The paper presents a study of various approaches to the classification of soil covers based on neural network algorithms using hyperspectral remote and proximal sensing of the Earth. The spectral distributions were recorded in the laboratory using an Offner imaging scanning hyperspectrometer. Spectral-spatial characteristics of nine soil samples from various parts of a farming land in the Samara region were experimentally studied. Using a method of energy dispersion microanalysis, the correspondence between the hyperspectral data and the chemical composition of the samples taken was established. Based on the data obtained, a neural network-aided classification of soil samples was implemented depending on the content of constituent elements such as carbon and calcium. A normalized spectral-spatial convolutional neural network was used as a classifier. As a result of the work, an approach to the classification of high-resolution hyper-spectral images based on the refinement of a multiclass convolutional neural network using an ensemble of binary classifiers is proposed. It is shown that the classification of soil samples by carbon and calcium content is carried out with an accuracy of 0.96.
{"title":"Ensembles of spectral-spatial convolutional neural network models for classifying soil types in hyperspectral images","authors":"N.A. Firsov, V.V. Podlipnov, N.A. Ivliev, D.D. Ryskova, A.V. Pirogov, A.A. Muzyka, A.R. Makarov, V.E. Lobanov, V.I. Platonov, A.N. Babichev, V.A. Monastyrskiy, V.I. Olgarenko, D.P. Nikolaev, R.V. Skidanov, A.V. Nikonorov, N.L. Kazanskiy, V.A. Soyfer","doi":"10.18287/2412-6179-co-1260","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1260","url":null,"abstract":"The paper presents a study of various approaches to the classification of soil covers based on neural network algorithms using hyperspectral remote and proximal sensing of the Earth. The spectral distributions were recorded in the laboratory using an Offner imaging scanning hyperspectrometer. Spectral-spatial characteristics of nine soil samples from various parts of a farming land in the Samara region were experimentally studied. Using a method of energy dispersion microanalysis, the correspondence between the hyperspectral data and the chemical composition of the samples taken was established. Based on the data obtained, a neural network-aided classification of soil samples was implemented depending on the content of constituent elements such as carbon and calcium. A normalized spectral-spatial convolutional neural network was used as a classifier. As a result of the work, an approach to the classification of high-resolution hyper-spectral images based on the refinement of a multiclass convolutional neural network using an ensemble of binary classifiers is proposed. It is shown that the classification of soil samples by carbon and calcium content is carried out with an accuracy of 0.96.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136059523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper describes a TurbidMC code that implements a perturbative Monte Carlo method to model temporal point spread functions and sensitivity functions for time-resolved fluorescence molecular tomography (FMT). The code is aimed at working with a particular FMT method published earlier (Ref. [22]) which defines the specificity of sensitivity function calculation. The method solves the inverse problem first for a generalized fluorescence parameter distribution function and then calculates separate distributions for the fluorophore absorption coefficient and the fluorescence lifetime. The proper operation of the code was verified through a comparison between fluorescence temporal point spread functions from test calculations and data from experiments where a phantom with a fluorophore was scanned with a three-channel probe in the mesoscopic reflectance regime. An example is given on the reconstruction of fluorescence parameter distributions. It shows that the sensitivity functions are calculated correctly.
{"title":"Monte Carlo modeling of temporal point spread functions and sensitivity functions for mesoscopic time-resolved fluorescence molecular tomography","authors":"S.I. Samarin, A.B. Konovalov, V.V. Vlasov, I.D. Solovyev, A.P. Savitsky, V.V. Tuchin","doi":"10.18287/2412-6179-co-1295","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1295","url":null,"abstract":"The paper describes a TurbidMC code that implements a perturbative Monte Carlo method to model temporal point spread functions and sensitivity functions for time-resolved fluorescence molecular tomography (FMT). The code is aimed at working with a particular FMT method published earlier (Ref. [22]) which defines the specificity of sensitivity function calculation. The method solves the inverse problem first for a generalized fluorescence parameter distribution function and then calculates separate distributions for the fluorophore absorption coefficient and the fluorescence lifetime. The proper operation of the code was verified through a comparison between fluorescence temporal point spread functions from test calculations and data from experiments where a phantom with a fluorophore was scanned with a three-channel probe in the mesoscopic reflectance regime. An example is given on the reconstruction of fluorescence parameter distributions. It shows that the sensitivity functions are calculated correctly.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136059838","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We investigate polarization transformations carried out with a refractive bi-conical axicon using the FDTD method. The approach is based on the transformation of a circularly polarized optical beam into an azimuthally polarized beam due to the use of a single refractive element with two conical surfaces. On the inner surface of the element, polarization conversion occurs due to the reflection and refraction of rays at the Brewster angle, while the outer surface operates as a converted beam collimator. The distributions of the components of the electric field vector and the polarization vector at different distances from the optical element are considered as criteria for a successful polarization transformation. By numerical simulation of the performance of a bi-conical axicon made of glass with a refractive index of n = 1.4958, the efficiency of the proposed approach for a circularly polarized Gaussian beam with a wavelength of λ = 1.5 µm is shown. The proposed element is shown to be immune to chromatic aberrations in a significant range of changes in the refractive index of the element material and incident wavelengths (1.5 ≤ n ≤ 1.7; 1 μm ≤ λ ≤ 1.5 μm).
