Natalya Yurievna Ilyasova
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Natalya Yurievna Ilyasova has a total of 81 co-authors. Here are the top co-authors by number of shared publications:
- Nikita Sergeevich Demin
Samara National Research University, Samara, Russian Federation
19 shared publications - Nikita Demin
Samara National Research University
10 shared publications Samara National Research University
10 shared publications- Alexander Kupriyanov
Samara National Research University, Samara, Russia
9 shared publications Ipsi Ras – Branch Of The Fsrc “Crystallography And Photonics” Ras
7 shared publications- Eduard Nikolaevich Alekhin
Tyumen State Medical University
6 shared publications
Latest Publications
- 30 October 2026
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 35 (S2) , S195-S206
Development of a Deep Learning-Based Algorithm for Detection and Analysis of Retinal Fluid Regions in OCT Images
This paper presents the development of an algorithm for detecting and analyzing retinal fluid regions in optical coherence tomography (OCT) images using de
- 30 October 2026
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 35 (S2) , S195-S206
Development of a Deep Learning-Based Algorithm for Detection and Analysis of Retinal Fluid Regions in OCT Images
This paper presents the development of an algorithm for detecting and analyzing retinal fluid regions in optical coherence tomography (OCT) images using de
- 30 October 2026
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 35 (S2) , S183-S194
Localization of Foci Pathological Radiopharmaceutical Accumulation Based on Artificial Intelligence Methods
This paper deals with the technology of localization of pathological foci of radiopharmaceutical accumulation based on deep learning methods. It can be use
- 30 October 2026
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 35 (S2) , S183-S194
Localization of Foci Pathological Radiopharmaceutical Accumulation Based on Artificial Intelligence Methods
This paper deals with the technology of localization of pathological foci of radiopharmaceutical accumulation based on deep learning methods. It can be use
- 1 October 2026
- Published by Springer Nature
- p. 471-480
Automatic System to Determine Indications for 2RT Treatment
- 1 October 2026
- Published by Springer Nature
- p. 471-480
Automatic System to Determine Indications for 2RT Treatment
- 1 October 2026
- Published by Springer Nature
- p. 373-387
Automated System for Osteoporotic Changes Detection in Vertebral Bodies Based on CT Image Analysis
- 1 October 2026
- Published by Springer Nature
- p. 373-387
Automated System for Osteoporotic Changes Detection in Vertebral Bodies Based on CT Image Analysis
- 8 September 2025
- Published by Media Sphere Publishing Group in Russian Annals of Ophthalmology
- Vol. 141 (4) , 60-65
Nanosecond retinal laser therapy: three years of practical experience
Objective. This study evaluated the outcomes of a 36-month follow-up after treatment with the ELLEX 2RT nanosecond laser. Material and methods. The study included 72 patients divided into two groups. Group 1 received 2RT nanosecond laser therapy, while group 2 did not undergo laser treatment. Patients with early and intermediate stages of age-related macular degeneration (AMD) were enrolled. The exclusion criteria from the study were the presence of reticular pseudodrusen, drusenoid detachment (avascular pigment epithelial detachment) measuring >1000 μm, and areas of retinal pigment epithelium (RPE) atrophy detected by optical coherence tomography (OCT). Results. After treatment, visual acuity in group 1 did not change and remained stable at 0.99, while in group 2 there was a decrease in mean uncorrected visual acuity (UCVA) from 0.98 to 0.86. In addition, OCT findings in group 1 showed no progression in 96% (41 eyes) of cases. At the same time, in 2% (1 eye) of cases, there was a significant positive trend in relation to retinal anatomy according to OCT, and in 2% (1 eye) of cases, despite some negative dynamics in retinal anatomy, there was no decrease in vision. In contrast, the disease progressed to the wet form in 19% of group 2 patients after 36 months of follow-up. According to microperimetry, retinal sensitivity in the macular area and in 2RT foci in group 1 was stable or slightly improved. There was a trend toward improved fixation on microperimetry. Conclusion. Results of the study show that after 2RT therapy the condition of the retina can stabilize or even improve, supporting the broader use of retinal laser stimulation using a nanosecond laser in patients with early forms of AMD to prevent the progression of the disease and its transition to the wet form.
