Searcharxiv⌕ Search

arXiv subjects

Ivan Tyukin

Publications and source records attributed to Ivan Tyukin.

At least 19 recordsLinked to original sources
arXiv2026

Deep Learning for Automated Quantification of Tumor-Associated Macrophages from H&E-Stained Slides in Diffuse Large B-Cell Lymphoma

While M2-polarized tumor-associated macrophages (TAMs) have been established as indicators of disease aggressiveness in diffuse large B-cell lymphoma (DLBCL), traditional CD163 immunohistochemistry (IHC) remains resource-intensive. This study aims to investigate the feasibility of using deep learning to quantify TAMs directly from standard hematoxylin and eosin-stained (HE) tissue sections. Using a curated dataset of 52 patients with DLBCL, with high-resolution HE images and IHC-validated annotations (1,713 TAM instances), five architectures were evaluated: U-Net, Swin-U-Net, Cerberus-U-Net3+, YOLOv11, and HoVer-Net. High CD163 TAM density (>20.04%) was associated with significantly reduced overall survival (HR 2.73; 95% CI:1.21-6.16; p=0.012) and progression-free survival (HR 2.88; 95% CI: 1.23-6.76; p=0.011). In multivariate Cox proportional hazards analysis adjusting for IPI, molecular subtype (GCB/non-GCB per Hans algorithm), EBV status, and age, CD163 TAM density showed a prognostic trend for overall survival (HR 3.24; 95% CI: 0.94-11.15; p=0.062) and progression-free survival (HR 2.41; 95% CI: 0.80-7.32; p=0.120). Among the evaluated models, the domain-specific Cerberus-U-Net3+ achieved the highest sensitivity (Recall 0.656), while the Transformer-based Swin-U-Net demonstrated superior segmentation fidelity (Precision 0.694, F1-score 0.633). Additionally, the survival analysis based on the predicted Swin-U-Net CD163 level revealed a 20.8% cutoff point for patients with high and low CD163 levels near IHC, as well as a downward trend in overall survival among patients with higher predicted CD163 values of 2.63 (95% CI: 0.85-8.33; p=0.083). These findings suggest that deep learning architectures using shifted-window self-attention show potential as a candidate surrogate for IHC that is scalable and cost-effective for prognostic assessment of TAMs in DLBCL.

eess.IV↗
arXiv2024

Physics-informed neural networks for aggregation kinetics

We introduce a novel physics-informed approach for accurately modeling aggregation kinetics which provides a comprehensive solution in a single run by outputting all model parameters simultaneously, a clear advancement over traditional single-output networks that require multiple executions. This method effectively captures the density distributions of both large and small clusters, showcasing a notable improvement in predicting small particles, which have historically posed challenges in computational models. This approach yields significant advancements in computational efficiency and accuracy for solving the Smoluchowski equations by minimizing the interval over which the physics-informed loss function operates, allowing for efficient computation over extended time-frames with minimal increase in computational cost. Due to the the independence of predefined shapes for bias or weight outputs, it removes the dependency on prior assumptions about output structures. Furthermore, our physics-informed framework exhibits high compatibility with the generalized Brownian kernel, maintaining robust accuracy for this previously unaddressed kernel type. The framework's notable novelty also lies in addressing four different kernels with one neural network architecture. Therefore with high computational efficiency, combined with low error margins it indicates significant potential for long-term predictions and integration into broader computational systems.

math.DS↗
arXiv2023

Knowledge-Informed Neuro-Integrators for Aggregation Kinetics

We report a novel approach for the efficient computation of solutions of a broad class of large-scale systems of non-linear ordinary differential equations, describing aggregation kinetics. The method is based on a new take on the dimensionality reduction for this class of equations which can be naturally implemented by a cascade of small feed-forward artificial neural networks. We show that this cascade, of otherwise static models, is capable of predicting solutions of the original large-scale system over large intervals of time, using the information about the solution computed over much smaller intervals. The computational cost of the method depends very mildly on the temporal horizon, which is a major improvement over the current state-of-the-art methods, whose complexity increases super-linearly with the system's size and proportionally to the simulation time. In cases when prior information about the values of solutions over a relatively small interval of time is already available, the method's computational complexity does not depend explicitly on the system's size. The successful application of the new method is illustrated for spatially-homogeneous systems, with a source of monomers, for a number of the most representative reaction rates kernels.

math.NA↗
arXiv2021

Scikit-dimension: a Python package for intrinsic dimension estimation

Dealing with uncertainty in applications of machine learning to real-life data critically depends on the knowledge of intrinsic dimensionality (ID). A number of methods have been suggested for the purpose of estimating ID, but no standard package to easily apply them one by one or all at once has been implemented in Python. This technical note introduces \texttt{scikit-dimension}, an open-source Python package for intrinsic dimension estimation. \texttt{scikit-dimension} package provides a uniform implementation of most of the known ID estimators based on scikit-learn application programming interface to evaluate global and local intrinsic dimension, as well as generators of synthetic toy and benchmark datasets widespread in the literature. The package is developed with tools assessing the code quality, coverage, unit testing and continuous integration. We briefly describe the package and demonstrate its use in a large-scale (more than 500 datasets) benchmarking of methods for ID estimation in real-life and synthetic data. The source code is available from https://github.com/j-bac/scikit-dimension , the documentation is available from https://scikit-dimension.readthedocs.io .