{"title":"Investigation of polarization transformations performed with a refractive bi-conical axicon using the FDTD method","authors":"P.A. Khorin, A.M. Algubili, S.A. Degtyarev, S.K. Sergunin, S.V. Karpeev, None S.N. Khonina 1,2","doi":"10.18287/2412-6179-co-1326","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1326","url":null,"abstract":"We investigate polarization transformations carried out with a refractive bi-conical axicon using the FDTD method. The approach is based on the transformation of a circularly polarized optical beam into an azimuthally polarized beam due to the use of a single refractive element with two conical surfaces. On the inner surface of the element, polarization conversion occurs due to the reflection and refraction of rays at the Brewster angle, while the outer surface operates as a converted beam collimator. The distributions of the components of the electric field vector and the polarization vector at different distances from the optical element are considered as criteria for a successful polarization transformation. By numerical simulation of the performance of a bi-conical axicon made of glass with a refractive index of n = 1.4958, the efficiency of the proposed approach for a circularly polarized Gaussian beam with a wavelength of λ = 1.5 µm is shown. The proposed element is shown to be immune to chromatic aberrations in a significant range of changes in the refractive index of the element material and incident wavelengths (1.5 ≤ n ≤ 1.7; 1 μm ≤ λ ≤ 1.5 μm).","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136056130","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-01DOI: 10.18287/2412-6179-co-1269
E.N. Churaev, A.V. Savchenko
In this paper, an approach that can significantly increase the accuracy of facial emotion recognition by adapting the model to the emotions of a particular user (e.g., smartphone owner) is considered. At the first stage, a neural network model, which was previously trained to recognize facial expressions in static photos, is used to extract visual features of faces in each frame. Next, the face features of video frames are aggregated into a single descriptor for a short video fragment. After that a neural network classifier is trained. At the second stage, it is proposed that adaptation (fine-tuning) to this classifier should be performed using a small set of video data with the facial expressions of a particular user. After emotion classification, the user can adjust the predicted emotions to further improve the accuracy of a personal model. As part of an experimental study for the RAVDESS dataset, it has been shown that the approach with model adaptation to a specific user can significantly (up to 20 – 50 %) improve the accuracy of facial expression recognition in the video.
{"title":"Facial expression recognition based on adaptation of the classifier to videos of the user","authors":"E.N. Churaev, A.V. Savchenko","doi":"10.18287/2412-6179-co-1269","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1269","url":null,"abstract":"In this paper, an approach that can significantly increase the accuracy of facial emotion recognition by adapting the model to the emotions of a particular user (e.g., smartphone owner) is considered. At the first stage, a neural network model, which was previously trained to recognize facial expressions in static photos, is used to extract visual features of faces in each frame. Next, the face features of video frames are aggregated into a single descriptor for a short video fragment. After that a neural network classifier is trained. At the second stage, it is proposed that adaptation (fine-tuning) to this classifier should be performed using a small set of video data with the facial expressions of a particular user. After emotion classification, the user can adjust the predicted emotions to further improve the accuracy of a personal model. As part of an experimental study for the RAVDESS dataset, it has been shown that the approach with model adaptation to a specific user can significantly (up to 20 – 50 %) improve the accuracy of facial expression recognition in the video.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136059843","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-01DOI: 10.18287/2412-6179-co-1346
A.G. Nalimov, V.V. Kotlyar, Yu.V. Khanenko
We conduct a comparative analysis of diffraction fields upon sharply focusing vortex and non-vortex incident beams, calculated using three non-paraxial methods. The methods employed are a finite difference time domain (FDTD) method, a Rayleigh–Sommerfeld integral, and a Richards–Wolf transformation. The Richards–Wolf transformation is used with two apodization functions of the exit pupil, for a spherical lens and a thin diffractive lens. The numerical simulation shows that the Rayleigh–Sommerfeld integral and the Richards–Wolf transformation can produce almost the same result and save time significantly. Meanwhile, the root-mean-square deviation of the results of both methods from the FDTD method can be as low as 2%. If an ultra-short focal length is used, the Richards–Wolf transformation is found to be more accurate, whereas with increasing distance from the initial plane and outside the focal plane, the Rayleigh-Sommerfeld integral is more accurate.
