Synthesis of neural network structure for the analysis of complex structured ocular fundus images

Tatarkanov, Aslan A.; Alexandrov, Islam A.; Glashev, Rasul M.

doi:10.5937/jaes0-31238

Cited by 2 publications

(1 citation statement)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently, in all subject areas of human activity, studies aimed at improving data processing technologies are of great practical importance [1][2][3][4]. Data processing in MIS is no exception to this trend, but it has some fundamental features related to the information security of PMD.…”

Section: Introductionmentioning

confidence: 99%

Development and Algorithmization of a Method for Analyzing the Degree of Uniqueness of Personal Medical Data

Lampezhev¹,

Kuklin²,

Chervyakov³

et al. 2023

HighTech. Innov. J.

View full text Add to dashboard Cite

The purpose of this investigation is to develop a method for quantitative assessment of the uniqueness of personal medical data (PMD) to improve their protection in medical information systems (MIS). The relevance of the goal is due to the fact that impersonal PMD can form unique combinations that are potentially of interest to intruders and threaten to reveal the patient's identity and medical confidentiality. Existing approaches were analyzed, and a new method for quantifying the degree of uniqueness of PMD was proposed. A weakness in existing approaches is the assumption that an attacker will use exact matching to identify people. The novelty of the method proposed in this paper lies in the fact that it is not limited to this hypothesis, although it has its limitations: it is not applicable to small samples. The developed method for determining the PMD uniqueness coefficient is based on the assumption of a multidimensional distribution of features, characterized by a covariance matrix, and a normal distribution, which provides the most reliable reflection of the existing relationships between features when analyzing large data samples. The results obtained in computational experiments show that efficiency is no worse than that of focus groups of specialized experts. Doi: 10.28991/HIJ-2023-04-01-09 Full Text: PDF

show abstract

Section: Introductionmentioning

confidence: 99%

Development and Algorithmization of a Method for Analyzing the Degree of Uniqueness of Personal Medical Data

Lampezhev¹,

Kuklin²,

Chervyakov³

et al. 2023

HighTech. Innov. J.

View full text Add to dashboard Cite

show abstract

Diabetic Retinopathy Diagnosis based on Convolutional Neural Network in the Russian Population: A Multicenter Prospective Study

Gognieva,

Durzhinskaya,

Vorobyeva

et al. 2024

CDR

View full text Add to dashboard Cite

Background:: Diabetic retinopathy is the most common complication of diabetes mellitus and is one of the leading causes of vision impairment globally, which is also relevant for the Russian Federation. Objective:: To evaluate the diagnostic efficiency of a convolutional neural network trained for the detection of diabetic retinopathy and estimation of its severity in fundus images of the Russian population. Methods:: In this cross-sectional multicenter study, the training data set was obtained from an open source and relabeled by a group of independent retina specialists; the sample size was 60,000 eyes. The test sample was recruited prospectively, 1186 fundus photographs of 593 patients were collected. The reference standard was the result of independent grading of the diabetic retinopathy stage by ophthalmologists. Results:: Sensitivity and specificity were 95.0% (95% CI; 90.8-96.4) and 96.8% (95% CI; 95.5- 99.0), respectively; positive predictive value – 98.8% (95% CI; 97.6-99.2); negative predictive value – 87.1% (95% CI, 83.4-96.5); accuracy – 95.9% (95% CI; 93.3-97.1); Kappa score – 0.887 (95% CI; 0.839-0.946); F1score – 0.909 (95% CI; 0.870-0.957); area under the ROC-curve – 95.9% (95% CI; 93.3-97.1). There was no statistically significant difference in diagnostic accuracy between the group with isolated diabetic retinopathy and those with hypertensive retinopathy as a concomitant diagnosis. Conclusion:: The method for diagnosing DR presented in this article has shown its high accuracy, which is consistent with the existing world analogues, however, this method should prove its clinical efficiency in large multicenter multinational controlled randomized studies, in which the reference diagnostic method would be unified and less subjective than an ophthalmologist.

show abstract

Synthesis of neural network structure for the analysis of complex structured ocular fundus images

Cited by 2 publications

References 41 publications

Development and Algorithmization of a Method for Analyzing the Degree of Uniqueness of Personal Medical Data

Development and Algorithmization of a Method for Analyzing the Degree of Uniqueness of Personal Medical Data

Diabetic Retinopathy Diagnosis based on Convolutional Neural Network in the Russian Population: A Multicenter Prospective Study

Contact Info

Product

Resources

About