Pub Date : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-29-39
D. A. Dorofeev, A. A. Antonov, E. Karlova, E. V. Kirilik, I. V. Kozlova, A. A. Markelova
Relevance. The main modifiable risk factor for the development and progression of glaucoma is intraocular pressure (IOP). For over two hundred years, there has been a search for a method for determining the level of IOP, which took into account the properties of the surface of the cornea and iatrogenic factors. Purpose. To assess the influence of individual characteristics of the eyeball on the difference in ophthalmotonometry, measured by the Maklakov's applanation method and using point contact tonometry (iCare). Material and methods. The work involved 226 patients aged 45 to 89 years (342 eyes) with a diagnosis of primary openangle glaucoma (POAG) (71 eyes) or suspected glaucoma (202 eyes). The study also used data on the observation of healthy eyes (69 eyes). The study is analytical, observational, case-control. The leading diagnoses at the time of the study were: primary open-angle glaucoma (POAG) and suspected glaucoma. Also, data on observation of healthy eyes were used in the work. Clinical refraction varied of ±6.0 diopters and astigmatism ±3.0 diopters. All patients underwent ophthalmic tonometry measurement using the Maklakov applanation method (with a load of 5, 10 and 15 g) and iCare point contact tonometry (Tiolat, Finland). Results. The results of point contact tonometry were relatively underestimated relative to the tonometric indicators by Maklakov's tonometry: 5 g – 4.1±4.0 (4.0 [1.0; 7.0]), 10 g – 9.7±4.0 (10.0 [6.5; 12.5]), 15 g – 14.7±4.2 (15.0 [12.0; 18.0]). Conclusion. The reasons for the difference from the Maklakov's tonometer require further study; they can be associated both with the measurement method, the patient's body position, the characteristics of the group set, and various approaches to the calibration of the tested tonometers. A positive point is the higher numbers of ophthalmotonus in Maklakov's tonometry, since this is the main screening method of ophthalmotonometry on the territory of the Russian Federation. Keywords: intraocular pressure, elastotometry, rebound tonometry, point contact tonometry, ophthalmotonometry, Maklakov's tonometer
的相关性。青光眼发生和发展的主要可改变的危险因素是眼压。两百多年来，人们一直在寻找一种既考虑角膜表面特性又考虑医源性因素的IOP水平测定方法。目的。目的探讨眼球个体特征对Maklakov压平法和点接触眼压仪(iCare)眼压测量差异的影响。材料和方法。研究涉及226例年龄在45 - 89岁之间的患者(342只眼)，诊断为原发性开角型青光眼(POAG)(71只眼)或疑似青光眼(202只眼)。该研究还使用了健康眼睛(69只眼睛)的观察数据。本研究为分析性、观察性、病例对照研究。在研究期间，主要的诊断是:原发性开角型青光眼(POAG)和疑似青光眼。工作中还使用了健康眼的观察资料。临床屈光±6.0屈光度，散光±3.0屈光度。所有患者均采用Maklakov眼压法(负荷分别为5、10和15 g)和iCare点接触眼压仪(芬兰Tiolat)进行眼压测量。结果。相对于Maklakov血压计的血压计指标，点接触血压计的结果被相对低估:5 g - 4.1±4.0 (4.0 [1.0;7.0])， 10 g - 9.7±4.0 (10.0 [6.5;12.5])， 15 g - 14.7±4.2 (15.0 [12.0;18.0])。结论。与马克拉科夫眼压计不同的原因有待进一步研究;它们可以与测量方法、患者体位、组组特征以及校准所测眼压计的各种方法相关联。积极的一点是，在Maklakov眼压测量中眼压的数量较多，因为这是俄罗斯联邦领土上眼压测量的主要筛查方法。关键词:眼压，弹性眼压，回弹眼压，点接触眼压，眼动眼压，Maklakov眼压计
{"title":"Influence of the individual characteristics of the patient and the biometric parameters of the eye on the difference between the indicators of point tonometry and tonometry according to Maklakov","authors":"D. A. Dorofeev, A. A. Antonov, E. Karlova, E. V. Kirilik, I. V. Kozlova, A. A. Markelova","doi":"10.25276/0235-4160-2022-4s-29-39","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-29-39","url":null,"abstract":"Relevance. The main modifiable risk factor for the development and progression of glaucoma is intraocular pressure (IOP). For over two hundred years, there has been a search for a method for determining the level of IOP, which took into account the properties of the surface of the cornea and iatrogenic factors. Purpose. To assess the influence of individual characteristics of the eyeball on the difference in ophthalmotonometry, measured by the Maklakov's applanation method and using point contact tonometry (iCare). Material and methods. The work involved 226 patients aged 45 to 89 years (342 eyes) with a diagnosis of primary openangle glaucoma (POAG) (71 eyes) or suspected glaucoma (202 eyes). The study also used data on the observation of healthy eyes (69 eyes). The study is analytical, observational, case-control. The leading diagnoses at the time of the study were: primary open-angle glaucoma (POAG) and suspected glaucoma. Also, data on observation of healthy eyes were used in the work. Clinical refraction varied of ±6.0 diopters and astigmatism ±3.0 diopters. All patients underwent ophthalmic tonometry measurement using the Maklakov applanation method (with a load of 5, 10 and 15 g) and iCare point contact tonometry (Tiolat, Finland). Results. The results of point contact tonometry were relatively underestimated relative to the tonometric indicators by Maklakov's tonometry: 5 g – 4.1±4.0 (4.0 [1.0; 7.0]), 10 g – 9.7±4.0 (10.0 [6.5; 12.5]), 15 g – 14.7±4.2 (15.0 [12.0; 18.0]). Conclusion. The reasons for the difference from the Maklakov's tonometer require further study; they can be associated both with the measurement method, the patient's body position, the characteristics of the group set, and various approaches to the calibration of the tested tonometers. A positive point is the higher numbers of ophthalmotonus in Maklakov's tonometry, since this is the main screening method of ophthalmotonometry on the territory of the Russian Federation. Keywords: intraocular pressure, elastotometry, rebound tonometry, point contact tonometry, ophthalmotonometry, Maklakov's tonometer","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129196956","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-13-20