{"title":"Calculation of the intensity at the sharp focus of a cylindrical vector beam by three methods","authors":"A.G. Nalimov, V.V. Kotlyar, Yu.V. Khanenko","doi":"10.18287/2412-6179-co-1346","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1346","url":null,"abstract":"We conduct a comparative analysis of diffraction fields upon sharply focusing vortex and non-vortex incident beams, calculated using three non-paraxial methods. The methods employed are a finite difference time domain (FDTD) method, a Rayleigh–Sommerfeld integral, and a Richards–Wolf transformation. The Richards–Wolf transformation is used with two apodization functions of the exit pupil, for a spherical lens and a thin diffractive lens. The numerical simulation shows that the Rayleigh–Sommerfeld integral and the Richards–Wolf transformation can produce almost the same result and save time significantly. Meanwhile, the root-mean-square deviation of the results of both methods from the FDTD method can be as low as 2%. If an ultra-short focal length is used, the Richards–Wolf transformation is found to be more accurate, whereas with increasing distance from the initial plane and outside the focal plane, the Rayleigh-Sommerfeld integral is more accurate.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136059831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-01DOI: 10.18287/2412-6179-co-1310
V.V. Kotlyar, S.S. Stafeev, E.S. Kozlova
In this work, by the Richards-Wolf method, which describes the behavior of electromagnetic radiation at the tight focus, it is shown that high-order spin and orbital Hall effects take place in the focal plane. It is shown that when focusing a linearly polarized optical vortex with unit topological charge, four local subwavelength regions are formed in the focal plane, in which directions of the longitudinal projection of the spin angular momentum are opposite in the neighboring regions. That is, photons falling into neighboring regions in the focus have the opposite spin. This is the spin Hall effect of the 2nd order. It is also shown that when tightly focusing of superposition of cylindrical vector beams of the m-th order and zero order, 2m subwavelength regions are formed in the plane of tight focus, in which directions of the longitudinal projection of the orbital angular momentum are opposite in the neighboring regions. That is, photons falling into the neighboring regions at the focus have the opposite-sign on-axis projections of the orbital angular momentum. This is the orbital Hall effect of the m-th order.
{"title":"High-order optical Hall effect at the tight focus of laser radiation","authors":"V.V. Kotlyar, S.S. Stafeev, E.S. Kozlova","doi":"10.18287/2412-6179-co-1310","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1310","url":null,"abstract":"In this work, by the Richards-Wolf method, which describes the behavior of electromagnetic radiation at the tight focus, it is shown that high-order spin and orbital Hall effects take place in the focal plane. It is shown that when focusing a linearly polarized optical vortex with unit topological charge, four local subwavelength regions are formed in the focal plane, in which directions of the longitudinal projection of the spin angular momentum are opposite in the neighboring regions. That is, photons falling into neighboring regions in the focus have the opposite spin. This is the spin Hall effect of the 2nd order. It is also shown that when tightly focusing of superposition of cylindrical vector beams of the m-th order and zero order, 2m subwavelength regions are formed in the plane of tight focus, in which directions of the longitudinal projection of the orbital angular momentum are opposite in the neighboring regions. That is, photons falling into the neighboring regions at the focus have the opposite-sign on-axis projections of the orbital angular momentum. This is the orbital Hall effect of the m-th order.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136059847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-10-01DOI: 10.18287/2412-6179-co-1258
S. Stepanenko, V. Evdokimova, M. Petrov, R. Skidanov, A. Nikonorov
The possibility of essentially reducing the weight and production cost of computer vision systems has led to the publication of a large number of research works dealing with the development of new imaging systems based on diffractive optics. This study proposes a new imaging system composed of three diffractive lenses, with each forming a separate channel of the color RGB image. This approach allows us to significantly narrow the spectral range of each lens, thus significantly reducing the image distortion caused by chromatic aberration inherent in diffractive optics. It shows that this scheme allows us to perform the neural network-aided image reconstruction, providing a significantly improved resulting image quality. The study proposes a false edge level criterion (FEL) for evaluating the neural network-aided reconstruction.
