arXiv subjects

Petr Holub

Publications and source records attributed to Petr Holub.

7 recordsLinked to original sources

arXiv2026

Anthropogenic disturbance expands the climatic limits of annual plant dominance

Disturbance regimes and nutrient inputs are changing worldwide, with consequences for the structure and functioning of plant communities. Classical life-history theory predicts that disturbance should shift communities from long-lived perennials toward short-lived annuals, and that nutrient enrichment may amplify this shift. However, these predictions have not been tested experimentally across broad environmental gradients. Here, using a global coordinated grassland experiment spanning 37 sites, we tested how physical disturbance, vegetation removal and shallow soil tillage, and fertilisation reshape annual-perennial balance, and whether disturbance relaxes the climatic limits of annual dominance. Disturbance nearly doubled the proportion of annual species and more than doubled the relative cover of annuals, whereas fertilisation had little influence and did not interact with disturbance. The disturbance-driven shift arose through contrasting pathways: in graminoids and legumes, it reflected the loss of perennial cover, while in forbs, the expansion of annual cover. In the absence of disturbance, annual dominance was restricted to systems with extremely hot and dry summers, but disturbance nearly tripled the extent of climate space in which annuals dominated. By rapidly reassembling after disturbance, annuals may help maintain vegetation cover, but their expansion also signals loss of perennial cover and the long-term ecosystem functions associated with it.

q-bio.OT↗

arXiv2026

LSP-DETR: Efficient and Scalable Nuclei Segmentation in Whole-Slide Images

Background and Objective: Precise and scalable instance segmentation of cell nuclei is a fundamental prerequisite for computational pathology, yet gigapixel whole-slide images (WSIs) pose significant computational challenges. While patch-based processing is standard during training, existing methods are often limited to small tile sizes during inference due to architectural bottlenecks or reliance on computationally expensive post-processing for instance separation. We introduce a faster, scalable, and end-to-end framework capable of processing large-scale image tiles while accurately modeling biologically realistic overlapping nuclei. Methods: We propose LSP-DETR (Local Star Polygon DEtection TRansformer). The model represents nuclei as star-convex polygons and employs a lightweight transformer with linear complexity, enabling the processing of high-resolution images in a single forward pass. A novel radial distance loss accommodates annotation uncertainty, allowing the segmentation of overlapping nuclei to emerge naturally without explicit overlap labels. Results: LSP-DETR achieves state-of-the-art efficiency, with an inference time of 0.45 s/mm^2, a 3.2x speedup over StarDist, the next-fastest method. On PanNuke, the model achieves competitive accuracy (67.5 bPQ), while yielding an F$_1$-score of 0.964 in polygon overlap when evaluated against consensus annotations from two expert pathologists. Furthermore, it outperforms larger models such as LKCell in generalization robustness, reaching an F1-score of 85.0 on MoNuSeg. Conclusions: LSP-DETR bridges the gap between high-fidelity segmentation and practical clinical requirements by eliminating heuristic post-processing. By providing a scalable, linear-complexity solution that naturally handles overlaps between nuclei, this framework sets a new direction for efficient high-throughput WSI analysis in digital pathology.

cs.CV↗

arXiv2025

Explaining Digital Pathology Models via Clustering Activations

We present a clustering-based explainability technique for digital pathology models based on convolutional neural networks. Unlike commonly used methods based on saliency maps, such as occlusion, GradCAM, or relevance propagation, which highlight regions that contribute the most to the prediction for a single slide, our method shows the global behaviour of the model under consideration, while also providing more fine-grained information. The result clusters can be visualised not only to understand the model, but also to increase confidence in its operation, leading to faster adoption in clinical practice. We also evaluate the performance of our technique on an existing model for detecting prostate cancer, demonstrating its usefulness.

cs.CV↗

arXiv2025

Evaluating Open-Weight Large Language Models for Structured Data Extraction from Narrative Medical Reports Across Multiple Use Cases and Languages

Large language models (LLMs) are increasingly used to extract structured information from free-text clinical records, but prior work often focuses on single tasks, limited models, and English-language reports. We evaluated 15 open-weight LLMs on pathology and radiology reports across six use cases, colorectal liver metastases, liver tumours, neurodegenerative diseases, soft-tissue tumours, melanomas, and sarcomas, at three institutes in the Netherlands, UK, and Czech Republic. Models included general-purpose and medical-specialised LLMs of various sizes, and six prompting strategies were compared: zero-shot, one-shot, few-shot, chain-of-thought, self-consistency, and prompt graph. Performance was assessed using task-appropriate metrics, with consensus rank aggregation and linear mixed-effects models quantifying variance. Top-ranked models achieved macro-average scores close to inter-rater agreement across tasks. Small-to-medium general-purpose models performed comparably to large models, while tiny and specialised models performed worse. Prompt graph and few-shot prompting improved performance by ~13%. Task-specific factors, including variable complexity and annotation variability, influenced results more than model size or prompting strategy. These findings show that open-weight LLMs can extract structured data from clinical reports across diseases, languages, and institutions, offering a scalable approach for clinical data curation.

cs.CL↗

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↗

arXiv2022

EOSC-LIFE WP4 TOOLBOX: Toolbox for sharing of sensitive data -- a concept description

The Horizon 2020 project EOSC-Life brings together the 13 Life Science 'ESFRI' research infrastructures to create an open, digital and collaborative space for biological and medical research. Sharing sensitive data is a specific challenge within EOSC-Life. For that reason, a toolbox is being developed, providing information to researchers who wish to share and/or use sensitive data in a cloud environment in general, and the European Open Science Cloud in particular. The sensitivity of the data may arise from its personal nature but can also be caused by intellectual property considerations, biohazard concerns, or the Nagoya protocol. The toolbox will not create new content, instead, it will allow researchers to find existing resources that are relevant for sharing sensitive data across all participating research infrastructures (F in FAIR). The toolbox will provide links to recommendations, procedures, and best practices, as well as to software (tools) to support data sharing and reuse. It will be based upon a tagging (categorisation) system, allowing consistent labelling and categorisation of resources. The current design document provides an outline for the anticipated toolbox, as well as its basic principles regarding content and sustainability.

q-bio.OT↗

arXiv2020

Non-repudiable provenance for clinical decision support systems

Provenance templates are now a recognised methodology for the construction of data provenance records. Each template defines the provenance of a domain-specific action in abstract form, which may then be instantiated as required by a single call to the provenance template service. As data reliability and trustworthiness becomes a critical issue in an increasing number of domains, there is a corresponding need to ensure that the provenance of that data is non-repudiable. In this paper we contribute two new, complementary modules to our template model and implementation to produce non-repudiable data provenance. The first, a module that traces the operation of the provenance template service itself, and records a provenance trace of the construction of an object-level document, at the level of individual service calls. The second, a non-repudiation module that generates evidence for the data recorded about each call, annotates the service trace accordingly, and submits a representation of that evidence to a provider-agnostic notary service. We evaluate the applicability of our approach in the context of a clinical decision support system. We first define a policy to ensure the non-repudiation of evidence with respect to a security threat analysis in order to demonstrate the suitability of our solution. We then select three use cases from within a particular system, Consult, with contrasting data provenance recording requirements and analyse the subsequent performance of our prototype implementation against three different notary providers.

cs.CR↗