S. Sakhnov, K. Axenov, L. Axenova, V.V. Vronskaya, A. O. Martsinkevich, V. Myasnikova
Relevance. Untreated cataract is the cause of permanent blindness. The main factors of untimely surgical treatment are the lack of patient's awareness about the need for surgical treatment (36.1%) and work or household employment (25.3%). Thus, regular cataract screening is an effective way to prevent blindness and identify patients in need of surgery. Purpose. Development of a cataract screening system based on an open data set, as well as its validation on clinical data. Material and methods. An open dataset (No. 1) of 9668 smartphone camera images, of which 4514 were cataracts and 5154 were normal eyes. The set for external validation (No. 2) was obtained under clinical conditions in the diagnostic department of the Krasnodar branch of the The S. Fyodorov Eye Microsurgery Federal State Institution. The set contained 51 cataract and normal images. To create a machine learning model, we used a convolutional neural network (CNN). Results. The data classification accuracy value was 0.97 for the internal validation set and 0.75 for the external one. The predictive value was low for cataract at the change in data set №2 and was only 0.54, as well as for sensitivity (0.87) and specificity (0.69) metrics. The area under the ROC curve was 0.99 (for dataset No. 1) and 0.78 (for dataset No. 2). Conclusion. These results indicate that it is necessary to fine-tune the model and provide the necessary levels of performance metrics for this scenario. Keywords: cataract, artificial intelligence, machine learning, screening, open datasets
{"title":"Development of a cataract screening model using an open dataset and deep machine learning algorithms","authors":"S. Sakhnov, K. Axenov, L. Axenova, V.V. Vronskaya, A. O. Martsinkevich, V. Myasnikova","doi":"10.25276/0235-4160-2022-4s-13-20","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-13-20","url":null,"abstract":"Relevance. Untreated cataract is the cause of permanent blindness. The main factors of untimely surgical treatment are the lack of patient's awareness about the need for surgical treatment (36.1%) and work or household employment (25.3%). Thus, regular cataract screening is an effective way to prevent blindness and identify patients in need of surgery. Purpose. Development of a cataract screening system based on an open data set, as well as its validation on clinical data. Material and methods. An open dataset (No. 1) of 9668 smartphone camera images, of which 4514 were cataracts and 5154 were normal eyes. The set for external validation (No. 2) was obtained under clinical conditions in the diagnostic department of the Krasnodar branch of the The S. Fyodorov Eye Microsurgery Federal State Institution. The set contained 51 cataract and normal images. To create a machine learning model, we used a convolutional neural network (CNN). Results. The data classification accuracy value was 0.97 for the internal validation set and 0.75 for the external one. The predictive value was low for cataract at the change in data set №2 and was only 0.54, as well as for sensitivity (0.87) and specificity (0.69) metrics. The area under the ROC curve was 0.99 (for dataset No. 1) and 0.78 (for dataset No. 2). Conclusion. These results indicate that it is necessary to fine-tune the model and provide the necessary levels of performance metrics for this scenario. Keywords: cataract, artificial intelligence, machine learning, screening, open datasets","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131281727","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-123-131
O. Rozanova, I. M. Mikhalevich
Purpose. To reveal functional transformation patterns of the visual system in normal aging using neural network analysis. Material and methods. We examined 170 people aged 18 to 60 with objective refraction (under conditions of cycloplegia) from +5.5 D to –5.5 D. The criteria for selecting patients in the study groups were: maximally corrected visual acuity in the distance of each eye on a decimal scale of 1.0 and higher, normal color perception, absence of concomitant ophthalmopathology. A comprehensive assessment of the anatomical and optical eye parameters, indicators of monocular sensory reception and binocular interaction was carried out. 90 individual indicators of the visual system were used for neural network analysis with pattern recognition in a genetic algorithm with reduced dimensionality and step-by-step discriminant analysis. Results. Neural network analysis made it possible to establish the sequence of inclusion of 14 informative signs of the transformation of the visual system during normal aging. The contribution to the transformation of the visual system from changes in the accommodation system was 52%, from a decrease in the level of binocular interaction – 22%, changes in the function of the pupillary diaphragm – 13%, an increase in the temporal characteristics of sensory reception and signs of fatigue of the visual system – 11%. Conclusion. Neural network analysis allowed us to establish the sequence of inclusion of 14 informative signs of transformation of the visual system in normal aging. Normal aging of the visual system is expressed not only in a decrease in accommodative ability, but also in a decrease in the level of binocular interaction and binocular summation, in an increase in the processes of functional fatigue in the process of sensory reception, accompanied by a change in the function of the pupil. Keywords: normal aging, visual system, presbyopia, artificial neural network
