arXiv subjects

Tomas Brazdil

Publications and source records attributed to Tomas Brazdil.

6 recordsLinked to original sources

arXiv2025

From slides to AI-ready maps: Standardized multi-layer tissue maps as metadata for artificial intelligence in digital pathology

A Whole Slide Image (WSI) is a high-resolution digital image created by scanning an entire glass slide containing a biological specimen, such as tissue sections or cell samples, at multiple magnifications. These images are digitally viewable, analyzable, and shareable, and are widely used for Artificial Intelligence (AI) algorithm development. WSIs play an important role in pathology for disease diagnosis and oncology for cancer research, but are also applied in neurology, veterinary medicine, hematology, microbiology, dermatology, pharmacology, toxicology, immunology, and forensic science. When assembling cohorts for AI training or validation, it is essential to know the content of a WSI. However, no standard currently exists for this metadata, and such a selection has largely relied on manual inspection, which is not suitable for large collections with millions of objects. We propose a general framework to generate 2D index maps (tissue maps) that describe the morphological content of WSIs using common syntax and semantics to achieve interoperability between catalogs. The tissue maps are structured in three layers: source, tissue type, and pathological alterations. Each layer assigns WSI segments to specific classes, providing AI-ready metadata. We demonstrate the advantages of this standard by applying AI-based metadata extraction from WSIs to generate tissue maps and integrating them into a WSI archive. This integration enhances search capabilities within WSI archives, thereby facilitating the accelerated assembly of high-quality, balanced, and more targeted datasets for AI training, validation, and cancer research.

cs.CV↗

arXiv2020

Reinforcement Learning of Risk-Constrained Policies in Markov Decision Processes

Markov decision processes (MDPs) are the defacto frame-work for sequential decision making in the presence ofstochastic uncertainty. A classical optimization criterion forMDPs is to maximize the expected discounted-sum pay-off, which ignores low probability catastrophic events withhighly negative impact on the system. On the other hand,risk-averse policies require the probability of undesirableevents to be below a given threshold, but they do not accountfor optimization of the expected payoff. We consider MDPswith discounted-sum payoff with failure states which repre-sent catastrophic outcomes. The objective of risk-constrainedplanning is to maximize the expected discounted-sum payoffamong risk-averse policies that ensure the probability to en-counter a failure state is below a desired threshold. Our maincontribution is an efficient risk-constrained planning algo-rithm that combines UCT-like search with a predictor learnedthrough interaction with the MDP (in the style of AlphaZero)and with a risk-constrained action selection via linear pro-gramming. We demonstrate the effectiveness of our approachwith experiments on classical MDPs from the literature, in-cluding benchmarks with an order of 10^6 states.

cs.AI↗

arXiv2015

Long-Run Average Behaviour of Probabilistic Vector Addition Systems

We study the pattern frequency vector for runs in probabilistic Vector Addition Systems with States (pVASS). Intuitively, each configuration of a given pVASS is assigned one of finitely many patterns, and every run can thus be seen as an infinite sequence of these patterns. The pattern frequency vector assigns to each run the limit of pattern frequencies computed for longer and longer prefixes of the run. If the limit does not exist, then the vector is undefined. We show that for one-counter pVASS, the pattern frequency vector is defined and takes only finitely many values for almost all runs. Further, these values and their associated probabilities can be approximated up to an arbitrarily small relative error in polynomial time. For stable two-counter pVASS, we show the same result, but we do not provide any upper complexity bound. As a byproduct of our study, we discover counterexamples falsifying some classical results about stochastic Petri nets published in the~80s.

cs.LO↗

arXiv2012

Runtime Analysis of Probabilistic Programs with Unbounded Recursion

We study termination time and recurrence time in programs with unbounded recursion, which are either randomized or operate on some statistically quantified inputs. As the underlying formal model for such programs we use probabilistic pushdown automata (pPDA) which are equivalent to probabilistic recursive state machines. We obtain tail bounds for the distribution of termination time for pPDA. We also study the recurrence time for probabilistic recursive programs that are not supposed to terminate (such as system daemons, network servers, etc.). Typically, such programs react to certain requests generated by their environment, and hence operate in finite request-service cycles. We obtain bounds for the frequency of long request-service cycles.

cs.LO↗

arXiv2011

Efficient Analysis of Probabilistic Programs with an Unbounded Counter

We show that a subclass of infinite-state probabilistic programs that can be modeled by probabilistic one-counter automata (pOC) admits an efficient quantitative analysis. In particular, we show that the expected termination time can be approximated up to an arbitrarily small relative error with polynomially many arithmetic operations, and the same holds for the probability of all runs that satisfy a given omega-regular property. Further, our results establish a powerful link between pOC and martingale theory, which leads to fundamental observations about quantitative properties of runs in pOC. In particular, we provide a "divergence gap theorem", which bounds a positive non-termination probability in pOC away from zero.

cs.FL↗

arXiv2010

Reachability Games on Extended Vector Addition Systems with States

We consider two-player turn-based games with zero-reachability and zero-safety objectives generated by extended vector addition systems with states. Although the problem of deciding the winner in such games is undecidable in general, we identify several decidable and even tractable subcases of this problem obtained by restricting the number of counters and/or the sets of target configurations.

cs.GT↗