Egor Ershov
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Egor Ershov has a total of 103 co-authors. Here are the top co-authors by number of shared publications:
- Dmitrii P. Nikolaev
Federal Research Center “Computer Science and Control” of the Russian Academy of Sciences, Moscow 119333, Russia
8 shared publications Alexander Belokopytov
Institute for Information Transmission Problems Moscow Russia
2 shared publications- Alexander V. Belokopytov
Institute for Information Transmission Problems (Kharkevich Institute), Russian Academy of Sciences, Moscow, Russian Federation
2 shared publications Daria Senshina
Institute for Information Transmission Problems Moscow Russia
2 shared publications- Denis Shepelev
Institute for Information Transmission Problems (Kharkevich Institute), Moscow, Russia
2 shared publications - Galina I. Rozhkova
Kharkevich Institute for Information Transmission Problems, Russian Academy of Sciences, Moscow, Russia
2 shared publications
Latest Publications
- 14 September 2026
- Published by Springer Nature
- p. 1-20
Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data
- 14 September 2026
- Published by Springer Nature
- p. 1-20
Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data
- 17 December 2025
- Published by Wiley in Laser & Photonics Reviews
- Vol. 20 (8)
Indocyanine Green‐Based Test‐Platform With Tunable Contrast for Optoacoustic and Fluorescence Lifetime Visualization
Multimodal approaches to diagnostics and therapy have lately attracted considerable attention. A promising combination of fluorescence lifetime and optoacoustic imaging offers complementary advantages: fluorescence signals provide metabolic tissue information, while optoacoustic data assess oxygen status and vascularization. This combination is particularly valuable for the in vivo differentiation of normal and pathological tissues, including cancer. Therefore, a stable platform for testing this equipment is crucial. Indocyanine Green (ICG), a clinically approved near‐infrared fluorescent dye, has limited optoacoustic imaging capabilities in its monomeric form. However, converting ICG into J‐aggregates (IJAs) enhances optoacoustic performance by decreasing fluorescence quantum yield and transferring ICG monomers/dimers to nanoparticles. This study evaluates the optical properties of tissue phantoms containing various ratios of vaterite nanoparticles with ICG and IJA for further use in fluorescence lifetime imaging microscopy (FLIM) and optoacoustic tomography. Loading ICG and IJA into vaterite allows for fine‐tuning of FLIM and OA contrast based on the nanoparticles concentrations. This approach facilitates testing of a novel imaging system combining FLIM and OA modalities, opening up new avenues for preclinical and clinical in vivo diagnostics.
- 17 December 2025
- Published by Wiley in Laser & Photonics Reviews
- Vol. 20 (8)
Indocyanine Green‐Based Test‐Platform With Tunable Contrast for Optoacoustic and Fluorescence Lifetime Visualization
Multimodal approaches to diagnostics and therapy have lately attracted considerable attention. A promising combination of fluorescence lifetime and optoacoustic imaging offers complementary advantages: fluorescence signals provide metabolic tissue information, while optoacoustic data assess oxygen status and vascularization. This combination is particularly valuable for the in vivo differentiation of normal and pathological tissues, including cancer. Therefore, a stable platform for testing this equipment is crucial. Indocyanine Green (ICG), a clinically approved near‐infrared fluorescent dye, has limited optoacoustic imaging capabilities in its monomeric form. However, converting ICG into J‐aggregates (IJAs) enhances optoacoustic performance by decreasing fluorescence quantum yield and transferring ICG monomers/dimers to nanoparticles. This study evaluates the optical properties of tissue phantoms containing various ratios of vaterite nanoparticles with ICG and IJA for further use in fluorescence lifetime imaging microscopy (FLIM) and optoacoustic tomography. Loading ICG and IJA into vaterite allows for fine‐tuning of FLIM and OA contrast based on the nanoparticles concentrations. This approach facilitates testing of a novel imaging system combining FLIM and OA modalities, opening up new avenues for preclinical and clinical in vivo diagnostics.