{"title":"Neural network analysis of the visual system functional transformation in normal aging","authors":"O. Rozanova, I. M. Mikhalevich","doi":"10.25276/0235-4160-2022-4s-123-131","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-123-131","url":null,"abstract":"Purpose. To reveal functional transformation patterns of the visual system in normal aging using neural network analysis. Material and methods. We examined 170 people aged 18 to 60 with objective refraction (under conditions of cycloplegia) from +5.5 D to –5.5 D. The criteria for selecting patients in the study groups were: maximally corrected visual acuity in the distance of each eye on a decimal scale of 1.0 and higher, normal color perception, absence of concomitant ophthalmopathology. A comprehensive assessment of the anatomical and optical eye parameters, indicators of monocular sensory reception and binocular interaction was carried out. 90 individual indicators of the visual system were used for neural network analysis with pattern recognition in a genetic algorithm with reduced dimensionality and step-by-step discriminant analysis. Results. Neural network analysis made it possible to establish the sequence of inclusion of 14 informative signs of the transformation of the visual system during normal aging. The contribution to the transformation of the visual system from changes in the accommodation system was 52%, from a decrease in the level of binocular interaction – 22%, changes in the function of the pupillary diaphragm – 13%, an increase in the temporal characteristics of sensory reception and signs of fatigue of the visual system – 11%. Conclusion. Neural network analysis allowed us to establish the sequence of inclusion of 14 informative signs of transformation of the visual system in normal aging. Normal aging of the visual system is expressed not only in a decrease in accommodative ability, but also in a decrease in the level of binocular interaction and binocular summation, in an increase in the processes of functional fatigue in the process of sensory reception, accompanied by a change in the function of the pupil. Keywords: normal aging, visual system, presbyopia, artificial neural network","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117273306","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-92-101
A. Krasov, D. Shakin, N.N. Lansere, I.I. Fadeev, A. Gelfand
Relevance. All healthcare institutions, including ophthalmology, belong to critical information infrastructure, which is described in law on «the security of critical information infrastructure of the Russian Federation» 26.07.2017 No. 187-FL. It is mandatory to carry out the compliance of critical information infrastructure objects with the established criteria and indicators of significance for these institutions. The article deals with the issues of information security risk assessment and categorization in relation to organizations working in the field of ophthalmology. The research was carried out as part of the implementation of the federal project «Information Security» of the national program «Digital Economy of the Russian Federation». Purpose. Analysis of the features of the categorization process for ophthalmology organizations, designing decision-making algorithm for assigning a category of significance. Material and methods. The article deals with the issues of information security risk assessment and categorization in relation to ophthalmology organizations. The study was carried out as part of the implementation of the federal project «Information Security» (the national program «Digital Economy of the Russian Federation»). Results. The consequences of the implementation of attacks on information systems that are significant for specific types of critical information infrastructure objects in the healthcare sector (in the field of ophthalmology) were considered. The choice of significance criteria was substantiated. An algorithm for making a decision on assigning a category of significance was developed. Conclusion. An analysis of current threats to critical information infrastructure facilities in the healthcare sector was explored. It was found that in the proposed methodologies, the detection of the possibility of detecting an object under the first detection is not wide enough, which may seem to be based on unreasonable costs to ensure the necessary level of security for healthcare and ophthalmology facilities. Keywords: critical information infrastructure, healthcare institution, ophthalmology, information security threats, intruder model, actual threats, computer incidents
{"title":"Current information security threats in healthcare and ophthalmology","authors":"A. Krasov, D. Shakin, N.N. Lansere, I.I. Fadeev, A. Gelfand","doi":"10.25276/0235-4160-2022-4s-92-101","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-92-101","url":null,"abstract":"Relevance. All healthcare institutions, including ophthalmology, belong to critical information infrastructure, which is described in law on «the security of critical information infrastructure of the Russian Federation» 26.07.2017 No. 187-FL. It is mandatory to carry out the compliance of critical information infrastructure objects with the established criteria and indicators of significance for these institutions. The article deals with the issues of information security risk assessment and categorization in relation to organizations working in the field of ophthalmology. The research was carried out as part of the implementation of the federal project «Information Security» of the national program «Digital Economy of the Russian Federation». Purpose. Analysis of the