of Polypoidal Choroidal Vasculopathy by Spectral Domain Optical Coherence Tomography

Purpose: This study was designed to measure the changes in the subfoveal choroidal thickness(SFCT) and choroidal maximal vessel diameter(MVD) of the affected and unaffected fellow eyes in patients with polypoidal choroidal vasculopathy(PCV) and compare them to healthy controls.Methods: In this cross-sectional observational clinical study,SFCT and MVD were measured in both eyes of 53 patients with unilateral PCV. PCV eyes were subgrouped into group A and unaffected fellow eyes into group B. All patients were diagnosed with PCV by fundus fluorescein angiography.(FFA)and indocyanine green angiography.(ICGA). Sixty age- and gender-matched healthy subjects were enrolled in the control group(group C).Results: No statistical difference was observed among groups in age and gender. Overall, SFCT was correlated with MVD in all subjects(P <0.001; correlation coefficient: 0.759). P values were < 0.001 with a correlation coefficient of 0.686,0.801, and 0.808 in groups A, B, and C, respectively. No statistical significance was noted in SFCT among groups A(266.45±99.51 μm),B(269.57 ± 105.10 μm),and C(243.83±99.68 μm)(P =0.335). However, the MVD in group A was(202.55±72.45 μm), significantly larger than that in group C(166.45 ±56.18 μm,P =0.008), while the MVD in group B(194.75±85.27 μm) was equally significantly greater than that in group C(166.45 ± 56.18 μm)(P=0.038).Conclusion: For both PCV patients and healthy subjects,SFCT was positively correlated with MVD. No statistical significance was noted in SFCT between PCV eyes and unaffected fellow / normal eyes. However, MVD was significantly larger in the PCV affected eyes than in unaffected fellow or normal control eyes, suggesting that MVD could be considered as a sensitive indicator to evaluate choroidal perfusion in PCV patients.

1310 nm Source Spectral-Domain Optical Coherence Tomography for Chinese Pigment and Jadeite Research

Optical Coherence Tomography (OCT) technique is a nondestructive optical detection technology based on low-coherence interferometer and it has become an attractive cultural heritage research method. A 1310 nm source spectral-domain optical coherence tomography (SD-OCT) system based on optical fiber Michelson interferometer and optical spectrum analyzer is proposed and demonstrated for Chinese cultural heritage research. The cross-section OCT images of Chinese pigment samples and jadeite samples can provide a lot of valuable microstructure information for the Chinese cultural heritage research and identification works.

基于专利文本多粒度深层语义的技术演化路径智能识别方法研究

[目的/意义]专利文本是技术演化分析的可靠知识来源。利用领域多层本体和Sentence-BERT深度学习预训练模型可分别从词和句子两个角度挖掘多粒度深层文本语义信息,提升专利文本语义挖掘的全面性,进而提高技术演化路径识别的准确性。[方法/过程]以深度学习、基于本体的相似度计算及谱聚类算法等大数据和人工智能技术为基础,实现准确、高效、全面的技术演化路径智能识别。构建领域词典和领域本体,根据领域词典抽取专利摘要中的领域术语,根据领域本体中不同术语的最近共同祖先节点的深度,从词语级别计算专利摘要间的语义相似度;利用Sentence-BERT对专利摘要进行向量化表示,计算句子层面的语义相似度;结合两种相似度的计算结果构建相似度矩阵并进行谱聚类,根据谱聚类结果和专利时序特征识别技术演化路径。最后以光刻领域专利数据为例进行实证研究。[结果/结论]实验结果表明,谱聚类得到的技术类别划分结果的准确率、精确率、召回率和F1值的平均值均达到了85%以上,说明文章提出的基于专利文本多粒度深层语义的技术演化路径智能识别方法是有效的,其有助于科研人员、企业决策者和政府决策者探究技术发展历程,研判技术创新方向,推动关键技术研发。