cs.LG↗
arXiv2019

Universal principles justify the existence of concept cells

It is largely believed that complex cognitive phenomena require the perfect orchestrated collaboration of many neurons. However, this is not what converging experimental evidence suggests. Single neurons, the so-called concept cells, may be responsible for complex tasks performed by an individual. Here, starting from a few first principles, we layout physical foundations showing that concept cells are not only possible but highly likely, given that neurons work in a high dimensional space.

q-bio.NC↗
arXiv2015

Leaders do not look back, or do they?

We study the effect of adding to a directed chain of interconnected systems a directed feedback from the last element in the chain to the first. The problem is closely related to the fundamental question of how a change in network topology may influence the behavior of coupled systems. We begin the analysis by investigating a simple linear system. The matrix that specifies the system dynamics is the transpose of the network Laplacian matrix, which codes the connectivity of the network. Our analysis shows that for any nonzero complex eigenvalue $λ$ of this matrix, the following inequality holds: $\frac{|\Im λ|}{|\Re λ|} \leq \cot\fracπ{n}$. This bound is sharp, as it becomes an equality for an eigenvalue of a simple directed cycle with uniform interaction weights. The latter has the slowest decay of oscillations among all other network configurations with the same number of states. The result is generalized to directed rings and chains of identical nonlinear oscillators. For directed rings, a lower bound $σ_c$ for the connection strengths that guarantees asymptotic synchronization is found to follow a similar pattern: $σ_c=\frac{1}{1-\cos\left( 2π/n\right)} $. Numerical analysis revealed that, depending on the network size $n$, multiple dynamic regimes co-exist in the state space of the system. In addition to the fully synchronous state a rotating wave solution occurs. The effect is observed in networks exceeding a certain critical size. The emergence of a rotating wave highlights the importance of long chains and loops in networks of oscillators: the larger the size of chains and loops, the more sensitive the network dynamics becomes to removal or addition of a single connection.

math.DS↗
arXiv2014

Uncertainty of visual measurement and efficient allocation of sensory resources

We review the reasoning underlying two approaches to combination of sensory uncertainties. First approach is noncommittal, making no assumptions about properties of uncertainty or parameters of stimulation. Then we explain the relationship between this approach and the one commonly used in modeling "higher level" aspects of sensory systems, such as in visual cue integration, where assumptions are made about properties of stimulation. The two approaches follow similar logic, except in one case maximal uncertainty is minimized, and in the other minimal certainty is maximized. Then we demonstrate how optimal solutions are found to the problem of resource allocation under uncertainty.

q-bio.NC↗
arXiv2014

Optimal measurement of visual motion across spatial and temporal scales

Sensory systems use limited resources to mediate the perception of a great variety of objects and events. Here a normative framework is presented for exploring how the problem of efficient allocation of resources can be solved in visual perception. Starting with a basic property of every measurement, captured by Gabor's uncertainty relation about the location and frequency content of signals, prescriptions are developed for optimal allocation of sensors for reliable perception of visual motion. This study reveals that a large-scale characteristic of human vision (the spatiotemporal contrast sensitivity function) is similar to the optimal prescription, and it suggests that some previously puzzling phenomena of visual sensitivity, adaptation, and perceptual organization have simple principled explanations.

cs.CV↗
arXiv2010

Observers for canonic models of neural oscillators

We consider the problem of state and parameter estimation for a wide class of nonlinear oscillators. Observable variables are limited to a few components of state vector and an input signal. The problem of state and parameter reconstruction is viewed within the classical framework of observer design. This framework offers computationally-efficient solutions to the problem of state and parameter reconstruction of a system of nonlinear differential equations, provided that these equations are in the so-called adaptive observer canonic form. We show that despite typical neural oscillators being locally observable they are not in the adaptive canonic observer form. Furthermore, we show that no parameter-independent diffeomorphism exists such that the original equations of these models can be transformed into the adaptive canonic observer form. We demonstrate, however, that for the class of Hindmarsh-Rose and FitzHugh-Nagumo models, parameter-dependent coordinate transformations can be used to render these systems into the adaptive observer canonical form. This allows reconstruction, at least partially and up to a (bi)linear transformation, of unknown state and parameter values with exponential rate of convergence. In order to avoid the problem of only partial reconstruction and to deal with more general nonlinear models in which the unknown parameters enter the system nonlinearly, we present a new method for state and parameter reconstruction for these systems. The method combines advantages of standard Lyapunov-based design with more flexible design and analysis techniques based on the non-uniform small-gain theorems. Effectiveness of the method is illustrated with simple numerical examples.