features of the categorization process for ophthalmology organizations, designing decision-making algorithm for assigning a category of significance. Material and methods. The article deals with the issues of information security risk assessment and categorization in relation to ophthalmology organizations. The study was carried out as part of the implementation of the federal project «Information Security» (the national program «Digital Economy of the Russian Federation»). Results. The consequences of the implementation of attacks on information systems that are significant for specific types of critical information infrastructure objects in the healthcare sector (in the field of ophthalmology) were considered. The choice of significance criteria was substantiated. An algorithm for making a decision on assigning a category of significance was developed. Conclusion. An analysis of current threats to critical information infrastructure facilities in the healthcare sector was explored. It was found that in the proposed methodologies, the detection of the possibility of detecting an object under the first detection is not wide enough, which may seem to be based on unreasonable costs to ensure the necessary level of security for healthcare and ophthalmology facilities. Keywords: critical information infrastructure, healthcare institution, ophthalmology, information security threats, intruder model, actual threats, computer incidents","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"52 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130905061","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-132-137
D. V. Sakharov, A. I. Peshkov
Purpose. To consider, characterize and analyze the regulatory framework of the Russian Federation, which determines the use of information technologies in ophthalmology, without which it is now impossible to provide high-tech medical care. Material and methods. The subject of this study is the legislation of the Russian Federation devoted both directly to the health care system in our country and to the requirements for ensuring information security. In accordance with the specifics of the subject under study, general scientific research methods were necessarily used in this work: analysis and synthesis, deduction and induction. Results. The legal system of the Russian Federation is not so specialized in the use of information technologies in medicine that in ophthalmology there would be some special regulatory framework, different from other types of medical activities. The objective basis of this universality is that it is practically the same technological base everywhere in medicine. Conclusion. The presence of all the necessary conditions determining belonging to the status of a subject of critical information infrastructure creates sufficient grounds for the applying of requirements related to the regulation of medical activities based on the Federal law «On the Security of Critical Information Infrastructure of the Russian Federation». Keywords: medicine, information technology, information security, critical information structure of the Russian Federation
{"title":"Regulatory and legal problems of security of territorially distributed information systems in ophthalmology","authors":"D. V. Sakharov, A. I. Peshkov","doi":"10.25276/0235-4160-2022-4s-132-137","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-132-137","url":null,"abstract":"Purpose. To consider, characterize and analyze the regulatory framework of the Russian Federation, which determines the use of information technologies in ophthalmology, without which it is now impossible to provide high-tech medical care. Material and methods. The subject of this study is the legislation of the Russian Federation devoted both directly to the health care system in our country and to the requirements for ensuring information security. In accordance with the specifics of the subject under study, general scientific research methods were necessarily used in this work: analysis and synthesis, deduction and induction. Results. The legal system of the Russian Federation is not so specialized in the use of information technologies in medicine that in ophthalmology there would be some special regulatory framework, different from other types of medical activities. The objective basis of this universality is that it is practically the same technological base everywhere in medicine. Conclusion. The presence of all the necessary conditions determining belonging to the status of a subject of critical information infrastructure creates sufficient grounds for the applying of requirements related to the regulation of medical activities based on the Federal law «On the Security of Critical Information Infrastructure of the Russian Federation». Keywords: medicine, information technology, information security, critical information structure of the Russian Federation","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131137121","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-102-107
E. Gerling, K. Akhrameeva