{"title":"Color imaging using a system based on 3 diffractive lenses","authors":"S. Stepanenko, V. Evdokimova, M. Petrov, R. Skidanov, A. Nikonorov","doi":"10.18287/2412-6179-co-1258","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1258","url":null,"abstract":"The possibility of essentially reducing the weight and production cost of computer vision systems has led to the publication of a large number of research works dealing with the development of new imaging systems based on diffractive optics. This study proposes a new imaging system composed of three diffractive lenses, with each forming a separate channel of the color RGB image. This approach allows us to significantly narrow the spectral range of each lens, thus significantly reducing the image distortion caused by chromatic aberration inherent in diffractive optics. It shows that this scheme allows us to perform the neural network-aided image reconstruction, providing a significantly improved resulting image quality. The study proposes a false edge level criterion (FEL) for evaluating the neural network-aided reconstruction.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136059837","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.18287/2412-6179-co-1237
I.A. Kunina, A.V. Sher, D.P. Nikolaev
This paper examines a presentation attack detection when a document recaptured from a screen is presented instead of the original document. We propose an algorithm based on analyzing a moiré pattern within document boundary regions as a distinctive feature of the recaptured image. It is assumed that the pattern overlapping the document boundaries is a recapture artifact, not a match between document and background textures. To detect such a pattern, we propose an algorithm that employs the result of the fast Hough transform of the document boundary regions with enhanced pattern contrast. The algorithm performance was measured for the open dataset DLC-2021, which contains images of mock documents as originals and their screen recaptures. The precision of the proposed solution was evaluated as 95.4 %, and the recall as 90.5 %.
{"title":"Screen recapture detection based on color-texture analysis of document boundary regions","authors":"I.A. Kunina, A.V. Sher, D.P. Nikolaev","doi":"10.18287/2412-6179-co-1237","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1237","url":null,"abstract":"This paper examines a presentation attack detection when a document recaptured from a screen is presented instead of the original document. We propose an algorithm based on analyzing a moiré pattern within document boundary regions as a distinctive feature of the recaptured image. It is assumed that the pattern overlapping the document boundaries is a recapture artifact, not a match between document and background textures. To detect such a pattern, we propose an algorithm that employs the result of the fast Hough transform of the document boundary regions with enhanced pattern contrast. The algorithm performance was measured for the open dataset DLC-2021, which contains images of mock documents as originals and their screen recaptures. The precision of the proposed solution was evaluated as 95.4 %, and the recall as 90.5 %.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134997845","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Advantages and prospects of using optical microresonators for the development of measuring instruments based on frequency combs are described. A principle of a frequency comb generator based on an optical microresonator is considered. An example of modeling the properties of microresonators used to generate optical frequency combs is considered. The influence of the nonuniformity of the optical microresonator’s generatrix on the value of the total dispersion has been studied. It is shown that the presence of nonuniformity on the surface affects the dispersion parameters and can also lead to the effect of mode shape splitting in microresonators. We have shown that this effect is particularly dependent on the position and the value of the depth of nonuniformity.