q-bio.NC↗
arXiv2009

Feasibility of random basis function approximators for modeling and control

We discuss the role of random basis function approximators in modeling and control. We analyze the published work on random basis function approximators and demonstrate that their favorable error rate of convergence O(1/n) is guaranteed only with very substantial computational resources. We also discuss implications of our analysis for applications of neural networks in modeling and control.

cs.NE↗
arXiv2009

Semi-passivity and synchronization of diffusively coupled neuronal oscillators

We discuss synchronization in networks of neuronal oscillators which are interconnected via diffusive coupling, i.e. linearly coupled via gap junctions. In particular, we present sufficient conditions for synchronization in these networks using the theory of semi-passive and passive systems. We show that the conductance-based neuronal models of Hodgkin-Huxley, Morris-Lecar, and the popular reduced models of FitzHugh-Nagumo and Hindmarsh-Rose all satisfy a semi-passivity property, i.e. that is the state trajectories of such a model remain oscillatory but bounded provided that the supplied (electrical) energy is bounded. As a result, for a wide range of coupling configurations, networks of these oscillators are guaranteed to possess ultimately bounded solutions. Moreover, we demonstrate that when the coupling is strong enough the oscillators become synchronized. Our theoretical conclusions are confirmed by computer simulations with coupled \HR and \ML oscillators. Finally we discuss possible "instabilities" in networks of oscillators induced by the diffusive coupling.

nlin.PS↗
arXiv2007

Invariant template matching in systems with spatiotemporal coding: a vote for instability

We consider the design of a pattern recognition that matches templates to images, both of which are spatially sampled and encoded as temporal sequences. The image is subject to a combination of various perturbations. These include ones that can be modeled as parameterized uncertainties such as image blur, luminance, translation, and rotation as well as unmodeled ones. Biological and neural systems require that these perturbations be processed through a minimal number of channels by simple adaptation mechanisms. We found that the most suitable mathematical framework to meet this requirement is that of weakly attracting sets. This framework provides us with a normative and unifying solution to the pattern recognition problem. We analyze the consequences of its explicit implementation in neural systems. Several properties inherent to the systems designed in accordance with our normative mathematical argument coincide with known empirical facts. This is illustrated in mental rotation, visual search and blur/intensity adaptation. We demonstrate how our results can be applied to a range of practical problems in template matching and pattern recognition.

cs.CV↗
arXiv2006

Non-uniform Small-gain Theorems for Systems with Unstable Invariant Sets

We consider the problem of asymptotic convergence to invariant sets in interconnected nonlinear dynamic systems. Standard approaches often require that the invariant sets be uniformly attracting. e.g. stable in the Lyapunov sense. This, however, is neither a necessary requirement, nor is it always useful. Systems may, for instance, be inherently unstable (e.g. intermittent, itinerant, meta-stable) or the problem statement may include requirements that cannot be satisfied with stable solutions. This is often the case in general optimization problems and in nonlinear parameter identification or adaptation. Conventional techniques for these cases rely either on detailed knowledge of the system's vector-fields or require boundeness of its states. The presently proposed method relies only on estimates of the input-output maps and steady-state characteristics. The method requires the possibility of representing the system as an interconnection of a stable, contracting, and an unstable, exploratory part. We illustrate with examples how the method can be applied to problems of analyzing the asymptotic behavior of locally unstable systems as well as to problems of parameter identification and adaptation in the presence of nonlinear parametrizations. The relation of our results to conventional small-gain theorems is discussed.

math.DS↗
arXiv2006

Decentralized adaptation in interconnected uncertain systems with nonlinear parametrization

We propose a technique for the design and analysis of decentralized adaptation algorithms in interconnected dynamical systems. Our technique does not require Lyapunov stability of the target dynamics and allows nonlinearly parameterized uncertainties. We show that for the considered class of systems, conditions for reaching the control goals can be formulated in terms of the nonlinear L_2-gains of target dynamics of each interconnected subsystem. Equations for decentralized controllers and corresponding adaptation algorithms are also explicitly provided.

math.OC↗
arXiv2004

Adaptive Regulation to Invariant Sets

A new framework for adaptive regulation to invariant sets is proposed. Reaching the target dynamics (invariant set) is to be ensured by state feedback while adaptation to parametric uncertainties is provided by additional adaptation algorithm. We show that for a sufficiently large class of nonlinear systems it is possible to adaptively steer the system trajectories to the desired non-equilibrium state without requiring knowledge or existence of a specific strict Lyapunov function.

math.OC↗
arXiv2004

Adaptation and nonlinear parametrization: nonlinear dynamics prospective

We consider adaptive control problem in presence of nonlinear parametrization of uncertainties in the model. It is shown that despite traditional approaches require for domination in the control loop during adaptation, it is not often necessary to use such energy inefficient compensators it in wide range of applications. In particular, we show that recently introduced adaptive control algorithms in finite form which are applicable to monotonic parameterized systems can be extended to general smooth non-monotonic parametrization. These schemes do not require any damping or domination in control inputs.

math.OC↗