Relevance. Modern methods of ophthalmic medical examinations, for example, ultrasound biomicroscopy, optical coherence tomography, axial MR tomography, and so on, allow you to save results, medical images in electronic form. The obtained image can be stored and transmitted via communication channels, which allows doctors to easily exchange information about the patient, since all tests are now in a single electronic patient card, as well as conduct long-distance consultations. Accurate diagnosis requires that ophthalmic medical images be protected from alteration, both intentional and accidental, when stored and transmitted over communication channels. Purpose. The goal of this work is to investigate the possibility of using modern digital watermark methods to control the integrity and immutability of stored and transmitted ophthalmic medical images. Material and methods. This article uses the results of a study of accurate authentication algorithms conducted using specially written software that allows you to attach and extract a digital watermark. Results. The possibility of using existing algorithms for embedding digital watermarks in ophthalmic medical images to control the absence of distortion during their storage and transmission has been investigated. Here is an example of accurate snapshot authentication using a digital watermark. Conclusion. The article considers the possibility of accurate authentication of ophthalmic medical images to control their invariability. State-of-the-art digital watermarking algorithms allow for monitoring the immutability of ophthalmic medical images during storage and transmission. Keywords: digital watermark, ophthalmic medical snapshot, accurate authentication, immutability, embedding algorithm
{"title":"Monitoring the invariability of medical images during transmission over communication channels","authors":"E. Gerling, K. Akhrameeva","doi":"10.25276/0235-4160-2022-4s-102-107","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-102-107","url":null,"abstract":"Relevance. Modern methods of ophthalmic medical examinations, for example, ultrasound biomicroscopy, optical coherence tomography, axial MR tomography, and so on, allow you to save results, medical images in electronic form. The obtained image can be stored and transmitted via communication channels, which allows doctors to easily exchange information about the patient, since all tests are now in a single electronic patient card, as well as conduct long-distance consultations. Accurate diagnosis requires that ophthalmic medical images be protected from alteration, both intentional and accidental, when stored and transmitted over communication channels. Purpose. The goal of this work is to investigate the possibility of using modern digital watermark methods to control the integrity and immutability of stored and transmitted ophthalmic medical images. Material and methods. This article uses the results of a study of accurate authentication algorithms conducted using specially written software that allows you to attach and extract a digital watermark. Results. The possibility of using existing algorithms for embedding digital watermarks in ophthalmic medical images to control the absence of distortion during their storage and transmission has been investigated. Here is an example of accurate snapshot authentication using a digital watermark. Conclusion. The article considers the possibility of accurate authentication of ophthalmic medical images to control their invariability. State-of-the-art digital watermarking algorithms allow for monitoring the immutability of ophthalmic medical images during storage and transmission. Keywords: digital watermark, ophthalmic medical snapshot, accurate authentication, immutability, embedding algorithm","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"7 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123650710","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-51-57
S. Shterenberg
Relevance. It is known that the method of electroretinography (hereinafter – ERG) in ophthalmology, which works on the key registration of changes in the bioelectric potential of the retina, uses the potential of exposure to light passing through the optical media of the eye. A similar method is conditionally applicable to the transmission of a light pulse over a fiber-optic cable, during which the correct transmission of information is carried out. If there is a violation or change in the electrical potential, there is every reason to believe that a person has any diseases. Purpose. To develop a technology for creating intellectual information security systems (IISS) is of a complex nature in which a quasi-biological paradigm is put in the first place, where the form of programming information processes, machine learning systems (MLS) and the construction of neural systems and ending with an AI architecture with built – in mechanisms for ensuring information security. Material and methods. In this article, a methodology for using a new artificial intelligence system (hereinafter referred to as AI) in a protected version for working with corrective devices for electroretinography in ophthalmology is compiled. Results. A set of methodological and scientific and technical solutions for the artificial intelligence system has been developed in order to ensure its «viability» and resistance to computer attacks aimed at violating the integrity. Conclusion. The article raises a key issue – the need to develop software architectural solutions for AI and adaptive neuro-fuzzy AI, which have «neurons» built into the software and hardware information protection systems with a universal set of commands for EG devices. Keywords: artificial intelligence, multi-agent system, electroretinography, neural network, integrity control, information security