- 8 September 2025
- Published by Media Sphere Publishing Group in Russian Annals of Ophthalmology
- Vol. 141 (4) , 60-65
Nanosecond retinal laser therapy: three years of practical experience
Objective. This study evaluated the outcomes of a 36-month follow-up after treatment with the ELLEX 2RT nanosecond laser. Material and methods. The study included 72 patients divided into two groups. Group 1 received 2RT nanosecond laser therapy, while group 2 did not undergo laser treatment. Patients with early and intermediate stages of age-related macular degeneration (AMD) were enrolled. The exclusion criteria from the study were the presence of reticular pseudodrusen, drusenoid detachment (avascular pigment epithelial detachment) measuring >1000 μm, and areas of retinal pigment epithelium (RPE) atrophy detected by optical coherence tomography (OCT). Results. After treatment, visual acuity in group 1 did not change and remained stable at 0.99, while in group 2 there was a decrease in mean uncorrected visual acuity (UCVA) from 0.98 to 0.86. In addition, OCT findings in group 1 showed no progression in 96% (41 eyes) of cases. At the same time, in 2% (1 eye) of cases, there was a significant positive trend in relation to retinal anatomy according to OCT, and in 2% (1 eye) of cases, despite some negative dynamics in retinal anatomy, there was no decrease in vision. In contrast, the disease progressed to the wet form in 19% of group 2 patients after 36 months of follow-up. According to microperimetry, retinal sensitivity in the macular area and in 2RT foci in group 1 was stable or slightly improved. There was a trend toward improved fixation on microperimetry. Conclusion. Results of the study show that after 2RT therapy the condition of the retina can stabilize or even improve, supporting the broader use of retinal laser stimulation using a nanosecond laser in patients with early forms of AMD to prevent the progression of the disease and its transition to the wet form.
- 1 January 2025
- Published by Publishing house "Radiotekhnika" in Biomedical Radioelectronics
- p. 141-144
Neural network and hybrid technologies in osteoporosis diagnostics: analysis of x-ray images of the spine
This study presents a comparative analysis of two approaches for the automatic diagnosis of osteoporosis from lumbar spine radiographs: a purely neural network method and a hybrid approach combining deep learning with texture feature analysis. The relevance of this research is due to the growing prevalence of osteoporosis, which affects one in three women and one in four men over the age of 50, and the need to enhance diagnostic accuracy and reduce subjectivity in clinical decision-making. The study aims to evaluate the effectiveness of both approaches by analyzing their segmentation and classifi-cation performance. The neural network method relies on deep learning architectures such as DeepLabV3+ for segmentation and ResNet-34 for classification, while the hybrid method integrates traditional texture feature extraction (GLCM, LBP, and wavelet transforms) with the Random Forest classifier. The results demonstrate that the neural network approach achieves an accuracy of 87.42%, while the hybrid method, despite a lower overall accuracy of 78%, provides higher recall (86%) for positive osteoporosis cases, minimizing false negatives. These findings indicate that deep learning offers high precision, whereas hybrid models provide better interpretability and sensitivity. The proposed approaches con-tribute to the development of automated diagnostic tools, enhancing the efficiency and reliability of osteoporosis detection in clinical practice.
- 1 January 2025
- Published by Publishing house "Radiotekhnika" in Biomedical Radioelectronics
- p. 141-144
Neural network and hybrid technologies in osteoporosis diagnostics: analysis of x-ray images of the spine
This study presents a comparative analysis of two approaches for the automatic diagnosis of osteoporosis from lumbar spine radiographs: a purely neural network method and a hybrid approach combining deep learning with texture feature analysis. The relevance of this research is due to the growing prevalence of osteoporosis, which affects one in three women and one in four men over the age of 50, and the need to enhance diagnostic accuracy and reduce subjectivity in clinical decision-making. The study aims to evaluate the effectiveness of both approaches by analyzing their segmentation and classifi-cation performance. The neural network method relies on deep learning architectures such as DeepLabV3+ for segmentation and ResNet-34 for classification, while the hybrid method integrates traditional texture feature extraction (GLCM, LBP, and wavelet transforms) with the Random Forest classifier. The results demonstrate that the neural network approach achieves an accuracy of 87.42%, while the hybrid method, despite a lower overall accuracy of 78%, provides higher recall (86%) for positive osteoporosis cases, minimizing false negatives. These findings indicate that deep learning offers high precision, whereas hybrid models provide better interpretability and sensitivity. The proposed approaches con-tribute to the development of automated diagnostic tools, enhancing the efficiency and reliability of osteoporosis detection in clinical practice.