- Open Access
Experts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data
Learned Image Signal Processing (ISP) pipelines offer powerful end-to-end performance but are critically dependent on large-scale paired raw-to-sRGB datasets. This reliance on costly-to-acquire paired data remains a significant bottleneck. To address this challenge, we introduce a novel, unsupervised training framework based on Optimal Transport capable of training arbitrary ISP architectures in both unpaired and paired modes. We are the first to successfully apply Unbalanced Optimal Transport (UOT) for this complex, cross-domain translation task. Our UOT-based framework provides robustness to outliers in the target sRGB data, allowing it to discount atypical samples that would be prohibitively costly to map. A key component of our framework is a novel ``committee of expert discriminators,'' a hybrid adversarial regularizer. This committee guides the optimal transport mapping by providing specialized, targeted gradients to correct specific ISP failure modes, including color fidelity, structural artifacts, and frequency-domain realism. To demonstrate the superiority of our approach, we retrained existing state-of-the-art ISP architectures using our paired and unpaired setups. Our experiments show that while our framework, when trained in paired mode, exceeds the performance of the original paired methods across all metrics, our unpaired mode concurrently achieves quantitative and qualitative performance that rivals, and in some cases surpasses, the original paired-trained counterparts. The code and pre-trained models are available at: https://github.com/gosha20777/EGUOT-ISP.git.
Open AccessExperts-Guided Unbalanced Optimal Transport for ISP Learning from Unpaired and/or Paired Data
Learned Image Signal Processing (ISP) pipelines offer powerful end-to-end performance but are critically dependent on large-scale paired raw-to-sRGB datasets. This reliance on costly-to-acquire paired data remains a significant bottleneck. To address this challenge, we introduce a novel, unsupervised training framework based on Optimal Transport capable of training arbitrary ISP architectures in both unpaired and paired modes. We are the first to successfully apply Unbalanced Optimal Transport (UOT) for this complex, cross-domain translation task. Our UOT-based framework provides robustness to outliers in the target sRGB data, allowing it to discount atypical samples that would be prohibitively costly to map. A key component of our framework is a novel ``committee of expert discriminators,'' a hybrid adversarial regularizer. This committee guides the optimal transport mapping by providing specialized, targeted gradients to correct specific ISP failure modes, including color fidelity, structural artifacts, and frequency-domain realism. To demonstrate the superiority of our approach, we retrained existing state-of-the-art ISP architectures using our paired and unpaired setups. Our experiments show that while our framework, when trained in paired mode, exceeds the performance of the original paired methods across all metrics, our unpaired mode concurrently achieves quantitative and qualitative performance that rivals, and in some cases surpasses, the original paired-trained counterparts. The code and pre-trained models are available at: https://github.com/gosha20777/EGUOT-ISP.git.
- Open Access
Expert-aware uncertainty estimation for quality control of neural-based blood typing
In medical diagnostics, accurate uncertainty estimation for neural-based models is essential for complementing second-opinion systems. Despite neural network ensembles' proficiency in this problem, a gap persists between actual uncertainties and predicted estimates. A major difficulty here is the lack of labels on the hardness of examples: a typical dataset includes only ground truth target labels, making the uncertainty estimation problem almost unsupervised. Our novel approach narrows this gap by integrating expert assessments of case complexity into the neural network's learning process, utilizing both definitive target labels and supplementary complexity ratings. We validate our methodology for blood typing, leveraging a new dataset "BloodyWell" unique in augmenting labeled reaction images with complexity scores from six medical specialists. Experiments demonstrate enhancement of our approach in uncertainty prediction, achieving a 2.5-fold improvement with expert labels and a 35% increase in performance with estimates of neural-based expert consensus.
Open AccessExpert-aware uncertainty estimation for quality control of neural-based blood typing
In medical diagnostics, accurate uncertainty estimation for neural-based models is essential for complementing second-opinion systems. Despite neural network ensembles' proficiency in this problem, a gap persists between actual uncertainties and predicted estimates. A major difficulty here is the lack of labels on the hardness of examples: a typical dataset includes only ground truth target labels, making the uncertainty estimation problem almost unsupervised. Our novel approach narrows this gap by integrating expert assessments of case complexity into the neural network's learning process, utilizing both definitive target labels and supplementary complexity ratings. We validate our methodology for blood typing, leveraging a new dataset "BloodyWell" unique in augmenting labeled reaction images with complexity scores from six medical specialists. Experiments demonstrate enhancement of our approach in uncertainty prediction, achieving a 2.5-fold improvement with expert labels and a 35% increase in performance with estimates of neural-based expert consensus.