{"title":"Methodology for building secure artificial intelligence systems for electroretinography in ophthalmology","authors":"S. Shterenberg","doi":"10.25276/0235-4160-2022-4s-51-57","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-51-57","url":null,"abstract":"Relevance. It is known that the method of electroretinography (hereinafter – ERG) in ophthalmology, which works on the key registration of changes in the bioelectric potential of the retina, uses the potential of exposure to light passing through the optical media of the eye. A similar method is conditionally applicable to the transmission of a light pulse over a fiber-optic cable, during which the correct transmission of information is carried out. If there is a violation or change in the electrical potential, there is every reason to believe that a person has any diseases. Purpose. To develop a technology for creating intellectual information security systems (IISS) is of a complex nature in which a quasi-biological paradigm is put in the first place, where the form of programming information processes, machine learning systems (MLS) and the construction of neural systems and ending with an AI architecture with built – in mechanisms for ensuring information security. Material and methods. In this article, a methodology for using a new artificial intelligence system (hereinafter referred to as AI) in a protected version for working with corrective devices for electroretinography in ophthalmology is compiled. Results. A set of methodological and scientific and technical solutions for the artificial intelligence system has been developed in order to ensure its «viability» and resistance to computer attacks aimed at violating the integrity. Conclusion. The article raises a key issue – the need to develop software architectural solutions for AI and adaptive neuro-fuzzy AI, which have «neurons» built into the software and hardware information protection systems with a universal set of commands for EG devices. Keywords: artificial intelligence, multi-agent system, electroretinography, neural network, integrity control, information security","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"67 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126209925","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-6-12
A. Arzamastsev, O. Fabrikantov, S. Belikov, N. Zenkova
Purpose. To evaluate possibility of using the mathematical models obtained as a result of deep learning of artificial neural networks (ANNmodels) to predict the optical power of modern intraocular lenses (IOL). Material and methods. The dataset included 455 depersonalized records of patients (26 columns of input factors and one column – output factor – calculation of IOL (dptr). For convenient construction of ANN models, a simulator program previously developed by the authors and Python language tools in the Google Colaboratory were used. Results. This article describes the possibility of using mathematical models obtained as a result of deep learning of ANN models to predict the optical power of modern IOLs, widely used in the surgical cataract treatment in ophthalmology. A distinctive feature of such ANN models in comparison with the wellknown formulas SRK II, SRK/T, Hoffer-Q, Holladay II, Haigis, Barrett is their ability to take into account a significant number of recorded input quantities, which makes it possible to reduce the mean relative error in calculating the optical power of IOL from 10 –12 to 3.5%. Conclusion. The resulting models, in contrast to the traditionally used formulas, reflect the regional specificity of patients to a much greater extent. They also make it possible to retrain and optimize the structure based on newly received data, which allows taking into account the non-stationarity of the object. Keywords: optical power of an intraocular lens, IOL, artificial neural networks, ANN-models, deep learning, training dataset
目的。评价利用人工神经网络(ANNmodels)深度学习获得的数学模型预测现代人工晶状体(IOL)光功率的可能性。材料和方法。数据集包括455例患者的非个性化记录(26列输入因素和1列输出因素-人工晶状体计算(dptr))。为了方便构建人工神经网络模型，使用了作者之前开发的仿真程序和Google协作实验室的Python语言工具。结果。本文描述了利用人工神经网络模型深度学习得到的数学模型来预测现代人工晶状体的光学功率的可能性，现代人工晶状体广泛应用于眼科白内障手术治疗。与众所周知的公式SRK II, SRK/T, Hoffer-Q, Holladay II, Haigis, Barrett相比，这种人工神经网络模型的一个显著特征是它们能够考虑到大量记录的输入量，这使得计算IOL光功率的平均相对误差从10 -12降低到3.5%。结论。与传统使用的公式相比，由此产生的模型在更大程度上反映了患者的区域特异性。它们还可以根据新接收到的数据重新训练和优化结构，这可以考虑到对象的非平稳性。关键词:人工晶状体光功率，人工晶体，人工神经网络，人工神经网络模型，深度学习，训练数据集
{"title":"The results of using machine learning technology for intraocular lenses optical power calculation","authors":"A. Arzamastsev, O. Fabrikantov, S. Belikov, N. Zenkova","doi":"10.25276/0235-4160-2022-4s-6-12","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-6-12","url":null,"abstract":"Purpose. To evaluate possibility of using the mathematical models obtained as a result of deep learning of artificial neural networks (ANNmodels) to predict the optical power of modern intraocular lenses (IOL). Material and methods. The dataset included 455 depersonalized records of patients (26 columns of input factors and one column – output factor – calculation of IOL (dptr). For convenient construction of ANN models, a simulator program previously developed by the authors and Python language tools in the Google Colaboratory were used. Results. This article describes the possibility of using mathematical models obtained as a result of deep learning of ANN models to predict the optical power of modern IOLs, widely used in the surgical cataract treatment in ophthalmology. A distinctive feature of such ANN models in comparison with the wellknown formulas SRK II, SRK/T, Hoffer-Q, Holladay II, Haigis, Barrett is their ability to take into account a significant number of recorded input quantities, which makes it possible to reduce the mean relative error in calculating the optical power of IOL from 10 –12 to 3.5%. Conclusion. The resulting models, in contrast to the traditionally used formulas, reflect the regional specificity of patients to a much greater extent. They also make it possible to retrain and optimize the structure based on newly received data, which allows taking into account the non-stationarity of the object. Keywords: optical power of an intraocular lens, IOL, artificial neural networks, ANN-models, deep learning, training dataset","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"345 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133807319","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-77-84