{"title":"Evaluation of the influence of surface irregularity of optical crystal microresonators on their dispersion characteristics","authors":"A.N. Danilyn, A.I. Yurin, N.M. Kondratyev, D.D. Ruzhitskaya, N.Yu. Dmitriev, F.V. Bulygin, S.G. Semenchinsky, M.I. Krasivskaya, K.N. Min’kov","doi":"10.18287/2412-6179-co-1100","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1100","url":null,"abstract":"Advantages and prospects of using optical microresonators for the development of measuring instruments based on frequency combs are described. A principle of a frequency comb generator based on an optical microresonator is considered. An example of modeling the properties of microresonators used to generate optical frequency combs is considered. The influence of the nonuniformity of the optical microresonator’s generatrix on the value of the total dispersion has been studied. It is shown that the presence of nonuniformity on the surface affects the dispersion parameters and can also lead to the effect of mode shape splitting in microresonators. We have shown that this effect is particularly dependent on the position and the value of the depth of nonuniformity.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"35 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134998061","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-08-01DOI: 10.18287/2412-6179-co-1261
J. Hou, H. Shi, W. Gao, P. Lin, B. Li, Y. Shi, I.A. Matveeva, V.P. Zakharov, I.A. Bratchenko
In this study, the diagnostic abilities of intensity parameters of optical coherence tomography angiography (OCTA) images in the early detection of diabetic retinopathy (DR) were determined. 78 normal healthy eyes, 10 diabetic eyes with mild non-proliferative diabetic retinopathy (NPDR), and 10 diabetic eyes with moderate NPDR were employed. Four retinal vascular plexuses were generated by using OCTA, which included the nerve fiber layer vascular plexus (NFLVP), superficial vascular plexus (SVP), intermediate capillary plexus (ICP) and deep capillary plexus (DCP). The parafoveal zone in each OCTA image was divided into four sectors which were the superior, temporal, inferior, and nasal sectors. Five intensity parameters including the mean, median, variance, skewness, and kurtosis of intensities were calculated for each sector. The factor of aging was evaluated among normal healthy subgroups. The diagnostic abilities of intensity parameters were evaluated between normal healthy subjects and diabetic patients with DR. Our results showed that the variance of intensities in superior sector in ICP achieved the highest AUROC value of 0.95 with the sensitivity of 0.87 and the specificity of 1.000 when comparing the diabetic patients with the mild NPDR to normal healthy subjects. The mean intensity in superior sector in ICP achieved the second highest AUROC value of 0.95 with the sensitivity of 0.90 and the specificity of 0.90 when comparing the diabetic patients with the moderate NPDR to normal healthy subjects. The proposed approach could offer a simple way to differentiate diabetic patients with early DR from normal healthy subjects without performing the relatively complicated image processing techniques.
{"title":"The preliminary study of diabetic retinopathy detection based on intensity parameters with optical coherence tomography angiography","authors":"J. Hou, H. Shi, W. Gao, P. Lin, B. Li, Y. Shi, I.A. Matveeva, V.P. Zakharov, I.A. Bratchenko","doi":"10.18287/2412-6179-co-1261","DOIUrl":"https://doi.org/10.18287/2412-6179-co-1261","url":null,"abstract":"In this study, the diagnostic abilities of intensity parameters of optical coherence tomography angiography (OCTA) images in the early detection of diabetic retinopathy (DR) were determined. 78 normal healthy eyes, 10 diabetic eyes with mild non-proliferative diabetic retinopathy (NPDR), and 10 diabetic eyes with moderate NPDR were employed. Four retinal vascular plexuses were generated by using OCTA, which included the nerve fiber layer vascular plexus (NFLVP), superficial vascular plexus (SVP), intermediate capillary plexus (ICP) and deep capillary plexus (DCP). The parafoveal zone in each OCTA image was divided into four sectors which were the superior, temporal, inferior, and nasal sectors. Five intensity parameters including the mean, median, variance, skewness, and kurtosis of intensities were calculated for each sector. The factor of aging was evaluated among normal healthy subgroups. The diagnostic abilities of intensity parameters were evaluated between normal healthy subjects and diabetic patients with DR. Our results showed that the variance of intensities in superior sector in ICP achieved the highest AUROC value of 0.95 with the sensitivity of 0.87 and the specificity of 1.000 when comparing the diabetic patients with the mild NPDR to normal healthy subjects. The mean intensity in superior sector in ICP achieved the second highest AUROC value of 0.95 with the sensitivity of 0.90 and the specificity of 0.90 when comparing the diabetic patients with the moderate NPDR to normal healthy subjects. The proposed approach could offer a simple way to differentiate diabetic patients with early DR from normal healthy subjects without performing the relatively complicated image processing techniques.","PeriodicalId":46692,"journal":{"name":"Computer Optics","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134998057","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：