- 2 April 2024
- Published by Springer Nature in Health Information Science and Systems
- Vol. 12 (1) , 28
Image-based second opinion for blood typing
This paper considers a new method for providing a recommendation (second opinion) for a laboratory assistant in manual blood typing based on serological plates. The manual method consists of two steps: preparation and analysis. During preparation step the laboratory assistant needs to fill each well of a plate with a blood sample and a reagent mixture according to methodological guidelines. In the second step it is necessary to visually determine the result of the reactions, named agglutination. Despite the popularity of this method, it is slow and highly influenced by human factor, which cause blood typing errors. To increase the quality and performance of the analysis step, we propose a novel neural-based classification method. Our solution provides a fast way to fill the results into a laboratory system. We collected a new large dataset consisting of 3139 well images with GTs from donors’ medical history and six experts’ assessment for each. We showed that the proposed solution based on state-of-the-art architectures is comparable with the best expert and has 2.75 times fewer errors than the average one, with an overall accuracy equal to 98.4%. Taking into account the low-semantic nature of the task, we also considered shallow neural networks, which showed accuracy comparable with state-of-the-art models.
- 2 April 2024
- Published by Springer Nature in Health Information Science and Systems
- Vol. 12 (1) , 28
Image-based second opinion for blood typing
This paper considers a new method for providing a recommendation (second opinion) for a laboratory assistant in manual blood typing based on serological plates. The manual method consists of two steps: preparation and analysis. During preparation step the laboratory assistant needs to fill each well of a plate with a blood sample and a reagent mixture according to methodological guidelines. In the second step it is necessary to visually determine the result of the reactions, named agglutination. Despite the popularity of this method, it is slow and highly influenced by human factor, which cause blood typing errors. To increase the quality and performance of the analysis step, we propose a novel neural-based classification method. Our solution provides a fast way to fill the results into a laboratory system. We collected a new large dataset consisting of 3139 well images with GTs from donors’ medical history and six experts’ assessment for each. We showed that the proposed solution based on state-of-the-art architectures is comparable with the best expert and has 2.75 times fewer errors than the average one, with an overall accuracy equal to 98.4%. Taking into account the low-semantic nature of the task, we also considered shallow neural networks, which showed accuracy comparable with state-of-the-art models.
- 1 December 2023
- Published by Samara National Research University in Computer Optics
- Vol. 47 (6) , 958-967
An algorithm of blood typing using serological plate images
- 1 December 2023
- Published by Samara National Research University in Computer Optics
- Vol. 47 (6) , 958-967
An algorithm of blood typing using serological plate images
- Open Access
- 29 July 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (15) , 3336
On a Fast Hough/Radon Transform as a Compact Summation Scheme over Digital Straight Line Segments
The Hough transform, interpreted as the discretization of the Radon transform, is a widely used tool in image processing and machine vision. The primary way to speed it up is to employ the Brady–Yong algorithm. However, the accuracy of the straight line discretization utilized in this algorithm is limited. In this study, we propose a novel algorithm called that offers fast computation of the Hough transform for images of arbitrary sizes. Our approach adopts a computation scheme similar to the Brady–Yong algorithm but incorporates the best possible line discretization for improved accuracy. By employing the Method of Four Russians, we demonstrate that for an image of size where and , the computational complexity of the algorithm is when summing over digital straight line segments.- 29 July 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (15) , 3336
Open AccessOn a Fast Hough/Radon Transform as a Compact Summation Scheme over Digital Straight Line Segments
The Hough transform, interpreted as the discretization of the Radon transform, is a widely used tool in image processing and machine vision. The primary way to speed it up is to employ the Brady–Yong algorithm. However, the accuracy of the straight line discretization utilized in this algorithm is limited. In this study, we propose a novel algorithm called that offers fast computation of the Hough transform for images of arbitrary sizes. Our approach adopts a computation scheme similar to the Brady–Yong algorithm but incorporates the best possible line discretization for improved accuracy. By employing the Method of Four Russians, we demonstrate that for an image of size where and , the computational complexity of the algorithm is when summing over digital straight line segments. - Open Access
Color Reproduction by Multi-Wavelength Bragg Diffraction of White Light
Accurate color reproduction is highly important in multiple industrial, biomedical and scientific applications. Versatile and tunable light sources with high color-rendering quality are very much in demand. In this study, we demonstrate the feasibility of multi-wavelength Bragg diffraction of light for this task. Tuning the frequencies and amplitudes of bulk acoustic waves in the birefringent crystal demonstrates high precision in setting the number, wavelengths and intensities of the monochromatic components necessary to reproduce a specific color assigned according to its coordinates in the CIE XYZ 1931 space. We assembled a setup based on multi-bandpass acousto-optic (AO) filtration of white light and verified the reproduced color balance in multiple experiments. The proposed approach delivers almost full coverage of the CIE XYZ 1931 space and facilitates building compact color reproduction systems (CRSs) for various purposes.