B. Malyugin, S. Sakhnov, L. Axenova, K. Axenov, E. Kozina, V.V. Vronskaya, V. Myasnikova
Relevance. Nearly 200 million people worldwide suffer from agerelated macular degeneration (AMD), 10% of which is neovascular, the cause of severe vision loss for most patients. Vascular endothelial growth factor inhibitors (anti-VEGF therapy) make it possible to achieve regression of the neovascularization process and preserve vision. However, today it is a rather expensive method of treatment, which is accompanied by various complications. The neovascular form of agerelated macular degeneration is the most common cause of such a complication as rupture of the pigment epithelium. Predictors of this anatomical outcome, as well as predictors of functional outcome or final visual acuity, can be assessed using optical coherence tomography (OCT). To automatize the processes of identifying morphological structures in OCT images deep learning methods are used. Purpose. The aim of this work was to create an algorithm for the automated detection of the antiVEGF therapy outcome biomarkers in patients with n-AMD and PED on OCT images. Material and methods. We used a set of retrospective data in the form of 251 annotated OCT images obtained during the initial examination of patients who were treated with n-AMD using anti-VEGF therapy from 2014 to 2021 to develop a segmentation algorithm. The architecture of the neural network was a convolutional neural network UNET. To evaluate the effectiveness of the proposed model, the Dice coefficient (DSC) was used. Results. The segmentation accuracy showed high values for the determination of all biomarkers – from 0.97 to 0.99. For retinal pigment epithelium detachment, DSC shows a good value of 0.8. However, for the pigment epithelium and subretinal fluid, DSC values are 0.4, and for other biomarkers from 0.3 to 0.15. Conclusion. The obtained results of segmentation of OCT images showed a high accuracy of pixel determination (accuracy). The Dice coefficient showed good values for segmentation of retinal pigment epithelium detachment. Further research will focus on increasing the neural network training and validation dataset and improving segmentation accuracy for other biomarkers. Keywords: age-related macular degeneration, OCT, artificial intelligence, machine learning, biomarkers, anti-VEGF therapy
{"title":"A deep machine learning model development for the biomarkers of the anatomical and functional anti-VEGF therapy outcome detection on retinal OCT images","authors":"B. Malyugin, S. Sakhnov, L. Axenova, K. Axenov, E. Kozina, V.V. Vronskaya, V. Myasnikova","doi":"10.25276/0235-4160-2022-4s-77-84","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-77-84","url":null,"abstract":"Relevance. Nearly 200 million people worldwide suffer from agerelated macular degeneration (AMD), 10% of which is neovascular, the cause of severe vision loss for most patients. Vascular endothelial growth factor inhibitors (anti-VEGF therapy) make it possible to achieve regression of the neovascularization process and preserve vision. However, today it is a rather expensive method of treatment, which is accompanied by various complications. The neovascular form of agerelated macular degeneration is the most common cause of such a complication as rupture of the pigment epithelium. Predictors of this anatomical outcome, as well as predictors of functional outcome or final visual acuity, can be assessed using optical coherence tomography (OCT). To automatize the processes of identifying morphological structures in OCT images deep learning methods are used. Purpose. The aim of this work was to create an algorithm for the automated detection of the antiVEGF therapy outcome biomarkers in patients with n-AMD and PED on OCT images. Material and methods. We used a set of retrospective data in the form of 251 annotated OCT images obtained during the initial examination of patients who were treated with n-AMD using anti-VEGF therapy from 2014 to 2021 to develop a segmentation algorithm. The architecture of the neural network was a convolutional neural network UNET. To evaluate the effectiveness of the proposed model, the Dice coefficient (DSC) was used. Results. The segmentation accuracy showed high values for the determination of all biomarkers – from 0.97 to 0.99. For retinal pigment epithelium detachment, DSC shows a good value of 0.8. However, for the pigment epithelium and subretinal fluid, DSC values are 0.4, and for other biomarkers from 0.3 to 0.15. Conclusion. The obtained results of segmentation of OCT images showed a high accuracy of pixel determination (accuracy). The Dice coefficient showed good values for segmentation of retinal pigment epithelium detachment. Further research will focus on increasing the neural network training and validation dataset and improving segmentation accuracy for other biomarkers. Keywords: age-related macular degeneration, OCT, artificial intelligence, machine learning, biomarkers, anti-VEGF therapy","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123988963","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 : 2023-02-17DOI: 10.25276/0235-4160-2022-4s-58-69
E. A. Katalevskaya, A.Y. Sizov, M.I. Tyurikov, Y. V. Vladimirova
Purpose. Development of artificial intelligence (AI) algorithms for diagnosing of diabetic retinopathy (DR), diabetic macular edema (DME), age-related macular degeneration (AMD), vitreomacular interface abnormalities (VMA) through the analysis of OCT scans and fundus images. Material and methods. Fundus images of patients with DR and DME, OCT scans of patients with DME, AMD and VMA were used as training and validation databases. The volume of training databases was 3600 fundus images and 10 000 OCT scans, the volume of validation databases was 400 fundus images and 1000 OCT scans. For fundus images analysis algorithms accuracy, sensitivity, specificity, AUROC were calculated for the following structures: microaneurysms, intraretinal hemorrhages, hard exudates, soft exudates, retinal and optic disc neovascularization, preretinal hemorrhages, epiretinal fibrosis, laser coagulates. For OCT scan analysis algorithms, these metrics were calculated for the features: intraretinal cysts, subretinal fluid, pigment epithelium detachment, subretinal hyperreflective material, drusen, epiretinal membrane, full thickness macular hole, lamellar macular hole, vitreomacular traction. Results. For fundus images analysis algorithms, accuracy exceeded 93% for all features except soft exudates (88.3%) and neovascularization (88.0%), sensitivity exceeded 90% for all features except neovascularization (80.2%) and epiretinal fibrosis (72.5%), specificity exceeded 91% for all features except microaneurysms (80.5%), hard exudates (83.5%) and soft exudates (88.7%), AUROC exceeded 0.90 for all signs except epiretinal fibrosis (0.88), neovascularization (0.87), preretinal hemorrhages (0.89). For OCT analysis algorithms, accuracy exceeded 93% for all features, sensitivity exceeded 90% for all features except lamellar macular hole (87.22%), specificity exceeded 93% for all features, AUROC exceeded 0.93 for all features. Conclusion. An algorithm for high precision segmentation of pathological signs has been developed. Based on these AI algorithms, the Retina.AI ophthalmological platform was developed, which allows automated analysis of OCT scans and fundus images and diagnosing of DR, DME, AMD and VMA. The platform is available for testing at https://www.screenretina.com/ Keywords: artificial intelligence, ophthalmic screening, diabetic retinopathy, diabetic macular edema, age-related macular degeneration, vitreomacular interface abnormalities
{"title":"Artificial intelligence algorithms for the diagnosis of signs of diabetic retinopathy, diabetic macular edema, age-related macular degeneration, vitreomacular interface abnormalities","authors":"E. A. Katalevskaya, A.Y. Sizov, M.I. Tyurikov, Y. V. Vladimirova","doi":"10.25276/0235-4160-2022-4s-58-69","DOIUrl":"https://doi.org/10.25276/0235-4160-2022-4s-58-69","url":null,"abstract":"Purpose. Development of artificial intelligence (AI) algorithms for diagnosing of diabetic retinopathy (DR), diabetic macular edema (DME), age-related macular degeneration (AMD), vitreomacular interface abnormalities (VMA) through the analysis of OCT scans and fundus images. Material and methods. Fundus images of patients with DR and DME, OCT scans of patients with DME, AMD and VMA were used as training and validation databases. The volume of training databases was 3600 fundus images and 10 000 OCT scans, the volume of validation databases was 400 fundus images and 1000 OCT scans. For fundus images analysis algorithms accuracy, sensitivity, specificity, AUROC were calculated for the following structures: microaneurysms, intraretinal hemorrhages, hard exudates, soft exudates, retinal and optic disc neovascularization, preretinal hemorrhages, epiretinal fibrosis, laser coagulates. For OCT scan analysis algorithms, these metrics were calculated for the features: intraretinal cysts, subretinal fluid, pigment epithelium detachment, subretinal hyperreflective material, drusen, epiretinal membrane, full thickness macular hole, lamellar macular hole, vitreomacular traction. Results. For fundus images analysis algorithms, accuracy exceeded 93% for all features except soft exudates (88.3%) and neovascularization (88.0%), sensitivity exceeded 90% for all features except neovascularization (80.2%) and epiretinal fibrosis (72.5%), specificity exceeded 91% for all features except microaneurysms (80.5%), hard exudates (83.5%) and soft exudates (88.7%), AUROC exceeded 0.90 for all signs except epiretinal fibrosis (0.88), neovascularization (0.87), preretinal hemorrhages (0.89). For OCT analysis algorithms, accuracy exceeded 93% for all features, sensitivity exceeded 90% for all features except lamellar macular hole (87.22%), specificity exceeded 93% for all features, AUROC exceeded 0.93 for all features. Conclusion. An algorithm for high precision segmentation of pathological signs has been developed. Based on these AI algorithms, the Retina.AI ophthalmological platform was developed, which allows automated analysis of OCT scans and fundus images and diagnosing of DR, DME, AMD and VMA. The platform is available for testing at https://www.screenretina.com/ Keywords: artificial intelligence, ophthalmic screening, diabetic retinopathy, diabetic macular edema, age-related macular degeneration, vitreomacular interface abnormalities","PeriodicalId":424200,"journal":{"name":"Fyodorov journal of ophthalmic surgery","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125155809","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：