Open AccessColor Reproduction by Multi-Wavelength Bragg Diffraction of White Light
Accurate color reproduction is highly important in multiple industrial, biomedical and scientific applications. Versatile and tunable light sources with high color-rendering quality are very much in demand. In this study, we demonstrate the feasibility of multi-wavelength Bragg diffraction of light for this task. Tuning the frequencies and amplitudes of bulk acoustic waves in the birefringent crystal demonstrates high precision in setting the number, wavelengths and intensities of the monochromatic components necessary to reproduce a specific color assigned according to its coordinates in the CIE XYZ 1931 space. We assembled a setup based on multi-bandpass acousto-optic (AO) filtration of white light and verified the reproduced color balance in multiple experiments. The proposed approach delivers almost full coverage of the CIE XYZ 1931 space and facilitates building compact color reproduction systems (CRSs) for various purposes.
- 15 December 2022
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 31 (S1) , 48-54
Smartphone Camera Self-Calibration Based on Sensors Reading Consistency
In large-scale series production the time for evaluating the camera spectral sensitivity is strongly limited and measured in units of seconds because of pr
- 15 December 2022
- Published by Allerton Press in Optical Memory and Neural Networks
- Vol. 31 (S1) , 48-54
Smartphone Camera Self-Calibration Based on Sensors Reading Consistency
In large-scale series production the time for evaluating the camera spectral sensitivity is strongly limited and measured in units of seconds because of pr
- Open Access
- 19 October 2022
- Published by MDPI AG in Journal of Imaging
- Vol. 8 (10) , 289
Experimental Study of Radial Distortion Compensation for Camera Submerged Underwater Using Open SaltWaterDistortion Data Set
This paper describes a new open data set, consisting of images of a chessboard collected underwater with different refractive indices, which allows for investigation of the quality of different radial distortion correction methods. The refractive index is regulated by the degree of salinity of the water. The collected data set consists of 662 images, and the chessboard cell corners are manually marked for each image (for a total of nodes). Two different mobile phone cameras were used for the shooting: telephoto and wide-angle. With the help of the collected data set, the practical applicability of the formula for correction of the radial distortion that occurs when the camera is submerged underwater was investigated. Our experiments show that the radial distortion correction formula makes it possible to correct images with high precision, comparable to the precision of classical calibration algorithms. We also show that this correction method is resistant to small inaccuracies in the indication of the refractive index of water. The data set, as well as the accompanying code, are publicly available.- 19 October 2022
- Published by MDPI AG in Journal of Imaging
- Vol. 8 (10) , 289
Open AccessExperimental Study of Radial Distortion Compensation for Camera Submerged Underwater Using Open SaltWaterDistortion Data Set
This paper describes a new open data set, consisting of images of a chessboard collected underwater with different refractive indices, which allows for investigation of the quality of different radial distortion correction methods. The refractive index is regulated by the degree of salinity of the water. The collected data set consists of 662 images, and the chessboard cell corners are manually marked for each image (for a total of nodes). Two different mobile phone cameras were used for the shooting: telephoto and wide-angle. With the help of the collected data set, the practical applicability of the formula for correction of the radial distortion that occurs when the camera is submerged underwater was investigated. Our experiments show that the radial distortion correction formula makes it possible to correct images with high precision, comparable to the precision of classical calibration algorithms. We also show that this correction method is resistant to small inaccuracies in the indication of the refractive index of water. The data set, as well as the accompanying code, are publicly available.